forked from vitalif/vitastor
Compare commits
1 Commits
hugo-docs
...
lrc-matrix
| Author | SHA1 | Date | |
|---|---|---|---|
| 61ae4e903a |
@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8)
|
||||
|
||||
project(vitastor)
|
||||
|
||||
set(VERSION "0.6.17")
|
||||
set(VERSION "0.6.16")
|
||||
|
||||
add_subdirectory(src)
|
||||
|
||||
43
README-ru.md
43
README-ru.md
@@ -52,7 +52,6 @@ Vitastor на данный момент находится в статусе п
|
||||
- Слияние снапшотов (vitastor-cli {snap-rm,flatten,merge})
|
||||
- Консольный интерфейс для управления образами (vitastor-cli {ls,create,modify})
|
||||
- Плагин для Proxmox
|
||||
- Упрощённая NFS-прокси для эмуляции файлового доступа к образам (подходит для VMWare)
|
||||
|
||||
## Планы развития
|
||||
|
||||
@@ -60,6 +59,7 @@ Vitastor на данный момент находится в статусе п
|
||||
- Другие инструменты администрирования
|
||||
- Плагины для OpenNebula и других облачных систем
|
||||
- iSCSI-прокси
|
||||
- Упрощённый NFS прокси
|
||||
- Более быстрое переключение при отказах
|
||||
- Фоновая проверка целостности без контрольных сумм (сверка реплик)
|
||||
- Контрольные суммы
|
||||
@@ -530,48 +530,9 @@ vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
|
||||
Для обращения по номеру инода, аналогично другим командам, можно использовать опции
|
||||
`--pool <POOL> --inode <INODE> --size <SIZE>` вместо `--image testimg`.
|
||||
|
||||
### NFS
|
||||
|
||||
В Vitastor реализована упрощённая NFS 3.0 прокси для эмуляции файлового доступа к образам.
|
||||
Это не полноценная файловая система, т.к. метаданные всех файлов (образов) сохраняются
|
||||
в etcd и всё время хранятся в оперативной памяти - то есть, положить туда много файлов
|
||||
не получится.
|
||||
|
||||
Однако в качестве способа доступа к образам виртуальных машин NFS прокси прекрасно подходит
|
||||
и позволяет подключить Vitastor, например, к VMWare.
|
||||
|
||||
При этом, если вы используете режим immediate_commit=all (для SSD с конденсаторами или HDD
|
||||
с отключённым кэшем), то NFS-сервер не имеет состояния и вы можете свободно поднять
|
||||
его в нескольких экземплярах и использовать поверх них сетевой балансировщик нагрузки или
|
||||
схему с отказоустойчивостью.
|
||||
|
||||
Использование vitastor-nfs:
|
||||
|
||||
```
|
||||
vitastor-nfs [--etcd_address ADDR] [ДРУГИЕ ОПЦИИ]
|
||||
|
||||
--subdir <DIR> экспортировать "поддиректорию" - образы с префиксом имени <DIR>/ (по умолчанию пусто - экспортировать все образы)
|
||||
--portmap 0 отключить сервис portmap/rpcbind на порту 111 (по умолчанию включён и требует root привилегий)
|
||||
--bind <IP> принимать соединения по адресу <IP> (по умолчанию 0.0.0.0 - на всех)
|
||||
--nfspath <PATH> установить путь NFS-экспорта в <PATH> (по умолчанию /)
|
||||
--port <PORT> использовать порт <PORT> для NFS-сервисов (по умолчанию 2049)
|
||||
--pool <POOL> исползовать пул <POOL> для новых образов (обязательно, если пул в кластере не один)
|
||||
--foreground 1 не уходить в фон после запуска
|
||||
```
|
||||
|
||||
Пример монтирования Vitastor через NFS:
|
||||
|
||||
```
|
||||
vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
|
||||
```
|
||||
|
||||
```
|
||||
mount localhost:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
|
||||
```
|
||||
|
||||
### Kubernetes
|
||||
|
||||
У Vitastor есть CSI-плагин для Kubernetes, поддерживающий RWO, а также блочные RWX, тома.
|
||||
У Vitastor есть CSI-плагин для Kubernetes, поддерживающий RWO-тома.
|
||||
|
||||
Для установки возьмите манифесты из директории [csi/deploy/](csi/deploy/), поместите
|
||||
вашу конфигурацию подключения к Vitastor в [csi/deploy/001-csi-config-map.yaml](001-csi-config-map.yaml),
|
||||
|
||||
44
README.md
44
README.md
@@ -46,7 +46,6 @@ breaking changes in the future. However, the following is implemented:
|
||||
- Snapshot merge tool (vitastor-cli {snap-rm,flatten,merge})
|
||||
- Image management CLI (vitastor-cli {ls,create,modify})
|
||||
- Proxmox storage plugin
|
||||
- Simplified NFS proxy for file-based image access emulation (suitable for VMWare)
|
||||
|
||||
## Roadmap
|
||||
|
||||
@@ -54,6 +53,7 @@ breaking changes in the future. However, the following is implemented:
|
||||
- Other administrative tools
|
||||
- Plugins for OpenNebula and other cloud systems
|
||||
- iSCSI proxy
|
||||
- Simplified NFS proxy
|
||||
- Faster failover
|
||||
- Scrubbing without checksums (verification of replicas)
|
||||
- Checksums
|
||||
@@ -479,49 +479,9 @@ It will output the device name, like /dev/nbd0 which you can then format and mou
|
||||
|
||||
Again, you can use `--pool <POOL> --inode <INODE> --size <SIZE>` insteaf of `--image <IMAGE>` if you want.
|
||||
|
||||
### NFS
|
||||
|
||||
Vitastor has a simplified NFS 3.0 proxy for file-based image access emulation. It's not
|
||||
suitable as a full-featured file system, at least because all file/image metadata is stored
|
||||
in etcd and kept in memory all the time - thus you can't put a lot of files in it.
|
||||
|
||||
However, NFS proxy is totally fine as a method to provide VM image access and allows to
|
||||
plug Vitastor into, for example, VMWare. It's important to note that for VMWare it's a much
|
||||
better access method than iSCSI, because with iSCSI we'd have to put all VM images into one
|
||||
Vitastor image exported as a LUN to VMWare and formatted with VMFS. VMWare doesn't use VMFS
|
||||
over NFS.
|
||||
|
||||
NFS proxy is stateless if you use immediate_commit=all mode (for SSD with capacitors or
|
||||
HDDs with disabled cache), so you can run multiple NFS proxies and use a network load
|
||||
balancer or any failover method you want to in that case.
|
||||
|
||||
vitastor-nfs usage:
|
||||
|
||||
```
|
||||
vitastor-nfs [--etcd_address ADDR] [OTHER OPTIONS]
|
||||
|
||||
--subdir <DIR> export images prefixed <DIR>/ (default empty - export all images)
|
||||
--portmap 0 do not listen on port 111 (portmap/rpcbind, requires root)
|
||||
--bind <IP> bind service to <IP> address (default 0.0.0.0)
|
||||
--nfspath <PATH> set NFS export path to <PATH> (default is /)
|
||||
--port <PORT> use port <PORT> for NFS services (default is 2049)
|
||||
--pool <POOL> use <POOL> as default pool for new files (images)
|
||||
--foreground 1 stay in foreground, do not daemonize
|
||||
```
|
||||
|
||||
Example start and mount commands:
|
||||
|
||||
```
|
||||
vitastor-nfs --etcd_address 192.168.5.10:2379 --portmap 0 --port 2050 --pool testpool
|
||||
```
|
||||
|
||||
```
|
||||
mount localhost:/ /mnt/ -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp
|
||||
```
|
||||
|
||||
### Kubernetes
|
||||
|
||||
Vitastor has a CSI plugin for Kubernetes which supports RWO (and block RWX) volumes.
|
||||
Vitastor has a CSI plugin for Kubernetes which supports RWO volumes.
|
||||
|
||||
To deploy it, take manifests from [csi/deploy/](csi/deploy/) directory, put your
|
||||
Vitastor configuration in [csi/deploy/001-csi-config-map.yaml](001-csi-config-map.yaml),
|
||||
|
||||
Submodule cpp-btree updated: 45e6d1f131...6e20146406
@@ -1,4 +1,4 @@
|
||||
VERSION ?= v0.6.17
|
||||
VERSION ?= v0.6.16
|
||||
|
||||
all: build push
|
||||
|
||||
|
||||
@@ -49,7 +49,7 @@ spec:
|
||||
capabilities:
|
||||
add: ["SYS_ADMIN"]
|
||||
allowPrivilegeEscalation: true
|
||||
image: vitalif/vitastor-csi:v0.6.17
|
||||
image: vitalif/vitastor-csi:v0.6.16
|
||||
args:
|
||||
- "--node=$(NODE_ID)"
|
||||
- "--endpoint=$(CSI_ENDPOINT)"
|
||||
|
||||
@@ -116,7 +116,7 @@ spec:
|
||||
privileged: true
|
||||
capabilities:
|
||||
add: ["SYS_ADMIN"]
|
||||
image: vitalif/vitastor-csi:v0.6.17
|
||||
image: vitalif/vitastor-csi:v0.6.16
|
||||
args:
|
||||
- "--node=$(NODE_ID)"
|
||||
- "--endpoint=$(CSI_ENDPOINT)"
|
||||
|
||||
@@ -1,13 +0,0 @@
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: PersistentVolumeClaim
|
||||
metadata:
|
||||
name: test-vitastor-pvc-block
|
||||
spec:
|
||||
storageClassName: vitastor
|
||||
volumeMode: Block
|
||||
accessModes:
|
||||
- ReadWriteMany
|
||||
resources:
|
||||
requests:
|
||||
storage: 10Gi
|
||||
@@ -1,17 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: Pod
|
||||
metadata:
|
||||
name: vitastor-test-block-pvc
|
||||
namespace: default
|
||||
spec:
|
||||
containers:
|
||||
- name: vitastor-test-block-pvc
|
||||
image: nginx
|
||||
volumeDevices:
|
||||
- name: data
|
||||
devicePath: /dev/xvda
|
||||
volumes:
|
||||
- name: data
|
||||
persistentVolumeClaim:
|
||||
claimName: test-vitastor-pvc-block
|
||||
readOnly: false
|
||||
@@ -1,17 +0,0 @@
|
||||
apiVersion: v1
|
||||
kind: Pod
|
||||
metadata:
|
||||
name: vitastor-test-nginx
|
||||
namespace: default
|
||||
spec:
|
||||
containers:
|
||||
- name: vitastor-test-nginx
|
||||
image: nginx
|
||||
volumeMounts:
|
||||
- mountPath: /usr/share/nginx/html/s3
|
||||
name: data
|
||||
volumes:
|
||||
- name: data
|
||||
persistentVolumeClaim:
|
||||
claimName: test-vitastor-pvc
|
||||
readOnly: false
|
||||
@@ -5,7 +5,7 @@ package vitastor
|
||||
|
||||
const (
|
||||
vitastorCSIDriverName = "csi.vitastor.io"
|
||||
vitastorCSIDriverVersion = "0.6.17"
|
||||
vitastorCSIDriverVersion = "0.6.16"
|
||||
)
|
||||
|
||||
// Config struct fills the parameters of request or user input
|
||||
|
||||
@@ -67,44 +67,29 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
|
||||
klog.Infof("received node publish volume request %+v", protosanitizer.StripSecrets(req))
|
||||
|
||||
targetPath := req.GetTargetPath()
|
||||
isBlock := req.GetVolumeCapability().GetBlock() != nil
|
||||
|
||||
// Check that it's not already mounted
|
||||
_, error := mount.IsNotMountPoint(ns.mounter, targetPath)
|
||||
free, error := mount.IsNotMountPoint(ns.mounter, targetPath)
|
||||
if (error != nil)
|
||||
{
|
||||
if (os.IsNotExist(error))
|
||||
{
|
||||
if (isBlock)
|
||||
error := os.MkdirAll(targetPath, 0777)
|
||||
if (error != nil)
|
||||
{
|
||||
pathFile, err := os.OpenFile(targetPath, os.O_CREATE|os.O_RDWR, 0o600)
|
||||
if (err != nil)
|
||||
{
|
||||
klog.Errorf("failed to create block device mount target %s with error: %v", targetPath, err)
|
||||
return nil, status.Error(codes.Internal, err.Error())
|
||||
}
|
||||
err = pathFile.Close()
|
||||
if (err != nil)
|
||||
{
|
||||
klog.Errorf("failed to close %s with error: %v", targetPath, err)
|
||||
return nil, status.Error(codes.Internal, err.Error())
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
err := os.MkdirAll(targetPath, 0777)
|
||||
if (err != nil)
|
||||
{
|
||||
klog.Errorf("failed to create fs mount target %s with error: %v", targetPath, err)
|
||||
return nil, status.Error(codes.Internal, err.Error())
|
||||
}
|
||||
return nil, status.Error(codes.Internal, error.Error())
|
||||
}
|
||||
free = true
|
||||
}
|
||||
else
|
||||
{
|
||||
return nil, status.Error(codes.Internal, error.Error())
|
||||
}
|
||||
}
|
||||
if (!free)
|
||||
{
|
||||
return &csi.NodePublishVolumeResponse{}, nil
|
||||
}
|
||||
|
||||
ctxVars := make(map[string]string)
|
||||
err := json.Unmarshal([]byte(req.VolumeId), &ctxVars)
|
||||
@@ -164,6 +149,7 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
|
||||
|
||||
// Format the device (ext4 or xfs)
|
||||
fsType := req.GetVolumeCapability().GetMount().GetFsType()
|
||||
isBlock := req.GetVolumeCapability().GetBlock() != nil
|
||||
opt := req.GetVolumeCapability().GetMount().GetMountFlags()
|
||||
opt = append(opt, "_netdev")
|
||||
if ((req.VolumeCapability.AccessMode.Mode == csi.VolumeCapability_AccessMode_MULTI_NODE_READER_ONLY ||
|
||||
|
||||
2
debian/changelog
vendored
2
debian/changelog
vendored
@@ -1,4 +1,4 @@
|
||||
vitastor (0.6.17-1) unstable; urgency=medium
|
||||
vitastor (0.6.16-1) unstable; urgency=medium
|
||||
|
||||
* RDMA support
|
||||
* Bugfixes
|
||||
|
||||
1
debian/vitastor-client.install
vendored
1
debian/vitastor-client.install
vendored
@@ -2,6 +2,5 @@ usr/bin/vita
|
||||
usr/bin/vitastor-cli
|
||||
usr/bin/vitastor-rm
|
||||
usr/bin/vitastor-nbd
|
||||
usr/bin/vitastor-nfs
|
||||
usr/lib/*/libvitastor*.so*
|
||||
mon/make-osd.sh /usr/lib/vitastor
|
||||
|
||||
8
debian/vitastor.Dockerfile
vendored
8
debian/vitastor.Dockerfile
vendored
@@ -33,8 +33,8 @@ RUN set -e -x; \
|
||||
mkdir -p /root/packages/vitastor-$REL; \
|
||||
rm -rf /root/packages/vitastor-$REL/*; \
|
||||
cd /root/packages/vitastor-$REL; \
|
||||
cp -r /root/vitastor vitastor-0.6.17; \
|
||||
cd vitastor-0.6.17; \
|
||||
cp -r /root/vitastor vitastor-0.6.16; \
|
||||
cd vitastor-0.6.16; \
|
||||
ln -s /root/fio-build/fio-*/ ./fio; \
|
||||
FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
|
||||
ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
|
||||
@@ -47,8 +47,8 @@ RUN set -e -x; \
|
||||
rm -rf a b; \
|
||||
echo "dep:fio=$FIO" > debian/fio_version; \
|
||||
cd /root/packages/vitastor-$REL; \
|
||||
tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.6.17.orig.tar.xz vitastor-0.6.17; \
|
||||
cd vitastor-0.6.17; \
|
||||
tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.6.16.orig.tar.xz vitastor-0.6.16; \
|
||||
cd vitastor-0.6.16; \
|
||||
V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
|
||||
DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$V""$REL" "Rebuild for $REL"; \
|
||||
DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \
|
||||
|
||||
@@ -1,55 +0,0 @@
|
||||
#!/usr/bin/nodejs
|
||||
|
||||
const fs = require('fs');
|
||||
const yaml = require('yaml');
|
||||
|
||||
const L = {
|
||||
en: {},
|
||||
ru: {
|
||||
Type: 'Тип',
|
||||
Default: 'Значение по умолчанию',
|
||||
Minimum: 'Минимальное значение',
|
||||
},
|
||||
};
|
||||
const types = {
|
||||
en: {
|
||||
string: 'string',
|
||||
bool: 'boolean',
|
||||
int: 'integer',
|
||||
sec: 'seconds',
|
||||
ms: 'milliseconds',
|
||||
us: 'microseconds',
|
||||
},
|
||||
ru: {
|
||||
string: 'строка',
|
||||
bool: 'булево (да/нет)',
|
||||
int: 'целое число',
|
||||
sec: 'секунды',
|
||||
ms: 'миллисекунды',
|
||||
us: 'микросекунды',
|
||||
},
|
||||
};
|
||||
const params_files = fs.readdirSync(__dirname+'/params')
|
||||
.filter(f => f.substr(-4) == '.yml')
|
||||
.map(f => f.substr(0, f.length-4));
|
||||
|
||||
for (const file of params_files)
|
||||
{
|
||||
const cfg = yaml.parse(fs.readFileSync(__dirname+'/params/'+file+'.yml', { encoding: 'utf-8' }));
|
||||
for (const lang in types)
|
||||
{
|
||||
let out = '\n\n{{< toc >}}';
|
||||
for (const c of cfg)
|
||||
{
|
||||
out += `\n\n## ${c.name}\n\n`;
|
||||
out += `- ${L[lang]['Type'] || 'Type'}: ${c["type_"+lang] || types[lang][c.type] || c.type}\n`;
|
||||
if (c.default !== undefined)
|
||||
out += `- ${L[lang]['Default'] || 'Default'}: ${c.default}\n`;
|
||||
if (c.min !== undefined)
|
||||
out += `- ${L[lang]['Minimum'] || 'Minimum'}: ${c.min}\n`;
|
||||
out += `\n`+(c["info_"+lang] || c["info"]).replace(/\s+$/, '');
|
||||
}
|
||||
const head = fs.readFileSync(__dirname+'/params/head/'+file+'.'+lang+'.md', { encoding: 'utf-8' });
|
||||
fs.writeFileSync(__dirname+'/hugo/content/config/'+file+'.'+lang+'.md', head.replace(/\s+$/, '')+out+"\n");
|
||||
}
|
||||
}
|
||||
@@ -1,6 +0,0 @@
|
||||
---
|
||||
title: "{{ replace .Name "-" " " | title }}"
|
||||
date: {{ .Date }}
|
||||
draft: true
|
||||
---
|
||||
|
||||
@@ -1,35 +0,0 @@
|
||||
baseURL: http://localhost
|
||||
title: Vitastor
|
||||
theme: hugo-geekdoc
|
||||
#languageCode: en-us
|
||||
|
||||
pluralizeListTitles: false
|
||||
|
||||
# Geekdoc required configuration
|
||||
pygmentsUseClasses: true
|
||||
pygmentsCodeFences: true
|
||||
disablePathToLower: true
|
||||
|
||||
# Required if you want to render robots.txt template
|
||||
enableRobotsTXT: true
|
||||
|
||||
defaultContentLanguage: en
|
||||
languages:
|
||||
en:
|
||||
weight: 1
|
||||
languageName: English
|
||||
ru:
|
||||
weight: 1
|
||||
languageName: Русский
|
||||
|
||||
markup:
|
||||
goldmark:
|
||||
renderer:
|
||||
# Needed for mermaid shortcode
|
||||
unsafe: true
|
||||
tableOfContents:
|
||||
startLevel: 1
|
||||
endLevel: 9
|
||||
|
||||
taxonomies:
|
||||
tag: tags
|
||||
@@ -1,6 +0,0 @@
|
||||
## The Idea
|
||||
|
||||
Vitastor is a small, simple and fast clustered block storage (storage for VM drives),
|
||||
architecturally similar to Ceph which means strong consistency, primary-replication,
|
||||
symmetric clustering and automatic data distribution over any number of drives
|
||||
of any size with configurable redundancy (replication or erasure codes/XOR).
|
||||
@@ -1,61 +0,0 @@
|
||||
---
|
||||
title: Parameter Reference
|
||||
weight: 1
|
||||
---
|
||||
|
||||
Vitastor configuration consists of:
|
||||
- Configuration parameters (key-value), described here
|
||||
- [Pool configuration]({{< ref "config/pool" >}})
|
||||
- OSD placement tree configuration
|
||||
- Inode configuration i.e. image metadata like name, size and parent reference
|
||||
|
||||
Configuration parameters can be set in 3 places:
|
||||
- Configuration file (`/etc/vitastor/vitastor.conf` or other path)
|
||||
- etcd key `/vitastor/config/global`. Most variables can be set there, but etcd
|
||||
connection parameters should obviously be set in the configuration file.
|
||||
- Command line of Vitastor components: OSD, mon, fio and QEMU options,
|
||||
OpenStack/Proxmox/etc configuration. The latter doesn't allow to set all
|
||||
variables directly, but it allows to override the configuration file and
|
||||
set everything you need inside it.
|
||||
|
||||
In the future, additional configuration methods may be added:
|
||||
- OSD superblock which will, by design, contain parameters related to the disk
|
||||
layout and to one specific OSD.
|
||||
- OSD-specific keys in etcd like `/vitastor/config/osd/<number>`.
|
||||
|
||||
## Common Parameters
|
||||
|
||||
These are the most common parameters which apply to all components of Vitastor.
|
||||
|
||||
[See the list]({{< ref "common" >}})
|
||||
|
||||
## Cluster-Wide Disk Layout Parameters
|
||||
|
||||
These parameters apply to clients and OSDs and can't be changed after OSD
|
||||
initialization.
|
||||
|
||||
[See the list]({{< ref "layout-cluster" >}})
|
||||
|
||||
## OSD Disk Layout Parameters
|
||||
|
||||
These parameters apply to OSDs and can't be changed after OSD initialization.
|
||||
|
||||
[See the list]({{< ref "layout-osd" >}})
|
||||
|
||||
## Network Protocol Parameters
|
||||
|
||||
These parameters apply to clients and OSDs and can be changed with a restart.
|
||||
|
||||
[See the list]({{< ref "network" >}})
|
||||
|
||||
## Runtime OSD Parameters
|
||||
|
||||
These parameters apply to OSDs and can be changed with an OSD restart.
|
||||
|
||||
[See the list]({{< ref "osd" >}})
|
||||
|
||||
## Monitor Parameters
|
||||
|
||||
These parameters only apply to Monitors.
|
||||
|
||||
[See the list]({{< ref "monitor" >}})
|
||||
@@ -1,63 +0,0 @@
|
||||
---
|
||||
title: Перечень настроек
|
||||
weight: 1
|
||||
---
|
||||
|
||||
Конфигурация Vitastor состоит из:
|
||||
- Параметров (ключ-значение), описанных на данной странице
|
||||
- Настроек пулов
|
||||
- Настроек дерева OSD
|
||||
- Настроек инодов, т.е. метаданных образов, таких, как имя, размер и ссылки на
|
||||
родительский образ
|
||||
|
||||
Параметры конфигурации могут задаваться в 3 местах:
|
||||
- Файле конфигурации (`/etc/vitastor/vitastor.conf` или по другому пути)
|
||||
- Ключе в etcd `/vitastor/config/global`. Большая часть параметров может
|
||||
задаваться там, кроме, естественно, самих параметров соединения с etcd,
|
||||
которые должны задаваться в файле конфигурации
|
||||
- В командной строке компонентов Vitastor: OSD, монитора, опциях fio и QEMU,
|
||||
настроек OpenStack, Proxmox и т.п. Последние, как правило, не включают полный
|
||||
набор параметров напрямую, но разрешают определить путь к файлу конфигурации
|
||||
и задать любые параметры в нём.
|
||||
|
||||
В будущем также могут быть добавлены другие способы конфигурации:
|
||||
- Суперблок OSD, в котором будут храниться параметры OSD, связанные с дисковым
|
||||
форматом и с этим конкретным OSD.
|
||||
- OSD-специфичные ключи в etcd типа `/vitastor/config/osd/<номер>`.
|
||||
|
||||
## Общие параметры
|
||||
|
||||
Это наиболее общие параметры, используемые всеми компонентами Vitastor.
|
||||
|
||||
[Посмотреть список]({{< ref "common" >}})
|
||||
|
||||
## Дисковые параметры уровня кластера
|
||||
|
||||
Эти параметры используются клиентами и OSD и не могут быть изменены после
|
||||
инициализации OSD.
|
||||
|
||||
[Посмотреть список]({{< ref "layout-cluster" >}})
|
||||
|
||||
## Дисковые параметры OSD
|
||||
|
||||
Эти параметры используются OSD и не могут быть изменены после инициализации OSD.
|
||||
|
||||
[Посмотреть список]({{< ref "layout-osd" >}})
|
||||
|
||||
## Параметры сетевого протокола
|
||||
|
||||
Эти параметры используются клиентами и OSD и могут быть изменены с перезапуском.
|
||||
|
||||
[Посмотреть список]({{< ref "network" >}})
|
||||
|
||||
## Изменяемые параметры OSD
|
||||
|
||||
Эти параметры используются OSD и могут быть изменены с перезапуском.
|
||||
|
||||
[Посмотреть список]({{< ref "osd" >}})
|
||||
|
||||
## Параметры мониторов
|
||||
|
||||
Данные параметры используются только мониторами Vitastor.
|
||||
|
||||
[Посмотреть список]({{< ref "monitor" >}})
|
||||
@@ -1,178 +0,0 @@
|
||||
---
|
||||
title: Pool configuration
|
||||
weight: 100
|
||||
---
|
||||
|
||||
Pool configuration is set in etcd key `/vitastor/config/pools` in the following
|
||||
JSON format:
|
||||
|
||||
```
|
||||
{
|
||||
"<Numeric ID>": {
|
||||
"name": "<name>",
|
||||
...other parameters...
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
{{< toc >}}
|
||||
|
||||
# Parameters
|
||||
|
||||
## name
|
||||
|
||||
- Type: string
|
||||
- Required
|
||||
|
||||
Pool name.
|
||||
|
||||
## scheme
|
||||
|
||||
- Type: string
|
||||
- Required
|
||||
- One of: "replicated", "xor" or "jerasure"
|
||||
|
||||
Redundancy scheme used for data in this pool.
|
||||
|
||||
## pg_size
|
||||
|
||||
- Type: integer
|
||||
- Required
|
||||
|
||||
Total number of disks for PGs of this pool - i.e., number of replicas for
|
||||
replicated pools and number of data plus parity disks for EC/XOR pools.
|
||||
|
||||
## parity_chunks
|
||||
|
||||
- Type: integer
|
||||
|
||||
Number of parity chunks for EC/XOR pools. For such pools, data will be lost
|
||||
if you lose more than parity_chunks disks at once, so this parameter can be
|
||||
equally described as FTT (number of failures to tolerate).
|
||||
|
||||
Required for EC/XOR pools, ignored for replicated pools.
|
||||
|
||||
## pg_minsize
|
||||
|
||||
- Type: integer
|
||||
- Required
|
||||
|
||||
Number of available live disks for PGs of this pool to remain active.
|
||||
That is, if it becomes impossible to place PG data on at least (pg_minsize)
|
||||
OSDs, PG is deactivated for both read and write. So you know that a fresh
|
||||
write always goes to at least (pg_minsize) OSDs (disks).
|
||||
|
||||
FIXME: pg_minsize behaviour may be changed in the future to only make PGs
|
||||
read-only instead of deactivating them.
|
||||
|
||||
## pg_count
|
||||
|
||||
- Type: integer
|
||||
- Required
|
||||
|
||||
Number of PGs for this pool. The value should be big enough for the monitor /
|
||||
LP solver to be able to optimize data placement.
|
||||
|
||||
"Enough" is usually around 64-128 PGs per OSD, i.e. you set pg_count for pool
|
||||
to (total OSD count * 100 / pg_size). You can round it to the closest power of 2,
|
||||
because it makes it easier to reduce or increase PG count later by dividing or
|
||||
multiplying it by 2.
|
||||
|
||||
In Vitastor, PGs are ephemeral, so you can change pool PG count anytime just
|
||||
by overwriting pool configuration in etcd. Amount of the data affected by
|
||||
rebalance will be smaller if the new PG count is a multiple of the old PG count
|
||||
or vice versa.
|
||||
|
||||
## failure_domain
|
||||
|
||||
- Type: string
|
||||
- Default: host
|
||||
|
||||
Failure domain specification. Must be "host" or "osd" or refer to one of the
|
||||
placement tree levels, defined in [placement_levels]({{< ref "config/monitor#placement_levels" >}}).
|
||||
|
||||
Two replicas, or two parts in case of EC/XOR, of the same block of data are
|
||||
never put on OSDs in the same failure domain (for example, on the same host).
|
||||
So failure domain specifies the unit which failure you are protecting yourself
|
||||
from.
|
||||
|
||||
## max_osd_combinations
|
||||
|
||||
- Type: integer
|
||||
- Default: 10000
|
||||
|
||||
Vitastor data placement algorithm is based on the LP solver and OSD combinations
|
||||
which are fed to it are generated ramdonly. This parameter specifies the maximum
|
||||
number of combinations to generate when optimising PG placement.
|
||||
|
||||
This parameter usually doesn't require to be changed.
|
||||
|
||||
## pg_stripe_size
|
||||
|
||||
- Type: integer
|
||||
- Default: 0
|
||||
|
||||
Specifies the stripe size for this pool according to which images are split into
|
||||
different PGs. Stripe size can't be smaller than [block_size]({{< ref "config/layout-cluster#block_size" >}})
|
||||
multiplied by (pg_size - parity_chunks) for EC/XOR pools, or 1 for replicated pools,
|
||||
and the same value is used by default.
|
||||
|
||||
This means first `pg_stripe_size = (block_size * (pg_size-parity_chunks))` bytes
|
||||
of an image go to one PG, next `pg_stripe_size` bytes go to another PG and so on.
|
||||
|
||||
Usually doesn't require to be changed separately from the block size.
|
||||
|
||||
## root_node
|
||||
|
||||
- Type: string
|
||||
|
||||
Specifies the root node of the OSD tree to restrict this pool OSDs to.
|
||||
Referenced root node must exist in /vitastor/config/node_placement.
|
||||
|
||||
## osd_tags
|
||||
|
||||
- Type: string or array of strings
|
||||
|
||||
Specifies OSD tags to restrict this pool to. If multiple tags are specified,
|
||||
only OSDs having all of these tags will be used for this pool.
|
||||
|
||||
## primary_affinity_tags
|
||||
|
||||
- Type: string or array of strings
|
||||
|
||||
Specifies OSD tags to prefer putting primary OSDs in this pool to.
|
||||
Note that for EC/XOR pools Vitastor always prefers to put primary OSD on one
|
||||
of the OSDs containing a data chunk for a PG.
|
||||
|
||||
# Examples
|
||||
|
||||
## Replicated pool
|
||||
|
||||
```
|
||||
{
|
||||
"1": {
|
||||
"name":"testpool",
|
||||
"scheme":"replicated",
|
||||
"pg_size":2,
|
||||
"pg_minsize":1,
|
||||
"pg_count":256,
|
||||
"failure_domain":"host"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## Erasure-coded pool
|
||||
|
||||
```
|
||||
{
|
||||
"2": {
|
||||
"name":"ecpool",
|
||||
"scheme":"jerasure",
|
||||
"pg_size":3,
|
||||
"parity_chunks":1,
|
||||
"pg_minsize":2,
|
||||
"pg_count":256,
|
||||
"failure_domain":"host"
|
||||
}
|
||||
}
|
||||
```
|
||||
@@ -1,41 +0,0 @@
|
||||
---
|
||||
title: Packages
|
||||
weight: 2
|
||||
---
|
||||
|
||||
## Debian
|
||||
|
||||
- Trust Vitastor package signing key:
|
||||
`wget -q -O - https://vitastor.io/debian/pubkey | sudo apt-key add -`
|
||||
- Add Vitastor package repository to your /etc/apt/sources.list:
|
||||
- Debian 11 (Bullseye/Sid): `deb https://vitastor.io/debian bullseye main`
|
||||
- Debian 10 (Buster): `deb https://vitastor.io/debian buster main`
|
||||
- For Debian 10 (Buster) also enable backports repository:
|
||||
`deb http://deb.debian.org/debian buster-backports main`
|
||||
- Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu`
|
||||
|
||||
## CentOS
|
||||
|
||||
- Add Vitastor package repository:
|
||||
- CentOS 7: `yum install https://vitastor.io/rpms/centos/7/vitastor-release-1.0-1.el7.noarch.rpm`
|
||||
- CentOS 8: `dnf install https://vitastor.io/rpms/centos/8/vitastor-release-1.0-1.el8.noarch.rpm`
|
||||
- Enable EPEL: `yum/dnf install epel-release`
|
||||
- Enable additional CentOS repositories:
|
||||
- CentOS 7: `yum install centos-release-scl`
|
||||
- CentOS 8: `dnf install centos-release-advanced-virtualization`
|
||||
- Enable elrepo-kernel:
|
||||
- CentOS 7: `yum install https://www.elrepo.org/elrepo-release-7.el7.elrepo.noarch.rpm`
|
||||
- CentOS 8: `dnf install https://www.elrepo.org/elrepo-release-8.el8.elrepo.noarch.rpm`
|
||||
- Install packages: `yum/dnf install vitastor lpsolve etcd kernel-ml qemu-kvm`
|
||||
|
||||
## Installation requirements
|
||||
|
||||
- Linux kernel 5.4 or newer, for io_uring support. 5.8 or later is highly
|
||||
recommended because io_uring is a relatively new technology and there is
|
||||
at least one bug which reproduces with io_uring and HP SmartArray
|
||||
controllers in 5.4
|
||||
- liburing 0.4 or newer
|
||||
- lp_solve
|
||||
- etcd 3.4.15 or newer. Earlier versions won't work because of various bugs,
|
||||
for example [#12402](https://github.com/etcd-io/etcd/pull/12402).
|
||||
- node.js 10 or newer
|
||||
@@ -1,72 +0,0 @@
|
||||
---
|
||||
title: Quick Start
|
||||
weight: 1
|
||||
---
|
||||
|
||||
Prepare:
|
||||
|
||||
- Get some SATA or NVMe SSDs with capacitors (server-grade drives). You can use desktop SSDs
|
||||
with lazy fsync, but prepare for inferior single-thread latency. Read more about capacitors
|
||||
[here]({{< ref "config/layout-cluster#immediate_commit" >}}).
|
||||
- Get a fast network (at least 10 Gbit/s). Something like Mellanox ConnectX-4 with RoCEv2 is ideal.
|
||||
- Disable CPU powersaving: `cpupower idle-set -D 0 && cpupower frequency-set -g performance`.
|
||||
- [Install Vitastor packages]({{< ref "installation/packages" >}}).
|
||||
|
||||
## Configure monitors
|
||||
|
||||
On the monitor hosts:
|
||||
- Edit variables at the top of `/usr/lib/vitastor/mon/make-units.sh` to desired values.
|
||||
- Create systemd units for the monitor and etcd: `/usr/lib/vitastor/mon/make-units.sh`
|
||||
- Start etcd and monitors: `systemctl start etcd vitastor-mon`
|
||||
|
||||
## Configure OSDs
|
||||
|
||||
- Put etcd_address and osd_network into `/etc/vitastor/vitastor.conf`. Example:
|
||||
```
|
||||
{
|
||||
"etcd_address": ["10.200.1.10:2379","10.200.1.11:2379","10.200.1.12:2379"],
|
||||
"osd_network": "10.200.1.0/24"
|
||||
}
|
||||
```
|
||||
- Initialize OSDs:
|
||||
- Simplest, SSD-only: `/usr/lib/vitastor/mon/make-osd.sh /dev/disk/by-partuuid/XXX [/dev/disk/by-partuuid/YYY ...]`
|
||||
- Hybrid, HDD+SSD: `/usr/lib/vitastor/mon/make-osd-hybrid.js /dev/sda /dev/sdb ...` — pass all your
|
||||
devices (HDD and SSD) to this script — it will partition disks and initialize journals on its own.
|
||||
This script skips HDDs which are already partitioned so if you want to use non-empty disks for
|
||||
Vitastor you should first wipe them with `wipefs -a`. SSDs with GPT partition table are not skipped,
|
||||
but some free unpartitioned space must be available because the script creates new partitions for journals.
|
||||
- You can change OSD configuration in units or in `vitastor.conf`.
|
||||
Check [Configuration Reference]({{< ref "config" >}}) for parameter descriptions.
|
||||
- `systemctl start vitastor.target` everywhere.
|
||||
- If all your drives have capacitors, create global configuration in etcd: \
|
||||
`etcdctl --endpoints=... put /vitastor/config/global '{"immediate_commit":"all"}'`
|
||||
|
||||
## Create a pool
|
||||
|
||||
Create pool configuration in etcd:
|
||||
|
||||
```
|
||||
etcdctl --endpoints=... put /vitastor/config/pools '{"1":{"name":"testpool",
|
||||
"scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":256,"failure_domain":"host"}}'
|
||||
```
|
||||
|
||||
For jerasure pools the configuration should look like the following:
|
||||
|
||||
```
|
||||
etcdctl --endpoints=... put /vitastor/config/pools '{"2":{"name":"ecpool",
|
||||
"scheme":"jerasure","pg_size":4,"parity_chunks":2,"pg_minsize":2,"pg_count":256,"failure_domain":"host"}`
|
||||
```
|
||||
|
||||
After you do this, one of the monitors will configure PGs and OSDs will start them.
|
||||
|
||||
You can check PG states with `etcdctl --endpoints=... get --prefix /vitastor/pg/state`. All PGs should become 'active'.
|
||||
|
||||
## Create an image
|
||||
|
||||
Use vitastor-cli ([read CLI documentation here]({{< ref "usage/cli" >}})):
|
||||
|
||||
```
|
||||
vitastor-cli create -s 10G testimg
|
||||
```
|
||||
|
||||
After that, you can run benchmarks or start QEMU manually with this image.
|
||||
@@ -1,54 +0,0 @@
|
||||
---
|
||||
title: Building from Source
|
||||
weight: 3
|
||||
---
|
||||
|
||||
## Requirements
|
||||
|
||||
- gcc and g++ 8 or newer, clang 10 or newer, or other compiler with C++11 plus
|
||||
designated initializers support from C++20
|
||||
- CMake
|
||||
- liburing, jerasure headers
|
||||
|
||||
## Basic instructions
|
||||
|
||||
Download source, for example using git: `git clone --recurse-submodules https://yourcmc.ru/git/vitalif/vitastor/`
|
||||
|
||||
Get `fio` source and symlink it into `<vitastor>/fio`. If you don't want to build fio engine,
|
||||
you can disable it by passing `-DWITH_FIO=no` to cmake.
|
||||
|
||||
Build and install Vitastor:
|
||||
|
||||
```
|
||||
cd vitastor
|
||||
mkdir build
|
||||
cd build
|
||||
cmake .. && make -j8 install
|
||||
```
|
||||
|
||||
## QEMU Driver
|
||||
|
||||
It's recommended to build the QEMU driver (qemu_driver.c) in-tree, as a part of
|
||||
QEMU build process. To do that:
|
||||
- Install vitastor client library headers (from source or from vitastor-client-dev package)
|
||||
- Take a corresponding patch from `patches/qemu-*-vitastor.patch` and apply it to QEMU source
|
||||
- Copy `src/qemu_driver.c` to QEMU source directory as `block/block-vitastor.c`
|
||||
- Build QEMU as usual
|
||||
|
||||
But it is also possible to build it out-of-tree. To do that:
|
||||
- Get QEMU source, begin to build it, stop the build and copy headers:
|
||||
- `<qemu>/include` → `<vitastor>/qemu/include`
|
||||
- Debian:
|
||||
* Use qemu packages from the main repository
|
||||
* `<qemu>/b/qemu/config-host.h` → `<vitastor>/qemu/b/qemu/config-host.h`
|
||||
* `<qemu>/b/qemu/qapi` → `<vitastor>/qemu/b/qemu/qapi`
|
||||
- CentOS 8:
|
||||
* Use qemu packages from the Advanced-Virtualization repository. To enable it, run
|
||||
`yum install centos-release-advanced-virtualization.noarch` and then `yum install qemu`
|
||||
* `<qemu>/config-host.h` → `<vitastor>/qemu/b/qemu/config-host.h`
|
||||
* For QEMU 3.0+: `<qemu>/qapi` → `<vitastor>/qemu/b/qemu/qapi`
|
||||
* For QEMU 2.0+: `<qemu>/qapi-types.h` → `<vitastor>/qemu/b/qemu/qapi-types.h`
|
||||
- `config-host.h` and `qapi` are required because they contain generated headers
|
||||
- Configure Vitastor with `WITH_QEMU=yes` and, if you're on RHEL, also with `QEMU_PLUGINDIR=qemu-kvm`:
|
||||
`cmake .. -DWITH_QEMU=yes`.
|
||||
- After that, Vitastor will build `block-vitastor.so` during its build process.
|
||||
@@ -1,4 +0,0 @@
|
||||
---
|
||||
title: Introduction
|
||||
weight: -1
|
||||
---
|
||||
@@ -1,73 +0,0 @@
|
||||
---
|
||||
title: Architecture
|
||||
weight: 3
|
||||
---
|
||||
|
||||
For people familiar with Ceph, Vitastor is quite similar:
|
||||
|
||||
- Vitastor also has Pools, PGs, OSDs, Monitors, Failure Domains, Placement Tree:
|
||||
- OSD (Object Storage Daemon) is a process that stores data and serves read/write requests.
|
||||
- PG (Placement Group) is a container for data that (normally) shares the same replicas.
|
||||
- Pool is a container for data that has the same redundancy scheme and placement rules.
|
||||
- Monitor is a separate daemon that watches cluster state and controls data distribution.
|
||||
- Failure Domain is a group of OSDs that you allow to fail. It's "host" by default.
|
||||
- Placement Tree groups OSDs in a hierarchy to later split them into Failure Domains.
|
||||
- Vitastor also distributes every image data across the whole cluster.
|
||||
- Vitastor is also transactional (every write to the cluster is atomic).
|
||||
- OSDs also have journal and metadata and they can also be put on separate drives.
|
||||
- Just like in Ceph, client library attempts to recover from any cluster failure so
|
||||
you can basically reboot the whole cluster and only pause, but not crash, your clients
|
||||
(please report a bug if the client crashes in that case).
|
||||
|
||||
However, there are also differences:
|
||||
|
||||
- Vitastor's main focus is on SSDs. Hybrid SSD+HDD setups are also possible.
|
||||
- Vitastor OSD is (and will always be) single-threaded. If you want to dedicate more than 1 core
|
||||
per drive you should run multiple OSDs each on a different partition of the drive.
|
||||
Vitastor isn't CPU-hungry though (as opposed to Ceph), so 1 core is sufficient in a lot of cases.
|
||||
- Metadata and journal are always kept in memory. Metadata size depends linearly on drive capacity
|
||||
and data store block size which is 128 KB by default. With 128 KB blocks metadata should occupy
|
||||
around 512 MB per 1 TB (which is still less than Ceph wants). Journal doesn't have to be big,
|
||||
the example test below was conducted with only 16 MB journal. A big journal is probably even
|
||||
harmful as dirty write metadata also take some memory.
|
||||
- Vitastor storage layer doesn't have internal copy-on-write or redirect-write. I know that maybe
|
||||
it's possible to create a good copy-on-write storage, but it's much harder and makes performance
|
||||
less deterministic, so CoW isn't used in Vitastor.
|
||||
- The basic layer of Vitastor is block storage with fixed-size blocks, not object storage with
|
||||
rich semantics like in Ceph (RADOS).
|
||||
- There's a "lazy fsync" mode which allows to batch writes before flushing them to the disk.
|
||||
This allows to use Vitastor with desktop SSDs, but still lowers performance due to additional
|
||||
network roundtrips, so use server SSDs with capacitor-based power loss protection
|
||||
("Advanced Power Loss Protection") for best performance.
|
||||
- PGs are ephemeral. This means that they aren't stored on data disks and only exist in memory
|
||||
while OSDs are running.
|
||||
- Recovery process is per-object (per-block), not per-PG. Also there are no PGLOGs.
|
||||
- Monitors don't store data. Cluster configuration and state is stored in etcd in simple human-readable
|
||||
JSON structures. Monitors only watch cluster state and handle data movement.
|
||||
Thus Vitastor's Monitor isn't a critical component of the system and is more similar to Ceph's Manager.
|
||||
Vitastor's Monitor is implemented in node.js.
|
||||
- PG distribution isn't based on consistent hashes. All PG mappings are stored in etcd.
|
||||
Rebalancing PGs between OSDs is done by mathematical optimization - data distribution problem
|
||||
is reduced to a linear programming problem and solved by lp_solve. This allows for almost
|
||||
perfect (96-99% uniformity compared to Ceph's 80-90%) data distribution in most cases, ability
|
||||
to map PGs by hand without breaking rebalancing logic, reduced OSD peer-to-peer communication
|
||||
(on average, OSDs have fewer peers) and less data movement. It also probably has a drawback -
|
||||
this method may fail in very large clusters, but up to several hundreds of OSDs it's perfectly fine.
|
||||
It's also easy to add consistent hashes in the future if something proves their necessity.
|
||||
- There's no separate CRUSH layer. You select pool redundancy scheme, placement root, failure domain
|
||||
and so on directly in pool configuration.
|
||||
- Images are global i.e. you can't create multiple images with the same name in different pools.
|
||||
|
||||
## Implementation Principles
|
||||
|
||||
- I like architecturally simple solutions. Vitastor is and will always be designed
|
||||
exactly like that.
|
||||
- I also like reinventing the wheel to some extent, like writing my own HTTP client
|
||||
for etcd interaction instead of using prebuilt libraries, because in this case
|
||||
I'm confident about what my code does and what it doesn't do.
|
||||
- I don't care about C++ "best practices" like RAII or proper inheritance or usage of
|
||||
smart pointers or whatever and I don't intend to change my mind, so if you're here
|
||||
looking for ideal reference C++ code, this probably isn't the right place.
|
||||
- I like node.js better than any other dynamically-typed language interpreter
|
||||
because it's faster than any other interpreter in the world, has neutral C-like
|
||||
syntax and built-in event loop. That's why Monitor is implemented in node.js.
|
||||
@@ -1,34 +0,0 @@
|
||||
---
|
||||
title: Author and License
|
||||
weight: 3
|
||||
---
|
||||
|
||||
Copyright (c) Vitaliy Filippov (vitalif [at] yourcmc.ru), 2019+
|
||||
|
||||
Join Vitastor Telegram Chat: https://t.me/vitastor
|
||||
|
||||
All server-side code (OSD, Monitor and so on) is licensed under the terms of
|
||||
Vitastor Network Public License 1.1 (VNPL 1.1), a copyleft license based on
|
||||
GNU GPLv3.0 with the additional "Network Interaction" clause which requires
|
||||
opensourcing all programs directly or indirectly interacting with Vitastor
|
||||
through a computer network and expressly designed to be used in conjunction
|
||||
with it ("Proxy Programs"). Proxy Programs may be made public not only under
|
||||
the terms of the same license, but also under the terms of any GPL-Compatible
|
||||
Free Software License, as listed by the Free Software Foundation.
|
||||
This is a stricter copyleft license than the Affero GPL.
|
||||
|
||||
Please note that VNPL doesn't require you to open the code of proprietary
|
||||
software running inside a VM if it's not specially designed to be used with
|
||||
Vitastor.
|
||||
|
||||
Basically, you can't use the software in a proprietary environment to provide
|
||||
its functionality to users without opensourcing all intermediary components
|
||||
standing between the user and Vitastor or purchasing a commercial license
|
||||
from the author 😀.
|
||||
|
||||
Client libraries (cluster_client and so on) are dual-licensed under the same
|
||||
VNPL 1.1 and also GNU GPL 2.0 or later to allow for compatibility with GPLed
|
||||
software like QEMU and fio.
|
||||
|
||||
You can find the full text of VNPL-1.1 in the file [VNPL-1.1.txt](VNPL-1.1.txt).
|
||||
GPL 2.0 is also included in this repository as [GPL-2.0.txt](GPL-2.0.txt).
|
||||
@@ -1,60 +0,0 @@
|
||||
---
|
||||
title: Features
|
||||
weight: 1
|
||||
---
|
||||
|
||||
Vitastor is currently a pre-release and it still misses some important features.
|
||||
However, the following is implemented:
|
||||
|
||||
- Basic part: highly-available block storage with symmetric clustering and no SPOF
|
||||
- Performance ;-D
|
||||
- Multiple redundancy schemes: Replication, XOR n+1, Reed-Solomon erasure codes
|
||||
based on jerasure library with any number of data and parity drives in a group
|
||||
- Configuration via simple JSON data structures in etcd (parameters, pools and images)
|
||||
- Automatic data distribution over OSDs, with support for:
|
||||
- Mathematical optimization for better uniformity and less data movement
|
||||
- Multiple pools
|
||||
- Placement tree, OSD selection by tags (device classes) and placement root
|
||||
- Configurable failure domains
|
||||
- Recovery of degraded blocks
|
||||
- Rebalancing (data movement between OSDs)
|
||||
- Lazy fsync support
|
||||
- Per-OSD and per-image I/O and space usage statistics in etcd
|
||||
- Snapshots and copy-on-write image clones
|
||||
- Write throttling to smooth random write workloads in SSD+HDD configurations
|
||||
- RDMA/RoCEv2 support via libibverbs
|
||||
|
||||
CLI (vitastor-cli):
|
||||
- Pool listing and space stats (df)
|
||||
- Image listing, space and I/O stats (ls)
|
||||
- Image and snapshot creation (create, modify)
|
||||
- Image removal and snapshot merge (rm, flatten, merge, rm-data)
|
||||
|
||||
Plugins and packaging:
|
||||
- Debian and CentOS packages
|
||||
- Generic user-space client library
|
||||
- Native QEMU driver
|
||||
- Loadable fio engine for benchmarks
|
||||
- NBD proxy for kernel mounts
|
||||
- CSI plugin for Kubernetes
|
||||
- OpenStack support: Cinder driver, Nova and libvirt patches
|
||||
- Proxmox storage plugin and packages
|
||||
|
||||
## Roadmap
|
||||
|
||||
The following features are planned for the future:
|
||||
|
||||
- Better OSD creation and auto-start tools
|
||||
- Other administrative tools
|
||||
- Web GUI
|
||||
- OpenNebula plugin
|
||||
- iSCSI proxy
|
||||
- Simplified NFS proxy
|
||||
- Multi-threaded client
|
||||
- Faster failover
|
||||
- Scrubbing without checksums (verification of replicas)
|
||||
- Checksums
|
||||
- Tiered storage (SSD caching)
|
||||
- NVDIMM support
|
||||
- Compression (possibly)
|
||||
- Read caching using system page cache (possibly)
|
||||
@@ -1,93 +0,0 @@
|
||||
---
|
||||
title: Example Comparison with Ceph
|
||||
weight: 4
|
||||
---
|
||||
|
||||
Hardware configuration: 4 nodes, each with:
|
||||
- 6x SATA SSD Intel D3-S4510 3.84 TB
|
||||
- 2x Xeon Gold 6242 (16 cores @ 2.8 GHz)
|
||||
- 384 GB RAM
|
||||
- 1x 25 GbE network interface (Mellanox ConnectX-4 LX), connected to a Juniper QFX5200 switch
|
||||
|
||||
CPU powersaving was disabled. Both Vitastor and Ceph were configured with 2 OSDs per 1 SSD.
|
||||
|
||||
All of the results below apply to 4 KB blocks and random access (unless indicated otherwise).
|
||||
|
||||
T8Q64 tests were conducted over 8 400GB RBD images from all hosts (every host was running 2 instances of fio).
|
||||
This is because Ceph has performance penalties related to running multiple clients over a single RBD image.
|
||||
|
||||
cephx_sign_messages was set to false during tests, RocksDB and Bluestore settings were left at defaults.
|
||||
|
||||
T8Q64 read test was conducted over 1 larger inode (3.2T) from all hosts (every host was running 2 instances of fio).
|
||||
Vitastor has no performance penalties related to running multiple clients over a single inode.
|
||||
If conducted from one node with all primary OSDs moved to other nodes the result was slightly lower (689000 iops),
|
||||
this is because all operations resulted in network roundtrips between the client and the primary OSD.
|
||||
When fio was colocated with OSDs (like in Ceph benchmarks above), 1/4 of the read workload actually
|
||||
used the loopback network.
|
||||
|
||||
Vitastor was configured with: `--disable_data_fsync true --immediate_commit all --flusher_count 8
|
||||
--disk_alignment 4096 --journal_block_size 4096 --meta_block_size 4096
|
||||
--journal_no_same_sector_overwrites true --journal_sector_buffer_count 1024
|
||||
--journal_size 16777216`.
|
||||
|
||||
## Raw drive performance
|
||||
|
||||
- T1Q1 write ~27000 iops (~0.037ms latency)
|
||||
- T1Q1 read ~9800 iops (~0.101ms latency)
|
||||
- T1Q32 write ~60000 iops
|
||||
- T1Q32 read ~81700 iops
|
||||
|
||||
## 2 replicas
|
||||
|
||||
### Ceph 15.2.4 (Bluestore)
|
||||
|
||||
- T1Q1 write ~1000 iops (~1ms latency)
|
||||
- T1Q1 read ~1750 iops (~0.57ms latency)
|
||||
- T8Q64 write ~100000 iops, total CPU usage by OSDs about 40 virtual cores on each node
|
||||
- T8Q64 read ~480000 iops, total CPU usage by OSDs about 40 virtual cores on each node
|
||||
|
||||
In fact, not that bad for Ceph. These servers are an example of well-balanced Ceph nodes.
|
||||
However, CPU usage and I/O latency were through the roof, as usual.
|
||||
|
||||
### Vitastor 0.4.0 (native)
|
||||
|
||||
- T1Q1 write: 7087 iops (0.14ms latency)
|
||||
- T1Q1 read: 6838 iops (0.145ms latency)
|
||||
- T2Q64 write: 162000 iops, total CPU usage by OSDs about 3 virtual cores on each node
|
||||
- T8Q64 read: 895000 iops, total CPU usage by OSDs about 4 virtual cores on each node
|
||||
- Linear write (4M T1Q32): 2800 MB/s
|
||||
- Linear read (4M T1Q32): 1500 MB/s
|
||||
|
||||
### Vitastor 0.4.0 (NBD)
|
||||
|
||||
NBD is currently required to mount Vitastor via kernel, but it imposes additional overhead
|
||||
due to additional copying between the kernel and userspace. This mostly hurts linear
|
||||
bandwidth, not iops.
|
||||
|
||||
Vitastor with single-threaded NBD on the same hardware:
|
||||
- T1Q1 write: 6000 iops (0.166ms latency)
|
||||
- T1Q1 read: 5518 iops (0.18ms latency)
|
||||
- T1Q128 write: 94400 iops
|
||||
- T1Q128 read: 103000 iops
|
||||
- Linear write (4M T1Q128): 1266 MB/s (compared to 2800 MB/s via fio)
|
||||
- Linear read (4M T1Q128): 975 MB/s (compared to 1500 MB/s via fio)
|
||||
|
||||
## EC/XOR 2+1
|
||||
|
||||
### Ceph 15.2.4
|
||||
|
||||
- T1Q1 write: 730 iops (~1.37ms latency)
|
||||
- T1Q1 read: 1500 iops with cold cache (~0.66ms latency), 2300 iops after 2 minute metadata cache warmup (~0.435ms latency)
|
||||
- T4Q128 write (4 RBD images): 45300 iops, total CPU usage by OSDs about 30 virtual cores on each node
|
||||
- T8Q64 read (4 RBD images): 278600 iops, total CPU usage by OSDs about 40 virtual cores on each node
|
||||
- Linear write (4M T1Q32): 1950 MB/s before preallocation, 2500 MB/s after preallocation
|
||||
- Linear read (4M T1Q32): 2400 MB/s
|
||||
|
||||
### Vitastor 0.4.0
|
||||
|
||||
- T1Q1 write: 2808 iops (~0.355ms latency)
|
||||
- T1Q1 read: 6190 iops (~0.16ms latency)
|
||||
- T2Q64 write: 85500 iops, total CPU usage by OSDs about 3.4 virtual cores on each node
|
||||
- T8Q64 read: 812000 iops, total CPU usage by OSDs about 4.7 virtual cores on each node
|
||||
- Linear write (4M T1Q32): 3200 MB/s
|
||||
- Linear read (4M T1Q32): 1800 MB/s
|
||||
@@ -1,46 +0,0 @@
|
||||
---
|
||||
title: Vitastor's Theoretical Maximum Performance
|
||||
weight: 3
|
||||
---
|
||||
|
||||
Replicated setups:
|
||||
- Single-threaded (T1Q1) read latency: 1 network roundtrip + 1 disk read.
|
||||
- Single-threaded write+fsync latency:
|
||||
- With immediate commit: 2 network roundtrips + 1 disk write.
|
||||
- With lazy commit: 4 network roundtrips + 1 disk write + 1 disk flush.
|
||||
- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
|
||||
- Saturated parallel write iops: min(network bandwidth, sum(disk write iops / number of replicas / write amplification)).
|
||||
|
||||
EC/XOR setups:
|
||||
- Single-threaded (T1Q1) read latency: 1.5 network roundtrips + 1 disk read.
|
||||
- Single-threaded write+fsync latency:
|
||||
- With immediate commit: 3.5 network roundtrips + 1 disk read + 2 disk writes.
|
||||
- With lazy commit: 5.5 network roundtrips + 1 disk read + 2 disk writes + 2 disk fsyncs.
|
||||
- 0.5 in actually (k-1)/k which means that an additional roundtrip doesn't happen when
|
||||
the read sub-operation can be served locally.
|
||||
- Saturated parallel read iops: min(network bandwidth, sum(disk read iops)).
|
||||
- Saturated parallel write iops: min(network bandwidth, sum(disk write iops * number of data drives / (number of data + parity drives) / write amplification)).
|
||||
In fact, you should put disk write iops under the condition of ~10% reads / ~90% writes in this formula.
|
||||
|
||||
Write amplification for 4 KB blocks is usually 3-5 in Vitastor:
|
||||
1. Journal block write
|
||||
2. Journal data write
|
||||
3. Metadata block write
|
||||
4. Another journal block write for EC/XOR setups
|
||||
5. Data block write
|
||||
|
||||
If you manage to get an SSD which handles 512 byte blocks well (Optane?) you may
|
||||
lower 1, 3 and 4 to 512 bytes (1/8 of data size) and get WA as low as 2.375.
|
||||
|
||||
Lazy fsync also reduces WA for parallel workloads because journal blocks are only
|
||||
written when they fill up or fsync is requested.
|
||||
|
||||
## In Practice
|
||||
|
||||
In practice, using tests from [Understanding Performance]({{< ref "performance/understanding" >}})
|
||||
and good server-grade SSD/NVMe drives, you should head for:
|
||||
- At least 5000 T1Q1 replicated read and write iops (maximum 0.2ms latency)
|
||||
- At least ~80k parallel read iops or ~30k write iops per 1 core (1 OSD)
|
||||
- Disk-speed or wire-speed linear reads and writes, whichever is the bottleneck in your case
|
||||
|
||||
If your results are lower, that may mean you have bad drives, bad network or some kind of misconfiguration.
|
||||
@@ -1,6 +0,0 @@
|
||||
---
|
||||
title: Tuning
|
||||
weight: 2
|
||||
---
|
||||
|
||||
- Disable CPU powersaving
|
||||
@@ -1,52 +0,0 @@
|
||||
---
|
||||
title: Understanding Storage Performance
|
||||
weight: 1
|
||||
---
|
||||
|
||||
The most important thing for fast storage is latency, not parallel iops.
|
||||
|
||||
The best possible latency is achieved with one thread and queue depth of 1 which basically means
|
||||
"client load as low as possible". In this case IOPS = 1/latency, and this number doesn't
|
||||
scale with number of servers, drives, server processes or threads and so on.
|
||||
Single-threaded IOPS and latency numbers only depend on *how fast a single daemon is*.
|
||||
|
||||
Why is it important? It's important because some of the applications *can't* use
|
||||
queue depth greater than 1 because their task isn't parallelizable. A notable example
|
||||
is any ACID DBMS because all of them write their WALs sequentially with fsync()s.
|
||||
|
||||
fsync, by the way, is another important thing often missing in benchmarks. The point is
|
||||
that drives have cache buffers and don't guarantee that your data is actually persisted
|
||||
until you call fsync() which is translated to a FLUSH CACHE command by the OS.
|
||||
|
||||
Desktop SSDs are very fast without fsync - NVMes, for example, can process ~80000 write
|
||||
operations per second with queue depth of 1 without fsync - but they're really slow with
|
||||
fsync because they have to actually write data to flash chips when you call fsync. Typical
|
||||
number is around 1000-2000 iops with fsync.
|
||||
|
||||
Server SSDs often have supercapacitors that act as a built-in UPS and allow the drive
|
||||
to flush its DRAM cache to the persistent flash storage when a power loss occurs.
|
||||
This makes them perform equally well with and without fsync. This feature is called
|
||||
"Advanced Power Loss Protection" by Intel; other vendors either call it similarly
|
||||
or directly as "Full Capacitor-Based Power Loss Protection".
|
||||
|
||||
All software-defined storages that I currently know are slow in terms of latency.
|
||||
Notable examples are Ceph and internal SDSes used by cloud providers like Amazon, Google,
|
||||
Yandex and so on. They're all slow and can only reach ~0.3ms read and ~0.6ms 4 KB write latency
|
||||
with best-in-slot hardware.
|
||||
|
||||
And that's in the SSD era when you can buy an SSD that has ~0.04ms latency for 100 $.
|
||||
|
||||
I use the following 6 commands with small variations to benchmark any storage:
|
||||
|
||||
- Linear write:
|
||||
`fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4M -iodepth=32 -rw=write -runtime=60 -filename=/dev/sdX`
|
||||
- Linear read:
|
||||
`fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4M -iodepth=32 -rw=read -runtime=60 -filename=/dev/sdX`
|
||||
- Random write latency (T1Q1, this hurts storages the most):
|
||||
`fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=1 -fsync=1 -rw=randwrite -runtime=60 -filename=/dev/sdX`
|
||||
- Random read latency (T1Q1):
|
||||
`fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=1 -rw=randread -runtime=60 -filename=/dev/sdX`
|
||||
- Parallel write iops (use numjobs if a single CPU core is insufficient to saturate the load):
|
||||
`fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=128 [-numjobs=4 -group_reporting] -rw=randwrite -runtime=60 -filename=/dev/sdX`
|
||||
- Parallel read iops (use numjobs if a single CPU core is insufficient to saturate the load):
|
||||
`fio -ioengine=libaio -direct=1 -invalidate=1 -name=test -bs=4k -iodepth=128 [-numjobs=4 -group_reporting] -rw=randread -runtime=60 -filename=/dev/sdX`
|
||||
@@ -1,183 +0,0 @@
|
||||
---
|
||||
title: Vitastor CLI
|
||||
weight: 1
|
||||
---
|
||||
|
||||
vitastor-cli is a command-line tool for administrative tasks like image management.
|
||||
|
||||
It supports the following commands:
|
||||
|
||||
{{< toc >}}
|
||||
|
||||
Global options:
|
||||
|
||||
```
|
||||
--etcd_address ADDR Etcd connection address
|
||||
--iodepth N Send N operations in parallel to each OSD when possible (default 32)
|
||||
--parallel_osds M Work with M osds in parallel when possible (default 4)
|
||||
--progress 1|0 Report progress (default 1)
|
||||
--cas 1|0 Use online CAS writes when possible (default auto)
|
||||
--no-color Disable colored output
|
||||
--json JSON output
|
||||
```
|
||||
|
||||
## status
|
||||
|
||||
`vitastor-cli status`
|
||||
|
||||
Show cluster status.
|
||||
|
||||
Example output:
|
||||
|
||||
```
|
||||
cluster:
|
||||
etcd: 1 / 1 up, 1.8 M database size
|
||||
mon: 1 up, master stump
|
||||
osd: 8 / 12 up
|
||||
|
||||
data:
|
||||
raw: 498.5 G used, 301.2 G / 799.7 G available, 399.8 G down
|
||||
state: 156.6 G clean, 97.6 G misplaced
|
||||
pools: 2 / 3 active
|
||||
pgs: 30 active
|
||||
34 active+has_misplaced
|
||||
32 offline
|
||||
|
||||
io:
|
||||
client: 0 B/s rd, 0 op/s rd, 0 B/s wr, 0 op/s wr
|
||||
rebalance: 989.8 M/s, 7.9 K op/s
|
||||
```
|
||||
|
||||
## df
|
||||
|
||||
`vitastor-cli df`
|
||||
|
||||
Show pool space statistics.
|
||||
|
||||
Example output:
|
||||
|
||||
```
|
||||
NAME SCHEME PGS TOTAL USED AVAILABLE USED% EFFICIENCY
|
||||
testpool 2/1 32 100 G 34.2 G 60.7 G 39.23% 100%
|
||||
size1 1/1 32 199.9 G 10 G 121.5 G 39.23% 100%
|
||||
kaveri 2/1 32 0 B 10 G 0 B 100% 0%
|
||||
```
|
||||
|
||||
In the example above, "kaveri" pool has "zero" efficiency because all its OSD are down.
|
||||
|
||||
## ls
|
||||
|
||||
`vitastor-cli ls [-l] [-p POOL] [--sort FIELD] [-r] [-n N] [<glob> ...]`
|
||||
|
||||
List images (only matching `<glob>` pattern(s) if passed).
|
||||
|
||||
Options:
|
||||
|
||||
```
|
||||
-p|--pool POOL Filter images by pool ID or name
|
||||
-l|--long Also report allocated size and I/O statistics
|
||||
--del Also include delete operation statistics
|
||||
--sort FIELD Sort by specified field (name, size, used_size, <read|write|delete>_<iops|bps|lat|queue>)
|
||||
-r|--reverse Sort in descending order
|
||||
-n|--count N Only list first N items
|
||||
```
|
||||
|
||||
Example output:
|
||||
|
||||
```
|
||||
NAME POOL SIZE USED READ IOPS QUEUE LAT WRITE IOPS QUEUE LAT FLAGS PARENT
|
||||
debian9 testpool 20 G 12.3 G 0 B/s 0 0 0 us 0 B/s 0 0 0 us RO
|
||||
pve/vm-100-disk-0 testpool 20 G 0 B 0 B/s 0 0 0 us 0 B/s 0 0 0 us - debian9
|
||||
pve/base-101-disk-0 testpool 20 G 0 B 0 B/s 0 0 0 us 0 B/s 0 0 0 us RO debian9
|
||||
pve/vm-102-disk-0 testpool 32 G 36.4 M 0 B/s 0 0 0 us 0 B/s 0 0 0 us - pve/base-101-disk-0
|
||||
debian9-test testpool 20 G 36.6 M 0 B/s 0 0 0 us 0 B/s 0 0 0 us - debian9
|
||||
bench testpool 10 G 10 G 0 B/s 0 0 0 us 0 B/s 0 0 0 us -
|
||||
bench-kaveri kaveri 10 G 10 G 0 B/s 0 0 0 us 0 B/s 0 0 0 us -
|
||||
```
|
||||
|
||||
## create
|
||||
|
||||
`vitastor-cli create -s|--size <size> [-p|--pool <id|name>] [--parent <parent_name>[@<snapshot>]] <name>`
|
||||
|
||||
Create an image. You may use K/M/G/T suffixes for `<size>`. If `--parent` is specified,
|
||||
a copy-on-write image clone is created. Parent must be a snapshot (readonly image).
|
||||
Pool must be specified if there is more than one pool.
|
||||
|
||||
```
|
||||
vitastor-cli create --snapshot <snapshot> [-p|--pool <id|name>] <image>
|
||||
vitastor-cli snap-create [-p|--pool <id|name>] <image>@<snapshot>
|
||||
```
|
||||
|
||||
Create a snapshot of image `<name>` (either form can be used). May be used live if only a single writer is active.
|
||||
|
||||
## modify
|
||||
|
||||
`vitastor-cli modify <name> [--rename <new-name>] [--resize <size>] [--readonly | --readwrite] [-f|--force]`
|
||||
|
||||
Rename, resize image or change its readonly status. Images with children can't be made read-write.
|
||||
If the new size is smaller than the old size, extra data will be purged.
|
||||
You should resize file system in the image, if present, before shrinking it.
|
||||
|
||||
```
|
||||
-f|--force Proceed with shrinking or setting readwrite flag even if the image has children.
|
||||
```
|
||||
|
||||
## rm
|
||||
|
||||
`vitastor-cli rm <from> [<to>] [--writers-stopped]`
|
||||
|
||||
Remove `<from>` or all layers between `<from>` and `<to>` (`<to>` must be a child of `<from>`),
|
||||
rebasing all their children accordingly. --writers-stopped allows merging to be a bit
|
||||
more effective in case of a single 'slim' read-write child and 'fat' removed parent:
|
||||
the child is merged into parent and parent is renamed to child in that case.
|
||||
In other cases parent layers are always merged into children.
|
||||
|
||||
## flatten
|
||||
|
||||
`vitastor-cli flatten <layer>`
|
||||
|
||||
Flatten a layer, i.e. merge data and detach it from parents.
|
||||
|
||||
## rm-data
|
||||
|
||||
`vitastor-cli rm-data --pool <pool> --inode <inode> [--wait-list] [--min-offset <offset>]`
|
||||
|
||||
Remove inode data without changing metadata.
|
||||
|
||||
```
|
||||
--wait-list Retrieve full objects listings before starting to remove objects.
|
||||
Requires more memory, but allows to show correct removal progress.
|
||||
--min-offset Purge only data starting with specified offset.
|
||||
```
|
||||
|
||||
## merge-data
|
||||
|
||||
`vitastor-cli merge-data <from> <to> [--target <target>]`
|
||||
|
||||
Merge layer data without changing metadata. Merge `<from>`..`<to>` to `<target>`.
|
||||
`<to>` must be a child of `<from>` and `<target>` may be one of the layers between
|
||||
`<from>` and `<to>`, including `<from>` and `<to>`.
|
||||
|
||||
## alloc-osd
|
||||
|
||||
`vitastor-cli alloc-osd`
|
||||
|
||||
Allocate a new OSD number and reserve it by creating empty `/osd/stats/<n>` key.
|
||||
|
||||
## simple-offsets
|
||||
|
||||
`vitastor-cli simple-offsets <device>`
|
||||
|
||||
Calculate offsets for simple&stupid (no superblock) OSD deployment.
|
||||
|
||||
Options:
|
||||
|
||||
```
|
||||
--object_size 128k Set blockstore block size
|
||||
--bitmap_granularity 4k Set bitmap granularity
|
||||
--journal_size 16M Set journal size
|
||||
--device_block_size 4k Set device block size
|
||||
--journal_offset 0 Set journal offset
|
||||
--device_size 0 Set device size
|
||||
--format text Result format: json, options, env, or text
|
||||
```
|
||||
@@ -1,20 +0,0 @@
|
||||
---
|
||||
title: NBD
|
||||
weight: 6
|
||||
---
|
||||
|
||||
To create a local block device for a Vitastor image, use NBD. For example:
|
||||
|
||||
```
|
||||
vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
|
||||
```
|
||||
|
||||
It will output the device name, like /dev/nbd0 which you can then format and mount as a normal block device.
|
||||
|
||||
You can also use `--pool <POOL> --inode <INODE> --size <SIZE>` instead of `--image <IMAGE>` if you want.
|
||||
|
||||
To unmap the device run:
|
||||
|
||||
```
|
||||
vitastor-nbd unmap /dev/nbd0
|
||||
```
|
||||
@@ -1,39 +0,0 @@
|
||||
---
|
||||
title: QEMU and qemu-img
|
||||
weight: 2
|
||||
---
|
||||
|
||||
You need patched QEMU version to use Vitastor driver.
|
||||
|
||||
To start a VM using plain QEMU command-line with Vitastor disk, use the following commands:
|
||||
|
||||
Old syntax (-drive):
|
||||
|
||||
```
|
||||
qemu-system-x86_64 -enable-kvm -m 1024 \
|
||||
-drive 'file=vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian9',
|
||||
format=raw,if=none,id=drive-virtio-disk0,cache=none \
|
||||
-device 'virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,
|
||||
id=virtio-disk0,bootindex=1,write-cache=off' \
|
||||
-vnc 0.0.0.0:0
|
||||
```
|
||||
|
||||
New syntax (-blockdev):
|
||||
|
||||
```
|
||||
qemu-system-x86_64 -enable-kvm -m 1024 \
|
||||
-blockdev '{"node-name":"drive-virtio-disk0","driver":"vitastor","image":"debian9",
|
||||
"cache":{"direct":true,"no-flush":false},"auto-read-only":true,"discard":"unmap"}' \
|
||||
-device 'virtio-blk-pci,scsi=off,bus=pci.0,addr=0x5,drive=drive-virtio-disk0,
|
||||
id=virtio-disk0,bootindex=1,write-cache=off' \
|
||||
-vnc 0.0.0.0:0
|
||||
```
|
||||
|
||||
For qemu-img, you should use `vitastor:etcd_host=<HOST>:image=<IMAGE>` as filename. For example:
|
||||
|
||||
```
|
||||
qemu-img convert -f qcow2 debian10.qcow2 -p -O raw 'vitastor:etcd_host=192.168.7.2\:2379/v3:image=debian10'
|
||||
```
|
||||
|
||||
You can also specify `:pool=<POOL>:inode=<INODE>:size=<SIZE>` instead of `:image=<IMAGE>`
|
||||
if you don't want to use inode metadata.
|
||||
@@ -1,37 +0,0 @@
|
||||
---
|
||||
nav_navigation: Навигация
|
||||
nav_tags: Теги
|
||||
nav_more: Подробнее
|
||||
nav_top: К началу
|
||||
|
||||
form_placeholder_search: Поиск
|
||||
|
||||
error_page_title: Открыта несуществующая страница
|
||||
error_message_title: Потерялись?
|
||||
error_message_code: Ошибка 404
|
||||
error_message_text: >
|
||||
Похоже, страница, которую вы открыли, не существует. Попробуйте найти
|
||||
нужную информацию с <a class="gdoc-error__link" href="{{ . }}">главной страницы</a>.
|
||||
|
||||
button_toggle_dark: Переключить тёмный/светлый/авто режим
|
||||
button_nav_open: Показать навигацию
|
||||
button_nav_close: Скрыть навигацию
|
||||
button_menu_open: Открыть меню
|
||||
button_menu_close: Закрыть меню
|
||||
button_homepage: На главную
|
||||
|
||||
title_anchor_prefix: "Ссылка на:"
|
||||
|
||||
posts_read_more: Читать подробнее
|
||||
posts_read_time:
|
||||
one: "Одна минута на чтение"
|
||||
other: "{{ . }} минут(ы) на чтение"
|
||||
posts_update_prefix: Обновлено
|
||||
|
||||
footer_build_with: >
|
||||
Сделано на <a href="https://gohugo.io/" class="gdoc-footer__link">Hugo</a> с
|
||||
<svg class="icon gdoc_heart"><use xlink:href="#gdoc_heart"></use></svg>
|
||||
footer_legal_notice: Правовая информация
|
||||
footer_privacy_policy: Приватность
|
||||
|
||||
language_switch_no_tranlation_prefix: "Страница не переведена:"
|
||||
@@ -1,34 +0,0 @@
|
||||
<footer class="gdoc-footer">
|
||||
<div class="container flex">
|
||||
<div class="flex flex-wrap" style="flex: 1">
|
||||
<span class="gdoc-footer__item gdoc-footer__item--row">
|
||||
© Vitaliy Filippov, 2021+
|
||||
</span>
|
||||
</div>
|
||||
<div class="flex flex-wrap">
|
||||
{{ with .Site.Params.GeekdocLegalNotice }}
|
||||
<span class="gdoc-footer__item gdoc-footer__item--row">
|
||||
<a href="{{ . | relURL }}" class="gdoc-footer__link">{{ i18n "footer_legal_notice" }}</a>
|
||||
</span>
|
||||
{{ end }}
|
||||
{{ with .Site.Params.GeekdocPrivacyPolicy }}
|
||||
<span class="gdoc-footer__item gdoc-footer__item--row">
|
||||
<a href="{{ . | relURL }}" class="gdoc-footer__link">{{ i18n "footer_privacy_policy" }}</a>
|
||||
</span>
|
||||
{{ end }}
|
||||
</div>
|
||||
{{ if (default true .Site.Params.GeekdocBackToTop) }}
|
||||
<div class="flex flex-25 justify-end">
|
||||
<span class="gdoc-footer__item gdoc-footer__item--row" style="margin-right: 50px">
|
||||
{{ i18n "footer_build_with" | safeHTML }}
|
||||
</span>
|
||||
<span class="gdoc-footer__item">
|
||||
<a class="gdoc-footer__link fake-link" href="#" aria-label="{{ i18n "nav_top" }}">
|
||||
<svg class="icon gdoc_keyboard_arrow_up"><use xlink:href="#gdoc_keyboard_arrow_up"></use></svg>
|
||||
<span class="hidden-mobile">{{ i18n "nav_top" }}</span>
|
||||
</a>
|
||||
</span>
|
||||
</div>
|
||||
{{ end }}
|
||||
</div>
|
||||
</footer>
|
||||
@@ -1,215 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
||||
<svg
|
||||
xmlns:osb="http://www.openswatchbook.org/uri/2009/osb"
|
||||
xmlns:dc="http://purl.org/dc/elements/1.1/"
|
||||
xmlns:cc="http://creativecommons.org/ns#"
|
||||
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
|
||||
xmlns:svg="http://www.w3.org/2000/svg"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
xmlns:xlink="http://www.w3.org/1999/xlink"
|
||||
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
|
||||
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
|
||||
sodipodi:docname="logo_only2.svg"
|
||||
inkscape:version="1.0.2 (e86c870879, 2021-01-15)"
|
||||
id="svg1340"
|
||||
version="1.1"
|
||||
viewBox="0 0 100 86.80192"
|
||||
height="86.801918mm"
|
||||
width="100mm"
|
||||
inkscape:export-filename="/var/home/vitali/SVN/vitastor/presentation/logos/logo_only.png"
|
||||
inkscape:export-xdpi="92.889999"
|
||||
inkscape:export-ydpi="92.889999">
|
||||
<defs
|
||||
id="defs1334">
|
||||
<linearGradient
|
||||
osb:paint="gradient"
|
||||
id="linearGradient866">
|
||||
<stop
|
||||
id="stop862"
|
||||
offset="0"
|
||||
style="stop-color:#c0c0c0;stop-opacity:1" />
|
||||
<stop
|
||||
id="stop864"
|
||||
offset="1"
|
||||
style="stop-color:#000000;stop-opacity:0" />
|
||||
</linearGradient>
|
||||
<linearGradient
|
||||
id="linearGradient846"
|
||||
osb:paint="gradient">
|
||||
<stop
|
||||
style="stop-color:#ffd42a;stop-opacity:1"
|
||||
offset="0"
|
||||
id="stop842" />
|
||||
<stop
|
||||
style="stop-color:#ffa200;stop-opacity:1"
|
||||
offset="1"
|
||||
id="stop844" />
|
||||
</linearGradient>
|
||||
<radialGradient
|
||||
r="50"
|
||||
fy="159.11139"
|
||||
fx="202.36813"
|
||||
cy="159.11139"
|
||||
cx="202.36813"
|
||||
gradientTransform="matrix(1.2462942,-1.2279529,0.77712408,0.78873143,-190.96813,230.1331)"
|
||||
gradientUnits="userSpaceOnUse"
|
||||
id="radialGradient1530"
|
||||
xlink:href="#linearGradient1352"
|
||||
inkscape:collect="always" />
|
||||
<linearGradient
|
||||
inkscape:collect="always"
|
||||
id="linearGradient1352">
|
||||
<stop
|
||||
style="stop-color:#00c9e6;stop-opacity:1"
|
||||
offset="0"
|
||||
id="stop1348" />
|
||||
<stop
|
||||
style="stop-color:#5240d3;stop-opacity:1"
|
||||
offset="1"
|
||||
id="stop1350" />
|
||||
</linearGradient>
|
||||
<linearGradient
|
||||
y2="62.555599"
|
||||
x2="51.484566"
|
||||
y1="62.555599"
|
||||
x1="38.105473"
|
||||
gradientTransform="rotate(-16.930773,271.11609,-412.42594)"
|
||||
gradientUnits="userSpaceOnUse"
|
||||
id="linearGradient1508"
|
||||
xlink:href="#linearGradient1323"
|
||||
inkscape:collect="always" />
|
||||
<linearGradient
|
||||
inkscape:collect="always"
|
||||
id="linearGradient1323">
|
||||
<stop
|
||||
style="stop-color:#000000;stop-opacity:0.47178105"
|
||||
offset="0"
|
||||
id="stop1319" />
|
||||
<stop
|
||||
style="stop-color:#eeaaff;stop-opacity:0;"
|
||||
offset="1"
|
||||
id="stop1321" />
|
||||
</linearGradient>
|
||||
<radialGradient
|
||||
r="21.541935"
|
||||
fy="24.614815"
|
||||
fx="45.312912"
|
||||
cy="24.614815"
|
||||
cx="45.312912"
|
||||
gradientTransform="matrix(1.0933447,0.13113705,-0.12664108,1.0558599,-1.082187,93.974708)"
|
||||
gradientUnits="userSpaceOnUse"
|
||||
id="radialGradient1504"
|
||||
xlink:href="#linearGradient846"
|
||||
inkscape:collect="always" />
|
||||
<filter
|
||||
style="color-interpolation-filters:sRGB"
|
||||
inkscape:label="Drop Shadow"
|
||||
id="filter1497"
|
||||
width="2"
|
||||
height="2"
|
||||
x="-0.5"
|
||||
y="-0.5">
|
||||
<feFlood
|
||||
flood-opacity="0.498039"
|
||||
flood-color="rgb(0,0,0)"
|
||||
result="flood"
|
||||
id="feFlood1487" />
|
||||
<feComposite
|
||||
in="flood"
|
||||
in2="SourceGraphic"
|
||||
operator="in"
|
||||
result="composite1"
|
||||
id="feComposite1489" />
|
||||
<feGaussianBlur
|
||||
in="composite1"
|
||||
stdDeviation="6"
|
||||
result="blur"
|
||||
id="feGaussianBlur1491" />
|
||||
<feOffset
|
||||
dx="0"
|
||||
dy="6"
|
||||
result="offset"
|
||||
id="feOffset1493" />
|
||||
<feComposite
|
||||
in="offset"
|
||||
in2="offset"
|
||||
operator="atop"
|
||||
result="composite2"
|
||||
id="feComposite1495" />
|
||||
</filter>
|
||||
<radialGradient
|
||||
r="21.541935"
|
||||
fy="24.614815"
|
||||
fx="45.312912"
|
||||
cy="24.614815"
|
||||
cx="45.312912"
|
||||
gradientTransform="matrix(1.0933447,0.13113705,-0.12664108,1.0558599,-1.082187,93.974708)"
|
||||
gradientUnits="userSpaceOnUse"
|
||||
id="radialGradient1506"
|
||||
xlink:href="#linearGradient846"
|
||||
inkscape:collect="always" />
|
||||
</defs>
|
||||
<sodipodi:namedview
|
||||
inkscape:window-maximized="1"
|
||||
inkscape:window-y="0"
|
||||
inkscape:window-x="0"
|
||||
inkscape:window-height="992"
|
||||
inkscape:window-width="1920"
|
||||
fit-margin-bottom="0"
|
||||
fit-margin-right="0"
|
||||
fit-margin-left="0"
|
||||
fit-margin-top="-30"
|
||||
showgrid="false"
|
||||
inkscape:document-rotation="0"
|
||||
inkscape:current-layer="layer1"
|
||||
inkscape:document-units="mm"
|
||||
inkscape:cy="47.914558"
|
||||
inkscape:cx="-103.69646"
|
||||
inkscape:zoom="0.7"
|
||||
inkscape:pageshadow="2"
|
||||
inkscape:pageopacity="1"
|
||||
borderopacity="1.0"
|
||||
bordercolor="#666666"
|
||||
pagecolor="#000000"
|
||||
id="base" />
|
||||
<metadata
|
||||
id="metadata1337">
|
||||
<rdf:RDF>
|
||||
<cc:Work
|
||||
rdf:about="">
|
||||
<dc:format>image/svg+xml</dc:format>
|
||||
<dc:type
|
||||
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
|
||||
<dc:title></dc:title>
|
||||
</cc:Work>
|
||||
</rdf:RDF>
|
||||
</metadata>
|
||||
<g
|
||||
transform="translate(-133.26969,-52.101187)"
|
||||
id="layer1"
|
||||
inkscape:groupmode="layer"
|
||||
inkscape:label="Слой 1">
|
||||
<path
|
||||
style="fill:url(#radialGradient1530);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1"
|
||||
d="m 133.26969,59.089473 50,75.000087 50,-75.000087 z"
|
||||
id="path1528"
|
||||
sodipodi:nodetypes="cccc" />
|
||||
<path
|
||||
d="m 194.29572,89.403603 -8.41706,2.562119 -2.50682,7.49308 7.17785,23.579008 9.60097,-14.40173 z"
|
||||
style="fill:url(#linearGradient1508);fill-opacity:1;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:0.501961"
|
||||
id="path1459" />
|
||||
<g
|
||||
transform="translate(135.70225,-49.385894)"
|
||||
id="g1465">
|
||||
<path
|
||||
id="path1461"
|
||||
style="fill:url(#radialGradient1504);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;filter:url(#filter1497)"
|
||||
d="m 28.817436,101.36529 c 3.112699,10.74423 6.225077,21.48892 9.333984,32.23438 2.519532,0 5.039063,0 7.558594,0 -0.985406,8.09729 -2.085815,16.18202 -2.951172,24.29297 -0.06053,0.88723 1.098131,1.61652 1.76,0.9155 1.007514,-1.05482 1.676008,-2.3829 2.528566,-3.56053 7.51538,-11.37722 14.987447,-22.78299 22.482919,-34.17333 -3.239584,0 -6.479167,0 -9.71875,0 2.887267,-6.79562 5.775365,-13.59088 8.662109,-20.38672 -13.284505,0 -26.56901,0 -39.853516,0 0.06576,0.22591 0.131511,0.45182 0.197266,0.67773 z" />
|
||||
<path
|
||||
sodipodi:nodetypes="cccccccc"
|
||||
id="path1463"
|
||||
d="m 30.735882,102.2764 h 35.342242 l -8.662729,20.3854 h 9.173783 l -22.106472,33.62346 3.027029,-24.27377 H 39.34604 Z"
|
||||
style="fill:url(#radialGradient1506);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1" />
|
||||
</g>
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 7.4 KiB |
@@ -1,138 +0,0 @@
|
||||
/* Global customization */
|
||||
|
||||
:root {
|
||||
--code-max-height: 60rem;
|
||||
}
|
||||
|
||||
/* Light mode theming */
|
||||
:root,
|
||||
:root[color-mode="light"] {
|
||||
--header-background: #404050;
|
||||
--header-font-color: #ffffff;
|
||||
|
||||
--body-background: #ffffff;
|
||||
--body-font-color: #343a40;
|
||||
|
||||
--button-background: #62cb97;
|
||||
--button-border-color: #4ec58a;
|
||||
|
||||
--link-color: #c54e8a;
|
||||
--link-color-visited: #c54e8a;
|
||||
|
||||
--code-background: #f5f6f8;
|
||||
--code-accent-color: #e3e7eb;
|
||||
--code-accent-color-lite: #eff1f3;
|
||||
|
||||
--accent-color: #e9ecef;
|
||||
--accent-color-lite: #f8f9fa;
|
||||
|
||||
--control-icons: #b2bac1;
|
||||
|
||||
--footer-background: #606070;
|
||||
--footer-font-color: #ffffff;
|
||||
--footer-link-color: #ffcc5c;
|
||||
--footer-link-color-visited: #ffcc5c;
|
||||
}
|
||||
@media (prefers-color-scheme: light) {
|
||||
:root {
|
||||
--header-background: #404050;
|
||||
--header-font-color: #ffffff;
|
||||
|
||||
--body-background: #ffffff;
|
||||
--body-font-color: #343a40;
|
||||
|
||||
--button-background: #62cb97;
|
||||
--button-border-color: #4ec58a;
|
||||
|
||||
--link-color: #c54e8a;
|
||||
--link-color-visited: #c54e8a;
|
||||
|
||||
--code-background: #f5f6f8;
|
||||
--code-accent-color: #e3e7eb;
|
||||
--code-accent-color-lite: #eff1f3;
|
||||
|
||||
--accent-color: #e9ecef;
|
||||
--accent-color-lite: #f8f9fa;
|
||||
|
||||
--control-icons: #b2bac1;
|
||||
|
||||
--footer-background: #606070;
|
||||
--footer-font-color: #ffffff;
|
||||
--footer-link-color: #ffcc5c;
|
||||
--footer-link-color-visited: #ffcc5c;
|
||||
}
|
||||
}
|
||||
|
||||
/* Dark mode theming */
|
||||
:root[color-mode="dark"] {
|
||||
--header-background: #202830;
|
||||
--header-font-color: #ffffff;
|
||||
|
||||
--body-background: #343a44;
|
||||
--body-font-color: #ced3d8;
|
||||
|
||||
--button-background: #62cb97;
|
||||
--button-border-color: #4ec58a;
|
||||
|
||||
--link-color: #7ac29e;
|
||||
--link-color-visited: #7ac29e;
|
||||
|
||||
--code-background: #2f353a;
|
||||
--code-accent-color: #262b2f;
|
||||
--code-accent-color-lite: #2b3035;
|
||||
|
||||
--accent-color: #2b3035;
|
||||
--accent-color-lite: #2f353a;
|
||||
|
||||
--control-icons: #b2bac1;
|
||||
|
||||
--footer-background: #2f333e;
|
||||
--footer-font-color: #cccccc;
|
||||
--footer-link-color: #7ac29e;
|
||||
--footer-link-color-visited: #7ac29e;
|
||||
}
|
||||
@media (prefers-color-scheme: dark) {
|
||||
:root {
|
||||
--header-background: #404070;
|
||||
--header-font-color: #ffffff;
|
||||
|
||||
--body-background: #343a40;
|
||||
--body-font-color: #ced3d8;
|
||||
|
||||
--button-background: #62cb97;
|
||||
--button-border-color: #4ec58a;
|
||||
|
||||
--link-color: #7ac29e;
|
||||
--link-color-visited: #7ac29e;
|
||||
|
||||
--code-background: #2f353a;
|
||||
--code-accent-color: #262b2f;
|
||||
--code-accent-color-lite: #2b3035;
|
||||
|
||||
--accent-color: #2b3035;
|
||||
--accent-color-lite: #2f353a;
|
||||
|
||||
--control-icons: #b2bac1;
|
||||
|
||||
--footer-background: #2f333e;
|
||||
--footer-font-color: #cccccc;
|
||||
--footer-link-color: #7ac29e;
|
||||
--footer-link-color-visited: #7ac29e;
|
||||
}
|
||||
}
|
||||
|
||||
.gdoc-brand__img {
|
||||
width: 48px;
|
||||
height: auto;
|
||||
margin-top: -4px;
|
||||
margin-bottom: -4px;
|
||||
}
|
||||
|
||||
.gdoc-menu-header > span {
|
||||
display: flex;
|
||||
flex-direction: row-reverse;
|
||||
}
|
||||
|
||||
span.gdoc-language {
|
||||
margin-right: 20px;
|
||||
}
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 709 B |
Binary file not shown.
|
Before Width: | Height: | Size: 1.5 KiB |
@@ -1,196 +0,0 @@
|
||||
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
||||
<svg
|
||||
xmlns:osb="http://www.openswatchbook.org/uri/2009/osb"
|
||||
xmlns:dc="http://purl.org/dc/elements/1.1/"
|
||||
xmlns:cc="http://creativecommons.org/ns#"
|
||||
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
|
||||
xmlns:svg="http://www.w3.org/2000/svg"
|
||||
xmlns="http://www.w3.org/2000/svg"
|
||||
xmlns:xlink="http://www.w3.org/1999/xlink"
|
||||
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
|
||||
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
|
||||
sodipodi:docname="favicon.svg"
|
||||
inkscape:version="1.0.2 (e86c870879, 2021-01-15)"
|
||||
id="svg1340"
|
||||
version="1.1"
|
||||
viewBox="0 0 100 100"
|
||||
height="100mm"
|
||||
width="100mm"
|
||||
inkscape:export-filename="/var/home/vitali/SVN/vitastor/docs/static/favicon/favicon-64x64.png"
|
||||
inkscape:export-xdpi="16.26"
|
||||
inkscape:export-ydpi="16.26">
|
||||
<defs
|
||||
id="defs1334">
|
||||
<linearGradient
|
||||
osb:paint="gradient"
|
||||
id="linearGradient866">
|
||||
<stop
|
||||
id="stop862"
|
||||
offset="0"
|
||||
style="stop-color:#c0c0c0;stop-opacity:1" />
|
||||
<stop
|
||||
id="stop864"
|
||||
offset="1"
|
||||
style="stop-color:#000000;stop-opacity:0" />
|
||||
</linearGradient>
|
||||
<linearGradient
|
||||
id="linearGradient846"
|
||||
osb:paint="gradient">
|
||||
<stop
|
||||
style="stop-color:#ffd42a;stop-opacity:1"
|
||||
offset="0"
|
||||
id="stop842" />
|
||||
<stop
|
||||
style="stop-color:#ffa200;stop-opacity:1"
|
||||
offset="1"
|
||||
id="stop844" />
|
||||
</linearGradient>
|
||||
<radialGradient
|
||||
r="50"
|
||||
fy="159.11139"
|
||||
fx="202.36813"
|
||||
cy="159.11139"
|
||||
cx="202.36813"
|
||||
gradientTransform="matrix(1.2462942,-1.2279529,0.77712408,0.78873143,-190.96813,230.1331)"
|
||||
gradientUnits="userSpaceOnUse"
|
||||
id="radialGradient1530"
|
||||
xlink:href="#linearGradient1352"
|
||||
inkscape:collect="always" />
|
||||
<linearGradient
|
||||
inkscape:collect="always"
|
||||
id="linearGradient1352">
|
||||
<stop
|
||||
style="stop-color:#00c9e6;stop-opacity:1"
|
||||
offset="0"
|
||||
id="stop1348" />
|
||||
<stop
|
||||
style="stop-color:#5240d3;stop-opacity:1"
|
||||
offset="1"
|
||||
id="stop1350" />
|
||||
</linearGradient>
|
||||
<linearGradient
|
||||
y2="62.555599"
|
||||
x2="51.484566"
|
||||
y1="62.555599"
|
||||
x1="38.105473"
|
||||
gradientTransform="rotate(-16.930773,271.11609,-412.42594)"
|
||||
gradientUnits="userSpaceOnUse"
|
||||
id="linearGradient1508"
|
||||
xlink:href="#linearGradient1323"
|
||||
inkscape:collect="always" />
|
||||
<linearGradient
|
||||
inkscape:collect="always"
|
||||
id="linearGradient1323">
|
||||
<stop
|
||||
style="stop-color:#000000;stop-opacity:0.47178105"
|
||||
offset="0"
|
||||
id="stop1319" />
|
||||
<stop
|
||||
style="stop-color:#eeaaff;stop-opacity:0;"
|
||||
offset="1"
|
||||
id="stop1321" />
|
||||
</linearGradient>
|
||||
<filter
|
||||
style="color-interpolation-filters:sRGB"
|
||||
inkscape:label="Drop Shadow"
|
||||
id="filter1497"
|
||||
width="2"
|
||||
height="2"
|
||||
x="-0.5"
|
||||
y="-0.5">
|
||||
<feFlood
|
||||
flood-opacity="0.498039"
|
||||
flood-color="rgb(0,0,0)"
|
||||
result="flood"
|
||||
id="feFlood1487" />
|
||||
<feComposite
|
||||
in="flood"
|
||||
in2="SourceGraphic"
|
||||
operator="in"
|
||||
result="composite1"
|
||||
id="feComposite1489" />
|
||||
<feGaussianBlur
|
||||
in="composite1"
|
||||
stdDeviation="6"
|
||||
result="blur"
|
||||
id="feGaussianBlur1491" />
|
||||
<feOffset
|
||||
dx="0"
|
||||
dy="6"
|
||||
result="offset"
|
||||
id="feOffset1493" />
|
||||
<feComposite
|
||||
in="offset"
|
||||
in2="offset"
|
||||
operator="atop"
|
||||
result="composite2"
|
||||
id="feComposite1495" />
|
||||
</filter>
|
||||
<radialGradient
|
||||
r="21.541935"
|
||||
fy="24.614815"
|
||||
fx="45.312912"
|
||||
cy="24.614815"
|
||||
cx="45.312912"
|
||||
gradientTransform="matrix(1.6678615,0.20004527,-0.19318681,1.6106796,108.48083,22.966962)"
|
||||
gradientUnits="userSpaceOnUse"
|
||||
id="radialGradient1506"
|
||||
xlink:href="#linearGradient846"
|
||||
inkscape:collect="always" />
|
||||
</defs>
|
||||
<sodipodi:namedview
|
||||
inkscape:window-maximized="1"
|
||||
inkscape:window-y="0"
|
||||
inkscape:window-x="0"
|
||||
inkscape:window-height="992"
|
||||
inkscape:window-width="1920"
|
||||
fit-margin-bottom="0"
|
||||
fit-margin-right="0"
|
||||
fit-margin-left="0"
|
||||
fit-margin-top="0"
|
||||
showgrid="false"
|
||||
inkscape:document-rotation="0"
|
||||
inkscape:current-layer="layer1"
|
||||
inkscape:document-units="mm"
|
||||
inkscape:cy="83.752268"
|
||||
inkscape:cx="-103.69645"
|
||||
inkscape:zoom="0.7"
|
||||
inkscape:pageshadow="2"
|
||||
inkscape:pageopacity="0"
|
||||
borderopacity="1.0"
|
||||
bordercolor="#666666"
|
||||
pagecolor="#000000"
|
||||
id="base" />
|
||||
<metadata
|
||||
id="metadata1337">
|
||||
<rdf:RDF>
|
||||
<cc:Work
|
||||
rdf:about="">
|
||||
<dc:format>image/svg+xml</dc:format>
|
||||
<dc:type
|
||||
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
|
||||
<dc:title></dc:title>
|
||||
</cc:Work>
|
||||
</rdf:RDF>
|
||||
</metadata>
|
||||
<g
|
||||
transform="translate(-133.26969,-35.630924)"
|
||||
id="layer1"
|
||||
inkscape:groupmode="layer"
|
||||
inkscape:label="Слой 1">
|
||||
<path
|
||||
style="fill:url(#radialGradient1530);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1"
|
||||
d="m 133.26969,59.089473 50,75.000087 50,-75.000087 z"
|
||||
id="path1528"
|
||||
sodipodi:nodetypes="cccc" />
|
||||
<path
|
||||
d="m 194.29572,89.403603 -8.41706,2.562119 -2.50682,7.49308 7.17785,23.579008 9.60097,-14.40173 z"
|
||||
style="fill:url(#linearGradient1508);fill-opacity:1;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:0.501961"
|
||||
id="path1459" />
|
||||
<path
|
||||
sodipodi:nodetypes="cccccccc"
|
||||
id="path1463"
|
||||
d="m 157.01826,35.630924 h 53.91343 l -13.21471,31.09726 h 13.99432 l -33.7227,51.291496 4.61762,-37.02885 h -12.45344 z"
|
||||
style="fill:url(#radialGradient1506);fill-opacity:1;fill-rule:evenodd;stroke:#000000;stroke-width:0;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1" />
|
||||
</g>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 6.2 KiB |
@@ -1,6 +0,0 @@
|
||||
---
|
||||
title: Common Parameters
|
||||
weight: 1
|
||||
---
|
||||
|
||||
These are the most common parameters which apply to all components of Vitastor.
|
||||
@@ -1,6 +0,0 @@
|
||||
---
|
||||
title: Общие параметры
|
||||
weight: 1
|
||||
---
|
||||
|
||||
Это наиболее общие параметры, используемые всеми компонентами Vitastor.
|
||||
@@ -1,7 +0,0 @@
|
||||
---
|
||||
title: Cluster-Wide Disk Layout Parameters
|
||||
weight: 2
|
||||
---
|
||||
|
||||
These parameters apply to clients and OSDs, are fixed at the moment of OSD drive
|
||||
initialization and can't be changed after it without losing data.
|
||||
@@ -1,7 +0,0 @@
|
||||
---
|
||||
title: Дисковые параметры уровня кластера
|
||||
weight: 2
|
||||
---
|
||||
|
||||
Данные параметры используются клиентами и OSD, задаются в момент инициализации
|
||||
диска OSD и не могут быть изменены после этого без потери данных.
|
||||
@@ -1,7 +0,0 @@
|
||||
---
|
||||
title: OSD Disk Layout Parameters
|
||||
weight: 3
|
||||
---
|
||||
|
||||
These parameters apply to OSDs, are fixed at the moment of OSD drive
|
||||
initialization and can't be changed after it without losing data.
|
||||
@@ -1,8 +0,0 @@
|
||||
---
|
||||
title: Дисковые параметры OSD
|
||||
weight: 3
|
||||
---
|
||||
|
||||
Данные параметры используются только OSD и, также как и общекластерные
|
||||
дисковые параметры, задаются в момент инициализации дисков OSD и не могут быть
|
||||
изменены после этого без потери данных.
|
||||
@@ -1,6 +0,0 @@
|
||||
---
|
||||
title: Monitor Parameters
|
||||
weight: 6
|
||||
---
|
||||
|
||||
These parameters only apply to Monitors.
|
||||
@@ -1,6 +0,0 @@
|
||||
---
|
||||
title: Параметры мониторов
|
||||
weight: 6
|
||||
---
|
||||
|
||||
Данные параметры используются только мониторами Vitastor.
|
||||
@@ -1,7 +0,0 @@
|
||||
---
|
||||
title: Network Protocol Parameters
|
||||
weight: 4
|
||||
---
|
||||
|
||||
These parameters apply to clients and OSDs and affect network connection logic
|
||||
between clients, OSDs and etcd.
|
||||
@@ -1,7 +0,0 @@
|
||||
---
|
||||
title: Параметры сетевого протокола
|
||||
weight: 4
|
||||
---
|
||||
|
||||
Данные параметры используются клиентами и OSD и влияют на логику сетевого
|
||||
взаимодействия между клиентами, OSD, а также etcd.
|
||||
@@ -1,7 +0,0 @@
|
||||
---
|
||||
title: Runtime OSD Parameters
|
||||
weight: 5
|
||||
---
|
||||
|
||||
These parameters only apply to OSDs, are not fixed at the moment of OSD drive
|
||||
initialization and can be changed with an OSD restart.
|
||||
@@ -1,8 +0,0 @@
|
||||
---
|
||||
title: Изменяемые параметры OSD
|
||||
weight: 5
|
||||
---
|
||||
|
||||
Данные параметры используются только OSD, но, в отличие от дисковых параметров,
|
||||
не фиксируются в момент инициализации дисков OSD и могут быть изменены в любой
|
||||
момент с перезапуском OSD.
|
||||
@@ -248,8 +248,6 @@
|
||||
row and slow down significantly (from 25000+ iops to ~3000 iops). When
|
||||
this option is set, Vitastor will always move to the next sector of the
|
||||
journal after writing it instead of possibly overwriting it the second time.
|
||||
|
||||
Most (99%) other SSDs don't need this option.
|
||||
info_ru: |
|
||||
Включайте данную опцию для SSD вроде Intel D3-S4510 и D3-S4610, которые
|
||||
ОЧЕНЬ не любят, когда ПО перезаписывает один и тот же сектор несколько раз
|
||||
@@ -258,8 +256,6 @@
|
||||
данная опция установлена, Vitastor всегда переходит к следующему сектору
|
||||
журнала после записи вместо потенциально повторной перезаписи того же
|
||||
самого сектора.
|
||||
|
||||
Почти все другие SSD (99% моделей) не требуют данной опции.
|
||||
- name: throttle_small_writes
|
||||
type: bool
|
||||
default: false
|
||||
|
||||
65
mon/mon.js
65
mon/mon.js
@@ -160,8 +160,6 @@ const etcd_tree = {
|
||||
root_node?: 'rack1',
|
||||
// restrict pool to OSDs having all of these tags
|
||||
osd_tags?: 'nvme' | [ 'nvme', ... ],
|
||||
// prefer to put primary on OSD with these tags
|
||||
primary_affinity_tags?: 'nvme' | [ 'nvme', ... ],
|
||||
},
|
||||
...
|
||||
}, */
|
||||
@@ -226,19 +224,15 @@ const etcd_tree = {
|
||||
}, */
|
||||
},
|
||||
inodestats: {
|
||||
/* <pool_id>: {
|
||||
<inode_t>: {
|
||||
read: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
|
||||
write: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
|
||||
delete: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
|
||||
},
|
||||
/* <inode_t>: {
|
||||
read: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
|
||||
write: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
|
||||
delete: { count: uint64_t, usec: uint64_t, bytes: uint64_t },
|
||||
}, */
|
||||
},
|
||||
space: {
|
||||
/* <osd_num_t>: {
|
||||
<pool_id>: {
|
||||
<inode_t>: uint64_t, // bytes
|
||||
},
|
||||
<inode_t>: uint64_t, // bytes
|
||||
}, */
|
||||
},
|
||||
},
|
||||
@@ -905,39 +899,27 @@ class Mon
|
||||
return this.seed + 2147483648;
|
||||
}
|
||||
|
||||
pick_primary(pool_id, osd_set, up_osds, aff_osds)
|
||||
pick_primary(pool_id, osd_set, up_osds)
|
||||
{
|
||||
let alive_set;
|
||||
if (this.state.config.pools[pool_id].scheme === 'replicated')
|
||||
{
|
||||
// Prefer "affinity" OSDs
|
||||
alive_set = osd_set.filter(osd_num => osd_num && aff_osds[osd_num]);
|
||||
if (!alive_set.length)
|
||||
alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
|
||||
}
|
||||
alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
|
||||
else
|
||||
{
|
||||
// Prefer data OSDs for EC because they can actually read something without an additional network hop
|
||||
const pg_data_size = (this.state.config.pools[pool_id].pg_size||0) -
|
||||
(this.state.config.pools[pool_id].parity_chunks||0);
|
||||
alive_set = osd_set.slice(0, pg_data_size).filter(osd_num => osd_num && aff_osds[osd_num]);
|
||||
alive_set = osd_set.slice(0, pg_data_size).filter(osd_num => osd_num && up_osds[osd_num]);
|
||||
if (!alive_set.length)
|
||||
alive_set = osd_set.filter(osd_num => osd_num && aff_osds[osd_num]);
|
||||
if (!alive_set.length)
|
||||
{
|
||||
alive_set = osd_set.slice(0, pg_data_size).filter(osd_num => osd_num && up_osds[osd_num]);
|
||||
if (!alive_set.length)
|
||||
alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
|
||||
}
|
||||
alive_set = osd_set.filter(osd_num => osd_num && up_osds[osd_num]);
|
||||
}
|
||||
if (!alive_set.length)
|
||||
return 0;
|
||||
return alive_set[this.rng() % alive_set.length];
|
||||
}
|
||||
|
||||
save_new_pgs_txn(request, pool_id, up_osds, osd_tree, prev_pgs, new_pgs, pg_history)
|
||||
save_new_pgs_txn(request, pool_id, up_osds, prev_pgs, new_pgs, pg_history)
|
||||
{
|
||||
const aff_osds = this.get_affinity_osds(this.state.config.pools[pool_id], up_osds, osd_tree);
|
||||
const pg_items = {};
|
||||
this.reset_rng();
|
||||
new_pgs.map((osd_set, i) =>
|
||||
@@ -945,7 +927,7 @@ class Mon
|
||||
osd_set = osd_set.map(osd_num => osd_num === LPOptimizer.NO_OSD ? 0 : osd_num);
|
||||
pg_items[i+1] = {
|
||||
osd_set,
|
||||
primary: this.pick_primary(pool_id, osd_set, up_osds, aff_osds),
|
||||
primary: this.pick_primary(pool_id, osd_set, up_osds),
|
||||
};
|
||||
if (prev_pgs[i] && prev_pgs[i].join(' ') != osd_set.join(' ') &&
|
||||
prev_pgs[i].filter(osd_num => osd_num).length > 0)
|
||||
@@ -1076,13 +1058,6 @@ class Mon
|
||||
console.log('Pool '+pool_id+' has invalid osd_tags (must be a string or array of strings)');
|
||||
return false;
|
||||
}
|
||||
if (pool_cfg.primary_affinity_tags && typeof(pool_cfg.primary_affinity_tags) != 'string' &&
|
||||
(!(pool_cfg.primary_affinity_tags instanceof Array) || pool_cfg.primary_affinity_tags.filter(t => typeof t != 'string').length > 0))
|
||||
{
|
||||
if (warn)
|
||||
console.log('Pool '+pool_id+' has invalid primary_affinity_tags (must be a string or array of strings)');
|
||||
return false;
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -1112,17 +1087,6 @@ class Mon
|
||||
}
|
||||
}
|
||||
|
||||
get_affinity_osds(pool_cfg, up_osds, osd_tree)
|
||||
{
|
||||
let aff_osds = up_osds;
|
||||
if (pool_cfg.primary_affinity_tags)
|
||||
{
|
||||
aff_osds = { ...up_osds };
|
||||
this.filter_osds_by_tags(osd_tree, { x: aff_osds }, pool_cfg.primary_affinity_tags);
|
||||
}
|
||||
return aff_osds;
|
||||
}
|
||||
|
||||
async recheck_pgs()
|
||||
{
|
||||
// Take configuration and state, check it against the stored configuration hash
|
||||
@@ -1153,7 +1117,7 @@ class Mon
|
||||
{
|
||||
prev_pgs[pg-1] = this.state.config.pgs.items[pool_id][pg].osd_set;
|
||||
}
|
||||
this.save_new_pgs_txn(etcd_request, pool_id, up_osds, osd_tree, prev_pgs, [], []);
|
||||
this.save_new_pgs_txn(etcd_request, pool_id, up_osds, prev_pgs, [], []);
|
||||
}
|
||||
}
|
||||
for (const pool_id in this.state.config.pools)
|
||||
@@ -1260,7 +1224,7 @@ class Mon
|
||||
key: b64(this.etcd_prefix+'/pool/stats/'+pool_id),
|
||||
value: b64(JSON.stringify(this.state.pool.stats[pool_id])),
|
||||
} });
|
||||
this.save_new_pgs_txn(etcd_request, pool_id, up_osds, osd_tree, real_prev_pgs, optimize_result.int_pgs, pg_history);
|
||||
this.save_new_pgs_txn(etcd_request, pool_id, up_osds, real_prev_pgs, optimize_result.int_pgs, pg_history);
|
||||
}
|
||||
this.state.config.pgs.hash = tree_hash;
|
||||
await this.save_pg_config(etcd_request);
|
||||
@@ -1277,14 +1241,13 @@ class Mon
|
||||
continue;
|
||||
}
|
||||
const replicated = pool_cfg.scheme === 'replicated';
|
||||
const aff_osds = this.get_affinity_osds(pool_cfg, up_osds, osd_tree);
|
||||
this.reset_rng();
|
||||
for (let pg_num = 1; pg_num <= pool_cfg.pg_count; pg_num++)
|
||||
{
|
||||
const pg_cfg = this.state.config.pgs.items[pool_id][pg_num];
|
||||
if (pg_cfg)
|
||||
{
|
||||
const new_primary = this.pick_primary(pool_id, pg_cfg.osd_set, up_osds, aff_osds);
|
||||
const new_primary = this.pick_primary(pool_id, pg_cfg.osd_set, up_osds);
|
||||
if (pg_cfg.primary != new_primary)
|
||||
{
|
||||
console.log(
|
||||
|
||||
@@ -50,7 +50,7 @@ from cinder.volume import configuration
|
||||
from cinder.volume import driver
|
||||
from cinder.volume import volume_utils
|
||||
|
||||
VERSION = '0.6.17'
|
||||
VERSION = '0.6.16'
|
||||
|
||||
LOG = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@@ -25,4 +25,4 @@ rm fio
|
||||
mv fio-copy fio
|
||||
FIO=`rpm -qi fio | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Version[\s:]+(\S+)/ && print $1; /^Release[\s:]+(\S+)/ && print "-$1"; }'`
|
||||
perl -i -pe 's/(Requires:\s*fio)([^\n]+)?/$1 = '$FIO'/' $VITASTOR/rpm/vitastor-el$EL.spec
|
||||
tar --transform 's#^#vitastor-0.6.17/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.6.17$(rpm --eval '%dist').tar.gz *
|
||||
tar --transform 's#^#vitastor-0.6.16/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.6.16$(rpm --eval '%dist').tar.gz *
|
||||
|
||||
@@ -34,7 +34,7 @@ ADD . /root/vitastor
|
||||
RUN set -e; \
|
||||
cd /root/vitastor/rpm; \
|
||||
sh build-tarball.sh; \
|
||||
cp /root/vitastor-0.6.17.el7.tar.gz ~/rpmbuild/SOURCES; \
|
||||
cp /root/vitastor-0.6.16.el7.tar.gz ~/rpmbuild/SOURCES; \
|
||||
cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
|
||||
cd ~/rpmbuild/SPECS/; \
|
||||
rpmbuild -ba vitastor.spec; \
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
Name: vitastor
|
||||
Version: 0.6.17
|
||||
Version: 0.6.16
|
||||
Release: 1%{?dist}
|
||||
Summary: Vitastor, a fast software-defined clustered block storage
|
||||
|
||||
License: Vitastor Network Public License 1.1
|
||||
URL: https://vitastor.io/
|
||||
Source0: vitastor-0.6.17.el7.tar.gz
|
||||
Source0: vitastor-0.6.16.el7.tar.gz
|
||||
|
||||
BuildRequires: liburing-devel >= 0.6
|
||||
BuildRequires: gperftools-devel
|
||||
@@ -119,7 +119,6 @@ cp -r mon %buildroot/usr/lib/vitastor
|
||||
|
||||
%files -n vitastor-client
|
||||
%_bindir/vitastor-nbd
|
||||
%_bindir/vitastor-nfs
|
||||
%_bindir/vitastor-cli
|
||||
%_bindir/vitastor-rm
|
||||
%_bindir/vita
|
||||
|
||||
@@ -33,7 +33,7 @@ ADD . /root/vitastor
|
||||
RUN set -e; \
|
||||
cd /root/vitastor/rpm; \
|
||||
sh build-tarball.sh; \
|
||||
cp /root/vitastor-0.6.17.el8.tar.gz ~/rpmbuild/SOURCES; \
|
||||
cp /root/vitastor-0.6.16.el8.tar.gz ~/rpmbuild/SOURCES; \
|
||||
cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
|
||||
cd ~/rpmbuild/SPECS/; \
|
||||
rpmbuild -ba vitastor.spec; \
|
||||
|
||||
@@ -1,11 +1,11 @@
|
||||
Name: vitastor
|
||||
Version: 0.6.17
|
||||
Version: 0.6.16
|
||||
Release: 1%{?dist}
|
||||
Summary: Vitastor, a fast software-defined clustered block storage
|
||||
|
||||
License: Vitastor Network Public License 1.1
|
||||
URL: https://vitastor.io/
|
||||
Source0: vitastor-0.6.17.el8.tar.gz
|
||||
Source0: vitastor-0.6.16.el8.tar.gz
|
||||
|
||||
BuildRequires: liburing-devel >= 0.6
|
||||
BuildRequires: gperftools-devel
|
||||
@@ -116,7 +116,6 @@ cp -r mon %buildroot/usr/lib/vitastor
|
||||
|
||||
%files -n vitastor-client
|
||||
%_bindir/vitastor-nbd
|
||||
%_bindir/vitastor-nfs
|
||||
%_bindir/vitastor-cli
|
||||
%_bindir/vitastor-rm
|
||||
%_bindir/vita
|
||||
|
||||
@@ -15,7 +15,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
|
||||
set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
|
||||
endif()
|
||||
|
||||
add_definitions(-DVERSION="0.6.17")
|
||||
add_definitions(-DVERSION="0.6.16")
|
||||
add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -I ${CMAKE_SOURCE_DIR}/src)
|
||||
if (${WITH_ASAN})
|
||||
add_definitions(-fsanitize=address -fno-omit-frame-pointer)
|
||||
@@ -124,18 +124,6 @@ add_library(vitastor_client SHARED
|
||||
cluster_client.cpp
|
||||
cluster_client_list.cpp
|
||||
vitastor_c.cpp
|
||||
cli_common.cpp
|
||||
cli_alloc_osd.cpp
|
||||
cli_simple_offsets.cpp
|
||||
cli_status.cpp
|
||||
cli_df.cpp
|
||||
cli_ls.cpp
|
||||
cli_create.cpp
|
||||
cli_modify.cpp
|
||||
cli_flatten.cpp
|
||||
cli_merge.cpp
|
||||
cli_rm_data.cpp
|
||||
cli_rm.cpp
|
||||
)
|
||||
set_target_properties(vitastor_client PROPERTIES PUBLIC_HEADER "vitastor_c.h")
|
||||
target_link_libraries(vitastor_client
|
||||
@@ -164,24 +152,10 @@ target_link_libraries(vitastor-nbd
|
||||
vitastor_client
|
||||
)
|
||||
|
||||
# vitastor-nfs
|
||||
add_executable(vitastor-nfs
|
||||
nfs_proxy.cpp
|
||||
nfs_conn.cpp
|
||||
nfs_portmap.cpp
|
||||
sha256.c
|
||||
nfs/xdr_impl.cpp
|
||||
nfs/rpc_xdr.cpp
|
||||
nfs/portmap_xdr.cpp
|
||||
nfs/nfs_xdr.cpp
|
||||
)
|
||||
target_link_libraries(vitastor-nfs
|
||||
vitastor_client
|
||||
)
|
||||
|
||||
# vitastor-cli
|
||||
add_executable(vitastor-cli
|
||||
cli.cpp
|
||||
cli.cpp cli_alloc_osd.cpp cli_simple_offsets.cpp cli_status.cpp cli_df.cpp
|
||||
cli_ls.cpp cli_create.cpp cli_modify.cpp cli_flatten.cpp cli_merge.cpp cli_rm_data.cpp cli_rm.cpp
|
||||
)
|
||||
target_link_libraries(vitastor-cli
|
||||
vitastor_client
|
||||
@@ -270,7 +244,7 @@ target_include_directories(test_cluster_client PUBLIC ${CMAKE_SOURCE_DIR}/src/mo
|
||||
|
||||
### Install
|
||||
|
||||
install(TARGETS vitastor-osd vitastor-dump-journal vitastor-nbd vitastor-nfs vitastor-cli RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
|
||||
install(TARGETS vitastor-osd vitastor-dump-journal vitastor-nbd vitastor-cli RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
|
||||
install_symlink(vitastor-cli ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/vitastor-rm)
|
||||
install_symlink(vitastor-cli ${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/vita)
|
||||
install(
|
||||
|
||||
@@ -25,7 +25,7 @@ allocator::allocator(uint64_t blocks)
|
||||
size = free = blocks;
|
||||
last_one_mask = (blocks % 64) == 0
|
||||
? UINT64_MAX
|
||||
: (((uint64_t)1 << (blocks % 64)) - 1);
|
||||
: ((1l << (blocks % 64)) - 1);
|
||||
for (uint64_t i = 0; i < total; i++)
|
||||
{
|
||||
mask[i] = 0;
|
||||
@@ -79,7 +79,7 @@ void allocator::set(uint64_t addr, bool value)
|
||||
}
|
||||
if (value)
|
||||
{
|
||||
mask[last] = mask[last] | ((uint64_t)1 << bit);
|
||||
mask[last] = mask[last] | (1l << bit);
|
||||
if (mask[last] != (!is_last || cur_addr/64 < size/64
|
||||
? UINT64_MAX : last_one_mask))
|
||||
{
|
||||
@@ -88,7 +88,7 @@ void allocator::set(uint64_t addr, bool value)
|
||||
}
|
||||
else
|
||||
{
|
||||
mask[last] = mask[last] & ~((uint64_t)1 << bit);
|
||||
mask[last] = mask[last] & ~(1l << bit);
|
||||
}
|
||||
is_last = false;
|
||||
if (p2 > 1)
|
||||
|
||||
@@ -131,7 +131,6 @@ resume_1:
|
||||
}
|
||||
// Skip superblock
|
||||
bs->meta_offset += bs->meta_block_size;
|
||||
bs->meta_len -= bs->meta_block_size;
|
||||
prev_done = 0;
|
||||
done_len = 0;
|
||||
done_pos = 0;
|
||||
|
||||
284
src/cli.cpp
284
src/cli.cpp
@@ -2,7 +2,8 @@
|
||||
// License: VNPL-1.1 (see README.md for details)
|
||||
|
||||
/**
|
||||
* CLI tool and also a library for administrative tasks
|
||||
* CLI tool
|
||||
* Currently can (a) remove inodes and (b) merge snapshot/clone layers
|
||||
*/
|
||||
|
||||
#include <vector>
|
||||
@@ -16,9 +17,7 @@
|
||||
|
||||
static const char *exe_name = NULL;
|
||||
|
||||
static void help();
|
||||
|
||||
static json11::Json::object parse_args(int narg, const char *args[])
|
||||
json11::Json::object cli_tool_t::parse_args(int narg, const char *args[])
|
||||
{
|
||||
json11::Json::object cfg;
|
||||
json11::Json::array cmd;
|
||||
@@ -80,7 +79,7 @@ static json11::Json::object parse_args(int narg, const char *args[])
|
||||
return cfg;
|
||||
}
|
||||
|
||||
static void help()
|
||||
void cli_tool_t::help()
|
||||
{
|
||||
printf(
|
||||
"Vitastor command-line tool\n"
|
||||
@@ -165,171 +164,224 @@ static void help()
|
||||
exit(0);
|
||||
}
|
||||
|
||||
static int run(cli_tool_t *p, json11::Json::object cfg)
|
||||
void cli_tool_t::change_parent(inode_t cur, inode_t new_parent)
|
||||
{
|
||||
auto cur_cfg_it = cli->st_cli.inode_config.find(cur);
|
||||
if (cur_cfg_it == cli->st_cli.inode_config.end())
|
||||
{
|
||||
fprintf(stderr, "Inode 0x%lx disappeared\n", cur);
|
||||
exit(1);
|
||||
}
|
||||
inode_config_t new_cfg = cur_cfg_it->second;
|
||||
std::string cur_name = new_cfg.name;
|
||||
std::string cur_cfg_key = base64_encode(cli->st_cli.etcd_prefix+
|
||||
"/config/inode/"+std::to_string(INODE_POOL(cur))+
|
||||
"/"+std::to_string(INODE_NO_POOL(cur)));
|
||||
new_cfg.parent_id = new_parent;
|
||||
json11::Json::object cur_cfg_json = cli->st_cli.serialize_inode_cfg(&new_cfg);
|
||||
waiting++;
|
||||
cli->st_cli.etcd_txn_slow(json11::Json::object {
|
||||
{ "compare", json11::Json::array {
|
||||
json11::Json::object {
|
||||
{ "target", "MOD" },
|
||||
{ "key", cur_cfg_key },
|
||||
{ "result", "LESS" },
|
||||
{ "mod_revision", new_cfg.mod_revision+1 },
|
||||
},
|
||||
} },
|
||||
{ "success", json11::Json::array {
|
||||
json11::Json::object {
|
||||
{ "request_put", json11::Json::object {
|
||||
{ "key", cur_cfg_key },
|
||||
{ "value", base64_encode(json11::Json(cur_cfg_json).dump()) },
|
||||
} }
|
||||
},
|
||||
} },
|
||||
}, [this, new_parent, cur, cur_name](std::string err, json11::Json res)
|
||||
{
|
||||
if (err != "")
|
||||
{
|
||||
fprintf(stderr, "Error changing parent of %s: %s\n", cur_name.c_str(), err.c_str());
|
||||
exit(1);
|
||||
}
|
||||
if (!res["succeeded"].bool_value())
|
||||
{
|
||||
fprintf(stderr, "Inode %s was modified during snapshot deletion\n", cur_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
if (new_parent)
|
||||
{
|
||||
auto new_parent_it = cli->st_cli.inode_config.find(new_parent);
|
||||
std::string new_parent_name = new_parent_it != cli->st_cli.inode_config.end()
|
||||
? new_parent_it->second.name : "<unknown>";
|
||||
printf(
|
||||
"Parent of layer %s (inode %lu in pool %u) changed to %s (inode %lu in pool %u)\n",
|
||||
cur_name.c_str(), INODE_NO_POOL(cur), INODE_POOL(cur),
|
||||
new_parent_name.c_str(), INODE_NO_POOL(new_parent), INODE_POOL(new_parent)
|
||||
);
|
||||
}
|
||||
else
|
||||
{
|
||||
printf(
|
||||
"Parent of layer %s (inode %lu in pool %u) detached\n",
|
||||
cur_name.c_str(), INODE_NO_POOL(cur), INODE_POOL(cur)
|
||||
);
|
||||
}
|
||||
waiting--;
|
||||
ringloop->wakeup();
|
||||
});
|
||||
}
|
||||
|
||||
void cli_tool_t::etcd_txn(json11::Json txn)
|
||||
{
|
||||
waiting++;
|
||||
cli->st_cli.etcd_txn_slow(txn, [this](std::string err, json11::Json res)
|
||||
{
|
||||
waiting--;
|
||||
if (err != "")
|
||||
{
|
||||
fprintf(stderr, "Error reading from etcd: %s\n", err.c_str());
|
||||
exit(1);
|
||||
}
|
||||
etcd_result = res;
|
||||
ringloop->wakeup();
|
||||
});
|
||||
}
|
||||
|
||||
inode_config_t* cli_tool_t::get_inode_cfg(const std::string & name)
|
||||
{
|
||||
for (auto & ic: cli->st_cli.inode_config)
|
||||
{
|
||||
if (ic.second.name == name)
|
||||
{
|
||||
return &ic.second;
|
||||
}
|
||||
}
|
||||
fprintf(stderr, "Layer %s not found\n", name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
|
||||
void cli_tool_t::run(json11::Json cfg)
|
||||
{
|
||||
cli_result_t result;
|
||||
p->parse_config(cfg);
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
cfg.erase("command");
|
||||
std::function<bool(cli_result_t &)> action_cb;
|
||||
if (!cmd.size())
|
||||
{
|
||||
result = { .err = EINVAL, .text = "command is missing" };
|
||||
fprintf(stderr, "command is missing\n");
|
||||
exit(1);
|
||||
}
|
||||
else if (cmd[0] == "status")
|
||||
{
|
||||
// Show cluster status
|
||||
action_cb = p->start_status(cfg);
|
||||
action_cb = start_status(cfg);
|
||||
}
|
||||
else if (cmd[0] == "df")
|
||||
{
|
||||
// Show pool space stats
|
||||
action_cb = p->start_df(cfg);
|
||||
action_cb = start_df(cfg);
|
||||
}
|
||||
else if (cmd[0] == "ls")
|
||||
{
|
||||
// List images
|
||||
if (cmd.size() > 1)
|
||||
{
|
||||
cmd.erase(cmd.begin(), cmd.begin()+1);
|
||||
cfg["names"] = cmd;
|
||||
}
|
||||
action_cb = p->start_ls(cfg);
|
||||
action_cb = start_ls(cfg);
|
||||
}
|
||||
else if (cmd[0] == "snap-create")
|
||||
{
|
||||
// Create snapshot
|
||||
std::string name = cmd.size() > 1 ? cmd[1].string_value() : "";
|
||||
int pos = name.find('@');
|
||||
if (pos == std::string::npos || pos == name.length()-1)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Please specify new snapshot name after @" };
|
||||
}
|
||||
else
|
||||
{
|
||||
cfg["image"] = name.substr(0, pos);
|
||||
cfg["snapshot"] = name.substr(pos + 1);
|
||||
action_cb = p->start_create(cfg);
|
||||
}
|
||||
}
|
||||
else if (cmd[0] == "create")
|
||||
else if (cmd[0] == "create" || cmd[0] == "snap-create")
|
||||
{
|
||||
// Create image/snapshot
|
||||
if (cmd.size() > 1)
|
||||
{
|
||||
cfg["image"] = cmd[1];
|
||||
}
|
||||
action_cb = p->start_create(cfg);
|
||||
action_cb = start_create(cfg);
|
||||
}
|
||||
else if (cmd[0] == "modify")
|
||||
{
|
||||
// Modify image
|
||||
if (cmd.size() > 1)
|
||||
{
|
||||
cfg["image"] = cmd[1];
|
||||
}
|
||||
action_cb = p->start_modify(cfg);
|
||||
action_cb = start_modify(cfg);
|
||||
}
|
||||
else if (cmd[0] == "rm-data")
|
||||
{
|
||||
// Delete inode data
|
||||
action_cb = p->start_rm_data(cfg);
|
||||
action_cb = start_rm(cfg);
|
||||
}
|
||||
else if (cmd[0] == "merge-data")
|
||||
{
|
||||
// Merge layer data without affecting metadata
|
||||
if (cmd.size() > 1)
|
||||
{
|
||||
cfg["from"] = cmd[1];
|
||||
if (cmd.size() > 2)
|
||||
cfg["to"] = cmd[2];
|
||||
}
|
||||
action_cb = p->start_merge(cfg);
|
||||
action_cb = start_merge(cfg);
|
||||
}
|
||||
else if (cmd[0] == "flatten")
|
||||
{
|
||||
// Merge layer data without affecting metadata
|
||||
if (cmd.size() > 1)
|
||||
{
|
||||
cfg["image"] = cmd[1];
|
||||
}
|
||||
action_cb = p->start_flatten(cfg);
|
||||
action_cb = start_flatten(cfg);
|
||||
}
|
||||
else if (cmd[0] == "rm")
|
||||
{
|
||||
// Remove multiple snapshots and rebase their children
|
||||
if (cmd.size() > 1)
|
||||
{
|
||||
cfg["from"] = cmd[1];
|
||||
if (cmd.size() > 2)
|
||||
cfg["to"] = cmd[2];
|
||||
}
|
||||
action_cb = p->start_rm(cfg);
|
||||
action_cb = start_snap_rm(cfg);
|
||||
}
|
||||
else if (cmd[0] == "alloc-osd")
|
||||
{
|
||||
// Allocate a new OSD number
|
||||
action_cb = p->start_alloc_osd(cfg);
|
||||
action_cb = start_alloc_osd(cfg);
|
||||
}
|
||||
else if (cmd[0] == "simple-offsets")
|
||||
{
|
||||
// Calculate offsets for simple & stupid OSD deployment without superblock
|
||||
if (cmd.size() > 1)
|
||||
{
|
||||
cfg["device"] = cmd[1];
|
||||
}
|
||||
action_cb = p->simple_offsets(cfg);
|
||||
action_cb = simple_offsets(cfg);
|
||||
}
|
||||
else
|
||||
{
|
||||
result = { .err = EINVAL, .text = "unknown command: "+cmd[0].string_value() };
|
||||
fprintf(stderr, "unknown command: %s\n", cmd[0].string_value().c_str());
|
||||
exit(1);
|
||||
}
|
||||
if (action_cb != NULL)
|
||||
if (action_cb == NULL)
|
||||
{
|
||||
// Create client
|
||||
json11::Json cfg_j = cfg;
|
||||
p->ringloop = new ring_loop_t(512);
|
||||
p->epmgr = new epoll_manager_t(p->ringloop);
|
||||
p->cli = new cluster_client_t(p->ringloop, p->epmgr->tfd, cfg_j);
|
||||
// Smaller timeout by default for more interactiveness
|
||||
p->cli->st_cli.etcd_slow_timeout = p->cli->st_cli.etcd_quick_timeout;
|
||||
p->loop_and_wait(action_cb, [&](const cli_result_t & r)
|
||||
return;
|
||||
}
|
||||
color = !cfg["no-color"].bool_value();
|
||||
json_output = cfg["json"].bool_value();
|
||||
iodepth = cfg["iodepth"].uint64_value();
|
||||
if (!iodepth)
|
||||
iodepth = 32;
|
||||
parallel_osds = cfg["parallel_osds"].uint64_value();
|
||||
if (!parallel_osds)
|
||||
parallel_osds = 4;
|
||||
log_level = cfg["log_level"].int64_value();
|
||||
progress = cfg["progress"].uint64_value() ? true : false;
|
||||
list_first = cfg["wait-list"].uint64_value() ? true : false;
|
||||
// Create client
|
||||
ringloop = new ring_loop_t(512);
|
||||
epmgr = new epoll_manager_t(ringloop);
|
||||
cli = new cluster_client_t(ringloop, epmgr->tfd, cfg);
|
||||
// Smaller timeout by default for more interactiveness
|
||||
cli->st_cli.etcd_slow_timeout = cli->st_cli.etcd_quick_timeout;
|
||||
cli->on_ready([this]()
|
||||
{
|
||||
// Initialize job
|
||||
consumer.loop = [this]()
|
||||
{
|
||||
result = r;
|
||||
action_cb = NULL;
|
||||
});
|
||||
// Loop until it completes
|
||||
while (action_cb != NULL)
|
||||
{
|
||||
p->ringloop->loop();
|
||||
if (action_cb != NULL)
|
||||
p->ringloop->wait();
|
||||
}
|
||||
// Destroy the client
|
||||
delete p->cli;
|
||||
delete p->epmgr;
|
||||
delete p->ringloop;
|
||||
p->cli = NULL;
|
||||
p->epmgr = NULL;
|
||||
p->ringloop = NULL;
|
||||
}
|
||||
// Print result
|
||||
if (p->json_output && !result.data.is_null())
|
||||
{
|
||||
bool done = action_cb();
|
||||
if (done)
|
||||
{
|
||||
action_cb = NULL;
|
||||
}
|
||||
}
|
||||
ringloop->submit();
|
||||
};
|
||||
ringloop->register_consumer(&consumer);
|
||||
consumer.loop();
|
||||
});
|
||||
// Loop until it completes
|
||||
while (action_cb != NULL)
|
||||
{
|
||||
printf("%s\n", result.data.dump().c_str());
|
||||
ringloop->loop();
|
||||
if (action_cb != NULL)
|
||||
ringloop->wait();
|
||||
}
|
||||
else if (p->json_output && result.err)
|
||||
{
|
||||
printf("%s\n", json11::Json(json11::Json::object {
|
||||
{ "error_code", result.err },
|
||||
{ "error_text", result.text },
|
||||
}).dump().c_str());
|
||||
}
|
||||
else if (result.text != "")
|
||||
{
|
||||
fprintf(result.err ? stderr : stdout, result.text[result.text.size()-1] == '\n' ? "%s" : "%s\n", result.text.c_str());
|
||||
}
|
||||
return result.err;
|
||||
// Destroy the client
|
||||
delete cli;
|
||||
delete epmgr;
|
||||
delete ringloop;
|
||||
cli = NULL;
|
||||
epmgr = NULL;
|
||||
ringloop = NULL;
|
||||
}
|
||||
|
||||
int main(int narg, const char *args[])
|
||||
@@ -338,7 +390,7 @@ int main(int narg, const char *args[])
|
||||
setvbuf(stderr, NULL, _IONBF, 0);
|
||||
exe_name = args[0];
|
||||
cli_tool_t *p = new cli_tool_t();
|
||||
int r = run(p, parse_args(narg, args));
|
||||
p->run(cli_tool_t::parse_args(narg, args));
|
||||
delete p;
|
||||
return r;
|
||||
return 0;
|
||||
}
|
||||
|
||||
46
src/cli.h
46
src/cli.h
@@ -19,18 +19,11 @@ class epoll_manager_t;
|
||||
class cluster_client_t;
|
||||
struct inode_config_t;
|
||||
|
||||
struct cli_result_t
|
||||
{
|
||||
int err;
|
||||
std::string text;
|
||||
json11::Json data;
|
||||
};
|
||||
|
||||
class cli_tool_t
|
||||
{
|
||||
public:
|
||||
uint64_t iodepth = 4, parallel_osds = 32;
|
||||
bool progress = false;
|
||||
uint64_t iodepth = 0, parallel_osds = 0;
|
||||
bool progress = true;
|
||||
bool list_first = false;
|
||||
bool json_output = false;
|
||||
int log_level = 0;
|
||||
@@ -41,33 +34,34 @@ public:
|
||||
cluster_client_t *cli = NULL;
|
||||
|
||||
int waiting = 0;
|
||||
cli_result_t etcd_err;
|
||||
json11::Json etcd_result;
|
||||
ring_consumer_t consumer;
|
||||
std::function<bool(void)> action_cb;
|
||||
|
||||
void parse_config(json11::Json cfg);
|
||||
void run(json11::Json cfg);
|
||||
|
||||
void change_parent(inode_t cur, inode_t new_parent, cli_result_t *result);
|
||||
void change_parent(inode_t cur, inode_t new_parent);
|
||||
inode_config_t* get_inode_cfg(const std::string & name);
|
||||
|
||||
static json11::Json::object parse_args(int narg, const char *args[]);
|
||||
static void help();
|
||||
|
||||
friend struct rm_inode_t;
|
||||
friend struct snap_merger_t;
|
||||
friend struct snap_flattener_t;
|
||||
friend struct snap_remover_t;
|
||||
|
||||
std::function<bool(cli_result_t &)> start_status(json11::Json);
|
||||
std::function<bool(cli_result_t &)> start_df(json11::Json);
|
||||
std::function<bool(cli_result_t &)> start_ls(json11::Json);
|
||||
std::function<bool(cli_result_t &)> start_create(json11::Json);
|
||||
std::function<bool(cli_result_t &)> start_modify(json11::Json);
|
||||
std::function<bool(cli_result_t &)> start_rm_data(json11::Json);
|
||||
std::function<bool(cli_result_t &)> start_merge(json11::Json);
|
||||
std::function<bool(cli_result_t &)> start_flatten(json11::Json);
|
||||
std::function<bool(cli_result_t &)> start_rm(json11::Json);
|
||||
std::function<bool(cli_result_t &)> start_alloc_osd(json11::Json cfg);
|
||||
std::function<bool(cli_result_t &)> simple_offsets(json11::Json cfg);
|
||||
|
||||
// Should be called like loop_and_wait(start_status(), <completion callback>)
|
||||
void loop_and_wait(std::function<bool(cli_result_t &)> loop_cb, std::function<void(const cli_result_t &)> complete_cb);
|
||||
std::function<bool(void)> start_status(json11::Json cfg);
|
||||
std::function<bool(void)> start_df(json11::Json);
|
||||
std::function<bool(void)> start_ls(json11::Json);
|
||||
std::function<bool(void)> start_create(json11::Json);
|
||||
std::function<bool(void)> start_modify(json11::Json);
|
||||
std::function<bool(void)> start_rm(json11::Json);
|
||||
std::function<bool(void)> start_merge(json11::Json);
|
||||
std::function<bool(void)> start_flatten(json11::Json);
|
||||
std::function<bool(void)> start_snap_rm(json11::Json);
|
||||
std::function<bool(void)> start_alloc_osd(json11::Json cfg, uint64_t *out = NULL);
|
||||
std::function<bool(void)> simple_offsets(json11::Json cfg);
|
||||
|
||||
void etcd_txn(json11::Json txn);
|
||||
};
|
||||
|
||||
@@ -16,7 +16,6 @@ struct alloc_osd_t
|
||||
uint64_t new_id = 1;
|
||||
|
||||
int state = 0;
|
||||
cli_result_t result;
|
||||
|
||||
bool is_done()
|
||||
{
|
||||
@@ -63,12 +62,6 @@ struct alloc_osd_t
|
||||
state = 1;
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
result = parent->etcd_err;
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (!parent->etcd_result["succeeded"].bool_value())
|
||||
{
|
||||
std::vector<osd_num_t> used;
|
||||
@@ -106,23 +99,23 @@ struct alloc_osd_t
|
||||
}
|
||||
} while (!parent->etcd_result["succeeded"].bool_value());
|
||||
state = 100;
|
||||
result = (cli_result_t){
|
||||
.text = std::to_string(new_id),
|
||||
.data = json11::Json(new_id),
|
||||
};
|
||||
}
|
||||
};
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_alloc_osd(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_alloc_osd(json11::Json cfg, uint64_t *out)
|
||||
{
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
auto alloc_osd = new alloc_osd_t();
|
||||
alloc_osd->parent = this;
|
||||
return [alloc_osd](cli_result_t & result)
|
||||
return [alloc_osd, out]()
|
||||
{
|
||||
alloc_osd->loop();
|
||||
if (alloc_osd->is_done())
|
||||
{
|
||||
result = alloc_osd->result;
|
||||
if (out)
|
||||
*out = alloc_osd->new_id;
|
||||
else if (alloc_osd->new_id)
|
||||
printf("%lu\n", alloc_osd->new_id);
|
||||
delete alloc_osd;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -1,149 +0,0 @@
|
||||
// Copyright (c) Vitaliy Filippov, 2019+
|
||||
// License: VNPL-1.1 (see README.md for details)
|
||||
|
||||
#include "base64.h"
|
||||
#include "cluster_client.h"
|
||||
#include "cli.h"
|
||||
|
||||
void cli_tool_t::change_parent(inode_t cur, inode_t new_parent, cli_result_t *result)
|
||||
{
|
||||
auto cur_cfg_it = cli->st_cli.inode_config.find(cur);
|
||||
if (cur_cfg_it == cli->st_cli.inode_config.end())
|
||||
{
|
||||
char buf[128];
|
||||
snprintf(buf, 128, "Inode 0x%lx disappeared", cur);
|
||||
*result = (cli_result_t){ .err = EIO, .text = buf };
|
||||
return;
|
||||
}
|
||||
inode_config_t new_cfg = cur_cfg_it->second;
|
||||
std::string cur_name = new_cfg.name;
|
||||
std::string cur_cfg_key = base64_encode(cli->st_cli.etcd_prefix+
|
||||
"/config/inode/"+std::to_string(INODE_POOL(cur))+
|
||||
"/"+std::to_string(INODE_NO_POOL(cur)));
|
||||
new_cfg.parent_id = new_parent;
|
||||
json11::Json::object cur_cfg_json = cli->st_cli.serialize_inode_cfg(&new_cfg);
|
||||
waiting++;
|
||||
cli->st_cli.etcd_txn_slow(json11::Json::object {
|
||||
{ "compare", json11::Json::array {
|
||||
json11::Json::object {
|
||||
{ "target", "MOD" },
|
||||
{ "key", cur_cfg_key },
|
||||
{ "result", "LESS" },
|
||||
{ "mod_revision", new_cfg.mod_revision+1 },
|
||||
},
|
||||
} },
|
||||
{ "success", json11::Json::array {
|
||||
json11::Json::object {
|
||||
{ "request_put", json11::Json::object {
|
||||
{ "key", cur_cfg_key },
|
||||
{ "value", base64_encode(json11::Json(cur_cfg_json).dump()) },
|
||||
} }
|
||||
},
|
||||
} },
|
||||
}, [this, result, new_parent, cur, cur_name](std::string err, json11::Json res)
|
||||
{
|
||||
if (err != "")
|
||||
{
|
||||
*result = (cli_result_t){ .err = EIO, .text = "Error changing parent of "+cur_name+": "+err };
|
||||
}
|
||||
else if (!res["succeeded"].bool_value())
|
||||
{
|
||||
*result = (cli_result_t){ .err = EAGAIN, .text = "Image "+cur_name+" was modified during change" };
|
||||
}
|
||||
else if (new_parent)
|
||||
{
|
||||
auto new_parent_it = cli->st_cli.inode_config.find(new_parent);
|
||||
std::string new_parent_name = new_parent_it != cli->st_cli.inode_config.end()
|
||||
? new_parent_it->second.name : "<unknown>";
|
||||
*result = (cli_result_t){
|
||||
.text = "Parent of layer "+cur_name+" (inode "+std::to_string(INODE_NO_POOL(cur))+
|
||||
" in pool "+std::to_string(INODE_POOL(cur))+") changed to "+new_parent_name+
|
||||
" (inode "+std::to_string(INODE_NO_POOL(new_parent))+" in pool "+std::to_string(INODE_POOL(new_parent))+")",
|
||||
};
|
||||
}
|
||||
else
|
||||
{
|
||||
*result = (cli_result_t){
|
||||
.text = "Parent of layer "+cur_name+" (inode "+std::to_string(INODE_NO_POOL(cur))+
|
||||
" in pool "+std::to_string(INODE_POOL(cur))+") detached",
|
||||
};
|
||||
}
|
||||
waiting--;
|
||||
ringloop->wakeup();
|
||||
});
|
||||
}
|
||||
|
||||
void cli_tool_t::etcd_txn(json11::Json txn)
|
||||
{
|
||||
waiting++;
|
||||
cli->st_cli.etcd_txn_slow(txn, [this](std::string err, json11::Json res)
|
||||
{
|
||||
waiting--;
|
||||
if (err != "")
|
||||
etcd_err = (cli_result_t){ .err = EIO, .text = "Error communicating with etcd: "+err };
|
||||
else
|
||||
etcd_err = (cli_result_t){ .err = 0 };
|
||||
etcd_result = res;
|
||||
ringloop->wakeup();
|
||||
});
|
||||
}
|
||||
|
||||
inode_config_t* cli_tool_t::get_inode_cfg(const std::string & name)
|
||||
{
|
||||
for (auto & ic: cli->st_cli.inode_config)
|
||||
{
|
||||
if (ic.second.name == name)
|
||||
{
|
||||
return &ic.second;
|
||||
}
|
||||
}
|
||||
return NULL;
|
||||
}
|
||||
|
||||
void cli_tool_t::parse_config(json11::Json cfg)
|
||||
{
|
||||
color = !cfg["no-color"].bool_value();
|
||||
json_output = cfg["json"].bool_value();
|
||||
iodepth = cfg["iodepth"].uint64_value();
|
||||
if (!iodepth)
|
||||
iodepth = 32;
|
||||
parallel_osds = cfg["parallel_osds"].uint64_value();
|
||||
if (!parallel_osds)
|
||||
parallel_osds = 4;
|
||||
log_level = cfg["log_level"].int64_value();
|
||||
progress = cfg["progress"].uint64_value() ? true : false;
|
||||
list_first = cfg["wait-list"].uint64_value() ? true : false;
|
||||
}
|
||||
|
||||
struct cli_result_looper_t
|
||||
{
|
||||
ring_consumer_t consumer;
|
||||
cli_result_t result;
|
||||
std::function<bool(cli_result_t &)> loop_cb;
|
||||
std::function<void(const cli_result_t &)> complete_cb;
|
||||
};
|
||||
|
||||
void cli_tool_t::loop_and_wait(std::function<bool(cli_result_t &)> loop_cb, std::function<void(const cli_result_t &)> complete_cb)
|
||||
{
|
||||
auto *looper = new cli_result_looper_t();
|
||||
looper->loop_cb = loop_cb;
|
||||
looper->complete_cb = complete_cb;
|
||||
looper->consumer.loop = [this, looper]()
|
||||
{
|
||||
bool done = looper->loop_cb(looper->result);
|
||||
if (done)
|
||||
{
|
||||
ringloop->unregister_consumer(&looper->consumer);
|
||||
looper->loop_cb = NULL;
|
||||
looper->complete_cb(looper->result);
|
||||
delete looper;
|
||||
return;
|
||||
}
|
||||
ringloop->submit();
|
||||
};
|
||||
cli->on_ready([this, looper]()
|
||||
{
|
||||
ringloop->register_consumer(&looper->consumer);
|
||||
ringloop->wakeup();
|
||||
});
|
||||
}
|
||||
@@ -25,18 +25,14 @@ struct image_creator_t
|
||||
pool_id_t new_pool_id = 0;
|
||||
std::string new_pool_name;
|
||||
std::string image_name, new_snap, new_parent;
|
||||
json11::Json new_meta;
|
||||
uint64_t size;
|
||||
bool force_size = false;
|
||||
|
||||
pool_id_t old_pool_id = 0;
|
||||
inode_t new_parent_id = 0;
|
||||
inode_t new_id = 0, old_id = 0;
|
||||
uint64_t max_id_mod_rev = 0, cfg_mod_rev = 0, idx_mod_rev = 0;
|
||||
inode_config_t new_cfg;
|
||||
|
||||
int state = 0;
|
||||
cli_result_t result;
|
||||
|
||||
bool is_done()
|
||||
{
|
||||
@@ -47,27 +43,13 @@ struct image_creator_t
|
||||
{
|
||||
if (state >= 1)
|
||||
goto resume_1;
|
||||
if (image_name == "")
|
||||
{
|
||||
// FIXME: EINVAL -> specific codes for every error
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Image name is missing" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (image_name.find('@') != std::string::npos)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Image name can't contain @ character" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (new_pool_id)
|
||||
{
|
||||
auto & pools = parent->cli->st_cli.pool_config;
|
||||
if (pools.find(new_pool_id) == pools.end())
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Pool "+std::to_string(new_pool_id)+" does not exist" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Pool %u does not exist\n", new_pool_id);
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
else if (new_pool_name != "")
|
||||
@@ -82,9 +64,8 @@ struct image_creator_t
|
||||
}
|
||||
if (!new_pool_id)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Pool "+new_pool_name+" does not exist" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Pool %s does not exist\n", new_pool_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
else if (parent->cli->st_cli.pool_config.size() == 1)
|
||||
@@ -110,9 +91,8 @@ struct image_creator_t
|
||||
{
|
||||
if (ic.second.name == image_name)
|
||||
{
|
||||
result = (cli_result_t){ .err = EEXIST, .text = "Image "+image_name+" already exists" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Image %s already exists\n", image_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
if (ic.second.name == new_parent)
|
||||
{
|
||||
@@ -129,21 +109,18 @@ struct image_creator_t
|
||||
}
|
||||
if (new_parent != "" && !new_parent_id)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Parent image "+new_parent+" not found" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Parent image not found\n");
|
||||
exit(1);
|
||||
}
|
||||
if (!new_pool_id)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Pool name or ID is missing" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Pool name or ID is missing\n");
|
||||
exit(1);
|
||||
}
|
||||
if (!size && !force_size)
|
||||
if (!size)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Image size is missing" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Image size is missing\n");
|
||||
exit(1);
|
||||
}
|
||||
do
|
||||
{
|
||||
@@ -154,36 +131,23 @@ struct image_creator_t
|
||||
resume_2:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
result = parent->etcd_err;
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
extract_next_id(parent->etcd_result["responses"][0]);
|
||||
attempt_create();
|
||||
state = 3;
|
||||
resume_3:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
result = parent->etcd_err;
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (!parent->etcd_result["succeeded"].bool_value() &&
|
||||
parent->etcd_result["responses"][0]["response_range"]["kvs"].array_items().size() > 0)
|
||||
{
|
||||
result = (cli_result_t){ .err = EEXIST, .text = "Image "+image_name+" already exists" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Image %s already exists\n", image_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
} while (!parent->etcd_result["succeeded"].bool_value());
|
||||
// Save into inode_config for library users to be able to take it from there immediately
|
||||
new_cfg.mod_revision = parent->etcd_result["responses"][0]["response_put"]["header"]["revision"].uint64_value();
|
||||
parent->cli->st_cli.insert_inode_config(new_cfg);
|
||||
result = (cli_result_t){ .err = 0, .text = "Image "+image_name+" created" };
|
||||
if (parent->progress)
|
||||
{
|
||||
printf("Image %s created\n", image_name.c_str());
|
||||
}
|
||||
state = 100;
|
||||
}
|
||||
|
||||
@@ -199,16 +163,14 @@ resume_3:
|
||||
{
|
||||
if (ic.second.name == image_name+"@"+new_snap)
|
||||
{
|
||||
result = (cli_result_t){ .err = EEXIST, .text = "Snapshot "+image_name+"@"+new_snap+" already exists" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Snapshot %s@%s already exists\n", image_name.c_str(), new_snap.c_str());
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
if (new_parent != "")
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Parent can't be specified for snapshots" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "--parent can't be used with snapshots\n");
|
||||
exit(1);
|
||||
}
|
||||
do
|
||||
{
|
||||
@@ -220,9 +182,8 @@ resume_3:
|
||||
return;
|
||||
if (!old_id)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Image "+image_name+" does not exist" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Image %s does not exist\n", image_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
if (!new_pool_id)
|
||||
{
|
||||
@@ -234,24 +195,17 @@ resume_3:
|
||||
resume_4:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
result = parent->etcd_err;
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (!parent->etcd_result["succeeded"].bool_value() &&
|
||||
parent->etcd_result["responses"][0]["response_range"]["kvs"].array_items().size() > 0)
|
||||
{
|
||||
result = (cli_result_t){ .err = EEXIST, .text = "Snapshot "+image_name+"@"+new_snap+" already exists" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Snapshot %s@%s already exists\n", image_name.c_str(), new_snap.c_str());
|
||||
exit(1);
|
||||
}
|
||||
} while (!parent->etcd_result["succeeded"].bool_value());
|
||||
// Save into inode_config for library users to be able to take it from there immediately
|
||||
new_cfg.mod_revision = parent->etcd_result["responses"][0]["response_put"]["header"]["revision"].uint64_value();
|
||||
parent->cli->st_cli.insert_inode_config(new_cfg);
|
||||
result = (cli_result_t){ .err = 0, .text = "Snapshot "+image_name+"@"+new_snap+" created" };
|
||||
if (parent->progress)
|
||||
{
|
||||
printf("Snapshot %s@%s created\n", image_name.c_str(), new_snap.c_str());
|
||||
}
|
||||
state = 100;
|
||||
}
|
||||
|
||||
@@ -305,12 +259,6 @@ resume_4:
|
||||
resume_2:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
result = parent->etcd_err;
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
extract_next_id(parent->etcd_result["responses"][0]);
|
||||
old_id = 0;
|
||||
old_pool_id = 0;
|
||||
@@ -340,9 +288,8 @@ resume_2:
|
||||
idx_mod_rev = kv.mod_revision;
|
||||
if (!old_id || !old_pool_id || old_pool_id >= POOL_ID_MAX)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Invalid pool or inode ID in etcd key "+kv.key };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Invalid pool or inode ID in etcd key %s\n", kv.key.c_str());
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
parent->etcd_txn(json11::Json::object {
|
||||
@@ -361,12 +308,6 @@ resume_2:
|
||||
resume_3:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
result = parent->etcd_err;
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
{
|
||||
auto kv = parent->cli->st_cli.parse_etcd_kv(parent->etcd_result["responses"][0]["response_range"]["kvs"][0]);
|
||||
size = kv.value["size"].uint64_value();
|
||||
@@ -383,13 +324,12 @@ resume_3:
|
||||
|
||||
void attempt_create()
|
||||
{
|
||||
new_cfg = {
|
||||
inode_config_t new_cfg = {
|
||||
.num = INODE_WITH_POOL(new_pool_id, new_id),
|
||||
.name = image_name,
|
||||
.size = size,
|
||||
.parent_id = (new_snap != "" ? INODE_WITH_POOL(old_pool_id, old_id) : new_parent_id),
|
||||
.readonly = false,
|
||||
.meta = new_meta,
|
||||
};
|
||||
json11::Json::array checks = json11::Json::array {
|
||||
json11::Json::object {
|
||||
@@ -517,76 +457,77 @@ uint64_t parse_size(std::string size_str)
|
||||
if (type_char == 'k' || type_char == 'm' || type_char == 'g' || type_char == 't')
|
||||
{
|
||||
if (type_char == 'k')
|
||||
mul = (uint64_t)1<<10;
|
||||
mul = 1l<<10;
|
||||
else if (type_char == 'm')
|
||||
mul = (uint64_t)1<<20;
|
||||
mul = 1l<<20;
|
||||
else if (type_char == 'g')
|
||||
mul = (uint64_t)1<<30;
|
||||
mul = 1l<<30;
|
||||
else /*if (type_char == 't')*/
|
||||
mul = (uint64_t)1<<40;
|
||||
mul = 1l<<40;
|
||||
size_str = size_str.substr(0, size_str.length()-1);
|
||||
}
|
||||
uint64_t size = json11::Json(size_str).uint64_value() * mul;
|
||||
if (size == 0 && size_str != "0" && (size_str != "" || mul != 1))
|
||||
{
|
||||
return UINT64_MAX;
|
||||
fprintf(stderr, "Invalid syntax for size: %s\n", size_str.c_str());
|
||||
exit(1);
|
||||
}
|
||||
return size;
|
||||
}
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_create(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_create(json11::Json cfg)
|
||||
{
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
auto image_creator = new image_creator_t();
|
||||
image_creator->parent = this;
|
||||
image_creator->image_name = cfg["image"].string_value();
|
||||
image_creator->image_name = cmd.size() > 1 ? cmd[1].string_value() : "";
|
||||
image_creator->new_pool_id = cfg["pool"].uint64_value();
|
||||
image_creator->new_pool_name = cfg["pool"].string_value();
|
||||
image_creator->force_size = cfg["force_size"].bool_value();
|
||||
if (cfg["image_meta"].is_object())
|
||||
{
|
||||
image_creator->new_meta = cfg["image-meta"];
|
||||
}
|
||||
if (cfg["snapshot"].string_value() != "")
|
||||
{
|
||||
image_creator->new_snap = cfg["snapshot"].string_value();
|
||||
}
|
||||
else if (cmd[0] == "snap-create")
|
||||
{
|
||||
int p = image_creator->image_name.find('@');
|
||||
if (p == std::string::npos || p == image_creator->image_name.length()-1)
|
||||
{
|
||||
fprintf(stderr, "Please specify new snapshot name after @\n");
|
||||
exit(1);
|
||||
}
|
||||
image_creator->new_snap = image_creator->image_name.substr(p + 1);
|
||||
image_creator->image_name = image_creator->image_name.substr(0, p);
|
||||
}
|
||||
image_creator->new_parent = cfg["parent"].string_value();
|
||||
if (cfg["size"].string_value() != "")
|
||||
{
|
||||
image_creator->size = parse_size(cfg["size"].string_value());
|
||||
if (image_creator->size == UINT64_MAX)
|
||||
if (image_creator->size % 4096)
|
||||
{
|
||||
return [size = cfg["size"].string_value()](cli_result_t & result)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Invalid syntax for size: "+size };
|
||||
return true;
|
||||
};
|
||||
}
|
||||
if ((image_creator->size % 4096) && !cfg["force_size"].bool_value())
|
||||
{
|
||||
delete image_creator;
|
||||
return [](cli_result_t & result)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Size should be a multiple of 4096" };
|
||||
return true;
|
||||
};
|
||||
fprintf(stderr, "Size should be a multiple of 4096\n");
|
||||
exit(1);
|
||||
}
|
||||
if (image_creator->new_snap != "")
|
||||
{
|
||||
delete image_creator;
|
||||
return [](cli_result_t & result)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Size can't be specified for snapshots" };
|
||||
return true;
|
||||
};
|
||||
fprintf(stderr, "--size can't be specified for snapshots\n");
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
return [image_creator](cli_result_t & result)
|
||||
if (image_creator->image_name == "")
|
||||
{
|
||||
fprintf(stderr, "Image name is missing\n");
|
||||
exit(1);
|
||||
}
|
||||
if (image_creator->image_name.find('@') != std::string::npos)
|
||||
{
|
||||
fprintf(stderr, "Image name can't contain @ character\n");
|
||||
exit(1);
|
||||
}
|
||||
return [image_creator]()
|
||||
{
|
||||
image_creator->loop();
|
||||
if (image_creator->is_done())
|
||||
{
|
||||
result = image_creator->result;
|
||||
delete image_creator;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -12,7 +12,6 @@ struct pool_lister_t
|
||||
|
||||
int state = 0;
|
||||
json11::Json space_info;
|
||||
cli_result_t result;
|
||||
std::map<pool_id_t, json11::Json::object> pool_stats;
|
||||
|
||||
bool is_done()
|
||||
@@ -53,12 +52,6 @@ struct pool_lister_t
|
||||
resume_1:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
result = parent->etcd_err;
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
space_info = parent->etcd_result;
|
||||
std::map<pool_id_t, uint64_t> osd_free;
|
||||
for (auto & kv_item: space_info["responses"][0]["response_range"]["kvs"].array_items())
|
||||
@@ -131,8 +124,8 @@ resume_1:
|
||||
{ "scheme_name", pool_cfg.scheme == POOL_SCHEME_REPLICATED
|
||||
? std::to_string(pool_cfg.pg_size)+"/"+std::to_string(pool_cfg.pg_minsize)
|
||||
: "EC "+std::to_string(pool_cfg.pg_size-pool_cfg.parity_chunks)+"+"+std::to_string(pool_cfg.parity_chunks) },
|
||||
{ "used_raw", (uint64_t)(pool_stats[pool_cfg.id]["used_raw_tb"].number_value() * ((uint64_t)1<<40)) },
|
||||
{ "total_raw", (uint64_t)(pool_stats[pool_cfg.id]["total_raw_tb"].number_value() * ((uint64_t)1<<40)) },
|
||||
{ "used_raw", (uint64_t)(pool_stats[pool_cfg.id]["used_raw_tb"].number_value() * (1l<<40)) },
|
||||
{ "total_raw", (uint64_t)(pool_stats[pool_cfg.id]["total_raw_tb"].number_value() * (1l<<40)) },
|
||||
{ "max_available", pool_avail },
|
||||
{ "raw_to_usable", pool_stats[pool_cfg.id]["raw_to_usable"].number_value() },
|
||||
{ "space_efficiency", pool_stats[pool_cfg.id]["space_efficiency"].number_value() },
|
||||
@@ -157,12 +150,10 @@ resume_1:
|
||||
get_stats();
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (state == 100)
|
||||
return;
|
||||
if (parent->json_output)
|
||||
{
|
||||
// JSON output
|
||||
result.data = to_list();
|
||||
printf("%s\n", json11::Json(to_list()).dump().c_str());
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
@@ -215,22 +206,21 @@ resume_1:
|
||||
: 100)+"%";
|
||||
kv.second["eff_fmt"] = format_q(kv.second["space_efficiency"].number_value()*100)+"%";
|
||||
}
|
||||
result.data = to_list();
|
||||
result.text = print_table(result.data, cols, parent->color);
|
||||
printf("%s", print_table(to_list(), cols, parent->color).c_str());
|
||||
state = 100;
|
||||
}
|
||||
};
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_df(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_df(json11::Json cfg)
|
||||
{
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
auto lister = new pool_lister_t();
|
||||
lister->parent = this;
|
||||
return [lister](cli_result_t & result)
|
||||
return [lister]()
|
||||
{
|
||||
lister->loop();
|
||||
if (lister->is_done())
|
||||
{
|
||||
result = lister->result;
|
||||
delete lister;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -22,19 +22,12 @@ struct snap_flattener_t
|
||||
std::string top_parent_name;
|
||||
inode_t target_id = 0;
|
||||
int state = 0;
|
||||
std::function<bool(cli_result_t &)> merger_cb;
|
||||
cli_result_t result;
|
||||
std::function<bool(void)> merger_cb;
|
||||
|
||||
void get_merge_parents()
|
||||
{
|
||||
// Get all parents of target
|
||||
inode_config_t *target_cfg = parent->get_inode_cfg(target_name);
|
||||
if (!target_cfg)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Layer "+target_name+" not found" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
target_id = target_cfg->num;
|
||||
std::vector<inode_t> chain_list;
|
||||
inode_config_t *cur = target_cfg;
|
||||
@@ -44,34 +37,23 @@ struct snap_flattener_t
|
||||
auto it = parent->cli->st_cli.inode_config.find(cur->parent_id);
|
||||
if (it == parent->cli->st_cli.inode_config.end())
|
||||
{
|
||||
result = (cli_result_t){
|
||||
.err = ENOENT,
|
||||
.text = "Parent inode of layer "+cur->name+" (id "+std::to_string(cur->parent_id)+") does not exist",
|
||||
.data = json11::Json::object {
|
||||
{ "error", "parent-not-found" },
|
||||
{ "inode_id", cur->num },
|
||||
{ "inode_name", cur->name },
|
||||
{ "parent_id", cur->parent_id },
|
||||
},
|
||||
};
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Parent inode of layer %s (id %ld) not found\n", cur->name.c_str(), cur->parent_id);
|
||||
exit(1);
|
||||
}
|
||||
cur = &it->second;
|
||||
chain_list.push_back(cur->num);
|
||||
}
|
||||
if (cur->parent_id != 0)
|
||||
{
|
||||
result = (cli_result_t){ .err = EBADF, .text = "Layer "+target_name+" has a loop in parents" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Layer %s has a loop in parents\n", target_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
top_parent_name = cur->name;
|
||||
}
|
||||
|
||||
bool is_done()
|
||||
{
|
||||
return state == 100;
|
||||
return state == 5;
|
||||
}
|
||||
|
||||
void loop()
|
||||
@@ -82,20 +64,11 @@ struct snap_flattener_t
|
||||
goto resume_2;
|
||||
else if (state == 3)
|
||||
goto resume_3;
|
||||
if (target_name == "")
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Layer to flatten not specified" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
// Get parent layers
|
||||
get_merge_parents();
|
||||
if (state == 100)
|
||||
return;
|
||||
// Start merger
|
||||
merger_cb = parent->start_merge(json11::Json::object {
|
||||
{ "from", top_parent_name },
|
||||
{ "to", target_name },
|
||||
{ "command", json11::Json::array{ "merge-data", top_parent_name, target_name } },
|
||||
{ "target", target_name },
|
||||
{ "delete-source", false },
|
||||
{ "cas", use_cas },
|
||||
@@ -103,19 +76,14 @@ struct snap_flattener_t
|
||||
});
|
||||
// Wait for it
|
||||
resume_1:
|
||||
while (!merger_cb(result))
|
||||
while (!merger_cb())
|
||||
{
|
||||
state = 1;
|
||||
return;
|
||||
}
|
||||
merger_cb = NULL;
|
||||
if (result.err)
|
||||
{
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
// Change parent
|
||||
parent->change_parent(target_id, 0, &result);
|
||||
parent->change_parent(target_id, 0);
|
||||
// Wait for it to complete
|
||||
state = 2;
|
||||
resume_2:
|
||||
@@ -124,26 +92,31 @@ resume_2:
|
||||
state = 3;
|
||||
resume_3:
|
||||
// Done
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
};
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_flatten(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_flatten(json11::Json cfg)
|
||||
{
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
auto flattener = new snap_flattener_t();
|
||||
flattener->parent = this;
|
||||
flattener->target_name = cfg["image"].string_value();
|
||||
flattener->target_name = cmd.size() > 1 ? cmd[1].string_value() : "";
|
||||
if (flattener->target_name == "")
|
||||
{
|
||||
fprintf(stderr, "Layer to flatten argument is missing\n");
|
||||
exit(1);
|
||||
}
|
||||
flattener->fsync_interval = cfg["fsync-interval"].uint64_value();
|
||||
if (!flattener->fsync_interval)
|
||||
flattener->fsync_interval = 128;
|
||||
if (!cfg["cas"].is_null())
|
||||
flattener->use_cas = cfg["cas"].uint64_value() ? 2 : 0;
|
||||
return [flattener](cli_result_t & result)
|
||||
return [flattener]()
|
||||
{
|
||||
flattener->loop();
|
||||
if (flattener->is_done())
|
||||
{
|
||||
result = flattener->result;
|
||||
delete flattener;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -24,7 +24,6 @@ struct image_lister_t
|
||||
int state = 0;
|
||||
std::map<inode_t, json11::Json::object> stats;
|
||||
json11::Json space_info;
|
||||
cli_result_t result;
|
||||
|
||||
bool is_done()
|
||||
{
|
||||
@@ -45,9 +44,8 @@ struct image_lister_t
|
||||
}
|
||||
if (!list_pool_id)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Pool "+list_pool_name+" does not exist" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Pool %s does not exist\n", list_pool_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
for (auto & ic: parent->cli->st_cli.inode_config)
|
||||
@@ -118,12 +116,6 @@ struct image_lister_t
|
||||
resume_1:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
result = parent->etcd_err;
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
space_info = parent->etcd_result;
|
||||
std::map<pool_id_t, uint64_t> pool_pg_real_size;
|
||||
for (auto & kv_item: space_info["responses"][0]["response_range"]["kvs"].array_items())
|
||||
@@ -253,13 +245,11 @@ resume_1:
|
||||
get_stats();
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (state == 100)
|
||||
return;
|
||||
}
|
||||
result.data = to_list();
|
||||
if (parent->json_output)
|
||||
{
|
||||
// JSON output
|
||||
printf("%s\n", json11::Json(to_list()).dump().c_str());
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
@@ -369,7 +359,7 @@ resume_1:
|
||||
kv.second["size_fmt"] = format_size(kv.second["size"].uint64_value());
|
||||
kv.second["ro"] = kv.second["readonly"].bool_value() ? "RO" : "-";
|
||||
}
|
||||
result.text = print_table(to_list(), cols, parent->color);
|
||||
printf("%s", print_table(to_list(), cols, parent->color).c_str());
|
||||
state = 100;
|
||||
}
|
||||
};
|
||||
@@ -446,8 +436,8 @@ std::string print_table(json11::Json items, json11::Json header, bool use_esc)
|
||||
return str;
|
||||
}
|
||||
|
||||
static uint64_t size_thresh[] = { (uint64_t)1024*1024*1024*1024, (uint64_t)1024*1024*1024, (uint64_t)1024*1024, 1024, 0 };
|
||||
static uint64_t size_thresh_d[] = { (uint64_t)1000000000000, (uint64_t)1000000000, (uint64_t)1000000, (uint64_t)1000, 0 };
|
||||
static uint64_t size_thresh[] = { 1024l*1024*1024*1024, 1024l*1024*1024, 1024l*1024, 1024, 0 };
|
||||
static uint64_t size_thresh_d[] = { 1000000000000l, 1000000000l, 1000000l, 1000l, 0 };
|
||||
static const int size_thresh_n = sizeof(size_thresh)/sizeof(size_thresh[0]);
|
||||
static const char *size_unit = "TGMKB";
|
||||
|
||||
@@ -556,8 +546,9 @@ back:
|
||||
return true;
|
||||
}
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_ls(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_ls(json11::Json cfg)
|
||||
{
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
auto lister = new image_lister_t();
|
||||
lister->parent = this;
|
||||
lister->list_pool_id = cfg["pool"].uint64_value();
|
||||
@@ -567,16 +558,15 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_ls(json11::Json cfg)
|
||||
lister->sort_field = cfg["sort"].string_value();
|
||||
lister->reverse = cfg["reverse"].bool_value();
|
||||
lister->max_count = cfg["count"].uint64_value();
|
||||
for (auto & item: cfg["names"].array_items())
|
||||
for (int i = 1; i < cmd.size(); i++)
|
||||
{
|
||||
lister->only_names.insert(item.string_value());
|
||||
lister->only_names.insert(cmd[i].string_value());
|
||||
}
|
||||
return [lister](cli_result_t & result)
|
||||
return [lister]()
|
||||
{
|
||||
lister->loop();
|
||||
if (lister->is_done())
|
||||
{
|
||||
result = lister->result;
|
||||
delete lister;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -12,9 +12,6 @@ struct snap_rw_op_t
|
||||
cluster_op_t op;
|
||||
int todo = 0;
|
||||
uint32_t start = 0, end = 0;
|
||||
int error_code = 0;
|
||||
uint64_t error_offset = 0;
|
||||
bool error_read = false;
|
||||
};
|
||||
|
||||
// Layer merge is the base for multiple operations:
|
||||
@@ -57,45 +54,17 @@ struct snap_merger_t
|
||||
uint64_t last_written_offset = 0;
|
||||
int deleted_unsynced = 0;
|
||||
uint64_t processed = 0, to_process = 0;
|
||||
std::string rwo_error;
|
||||
|
||||
cli_result_t result;
|
||||
|
||||
void start_merge()
|
||||
{
|
||||
if (from_name == "" || to_name == "")
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Beginning or end of the merge sequence is missing" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
check_delete_source = delete_source || check_delete_source;
|
||||
inode_config_t *from_cfg = parent->get_inode_cfg(from_name);
|
||||
if (!from_cfg)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Layer "+from_name+" not found" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
inode_config_t *to_cfg = parent->get_inode_cfg(to_name);
|
||||
if (!to_cfg)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Layer "+to_name+" not found" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
inode_config_t *target_cfg = target_name == "" ? from_cfg : parent->get_inode_cfg(target_name);
|
||||
if (!target_cfg)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Layer "+target_name+" not found" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (to_cfg->num == from_cfg->num)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Only one layer specified, nothing to merge" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Only one layer specified, nothing to merge\n");
|
||||
exit(1);
|
||||
}
|
||||
// Check that to_cfg is actually a child of from_cfg and target_cfg is somewhere between them
|
||||
std::vector<inode_t> chain_list;
|
||||
@@ -109,18 +78,8 @@ struct snap_merger_t
|
||||
auto it = parent->cli->st_cli.inode_config.find(cur->parent_id);
|
||||
if (it == parent->cli->st_cli.inode_config.end())
|
||||
{
|
||||
result = (cli_result_t){
|
||||
.err = ENOENT,
|
||||
.text = "Parent inode of layer "+cur->name+" (id "+std::to_string(cur->parent_id)+") does not exist",
|
||||
.data = json11::Json::object {
|
||||
{ "error", "parent-not-found" },
|
||||
{ "inode_id", cur->num },
|
||||
{ "inode_name", cur->name },
|
||||
{ "parent_id", cur->parent_id },
|
||||
},
|
||||
};
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Parent inode of layer %s (id %ld) not found\n", cur->name.c_str(), cur->parent_id);
|
||||
exit(1);
|
||||
}
|
||||
cur = &it->second;
|
||||
chain_list.push_back(cur->num);
|
||||
@@ -128,9 +87,8 @@ struct snap_merger_t
|
||||
}
|
||||
if (cur->parent_id != from_cfg->num)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Layer "+to_name+" is not a child of "+from_name };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Layer %s is not a child of %s\n", to_name.c_str(), from_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
chain_list.push_back(from_cfg->num);
|
||||
layer_block_size[from_cfg->num] = get_block_size(from_cfg->num);
|
||||
@@ -141,9 +99,8 @@ struct snap_merger_t
|
||||
}
|
||||
if (sources.find(target_cfg->num) == sources.end())
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Layer "+target_name+" is not between "+to_name+" and "+from_name };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Layer %s is not between %s and %s\n", target_name.c_str(), to_name.c_str(), from_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
target = target_cfg->num;
|
||||
target_rank = sources.at(target);
|
||||
@@ -173,15 +130,14 @@ struct snap_merger_t
|
||||
int parent_rank = it->second;
|
||||
if (parent_rank < to_rank && (parent_rank >= target_rank || check_delete_source))
|
||||
{
|
||||
result = (cli_result_t){
|
||||
.err = EINVAL,
|
||||
.text = "Layers at or above "+(check_delete_source ? from_name : target_name)+
|
||||
", but below "+to_name+" are not allowed to have other children, but "+
|
||||
ic.second.name+" is a child of "+
|
||||
parent->cli->st_cli.inode_config.at(ic.second.parent_id).name,
|
||||
};
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(
|
||||
stderr, "Layers at or above %s, but below %s are not allowed"
|
||||
" to have other children, but %s is a child of %s\n",
|
||||
(check_delete_source ? from_name.c_str() : target_name.c_str()),
|
||||
to_name.c_str(), ic.second.name.c_str(),
|
||||
parent->cli->st_cli.inode_config.at(ic.second.parent_id).name.c_str()
|
||||
);
|
||||
exit(1);
|
||||
}
|
||||
if (parent_rank >= to_rank)
|
||||
{
|
||||
@@ -196,14 +152,11 @@ struct snap_merger_t
|
||||
use_cas = 0;
|
||||
}
|
||||
sources.erase(target);
|
||||
if (parent->progress)
|
||||
{
|
||||
printf(
|
||||
"Merging %ld layer(s) into target %s%s (inode %lu in pool %u)\n",
|
||||
sources.size(), target_cfg->name.c_str(),
|
||||
use_cas ? " online (with CAS)" : "", INODE_NO_POOL(target), INODE_POOL(target)
|
||||
);
|
||||
}
|
||||
printf(
|
||||
"Merging %ld layer(s) into target %s%s (inode %lu in pool %u)\n",
|
||||
sources.size(), target_cfg->name.c_str(),
|
||||
use_cas ? " online (with CAS)" : "", INODE_NO_POOL(target), INODE_POOL(target)
|
||||
);
|
||||
target_block_size = get_block_size(target);
|
||||
}
|
||||
|
||||
@@ -226,7 +179,7 @@ struct snap_merger_t
|
||||
|
||||
bool is_done()
|
||||
{
|
||||
return state == 100;
|
||||
return state == 6;
|
||||
}
|
||||
|
||||
void continue_merge()
|
||||
@@ -241,8 +194,8 @@ struct snap_merger_t
|
||||
goto resume_4;
|
||||
else if (state == 5)
|
||||
goto resume_5;
|
||||
else if (state == 100)
|
||||
goto resume_100;
|
||||
else if (state == 6)
|
||||
goto resume_6;
|
||||
// Get parents and so on
|
||||
start_merge();
|
||||
// First list lower layers
|
||||
@@ -300,8 +253,7 @@ struct snap_merger_t
|
||||
oit = merge_offsets.begin();
|
||||
resume_5:
|
||||
// Now read, overwrite and optionally delete offsets one by one
|
||||
while (in_flight < parent->iodepth*parent->parallel_osds &&
|
||||
oit != merge_offsets.end() && !rwo_error.size())
|
||||
while (in_flight < parent->iodepth*parent->parallel_osds && oit != merge_offsets.end())
|
||||
{
|
||||
in_flight++;
|
||||
read_and_write(*oit);
|
||||
@@ -312,15 +264,6 @@ struct snap_merger_t
|
||||
printf("\rOverwriting blocks: %lu/%lu", processed, to_process);
|
||||
}
|
||||
}
|
||||
if (in_flight == 0 && rwo_error.size())
|
||||
{
|
||||
result = (cli_result_t){
|
||||
.err = EIO,
|
||||
.text = rwo_error,
|
||||
};
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (in_flight > 0 || oit != merge_offsets.end())
|
||||
{
|
||||
// Wait until overwrites finish
|
||||
@@ -331,9 +274,9 @@ struct snap_merger_t
|
||||
printf("\rOverwriting blocks: %lu/%lu\n", to_process, to_process);
|
||||
}
|
||||
// Done
|
||||
result = (cli_result_t){ .text = "Done, layers from "+from_name+" to "+to_name+" merged into "+target_name };
|
||||
state = 100;
|
||||
resume_100:
|
||||
printf("Done, layers from %s to %s merged into %s\n", from_name.c_str(), to_name.c_str(), target_name.c_str());
|
||||
state = 6;
|
||||
resume_6:
|
||||
return;
|
||||
}
|
||||
|
||||
@@ -371,10 +314,7 @@ struct snap_merger_t
|
||||
if (status & INODE_LIST_DONE)
|
||||
{
|
||||
auto & name = parent->cli->st_cli.inode_config.at(src).name;
|
||||
if (parent->progress)
|
||||
{
|
||||
printf("Got listing of layer %s (inode %lu in pool %u)\n", name.c_str(), INODE_NO_POOL(src), INODE_POOL(src));
|
||||
}
|
||||
printf("Got listing of layer %s (inode %lu in pool %u)\n", name.c_str(), INODE_NO_POOL(src), INODE_POOL(src));
|
||||
if (delete_source)
|
||||
{
|
||||
// Sort the inode listing
|
||||
@@ -456,9 +396,8 @@ struct snap_merger_t
|
||||
{
|
||||
if (op->retval != op->len)
|
||||
{
|
||||
rwo->error_code = -op->retval;
|
||||
rwo->error_offset = op->offset;
|
||||
rwo->error_read = true;
|
||||
fprintf(stderr, "error reading target at offset %lx: %s\n", op->offset, strerror(-op->retval));
|
||||
exit(1);
|
||||
}
|
||||
next_write(rwo);
|
||||
};
|
||||
@@ -471,7 +410,7 @@ struct snap_merger_t
|
||||
// FIXME: Allow to use single write with "holes" (OSDs don't allow it yet)
|
||||
uint32_t gran = parent->cli->get_bs_bitmap_granularity();
|
||||
uint64_t bitmap_size = target_block_size / gran;
|
||||
while (rwo->end < bitmap_size && !rwo->error_code)
|
||||
while (rwo->end < bitmap_size)
|
||||
{
|
||||
auto bit = ((*((uint8_t*)rwo->op.bitmap_buf + (rwo->end >> 3))) & (1 << (rwo->end & 0x7)));
|
||||
if (!bit)
|
||||
@@ -495,7 +434,7 @@ struct snap_merger_t
|
||||
rwo->end++;
|
||||
}
|
||||
}
|
||||
if (rwo->end > rwo->start && !rwo->error_code)
|
||||
if (rwo->end > rwo->start)
|
||||
{
|
||||
// write start->end
|
||||
rwo->todo++;
|
||||
@@ -534,9 +473,8 @@ struct snap_merger_t
|
||||
delete subop;
|
||||
return;
|
||||
}
|
||||
rwo->error_code = -subop->retval;
|
||||
rwo->error_offset = subop->offset;
|
||||
rwo->error_read = false;
|
||||
fprintf(stderr, "error writing target at offset %lx: %s\n", subop->offset, strerror(-subop->retval));
|
||||
exit(1);
|
||||
}
|
||||
// Increment CAS version
|
||||
rwo->op.version++;
|
||||
@@ -572,12 +510,11 @@ struct snap_merger_t
|
||||
{
|
||||
if (!rwo->todo)
|
||||
{
|
||||
if (!rwo->error_code &&
|
||||
last_written_offset < rwo->op.offset+target_block_size)
|
||||
if (last_written_offset < rwo->op.offset+target_block_size)
|
||||
{
|
||||
last_written_offset = rwo->op.offset+target_block_size;
|
||||
}
|
||||
if (!rwo->error_code && delete_source)
|
||||
if (delete_source)
|
||||
{
|
||||
deleted_unsynced++;
|
||||
if (deleted_unsynced >= fsync_interval)
|
||||
@@ -607,13 +544,6 @@ struct snap_merger_t
|
||||
}
|
||||
}
|
||||
free(rwo->buf);
|
||||
if (rwo->error_code)
|
||||
{
|
||||
char buf[1024];
|
||||
snprintf(buf, 1024, "Error %s target at offset %lx: %s",
|
||||
rwo->error_read ? "reading" : "writing", rwo->error_offset, strerror(rwo->error_code));
|
||||
rwo_error = std::string(buf);
|
||||
}
|
||||
delete rwo;
|
||||
in_flight--;
|
||||
continue_merge_reent();
|
||||
@@ -621,25 +551,30 @@ struct snap_merger_t
|
||||
}
|
||||
};
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_merge(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_merge(json11::Json cfg)
|
||||
{
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
auto merger = new snap_merger_t();
|
||||
merger->parent = this;
|
||||
merger->from_name = cfg["from"].string_value();
|
||||
merger->to_name = cfg["to"].string_value();
|
||||
merger->from_name = cmd.size() > 1 ? cmd[1].string_value() : "";
|
||||
merger->to_name = cmd.size() > 2 ? cmd[2].string_value() : "";
|
||||
merger->target_name = cfg["target"].string_value();
|
||||
if (merger->from_name == "" || merger->to_name == "")
|
||||
{
|
||||
fprintf(stderr, "Beginning or end of the merge sequence is missing\n");
|
||||
exit(1);
|
||||
}
|
||||
merger->delete_source = cfg["delete-source"].string_value() != "";
|
||||
merger->fsync_interval = cfg["fsync-interval"].uint64_value();
|
||||
if (!merger->fsync_interval)
|
||||
merger->fsync_interval = 128;
|
||||
if (!cfg["cas"].is_null())
|
||||
merger->use_cas = cfg["cas"].uint64_value() ? 2 : 0;
|
||||
return [merger](cli_result_t & result)
|
||||
return [merger]()
|
||||
{
|
||||
merger->continue_merge_reent();
|
||||
if (merger->is_done())
|
||||
{
|
||||
result = merger->result;
|
||||
delete merger;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -13,7 +13,6 @@ struct image_changer_t
|
||||
std::string image_name;
|
||||
std::string new_name;
|
||||
uint64_t new_size = 0;
|
||||
bool force_size = false;
|
||||
bool set_readonly = false, set_readwrite = false, force = false;
|
||||
// interval between fsyncs
|
||||
int fsync_interval = 128;
|
||||
@@ -24,8 +23,7 @@ struct image_changer_t
|
||||
bool has_children = false;
|
||||
|
||||
int state = 0;
|
||||
std::function<bool(cli_result_t &)> cb;
|
||||
cli_result_t result;
|
||||
std::function<bool(void)> cb;
|
||||
|
||||
bool is_done()
|
||||
{
|
||||
@@ -38,18 +36,6 @@ struct image_changer_t
|
||||
goto resume_1;
|
||||
else if (state == 2)
|
||||
goto resume_2;
|
||||
if (image_name == "")
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Image name is missing" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (new_size != 0 && (new_size % 4096) && !force_size)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Image size should be a multiple of 4096" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
for (auto & ic: parent->cli->st_cli.inode_config)
|
||||
{
|
||||
if (ic.second.name == image_name)
|
||||
@@ -60,16 +46,14 @@ struct image_changer_t
|
||||
}
|
||||
if (new_name != "" && ic.second.name == new_name)
|
||||
{
|
||||
result = (cli_result_t){ .err = EEXIST, .text = "Image "+new_name+" already exists" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Image %s already exists\n", new_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
if (!inode_num)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Image "+image_name+" does not exist" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Image %s does not exist\n", image_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
for (auto & ic: parent->cli->st_cli.inode_config)
|
||||
{
|
||||
@@ -81,43 +65,37 @@ struct image_changer_t
|
||||
}
|
||||
if ((!set_readwrite || !cfg.readonly) &&
|
||||
(!set_readonly || cfg.readonly) &&
|
||||
(!new_size && !force_size || cfg.size == new_size) &&
|
||||
(!new_size || cfg.size == new_size) &&
|
||||
(new_name == "" || new_name == image_name))
|
||||
{
|
||||
result = (cli_result_t){ .text = "No change" };
|
||||
printf("No change\n");
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (new_size != 0 || force_size)
|
||||
if (new_size != 0)
|
||||
{
|
||||
if (cfg.size >= new_size)
|
||||
{
|
||||
// Check confirmation when trimming an image with children
|
||||
if (has_children && !force)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Image "+image_name+" has children. Refusing to shrink it without --force" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Image %s has children. Refusing to shrink it without --force\n", image_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
// Shrink the image first
|
||||
cb = parent->start_rm_data(json11::Json::object {
|
||||
cb = parent->start_rm(json11::Json::object {
|
||||
{ "inode", INODE_NO_POOL(inode_num) },
|
||||
{ "pool", (uint64_t)INODE_POOL(inode_num) },
|
||||
{ "fsync-interval", fsync_interval },
|
||||
{ "min-offset", ((new_size+4095)/4096)*4096 },
|
||||
{ "min-offset", new_size },
|
||||
});
|
||||
resume_1:
|
||||
while (!cb(result))
|
||||
while (!cb())
|
||||
{
|
||||
state = 1;
|
||||
return;
|
||||
}
|
||||
cb = NULL;
|
||||
if (result.err)
|
||||
{
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
}
|
||||
cfg.size = new_size;
|
||||
}
|
||||
@@ -131,9 +109,8 @@ resume_1:
|
||||
// Check confirmation when making an image with children read-write
|
||||
if (has_children && !force)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Image "+image_name+" has children. Refusing to make it read-write without --force" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Image %s has children. Refusing to make it read-write without --force\n", image_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
if (new_name != "")
|
||||
@@ -201,38 +178,34 @@ resume_1:
|
||||
resume_2:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
result = parent->etcd_err;
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (!parent->etcd_result["succeeded"].bool_value())
|
||||
{
|
||||
result = (cli_result_t){ .err = EAGAIN, .text = "Image "+image_name+" was modified by someone else, please repeat your request" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Image %s was modified by someone else, please repeat your request\n", image_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
// Save into inode_config for library users to be able to take it from there immediately
|
||||
cfg.mod_revision = parent->etcd_result["responses"][0]["response_put"]["header"]["revision"].uint64_value();
|
||||
if (new_name != "")
|
||||
{
|
||||
parent->cli->st_cli.inode_by_name.erase(image_name);
|
||||
}
|
||||
parent->cli->st_cli.insert_inode_config(cfg);
|
||||
result = (cli_result_t){ .err = 0, .text = "Image "+image_name+" modified" };
|
||||
printf("Image %s modified\n", image_name.c_str());
|
||||
state = 100;
|
||||
}
|
||||
};
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_modify(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_modify(json11::Json cfg)
|
||||
{
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
auto changer = new image_changer_t();
|
||||
changer->parent = this;
|
||||
changer->image_name = cfg["image"].string_value();
|
||||
changer->image_name = cmd.size() > 1 ? cmd[1].string_value() : "";
|
||||
if (changer->image_name == "")
|
||||
{
|
||||
fprintf(stderr, "Image name is missing\n");
|
||||
exit(1);
|
||||
}
|
||||
changer->new_name = cfg["rename"].string_value();
|
||||
changer->new_size = parse_size(cfg["resize"].as_string());
|
||||
changer->force_size = cfg["force_size"].bool_value();
|
||||
changer->new_size = parse_size(cfg["resize"].string_value());
|
||||
if (changer->new_size != 0 && (changer->new_size % 4096))
|
||||
{
|
||||
fprintf(stderr, "Image size should be a multiple of 4096\n");
|
||||
exit(1);
|
||||
}
|
||||
changer->force = cfg["force"].bool_value();
|
||||
changer->set_readonly = cfg["readonly"].bool_value();
|
||||
changer->set_readwrite = cfg["readwrite"].bool_value();
|
||||
@@ -240,12 +213,11 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_modify(json11::Json cfg)
|
||||
if (!changer->fsync_interval)
|
||||
changer->fsync_interval = 128;
|
||||
// FIXME Check that the image doesn't have children when shrinking
|
||||
return [changer](cli_result_t & result)
|
||||
return [changer]()
|
||||
{
|
||||
changer->loop();
|
||||
if (changer->is_done())
|
||||
{
|
||||
result = changer->result;
|
||||
delete changer;
|
||||
return true;
|
||||
}
|
||||
|
||||
218
src/cli_rm.cpp
218
src/cli_rm.cpp
@@ -63,13 +63,11 @@ struct snap_remover_t
|
||||
inode_t new_parent = 0;
|
||||
int state = 0;
|
||||
int current_child = 0;
|
||||
std::function<bool(cli_result_t &)> cb;
|
||||
|
||||
cli_result_t result;
|
||||
std::function<bool(void)> cb;
|
||||
|
||||
bool is_done()
|
||||
{
|
||||
return state == 100;
|
||||
return state == 9;
|
||||
}
|
||||
|
||||
void loop()
|
||||
@@ -90,28 +88,13 @@ struct snap_remover_t
|
||||
goto resume_7;
|
||||
else if (state == 8)
|
||||
goto resume_8;
|
||||
else if (state == 100)
|
||||
goto resume_100;
|
||||
assert(!state);
|
||||
if (from_name == "")
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Layer to remove argument is missing" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
if (to_name == "")
|
||||
{
|
||||
to_name = from_name;
|
||||
}
|
||||
else if (state == 9)
|
||||
goto resume_9;
|
||||
// Get children to merge
|
||||
get_merge_children();
|
||||
if (state == 100)
|
||||
return;
|
||||
// Try to select an inode for the "inverse" optimized scenario
|
||||
// Read statistics from etcd to do it
|
||||
read_stats();
|
||||
if (state == 100)
|
||||
return;
|
||||
state = 1;
|
||||
resume_1:
|
||||
if (parent->waiting > 0)
|
||||
@@ -123,72 +106,42 @@ resume_1:
|
||||
if (merge_children[current_child] == inverse_child)
|
||||
continue;
|
||||
start_merge_child(merge_children[current_child], merge_children[current_child]);
|
||||
if (state == 100)
|
||||
return;
|
||||
resume_2:
|
||||
while (!cb(result))
|
||||
while (!cb())
|
||||
{
|
||||
state = 2;
|
||||
return;
|
||||
}
|
||||
cb = NULL;
|
||||
if (result.err)
|
||||
{
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
parent->change_parent(merge_children[current_child], new_parent, &result);
|
||||
parent->change_parent(merge_children[current_child], new_parent);
|
||||
state = 3;
|
||||
resume_3:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (result.err)
|
||||
{
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
else if (parent->progress)
|
||||
printf("%s\n", result.text.c_str());
|
||||
}
|
||||
// Merge our "inverse" child into our "inverse" parent
|
||||
if (inverse_child != 0)
|
||||
{
|
||||
start_merge_child(inverse_child, inverse_parent);
|
||||
if (state == 100)
|
||||
return;
|
||||
resume_4:
|
||||
while (!cb(result))
|
||||
while (!cb())
|
||||
{
|
||||
state = 4;
|
||||
return;
|
||||
}
|
||||
cb = NULL;
|
||||
if (result.err)
|
||||
{
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
// Delete "inverse" child data
|
||||
start_delete_source(inverse_child);
|
||||
if (state == 100)
|
||||
return;
|
||||
resume_5:
|
||||
while (!cb(result))
|
||||
while (!cb())
|
||||
{
|
||||
state = 5;
|
||||
return;
|
||||
}
|
||||
cb = NULL;
|
||||
if (result.err)
|
||||
{
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
// Delete "inverse" child metadata, rename parent over it,
|
||||
// and also change parent links of the previous "inverse" child
|
||||
rename_inverse_parent();
|
||||
if (state == 100)
|
||||
return;
|
||||
state = 6;
|
||||
resume_6:
|
||||
if (parent->waiting > 0)
|
||||
@@ -201,27 +154,20 @@ resume_6:
|
||||
continue;
|
||||
start_delete_source(chain_list[current_child]);
|
||||
resume_7:
|
||||
while (!cb(result))
|
||||
while (!cb())
|
||||
{
|
||||
state = 7;
|
||||
return;
|
||||
}
|
||||
cb = NULL;
|
||||
if (result.err)
|
||||
{
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
delete_inode_config(chain_list[current_child]);
|
||||
if (state == 100)
|
||||
return;
|
||||
state = 8;
|
||||
resume_8:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
}
|
||||
state = 100;
|
||||
resume_100:
|
||||
state = 9;
|
||||
resume_9:
|
||||
// Done
|
||||
return;
|
||||
}
|
||||
@@ -230,19 +176,7 @@ resume_100:
|
||||
{
|
||||
// Get all children of from..to
|
||||
inode_config_t *from_cfg = parent->get_inode_cfg(from_name);
|
||||
if (!from_cfg)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Layer "+from_name+" not found" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
inode_config_t *to_cfg = parent->get_inode_cfg(to_name);
|
||||
if (!to_cfg)
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Layer "+to_name+" not found" };
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
// Check that to_cfg is actually a child of from_cfg
|
||||
// FIXME de-copypaste the following piece of code with snap_merger_t
|
||||
inode_config_t *cur = to_cfg;
|
||||
@@ -252,19 +186,16 @@ resume_100:
|
||||
auto it = parent->cli->st_cli.inode_config.find(cur->parent_id);
|
||||
if (it == parent->cli->st_cli.inode_config.end())
|
||||
{
|
||||
char buf[1024];
|
||||
snprintf(buf, 1024, "Parent inode of layer %s (id 0x%lx) not found", cur->name.c_str(), cur->parent_id);
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Parent inode of layer %s (id %ld) not found\n", cur->name.c_str(), cur->parent_id);
|
||||
exit(1);
|
||||
}
|
||||
cur = &it->second;
|
||||
chain_list.push_back(cur->num);
|
||||
}
|
||||
if (cur->num != from_cfg->num)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Layer "+to_name+" is not a child of "+from_name };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Layer %s is not a child of %s\n", to_name.c_str(), from_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
new_parent = from_cfg->parent_id;
|
||||
// Calculate ranks
|
||||
@@ -332,9 +263,8 @@ resume_100:
|
||||
parent->waiting--;
|
||||
if (err != "")
|
||||
{
|
||||
result = (cli_result_t){ .err = EIO, .text = "Error reading layer statistics from etcd: "+err };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Error reading layer statistics from etcd: %s\n", err.c_str());
|
||||
exit(1);
|
||||
}
|
||||
for (auto inode_result: data["responses"].array_items())
|
||||
{
|
||||
@@ -345,16 +275,14 @@ resume_100:
|
||||
sscanf(kv.key.c_str() + parent->cli->st_cli.etcd_prefix.length()+13, "%u/%lu%c", &pool_id, &inode, &null_byte);
|
||||
if (!inode || null_byte != 0)
|
||||
{
|
||||
result = (cli_result_t){ .err = EIO, .text = "Bad key returned from etcd: "+kv.key };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Bad key returned from etcd: %s\n", kv.key.c_str());
|
||||
exit(1);
|
||||
}
|
||||
auto pool_cfg_it = parent->cli->st_cli.pool_config.find(pool_id);
|
||||
if (pool_cfg_it == parent->cli->st_cli.pool_config.end())
|
||||
{
|
||||
result = (cli_result_t){ .err = ENOENT, .text = "Pool "+std::to_string(pool_id)+" does not exist" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Pool %u does not exist\n", pool_id);
|
||||
exit(1);
|
||||
}
|
||||
inode = INODE_WITH_POOL(pool_id, inode);
|
||||
auto & pool_cfg = pool_cfg_it->second;
|
||||
@@ -396,20 +324,14 @@ resume_100:
|
||||
auto child_it = parent->cli->st_cli.inode_config.find(inverse_child);
|
||||
if (child_it == parent->cli->st_cli.inode_config.end())
|
||||
{
|
||||
char buf[1024];
|
||||
snprintf(buf, 1024, "Inode 0x%lx disappeared", inverse_child);
|
||||
result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Inode %ld disappeared\n", inverse_child);
|
||||
exit(1);
|
||||
}
|
||||
auto target_it = parent->cli->st_cli.inode_config.find(inverse_parent);
|
||||
if (target_it == parent->cli->st_cli.inode_config.end())
|
||||
{
|
||||
char buf[1024];
|
||||
snprintf(buf, 1024, "Inode 0x%lx disappeared", inverse_parent);
|
||||
result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Inode %ld disappeared\n", inverse_parent);
|
||||
exit(1);
|
||||
}
|
||||
inode_config_t *child_cfg = &child_it->second;
|
||||
inode_config_t *target_cfg = &target_it->second;
|
||||
@@ -500,22 +422,18 @@ resume_100:
|
||||
parent->waiting--;
|
||||
if (err != "")
|
||||
{
|
||||
result = (cli_result_t){ .err = EIO, .text = "Error renaming "+target_name+" to "+child_name+": "+err };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Error renaming %s to %s: %s\n", target_name.c_str(), child_name.c_str(), err.c_str());
|
||||
exit(1);
|
||||
}
|
||||
if (!res["succeeded"].bool_value())
|
||||
{
|
||||
result = (cli_result_t){
|
||||
.err = EAGAIN,
|
||||
.text = "Parent ("+target_name+"), child ("+child_name+"), or one of its children"
|
||||
" configuration was modified during rename",
|
||||
};
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(
|
||||
stderr, "Parent (%s), child (%s), or one of its children"
|
||||
" configuration was modified during rename\n", target_name.c_str(), child_name.c_str()
|
||||
);
|
||||
exit(1);
|
||||
}
|
||||
if (parent->progress)
|
||||
printf("Layer %s renamed to %s\n", target_name.c_str(), child_name.c_str());
|
||||
printf("Layer %s renamed to %s\n", target_name.c_str(), child_name.c_str());
|
||||
parent->ringloop->wakeup();
|
||||
});
|
||||
}
|
||||
@@ -525,11 +443,8 @@ resume_100:
|
||||
auto cur_cfg_it = parent->cli->st_cli.inode_config.find(cur);
|
||||
if (cur_cfg_it == parent->cli->st_cli.inode_config.end())
|
||||
{
|
||||
char buf[1024];
|
||||
snprintf(buf, 1024, "Inode 0x%lx disappeared", cur);
|
||||
result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Inode 0x%lx disappeared\n", cur);
|
||||
exit(1);
|
||||
}
|
||||
inode_config_t *cur_cfg = &cur_cfg_it->second;
|
||||
std::string cur_name = cur_cfg->name;
|
||||
@@ -560,26 +475,20 @@ resume_100:
|
||||
} },
|
||||
},
|
||||
} },
|
||||
}, [this, cur, cur_name](std::string err, json11::Json res)
|
||||
}, [this, cur_name](std::string err, json11::Json res)
|
||||
{
|
||||
parent->waiting--;
|
||||
if (err != "")
|
||||
{
|
||||
result = (cli_result_t){ .err = EIO, .text = "Error deleting "+cur_name+": "+err };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Error deleting %s: %s\n", cur_name.c_str(), err.c_str());
|
||||
exit(1);
|
||||
}
|
||||
if (!res["succeeded"].bool_value())
|
||||
{
|
||||
result = (cli_result_t){ .err = EAGAIN, .text = "Layer "+cur_name+" was modified during deletion" };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Layer %s configuration was modified during deletion\n", cur_name.c_str());
|
||||
exit(1);
|
||||
}
|
||||
// Modify inode_config for library users to be able to take it from there immediately
|
||||
parent->cli->st_cli.inode_by_name.erase(cur_name);
|
||||
parent->cli->st_cli.inode_config.erase(cur);
|
||||
if (parent->progress)
|
||||
printf("Layer %s deleted\n", cur_name.c_str());
|
||||
printf("Layer %s deleted\n", cur_name.c_str());
|
||||
parent->ringloop->wakeup();
|
||||
});
|
||||
}
|
||||
@@ -589,24 +498,17 @@ resume_100:
|
||||
auto child_it = parent->cli->st_cli.inode_config.find(child_inode);
|
||||
if (child_it == parent->cli->st_cli.inode_config.end())
|
||||
{
|
||||
char buf[1024];
|
||||
snprintf(buf, 1024, "Inode 0x%lx disappeared", child_inode);
|
||||
result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Inode %ld disappeared\n", child_inode);
|
||||
exit(1);
|
||||
}
|
||||
auto target_it = parent->cli->st_cli.inode_config.find(target_inode);
|
||||
if (target_it == parent->cli->st_cli.inode_config.end())
|
||||
{
|
||||
char buf[1024];
|
||||
snprintf(buf, 1024, "Inode 0x%lx disappeared", target_inode);
|
||||
result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Inode %ld disappeared\n", target_inode);
|
||||
exit(1);
|
||||
}
|
||||
cb = parent->start_merge(json11::Json::object {
|
||||
{ "from", from_name },
|
||||
{ "to", child_it->second.name },
|
||||
{ "command", json11::Json::array{ "merge-data", from_name, child_it->second.name } },
|
||||
{ "target", target_it->second.name },
|
||||
{ "delete-source", false },
|
||||
{ "cas", use_cas },
|
||||
@@ -619,13 +521,10 @@ resume_100:
|
||||
auto source = parent->cli->st_cli.inode_config.find(inode);
|
||||
if (source == parent->cli->st_cli.inode_config.end())
|
||||
{
|
||||
char buf[1024];
|
||||
snprintf(buf, 1024, "Inode 0x%lx disappeared", inode);
|
||||
result = (cli_result_t){ .err = EIO, .text = std::string(buf) };
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Inode %ld disappeared\n", inode);
|
||||
exit(1);
|
||||
}
|
||||
cb = parent->start_rm_data(json11::Json::object {
|
||||
cb = parent->start_rm(json11::Json::object {
|
||||
{ "inode", inode },
|
||||
{ "pool", (uint64_t)INODE_POOL(inode) },
|
||||
{ "fsync-interval", fsync_interval },
|
||||
@@ -633,12 +532,22 @@ resume_100:
|
||||
}
|
||||
};
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_rm(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_snap_rm(json11::Json cfg)
|
||||
{
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
auto snap_remover = new snap_remover_t();
|
||||
snap_remover->parent = this;
|
||||
snap_remover->from_name = cfg["from"].string_value();
|
||||
snap_remover->to_name = cfg["to"].string_value();
|
||||
snap_remover->from_name = cmd.size() > 1 ? cmd[1].string_value() : "";
|
||||
snap_remover->to_name = cmd.size() > 2 ? cmd[2].string_value() : "";
|
||||
if (snap_remover->from_name == "")
|
||||
{
|
||||
fprintf(stderr, "Layer to remove argument is missing\n");
|
||||
exit(1);
|
||||
}
|
||||
if (snap_remover->to_name == "")
|
||||
{
|
||||
snap_remover->to_name = snap_remover->from_name;
|
||||
}
|
||||
snap_remover->fsync_interval = cfg["fsync-interval"].uint64_value();
|
||||
if (!snap_remover->fsync_interval)
|
||||
snap_remover->fsync_interval = 128;
|
||||
@@ -646,12 +555,11 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_rm(json11::Json cfg)
|
||||
snap_remover->use_cas = cfg["cas"].uint64_value() ? 2 : 0;
|
||||
if (!cfg["writers_stopped"].is_null())
|
||||
snap_remover->writers_stopped = true;
|
||||
return [snap_remover](cli_result_t & result)
|
||||
return [snap_remover]()
|
||||
{
|
||||
snap_remover->loop();
|
||||
if (snap_remover->is_done())
|
||||
{
|
||||
result = snap_remover->result;
|
||||
delete snap_remover;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -32,9 +32,6 @@ struct rm_inode_t
|
||||
uint64_t pgs_to_list = 0;
|
||||
bool lists_done = false;
|
||||
int state = 0;
|
||||
int error_count = 0;
|
||||
|
||||
cli_result_t result;
|
||||
|
||||
void start_delete()
|
||||
{
|
||||
@@ -77,13 +74,8 @@ struct rm_inode_t
|
||||
});
|
||||
if (!lister)
|
||||
{
|
||||
result = (cli_result_t){
|
||||
.err = EIO,
|
||||
.text = "Failed to list objects of inode "+std::to_string(INODE_NO_POOL(inode))+
|
||||
" from pool "+std::to_string(INODE_POOL(inode)),
|
||||
};
|
||||
state = 100;
|
||||
return;
|
||||
fprintf(stderr, "Failed to list inode %lu from pool %u objects\n", INODE_NO_POOL(inode), INODE_POOL(inode));
|
||||
exit(1);
|
||||
}
|
||||
pgs_to_list = parent->cli->list_pg_count(lister);
|
||||
parent->cli->list_inode_next(lister, parent->parallel_osds);
|
||||
@@ -126,7 +118,6 @@ struct rm_inode_t
|
||||
fprintf(stderr, "Failed to remove object %lx:%lx from PG %u (OSD %lu) (retval=%ld)\n",
|
||||
op->req.rw.inode, op->req.rw.offset,
|
||||
cur_list->pg_num, cur_list->rm_osd_num, op->reply.hdr.retval);
|
||||
error_count++;
|
||||
}
|
||||
delete op;
|
||||
cur_list->obj_done++;
|
||||
@@ -170,43 +161,31 @@ struct rm_inode_t
|
||||
}
|
||||
if (lists_done && !lists.size())
|
||||
{
|
||||
result = (cli_result_t){
|
||||
.err = error_count > 0 ? EIO : 0,
|
||||
.text = error_count > 0 ? "Some blocks were not removed" : (
|
||||
"Done, inode "+std::to_string(INODE_NO_POOL(inode))+" from pool "+
|
||||
std::to_string(pool_id)+" removed"),
|
||||
};
|
||||
state = 100;
|
||||
printf("Done, inode %lu in pool %u data removed\n", INODE_NO_POOL(inode), pool_id);
|
||||
state = 2;
|
||||
}
|
||||
}
|
||||
|
||||
bool is_done()
|
||||
bool loop()
|
||||
{
|
||||
return state == 100;
|
||||
}
|
||||
|
||||
void loop()
|
||||
{
|
||||
if (state == 1)
|
||||
goto resume_1;
|
||||
if (state == 100)
|
||||
return;
|
||||
if (!pool_id)
|
||||
if (state == 0)
|
||||
{
|
||||
result = (cli_result_t){ .err = EINVAL, .text = "Pool is not specified" };
|
||||
state = 100;
|
||||
return;
|
||||
start_delete();
|
||||
state = 1;
|
||||
}
|
||||
start_delete();
|
||||
if (state == 100)
|
||||
return;
|
||||
state = 1;
|
||||
resume_1:
|
||||
continue_delete();
|
||||
else if (state == 1)
|
||||
{
|
||||
continue_delete();
|
||||
}
|
||||
else if (state == 2)
|
||||
{
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
};
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_rm_data(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_rm(json11::Json cfg)
|
||||
{
|
||||
auto remover = new rm_inode_t();
|
||||
remover->parent = this;
|
||||
@@ -214,16 +193,19 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_rm_data(json11::Json cfg)
|
||||
remover->pool_id = cfg["pool"].uint64_value();
|
||||
if (remover->pool_id)
|
||||
{
|
||||
remover->inode = (remover->inode & (((uint64_t)1 << (64-POOL_ID_BITS)) - 1)) | (((uint64_t)remover->pool_id) << (64-POOL_ID_BITS));
|
||||
remover->inode = (remover->inode & ((1l << (64-POOL_ID_BITS)) - 1)) | (((uint64_t)remover->pool_id) << (64-POOL_ID_BITS));
|
||||
}
|
||||
remover->pool_id = INODE_POOL(remover->inode);
|
||||
remover->min_offset = cfg["min-offset"].uint64_value();
|
||||
return [remover](cli_result_t & result)
|
||||
if (!remover->pool_id)
|
||||
{
|
||||
remover->loop();
|
||||
if (remover->is_done())
|
||||
fprintf(stderr, "pool is missing\n");
|
||||
exit(1);
|
||||
}
|
||||
remover->min_offset = cfg["min-offset"].uint64_value();
|
||||
return [remover]()
|
||||
{
|
||||
if (remover->loop())
|
||||
{
|
||||
result = remover->result;
|
||||
delete remover;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -11,9 +11,9 @@
|
||||
#include <sys/stat.h>
|
||||
|
||||
// Calculate offsets for a block device and print OSD command line parameters
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::simple_offsets(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::simple_offsets(json11::Json cfg)
|
||||
{
|
||||
std::string device = cfg["device"].string_value();
|
||||
std::string device = cfg["command"][1].string_value();
|
||||
uint64_t object_size = parse_size(cfg["object_size"].string_value());
|
||||
uint64_t bitmap_granularity = parse_size(cfg["bitmap_granularity"].string_value());
|
||||
uint64_t journal_size = parse_size(cfg["journal_size"].string_value());
|
||||
|
||||
@@ -83,12 +83,6 @@ resume_1:
|
||||
resume_2:
|
||||
if (parent->waiting > 0)
|
||||
return;
|
||||
if (parent->etcd_err.err)
|
||||
{
|
||||
fprintf(stderr, "%s\n", parent->etcd_err.text.c_str());
|
||||
state = 100;
|
||||
return;
|
||||
}
|
||||
mon_members = parent->etcd_result["responses"][0]["response_range"]["kvs"].array_items();
|
||||
osd_stats = parent->etcd_result["responses"][1]["response_range"]["kvs"].array_items();
|
||||
if (parent->etcd_result["responses"][2]["response_range"]["kvs"].array_items().size() > 0)
|
||||
@@ -223,7 +217,7 @@ resume_2:
|
||||
// JSON output
|
||||
printf("%s\n", json11::Json(json11::Json::object {
|
||||
{ "etcd_alive", etcd_alive },
|
||||
{ "etcd_count", (uint64_t)etcd_states.size() },
|
||||
{ "etcd_count", etcd_states.size() },
|
||||
{ "etcd_db_size", etcd_db_size },
|
||||
{ "mon_count", mon_count },
|
||||
{ "mon_master", mon_master },
|
||||
@@ -283,16 +277,16 @@ resume_2:
|
||||
}
|
||||
};
|
||||
|
||||
std::function<bool(cli_result_t &)> cli_tool_t::start_status(json11::Json cfg)
|
||||
std::function<bool(void)> cli_tool_t::start_status(json11::Json cfg)
|
||||
{
|
||||
json11::Json::array cmd = cfg["command"].array_items();
|
||||
auto printer = new status_printer_t();
|
||||
printer->parent = this;
|
||||
return [printer](cli_result_t & result)
|
||||
return [printer]()
|
||||
{
|
||||
printer->loop();
|
||||
if (printer->is_done())
|
||||
{
|
||||
result = { .err = 0 };
|
||||
delete printer;
|
||||
return true;
|
||||
}
|
||||
|
||||
@@ -9,7 +9,6 @@
|
||||
#define PART_SENT 1
|
||||
#define PART_DONE 2
|
||||
#define PART_ERROR 4
|
||||
#define PART_RETRY 8
|
||||
#define CACHE_DIRTY 1
|
||||
#define CACHE_FLUSHING 2
|
||||
#define CACHE_REPEATING 3
|
||||
@@ -374,11 +373,6 @@ void cluster_client_t::on_change_hook(std::map<std::string, etcd_kv_t> & changes
|
||||
continue_ops();
|
||||
}
|
||||
|
||||
bool cluster_client_t::get_immediate_commit()
|
||||
{
|
||||
return immediate_commit;
|
||||
}
|
||||
|
||||
void cluster_client_t::on_change_osd_state_hook(uint64_t peer_osd)
|
||||
{
|
||||
if (msgr.wanted_peers.find(peer_osd) != msgr.wanted_peers.end())
|
||||
@@ -676,17 +670,14 @@ resume_2:
|
||||
if (!try_send(op, i))
|
||||
{
|
||||
// We'll need to retry again
|
||||
if (op->parts[i].flags & PART_RETRY)
|
||||
op->up_wait = true;
|
||||
if (!retry_timeout_id)
|
||||
{
|
||||
op->up_wait = true;
|
||||
if (!retry_timeout_id)
|
||||
retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
|
||||
{
|
||||
retry_timeout_id = tfd->set_timer(up_wait_retry_interval, false, [this](int)
|
||||
{
|
||||
retry_timeout_id = 0;
|
||||
continue_ops(true);
|
||||
});
|
||||
}
|
||||
retry_timeout_id = 0;
|
||||
continue_ops(true);
|
||||
});
|
||||
}
|
||||
op->state = 2;
|
||||
}
|
||||
@@ -755,7 +746,7 @@ resume_3:
|
||||
{
|
||||
for (int i = 0; i < op->parts.size(); i++)
|
||||
{
|
||||
op->parts[i].flags = PART_RETRY;
|
||||
op->parts[i].flags = 0;
|
||||
}
|
||||
goto resume_2;
|
||||
}
|
||||
|
||||
@@ -118,8 +118,6 @@ public:
|
||||
bool is_ready();
|
||||
void on_ready(std::function<void(void)> fn);
|
||||
|
||||
bool get_immediate_commit();
|
||||
|
||||
static void copy_write(cluster_op_t *op, std::map<object_id, cluster_buffer_t> & dirty_buffers);
|
||||
void continue_ops(bool up_retry = false);
|
||||
inode_list_t *list_inode_start(inode_t inode,
|
||||
|
||||
@@ -89,7 +89,7 @@ void etcd_state_client_t::etcd_call_oneshot(std::string etcd_address, std::strin
|
||||
"Connection: close\r\n"
|
||||
"\r\n"+req;
|
||||
auto http_cli = http_init(tfd);
|
||||
auto cb = [http_cli, callback](const http_response_t *response)
|
||||
auto cb = [this, http_cli, callback](const http_response_t *response)
|
||||
{
|
||||
std::string err;
|
||||
json11::Json data;
|
||||
@@ -338,14 +338,9 @@ void etcd_state_client_t::start_etcd_watcher()
|
||||
{
|
||||
if (data["result"]["created"].bool_value())
|
||||
{
|
||||
uint64_t watch_id = data["result"]["watch_id"].uint64_value();
|
||||
if (watch_id == ETCD_CONFIG_WATCH_ID ||
|
||||
watch_id == ETCD_PG_STATE_WATCH_ID ||
|
||||
watch_id == ETCD_PG_HISTORY_WATCH_ID ||
|
||||
watch_id == ETCD_OSD_STATE_WATCH_ID)
|
||||
etcd_watches_initialised++;
|
||||
if (etcd_watches_initialised == 4 && this->log_level > 0)
|
||||
if (etcd_watches_initialised == 3 && this->log_level > 0)
|
||||
fprintf(stderr, "Successfully subscribed to etcd at %s\n", selected_etcd_address.c_str());
|
||||
etcd_watches_initialised++;
|
||||
}
|
||||
if (data["result"]["canceled"].bool_value())
|
||||
{
|
||||
@@ -474,10 +469,6 @@ void etcd_state_client_t::start_etcd_watcher()
|
||||
{ "progress_notify", true },
|
||||
} }
|
||||
}).dump());
|
||||
if (on_start_watcher_hook)
|
||||
{
|
||||
on_start_watcher_hook(etcd_watch_ws);
|
||||
}
|
||||
if (ws_keepalive_timer < 0)
|
||||
{
|
||||
ws_keepalive_timer = tfd->set_timer(etcd_ws_keepalive_interval*1000, true, [this](int)
|
||||
@@ -963,10 +954,6 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
|
||||
}
|
||||
if (!value.is_object())
|
||||
{
|
||||
if (on_inode_change_hook != NULL)
|
||||
{
|
||||
on_inode_change_hook(inode_num, true);
|
||||
}
|
||||
this->inode_config.erase(inode_num);
|
||||
}
|
||||
else
|
||||
@@ -981,47 +968,38 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
|
||||
{
|
||||
fprintf(
|
||||
stderr, "Inode %lu/%lu parent_pool value is invalid, ignoring parent setting\n",
|
||||
inode_num >> (64-POOL_ID_BITS), inode_num & (((uint64_t)1 << (64-POOL_ID_BITS)) - 1)
|
||||
inode_num >> (64-POOL_ID_BITS), inode_num & ((1l << (64-POOL_ID_BITS)) - 1)
|
||||
);
|
||||
parent_inode_num = 0;
|
||||
}
|
||||
else
|
||||
parent_inode_num |= parent_pool_id << (64-POOL_ID_BITS);
|
||||
}
|
||||
insert_inode_config((inode_config_t){
|
||||
inode_config_t cfg = (inode_config_t){
|
||||
.num = inode_num,
|
||||
.name = value["name"].string_value(),
|
||||
.size = value["size"].uint64_value(),
|
||||
.parent_id = parent_inode_num,
|
||||
.readonly = value["readonly"].bool_value(),
|
||||
.meta = value["meta"],
|
||||
.mod_revision = kv.mod_revision,
|
||||
});
|
||||
};
|
||||
this->inode_config[inode_num] = cfg;
|
||||
if (cfg.name != "")
|
||||
{
|
||||
this->inode_by_name[cfg.name] = inode_num;
|
||||
for (auto w: watches)
|
||||
{
|
||||
if (w->name == value["name"].string_value())
|
||||
{
|
||||
w->cfg = cfg;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void etcd_state_client_t::insert_inode_config(const inode_config_t & cfg)
|
||||
{
|
||||
this->inode_config[cfg.num] = cfg;
|
||||
if (cfg.name != "")
|
||||
{
|
||||
this->inode_by_name[cfg.name] = cfg.num;
|
||||
for (auto w: watches)
|
||||
{
|
||||
if (w->name == cfg.name)
|
||||
{
|
||||
w->cfg = cfg;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (on_inode_change_hook != NULL)
|
||||
{
|
||||
on_inode_change_hook(cfg.num, false);
|
||||
}
|
||||
}
|
||||
|
||||
inode_watch_t* etcd_state_client_t::watch_inode(std::string name)
|
||||
{
|
||||
inode_watch_t *watch = new inode_watch_t;
|
||||
@@ -1064,10 +1042,6 @@ json11::Json::object etcd_state_client_t::serialize_inode_cfg(inode_config_t *cf
|
||||
{
|
||||
new_cfg["readonly"] = true;
|
||||
}
|
||||
if (cfg->meta.is_object())
|
||||
{
|
||||
new_cfg["meta"] = cfg->meta;
|
||||
}
|
||||
return new_cfg;
|
||||
}
|
||||
|
||||
|
||||
@@ -56,8 +56,6 @@ struct inode_config_t
|
||||
uint64_t size;
|
||||
inode_t parent_id;
|
||||
bool readonly;
|
||||
// Arbitrary metadata
|
||||
json11::Json meta;
|
||||
// Change revision of the metadata in etcd
|
||||
uint64_t mod_revision;
|
||||
};
|
||||
@@ -111,8 +109,6 @@ public:
|
||||
std::function<void(pool_id_t, pg_num_t)> on_change_pg_history_hook;
|
||||
std::function<void(osd_num_t)> on_change_osd_state_hook;
|
||||
std::function<void()> on_reload_hook;
|
||||
std::function<void(inode_t, bool)> on_inode_change_hook;
|
||||
std::function<void(http_co_t *)> on_start_watcher_hook;
|
||||
|
||||
json11::Json::object serialize_inode_cfg(inode_config_t *cfg);
|
||||
etcd_kv_t parse_etcd_kv(const json11::Json & kv_json);
|
||||
@@ -126,7 +122,6 @@ public:
|
||||
void load_pgs();
|
||||
void parse_state(const etcd_kv_t & kv);
|
||||
void parse_config(const json11::Json & config);
|
||||
void insert_inode_config(const inode_config_t & cfg);
|
||||
inode_watch_t* watch_inode(std::string name);
|
||||
void close_watch(inode_watch_t* watch);
|
||||
int address_count();
|
||||
|
||||
@@ -214,14 +214,14 @@ static int sec_setup(struct thread_data *td)
|
||||
|
||||
if (!o->image)
|
||||
{
|
||||
if (!(o->inode & (((uint64_t)1 << (64-POOL_ID_BITS)) - 1)))
|
||||
if (!(o->inode & ((1l << (64-POOL_ID_BITS)) - 1)))
|
||||
{
|
||||
td_verror(td, EINVAL, "inode number is missing");
|
||||
return 1;
|
||||
}
|
||||
if (o->pool)
|
||||
{
|
||||
o->inode = (o->inode & (((uint64_t)1 << (64-POOL_ID_BITS)) - 1)) | (o->pool << (64-POOL_ID_BITS));
|
||||
o->inode = (o->inode & ((1l << (64-POOL_ID_BITS)) - 1)) | (o->pool << (64-POOL_ID_BITS));
|
||||
}
|
||||
if (!(o->inode >> (64-POOL_ID_BITS)))
|
||||
{
|
||||
|
||||
2
src/lrc/Makefile
Normal file
2
src/lrc/Makefile
Normal file
@@ -0,0 +1,2 @@
|
||||
mat: mat.c
|
||||
gcc -O3 -I/usr/include/jerasure -o mat mat.c -lJerasure
|
||||
277
src/lrc/mat.c
Normal file
277
src/lrc/mat.c
Normal file
@@ -0,0 +1,277 @@
|
||||
#include <jerasure/reed_sol.h>
|
||||
#include <jerasure.h>
|
||||
#include <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
// Generate LRC matrix: (groups*local + global) code rows with (data_drives) columns
|
||||
// w should be >= log2(data_drives + groups*local + global), but not necessary 8/16/32
|
||||
int* reed_sol_vandermonde_lrc_matrix(int data_drives, int groups, int local, int global, int w)
|
||||
{
|
||||
if (w < 0 || w > 32 || data_drives + groups*local + global > (1<<w))
|
||||
{
|
||||
return NULL;
|
||||
}
|
||||
int *lrc_matrix = (int*)malloc(sizeof(int) * (local*groups+global));
|
||||
int *matrix = reed_sol_vandermonde_coding_matrix(data_drives, local+global, w);
|
||||
for (int gr = 0; gr < groups; gr++)
|
||||
{
|
||||
for (int l = 0; l < local; l++)
|
||||
{
|
||||
for (int j = 0; j < data_drives; j++)
|
||||
{
|
||||
lrc_matrix[(gr*local+l)*data_drives + j] = (j / (data_drives/groups)) == gr ? matrix[l*data_drives + j] : 0;
|
||||
}
|
||||
}
|
||||
}
|
||||
for (int i = 0; i < global; i++)
|
||||
{
|
||||
for (int j = 0; j < data_drives; j++)
|
||||
{
|
||||
lrc_matrix[(groups*local+i)*data_drives + j] = matrix[(local+i)*data_drives + j];
|
||||
}
|
||||
}
|
||||
free(matrix);
|
||||
return lrc_matrix;
|
||||
}
|
||||
|
||||
// Check if the generated LRC with given parameters is Maximally Reconstructible (MR-LRC)
|
||||
// Example of a MR-LRC: (8, 2, 1, 2, 6, 8)
|
||||
void check_mr_lrc(int data_drives, int groups, int local, int global, int matrix_w, int w, int print)
|
||||
{
|
||||
|
||||
}
|
||||
|
||||
int main()
|
||||
{
|
||||
int W = 8, MATRIX_W = 6;
|
||||
int n = 8, groups = 2, local = 1, global = 2;
|
||||
//n = 4, groups = 2, local = 1, global = 1;
|
||||
int total_rows = n+groups*local+global;
|
||||
int *matrix = reed_sol_vandermonde_lrc_matrix(n, groups, local, global, MATRIX_W);
|
||||
int *lrc_matrix = (int*)malloc(sizeof(int) * total_rows*n);
|
||||
// Fill identity+LRC matrix
|
||||
for (int i = 0; i < n; i++)
|
||||
for (int j = 0; j < n; j++)
|
||||
lrc_matrix[i*n + j] = j == i ? 1 : 0;
|
||||
memcpy(lrc_matrix + n*n, matrix, (total_rows-n)*n*sizeof(int));
|
||||
free(matrix);
|
||||
matrix = NULL;
|
||||
// Print LRC matrix
|
||||
for (int i = 0; i < total_rows; i++)
|
||||
{
|
||||
for (int j = 0; j < n; j++)
|
||||
{
|
||||
printf("%d ", lrc_matrix[i*n+j]);
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
int impossible = 0, success = 0, failures = 0;
|
||||
int *lost_per_group = (int*)malloc(sizeof(int) * groups);
|
||||
for (int lost = local+global+1; lost <= groups*local+global; lost++)
|
||||
//int lost = groups*local+global;
|
||||
{
|
||||
int *erased_matrix = (int*)malloc(sizeof(int) * (total_rows-lost)*n);
|
||||
int *inverted_matrix = (int*)malloc(sizeof(int) * (total_rows-lost)*n);
|
||||
int *p = (int*)malloc(sizeof(int) * (total_rows-lost));
|
||||
for (int i = 0; i < n; i++)
|
||||
p[i] = i;
|
||||
int *p2 = (int*)malloc(sizeof(int) * n);
|
||||
if (total_rows-lost > n)
|
||||
{
|
||||
p[n-1] = n; // skip combinations with all N data disks (0..n-1)
|
||||
for (int i = n; i < total_rows-lost; i++)
|
||||
p[i] = i+1;
|
||||
p[total_rows-lost-1]--; // will be incremented on the first step
|
||||
}
|
||||
int inc = total_rows-lost-1;
|
||||
while (1)
|
||||
{
|
||||
p[inc]++;
|
||||
if (p[inc] >= n+groups*local+global)
|
||||
{
|
||||
if (inc == 0)
|
||||
break;
|
||||
inc--;
|
||||
}
|
||||
else if (inc+1 < total_rows-lost)
|
||||
{
|
||||
p[inc+1] = p[inc];
|
||||
inc++;
|
||||
}
|
||||
else
|
||||
{
|
||||
// Check if it should be recoverable
|
||||
for (int gr = 0; gr < groups; gr++)
|
||||
{
|
||||
lost_per_group[gr] = ((gr+1)*(n/groups) > n ? (n - gr*(n/groups)) : n/groups);
|
||||
}
|
||||
// Calculate count of data chunks lost in each group
|
||||
for (int j = 0; j < total_rows-lost; j++)
|
||||
{
|
||||
if (j < n)
|
||||
{
|
||||
lost_per_group[(p[j] / (n/groups))]--;
|
||||
}
|
||||
}
|
||||
// Every local parity chunk is supposed to restore 1 missing chunk inside its group
|
||||
// So, subtract local parity chunk counts from each group lost chunk count
|
||||
for (int j = 0; j < total_rows-lost; j++)
|
||||
{
|
||||
if (p[j] >= n && p[j] < n+groups*local && lost_per_group[(p[j]-n)/local] > 0)
|
||||
{
|
||||
lost_per_group[(p[j]-n)/local]--;
|
||||
}
|
||||
}
|
||||
// Every global parity chunk is supposed to restore 1 chunk of all that are still missing
|
||||
int still_missing = 0;
|
||||
for (int gr = 0; gr < groups; gr++)
|
||||
{
|
||||
still_missing += lost_per_group[gr];
|
||||
}
|
||||
for (int j = 0; j < total_rows-lost; j++)
|
||||
{
|
||||
if (p[j] >= n+groups*local && still_missing > 0)
|
||||
{
|
||||
still_missing--;
|
||||
}
|
||||
}
|
||||
if (still_missing <= 0)
|
||||
{
|
||||
// We hope it can be recoverable. Try to invert it
|
||||
int invert_ok = -1;
|
||||
if (total_rows-lost == n)
|
||||
{
|
||||
for (int i = 0; i < n; i++)
|
||||
for (int j = 0; j < n; j++)
|
||||
erased_matrix[i*n+j] = lrc_matrix[p[i]*n+j];
|
||||
invert_ok = jerasure_invert_matrix(erased_matrix, inverted_matrix, n, W);
|
||||
}
|
||||
else
|
||||
{
|
||||
// Check submatrices
|
||||
for (int i = 0; i < n; i++)
|
||||
p2[i] = i;
|
||||
p2[n-1]--;
|
||||
int inc2 = n-1;
|
||||
while (1)
|
||||
{
|
||||
p2[inc2]++;
|
||||
if (p2[inc2] >= total_rows-lost)
|
||||
{
|
||||
if (inc2 == 0)
|
||||
break;
|
||||
inc2--;
|
||||
}
|
||||
else if (inc2+1 < n)
|
||||
{
|
||||
p2[inc2+1] = p2[inc2];
|
||||
inc2++;
|
||||
}
|
||||
else
|
||||
{
|
||||
for (int i = 0; i < n; i++)
|
||||
for (int j = 0; j < n; j++)
|
||||
erased_matrix[i*n+j] = lrc_matrix[p[p2[i]]*n+j];
|
||||
invert_ok = jerasure_invert_matrix(erased_matrix, inverted_matrix, n, W);
|
||||
if (invert_ok == 0)
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (invert_ok < 0)
|
||||
{
|
||||
failures++;
|
||||
printf("\nFAIL: ");
|
||||
for (int i = 0; i < total_rows-lost; i++)
|
||||
{
|
||||
printf("%d ", p[i]);
|
||||
}
|
||||
printf("\nDIRECT:\n");
|
||||
for (int i = 0; i < total_rows-lost; i++)
|
||||
{
|
||||
for (int j = 0; j < n; j++)
|
||||
printf("%d ", lrc_matrix[p[i]*n+j]);
|
||||
printf("\n");
|
||||
}
|
||||
printf("INVERSE:\n");
|
||||
for (int i = 0; i < total_rows-lost; i++)
|
||||
{
|
||||
for (int j = 0; j < n; j++)
|
||||
printf("%d ", inverted_matrix[i*n+j]);
|
||||
printf("\n");
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
success++;
|
||||
printf("OK: ");
|
||||
for (int i = 0; i < total_rows-lost; i++)
|
||||
{
|
||||
printf("%d ", p[i]);
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
}
|
||||
else
|
||||
{
|
||||
impossible++;
|
||||
printf("IMPOSSIBLE: ");
|
||||
for (int i = 0; i < total_rows-lost; i++)
|
||||
{
|
||||
printf("%d ", p[i]);
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
}
|
||||
}
|
||||
free(p2);
|
||||
free(p);
|
||||
free(inverted_matrix);
|
||||
free(erased_matrix);
|
||||
}
|
||||
free(lost_per_group);
|
||||
printf("\n%d recovered, %d impossible, %d failures\n", success, impossible, failures);
|
||||
return 0;
|
||||
}
|
||||
|
||||
// 1 1 1 1 0 0 0 0
|
||||
// 0 0 0 0 1 1 1 1
|
||||
// 1 55 39 73 84 181 225 217
|
||||
// 1 172 70 235 143 34 200 101
|
||||
//
|
||||
// Can't recover
|
||||
// 1 2 4 5 8 9 10 11 -1
|
||||
// 2 3 4 6 8 9 10 11 -1
|
||||
// FULL:
|
||||
// 1 0 0 0 0 0 0 0
|
||||
// 0 1 0 0 0 0 0 0
|
||||
// 0 0 1 0 0 0 0 0
|
||||
// 0 0 0 1 0 0 0 0
|
||||
// 0 0 0 0 1 0 0 0
|
||||
// 0 0 0 0 0 1 0 0
|
||||
// 0 0 0 0 0 0 1 0
|
||||
// 0 0 0 0 0 0 0 1
|
||||
// 1 1 1 1 0 0 0 0
|
||||
// 0 0 0 0 1 1 1 1
|
||||
// 1 55 39 73 84 181 225 217
|
||||
// 1 172 70 235 143 34 200 101
|
||||
// FIRST UNRECOVERABLE:
|
||||
// 0 1 0 0 0 0 0 0
|
||||
// 0 0 1 0 0 0 0 0
|
||||
// 0 0 0 0 1 0 0 0
|
||||
// 0 0 0 0 0 1 0 0
|
||||
// 1 1 1 1 0 0 0 0
|
||||
// 0 0 0 0 1 1 1 1
|
||||
// 1 55 39 73 84 181 225 217
|
||||
// 1 172 70 235 143 34 200 101
|
||||
// SECOND UNRECOVERABLE:
|
||||
// 0 0 1 0 0 0 0 0
|
||||
// 0 0 0 1 0 0 0 0
|
||||
// 0 0 0 0 1 0 0 0
|
||||
// 0 0 0 0 0 0 1 0
|
||||
// 1 1 1 1 0 0 0 0
|
||||
// 0 0 0 0 1 1 1 1
|
||||
// 1 55 39 73 84 181 225 217
|
||||
// 1 172 70 235 143 34 200 101
|
||||
// Ho ho ho
|
||||
@@ -189,7 +189,7 @@ public:
|
||||
uint64_t pool = cfg["pool"].uint64_value();
|
||||
if (pool)
|
||||
{
|
||||
inode = (inode & (((uint64_t)1 << (64-POOL_ID_BITS)) - 1)) | (pool << (64-POOL_ID_BITS));
|
||||
inode = (inode & ((1l << (64-POOL_ID_BITS)) - 1)) | (pool << (64-POOL_ID_BITS));
|
||||
}
|
||||
if (!(inode >> (64-POOL_ID_BITS)))
|
||||
{
|
||||
|
||||
1690
src/nfs/nfs.h
1690
src/nfs/nfs.h
File diff suppressed because it is too large
Load Diff
1380
src/nfs/nfs.x
1380
src/nfs/nfs.x
File diff suppressed because it is too large
Load Diff
2954
src/nfs/nfs_xdr.cpp
2954
src/nfs/nfs_xdr.cpp
File diff suppressed because it is too large
Load Diff
@@ -1,190 +0,0 @@
|
||||
/*
|
||||
* Please do not edit this file.
|
||||
* It was generated using rpcgen.
|
||||
*/
|
||||
|
||||
#ifndef _PORTMAP_H_RPCGEN
|
||||
#define _PORTMAP_H_RPCGEN
|
||||
|
||||
#include "xdr_impl.h"
|
||||
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#define PMAP_PORT 111
|
||||
|
||||
struct pmap2_mapping {
|
||||
u_int prog;
|
||||
u_int vers;
|
||||
u_int prot;
|
||||
u_int port;
|
||||
};
|
||||
typedef struct pmap2_mapping pmap2_mapping;
|
||||
|
||||
struct pmap2_call_args {
|
||||
u_int prog;
|
||||
u_int vers;
|
||||
u_int proc;
|
||||
xdr_string_t args;
|
||||
};
|
||||
typedef struct pmap2_call_args pmap2_call_args;
|
||||
|
||||
struct pmap2_call_result {
|
||||
u_int port;
|
||||
xdr_string_t res;
|
||||
};
|
||||
typedef struct pmap2_call_result pmap2_call_result;
|
||||
|
||||
struct pmap2_mapping_list {
|
||||
pmap2_mapping map;
|
||||
struct pmap2_mapping_list *next;
|
||||
};
|
||||
typedef struct pmap2_mapping_list pmap2_mapping_list;
|
||||
|
||||
struct pmap2_dump_result {
|
||||
struct pmap2_mapping_list *list;
|
||||
};
|
||||
typedef struct pmap2_dump_result pmap2_dump_result;
|
||||
|
||||
struct pmap3_string_result {
|
||||
xdr_string_t addr;
|
||||
};
|
||||
typedef struct pmap3_string_result pmap3_string_result;
|
||||
|
||||
struct pmap3_mapping {
|
||||
u_int prog;
|
||||
u_int vers;
|
||||
xdr_string_t netid;
|
||||
xdr_string_t addr;
|
||||
xdr_string_t owner;
|
||||
};
|
||||
typedef struct pmap3_mapping pmap3_mapping;
|
||||
|
||||
struct pmap3_mapping_list {
|
||||
pmap3_mapping map;
|
||||
struct pmap3_mapping_list *next;
|
||||
};
|
||||
typedef struct pmap3_mapping_list pmap3_mapping_list;
|
||||
|
||||
struct pmap3_dump_result {
|
||||
struct pmap3_mapping_list *list;
|
||||
};
|
||||
typedef struct pmap3_dump_result pmap3_dump_result;
|
||||
|
||||
struct pmap3_call_args {
|
||||
u_int prog;
|
||||
u_int vers;
|
||||
u_int proc;
|
||||
xdr_string_t args;
|
||||
};
|
||||
typedef struct pmap3_call_args pmap3_call_args;
|
||||
|
||||
struct pmap3_call_result {
|
||||
u_int port;
|
||||
xdr_string_t res;
|
||||
};
|
||||
typedef struct pmap3_call_result pmap3_call_result;
|
||||
|
||||
struct pmap3_netbuf {
|
||||
u_int maxlen;
|
||||
xdr_string_t buf;
|
||||
};
|
||||
typedef struct pmap3_netbuf pmap3_netbuf;
|
||||
|
||||
typedef pmap2_mapping PMAP2SETargs;
|
||||
|
||||
typedef pmap2_mapping PMAP2UNSETargs;
|
||||
|
||||
typedef pmap2_mapping PMAP2GETPORTargs;
|
||||
|
||||
typedef pmap2_call_args PMAP2CALLITargs;
|
||||
|
||||
typedef pmap2_call_result PMAP2CALLITres;
|
||||
|
||||
typedef pmap2_dump_result PMAP2DUMPres;
|
||||
|
||||
typedef pmap3_mapping PMAP3SETargs;
|
||||
|
||||
typedef pmap3_mapping PMAP3UNSETargs;
|
||||
|
||||
typedef pmap3_mapping PMAP3GETADDRargs;
|
||||
|
||||
typedef pmap3_string_result PMAP3GETADDRres;
|
||||
|
||||
typedef pmap3_dump_result PMAP3DUMPres;
|
||||
|
||||
typedef pmap3_call_result PMAP3CALLITargs;
|
||||
|
||||
typedef pmap3_call_result PMAP3CALLITres;
|
||||
|
||||
typedef pmap3_netbuf PMAP3UADDR2TADDRres;
|
||||
|
||||
typedef pmap3_netbuf PMAP3TADDR2UADDRargs;
|
||||
|
||||
typedef pmap3_string_result PMAP3TADDR2UADDRres;
|
||||
|
||||
#define PMAP_PROGRAM 100000
|
||||
#define PMAP_V2 2
|
||||
|
||||
|
||||
#define PMAP2_NULL 0
|
||||
#define PMAP2_SET 1
|
||||
#define PMAP2_UNSET 2
|
||||
#define PMAP2_GETPORT 3
|
||||
#define PMAP2_DUMP 4
|
||||
#define PMAP2_CALLIT 5
|
||||
|
||||
#define PMAP_V3 3
|
||||
|
||||
|
||||
#define PMAP3_NULL 0
|
||||
#define PMAP3_SET 1
|
||||
#define PMAP3_UNSET 2
|
||||
#define PMAP3_GETADDR 3
|
||||
#define PMAP3_DUMP 4
|
||||
#define PMAP3_CALLIT 5
|
||||
#define PMAP3_GETTIME 6
|
||||
#define PMAP3_UADDR2TADDR 7
|
||||
#define PMAP3_TADDR2UADDR 8
|
||||
|
||||
|
||||
/* the xdr functions */
|
||||
|
||||
|
||||
extern bool_t xdr_pmap2_mapping (XDR *, pmap2_mapping*);
|
||||
extern bool_t xdr_pmap2_call_args (XDR *, pmap2_call_args*);
|
||||
extern bool_t xdr_pmap2_call_result (XDR *, pmap2_call_result*);
|
||||
extern bool_t xdr_pmap2_mapping_list (XDR *, pmap2_mapping_list*);
|
||||
extern bool_t xdr_pmap2_dump_result (XDR *, pmap2_dump_result*);
|
||||
extern bool_t xdr_pmap3_string_result (XDR *, pmap3_string_result*);
|
||||
extern bool_t xdr_pmap3_mapping (XDR *, pmap3_mapping*);
|
||||
extern bool_t xdr_pmap3_mapping_list (XDR *, pmap3_mapping_list*);
|
||||
extern bool_t xdr_pmap3_dump_result (XDR *, pmap3_dump_result*);
|
||||
extern bool_t xdr_pmap3_call_args (XDR *, pmap3_call_args*);
|
||||
extern bool_t xdr_pmap3_call_result (XDR *, pmap3_call_result*);
|
||||
extern bool_t xdr_pmap3_netbuf (XDR *, pmap3_netbuf*);
|
||||
extern bool_t xdr_PMAP2SETargs (XDR *, PMAP2SETargs*);
|
||||
extern bool_t xdr_PMAP2UNSETargs (XDR *, PMAP2UNSETargs*);
|
||||
extern bool_t xdr_PMAP2GETPORTargs (XDR *, PMAP2GETPORTargs*);
|
||||
extern bool_t xdr_PMAP2CALLITargs (XDR *, PMAP2CALLITargs*);
|
||||
extern bool_t xdr_PMAP2CALLITres (XDR *, PMAP2CALLITres*);
|
||||
extern bool_t xdr_PMAP2DUMPres (XDR *, PMAP2DUMPres*);
|
||||
extern bool_t xdr_PMAP3SETargs (XDR *, PMAP3SETargs*);
|
||||
extern bool_t xdr_PMAP3UNSETargs (XDR *, PMAP3UNSETargs*);
|
||||
extern bool_t xdr_PMAP3GETADDRargs (XDR *, PMAP3GETADDRargs*);
|
||||
extern bool_t xdr_PMAP3GETADDRres (XDR *, PMAP3GETADDRres*);
|
||||
extern bool_t xdr_PMAP3DUMPres (XDR *, PMAP3DUMPres*);
|
||||
extern bool_t xdr_PMAP3CALLITargs (XDR *, PMAP3CALLITargs*);
|
||||
extern bool_t xdr_PMAP3CALLITres (XDR *, PMAP3CALLITres*);
|
||||
extern bool_t xdr_PMAP3UADDR2TADDRres (XDR *, PMAP3UADDR2TADDRres*);
|
||||
extern bool_t xdr_PMAP3TADDR2UADDRargs (XDR *, PMAP3TADDR2UADDRargs*);
|
||||
extern bool_t xdr_PMAP3TADDR2UADDRres (XDR *, PMAP3TADDR2UADDRres*);
|
||||
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* !_PORTMAP_H_RPCGEN */
|
||||
@@ -1,168 +0,0 @@
|
||||
/*
|
||||
Copyright (c) 2014, Ronnie Sahlberg
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
1. Redistributions of source code must retain the above copyright notice, this
|
||||
list of conditions and the following disclaimer.
|
||||
2. Redistributions in binary form must reproduce the above copyright notice,
|
||||
this list of conditions and the following disclaimer in the documentation
|
||||
and/or other materials provided with the distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
|
||||
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
|
||||
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
|
||||
ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
|
||||
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
|
||||
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
|
||||
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
|
||||
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
The views and conclusions contained in the software and documentation are those
|
||||
of the authors and should not be interpreted as representing official policies,
|
||||
either expressed or implied, of the FreeBSD Project.
|
||||
*/
|
||||
|
||||
const PMAP_PORT = 111; /* portmapper port number */
|
||||
|
||||
struct pmap2_mapping {
|
||||
unsigned int prog;
|
||||
unsigned int vers;
|
||||
unsigned int prot;
|
||||
unsigned int port;
|
||||
};
|
||||
|
||||
struct pmap2_call_args {
|
||||
unsigned int prog;
|
||||
unsigned int vers;
|
||||
unsigned int proc;
|
||||
opaque args<>;
|
||||
};
|
||||
|
||||
struct pmap2_call_result {
|
||||
unsigned int port;
|
||||
opaque res<>;
|
||||
};
|
||||
|
||||
struct pmap2_mapping_list {
|
||||
pmap2_mapping map;
|
||||
pmap2_mapping_list *next;
|
||||
};
|
||||
|
||||
struct pmap2_dump_result {
|
||||
struct pmap2_mapping_list *list;
|
||||
};
|
||||
|
||||
struct pmap3_string_result {
|
||||
string addr<>;
|
||||
};
|
||||
|
||||
struct pmap3_mapping {
|
||||
unsigned int prog;
|
||||
unsigned int vers;
|
||||
string netid<>;
|
||||
string addr<>;
|
||||
string owner<>;
|
||||
};
|
||||
|
||||
struct pmap3_mapping_list {
|
||||
pmap3_mapping map;
|
||||
pmap3_mapping_list *next;
|
||||
};
|
||||
|
||||
struct pmap3_dump_result {
|
||||
struct pmap3_mapping_list *list;
|
||||
};
|
||||
|
||||
struct pmap3_call_args {
|
||||
unsigned int prog;
|
||||
unsigned int vers;
|
||||
unsigned int proc;
|
||||
opaque args<>;
|
||||
};
|
||||
|
||||
struct pmap3_call_result {
|
||||
unsigned int port;
|
||||
opaque res<>;
|
||||
};
|
||||
|
||||
struct pmap3_netbuf {
|
||||
unsigned int maxlen;
|
||||
/* This pretty much contains a sockaddr_storage.
|
||||
* Beware differences in endianess for ss_family
|
||||
* and whether or not ss_len exists.
|
||||
*/
|
||||
opaque buf<>;
|
||||
};
|
||||
|
||||
typedef pmap2_mapping PMAP2SETargs;
|
||||
typedef pmap2_mapping PMAP2UNSETargs;
|
||||
typedef pmap2_mapping PMAP2GETPORTargs;
|
||||
typedef pmap2_call_args PMAP2CALLITargs;
|
||||
typedef pmap2_call_result PMAP2CALLITres;
|
||||
typedef pmap2_dump_result PMAP2DUMPres;
|
||||
|
||||
typedef pmap3_mapping PMAP3SETargs;
|
||||
typedef pmap3_mapping PMAP3UNSETargs;
|
||||
typedef pmap3_mapping PMAP3GETADDRargs;
|
||||
typedef pmap3_string_result PMAP3GETADDRres;
|
||||
typedef pmap3_dump_result PMAP3DUMPres;
|
||||
typedef pmap3_call_result PMAP3CALLITargs;
|
||||
typedef pmap3_call_result PMAP3CALLITres;
|
||||
typedef pmap3_netbuf PMAP3UADDR2TADDRres;
|
||||
typedef pmap3_netbuf PMAP3TADDR2UADDRargs;
|
||||
typedef pmap3_string_result PMAP3TADDR2UADDRres;
|
||||
|
||||
program PMAP_PROGRAM {
|
||||
version PMAP_V2 {
|
||||
void
|
||||
PMAP2_NULL(void) = 0;
|
||||
|
||||
uint32_t
|
||||
PMAP2_SET(PMAP2SETargs) = 1;
|
||||
|
||||
uint32_t
|
||||
PMAP2_UNSET(PMAP2UNSETargs) = 2;
|
||||
|
||||
uint32_t
|
||||
PMAP2_GETPORT(PMAP2GETPORTargs) = 3;
|
||||
|
||||
PMAP2DUMPres
|
||||
PMAP2_DUMP(void) = 4;
|
||||
|
||||
PMAP2CALLITres
|
||||
PMAP2_CALLIT(PMAP2CALLITargs) = 5;
|
||||
} = 2;
|
||||
version PMAP_V3 {
|
||||
void
|
||||
PMAP3_NULL(void) = 0;
|
||||
|
||||
uint32_t
|
||||
PMAP3_SET(PMAP3SETargs) = 1;
|
||||
|
||||
uint32_t
|
||||
PMAP3_UNSET(PMAP3UNSETargs) = 2;
|
||||
|
||||
PMAP3GETADDRres
|
||||
PMAP3_GETADDR(PMAP3GETADDRargs) = 3;
|
||||
|
||||
PMAP3DUMPres
|
||||
PMAP3_DUMP(void) = 4;
|
||||
|
||||
PMAP3CALLITres
|
||||
PMAP3_CALLIT(PMAP3CALLITargs) = 5;
|
||||
|
||||
uint32_t
|
||||
PMAP3_GETTIME(void) = 6;
|
||||
|
||||
PMAP3UADDR2TADDRres
|
||||
PMAP3_UADDR2TADDR(string) = 7;
|
||||
|
||||
PMAP3TADDR2UADDRres
|
||||
PMAP3_TADDR2UADDR(PMAP3TADDR2UADDRargs) = 8;
|
||||
} = 3;
|
||||
} = 100000;
|
||||
@@ -1,406 +0,0 @@
|
||||
/*
|
||||
* Please do not edit this file.
|
||||
* It was generated using rpcgen.
|
||||
*/
|
||||
|
||||
#include "portmap.h"
|
||||
#include "xdr_impl_inline.h"
|
||||
|
||||
bool_t
|
||||
xdr_pmap2_mapping (XDR *xdrs, pmap2_mapping *objp)
|
||||
{
|
||||
|
||||
|
||||
if (xdrs->x_op == XDR_ENCODE) {
|
||||
if (1) {
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->prot))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->port))
|
||||
return FALSE;
|
||||
} else {
|
||||
IXDR_PUT_U_LONG(buf, objp->prog);
|
||||
IXDR_PUT_U_LONG(buf, objp->vers);
|
||||
IXDR_PUT_U_LONG(buf, objp->prot);
|
||||
IXDR_PUT_U_LONG(buf, objp->port);
|
||||
}
|
||||
return TRUE;
|
||||
} else if (xdrs->x_op == XDR_DECODE) {
|
||||
if (1) {
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->prot))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->port))
|
||||
return FALSE;
|
||||
} else {
|
||||
objp->prog = IXDR_GET_U_LONG(buf);
|
||||
objp->vers = IXDR_GET_U_LONG(buf);
|
||||
objp->prot = IXDR_GET_U_LONG(buf);
|
||||
objp->port = IXDR_GET_U_LONG(buf);
|
||||
}
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->prot))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->port))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap2_call_args (XDR *xdrs, pmap2_call_args *objp)
|
||||
{
|
||||
|
||||
|
||||
if (xdrs->x_op == XDR_ENCODE) {
|
||||
if (1) {
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->proc))
|
||||
return FALSE;
|
||||
|
||||
} else {
|
||||
IXDR_PUT_U_LONG(buf, objp->prog);
|
||||
IXDR_PUT_U_LONG(buf, objp->vers);
|
||||
IXDR_PUT_U_LONG(buf, objp->proc);
|
||||
}
|
||||
if (!xdr_bytes(xdrs, &objp->args, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
} else if (xdrs->x_op == XDR_DECODE) {
|
||||
if (1) {
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->proc))
|
||||
return FALSE;
|
||||
|
||||
} else {
|
||||
objp->prog = IXDR_GET_U_LONG(buf);
|
||||
objp->vers = IXDR_GET_U_LONG(buf);
|
||||
objp->proc = IXDR_GET_U_LONG(buf);
|
||||
}
|
||||
if (!xdr_bytes(xdrs, &objp->args, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->proc))
|
||||
return FALSE;
|
||||
if (!xdr_bytes(xdrs, &objp->args, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap2_call_result (XDR *xdrs, pmap2_call_result *objp)
|
||||
{
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->port))
|
||||
return FALSE;
|
||||
if (!xdr_bytes(xdrs, &objp->res, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap2_mapping_list (XDR *xdrs, pmap2_mapping_list *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap2_mapping (xdrs, &objp->map))
|
||||
return FALSE;
|
||||
if (!xdr_pointer (xdrs, (char **)&objp->next, sizeof (pmap2_mapping_list), (xdrproc_t) xdr_pmap2_mapping_list))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap2_dump_result (XDR *xdrs, pmap2_dump_result *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pointer (xdrs, (char **)&objp->list, sizeof (pmap2_mapping_list), (xdrproc_t) xdr_pmap2_mapping_list))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap3_string_result (XDR *xdrs, pmap3_string_result *objp)
|
||||
{
|
||||
|
||||
if (!xdr_string (xdrs, &objp->addr, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap3_mapping (XDR *xdrs, pmap3_mapping *objp)
|
||||
{
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_string (xdrs, &objp->netid, ~0))
|
||||
return FALSE;
|
||||
if (!xdr_string (xdrs, &objp->addr, ~0))
|
||||
return FALSE;
|
||||
if (!xdr_string (xdrs, &objp->owner, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap3_mapping_list (XDR *xdrs, pmap3_mapping_list *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_mapping (xdrs, &objp->map))
|
||||
return FALSE;
|
||||
if (!xdr_pointer (xdrs, (char **)&objp->next, sizeof (pmap3_mapping_list), (xdrproc_t) xdr_pmap3_mapping_list))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap3_dump_result (XDR *xdrs, pmap3_dump_result *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pointer (xdrs, (char **)&objp->list, sizeof (pmap3_mapping_list), (xdrproc_t) xdr_pmap3_mapping_list))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap3_call_args (XDR *xdrs, pmap3_call_args *objp)
|
||||
{
|
||||
|
||||
|
||||
if (xdrs->x_op == XDR_ENCODE) {
|
||||
if (1) {
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->proc))
|
||||
return FALSE;
|
||||
|
||||
} else {
|
||||
IXDR_PUT_U_LONG(buf, objp->prog);
|
||||
IXDR_PUT_U_LONG(buf, objp->vers);
|
||||
IXDR_PUT_U_LONG(buf, objp->proc);
|
||||
}
|
||||
if (!xdr_bytes(xdrs, &objp->args, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
} else if (xdrs->x_op == XDR_DECODE) {
|
||||
if (1) {
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->proc))
|
||||
return FALSE;
|
||||
|
||||
} else {
|
||||
objp->prog = IXDR_GET_U_LONG(buf);
|
||||
objp->vers = IXDR_GET_U_LONG(buf);
|
||||
objp->proc = IXDR_GET_U_LONG(buf);
|
||||
}
|
||||
if (!xdr_bytes(xdrs, &objp->args, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->proc))
|
||||
return FALSE;
|
||||
if (!xdr_bytes(xdrs, &objp->args, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap3_call_result (XDR *xdrs, pmap3_call_result *objp)
|
||||
{
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->port))
|
||||
return FALSE;
|
||||
if (!xdr_bytes(xdrs, &objp->res, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_pmap3_netbuf (XDR *xdrs, pmap3_netbuf *objp)
|
||||
{
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->maxlen))
|
||||
return FALSE;
|
||||
if (!xdr_bytes(xdrs, &objp->buf, ~0))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP2SETargs (XDR *xdrs, PMAP2SETargs *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap2_mapping (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP2UNSETargs (XDR *xdrs, PMAP2UNSETargs *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap2_mapping (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP2GETPORTargs (XDR *xdrs, PMAP2GETPORTargs *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap2_mapping (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP2CALLITargs (XDR *xdrs, PMAP2CALLITargs *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap2_call_args (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP2CALLITres (XDR *xdrs, PMAP2CALLITres *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap2_call_result (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP2DUMPres (XDR *xdrs, PMAP2DUMPres *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap2_dump_result (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3SETargs (XDR *xdrs, PMAP3SETargs *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_mapping (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3UNSETargs (XDR *xdrs, PMAP3UNSETargs *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_mapping (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3GETADDRargs (XDR *xdrs, PMAP3GETADDRargs *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_mapping (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3GETADDRres (XDR *xdrs, PMAP3GETADDRres *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_string_result (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3DUMPres (XDR *xdrs, PMAP3DUMPres *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_dump_result (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3CALLITargs (XDR *xdrs, PMAP3CALLITargs *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_call_result (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3CALLITres (XDR *xdrs, PMAP3CALLITres *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_call_result (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3UADDR2TADDRres (XDR *xdrs, PMAP3UADDR2TADDRres *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_netbuf (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3TADDR2UADDRargs (XDR *xdrs, PMAP3TADDR2UADDRargs *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_netbuf (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_PMAP3TADDR2UADDRres (XDR *xdrs, PMAP3TADDR2UADDRres *objp)
|
||||
{
|
||||
|
||||
if (!xdr_pmap3_string_result (xdrs, objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
160
src/nfs/rpc.h
160
src/nfs/rpc.h
@@ -1,160 +0,0 @@
|
||||
/*
|
||||
* Please do not edit this file.
|
||||
* It was generated using rpcgen.
|
||||
*/
|
||||
|
||||
#ifndef _RPC_H_RPCGEN
|
||||
#define _RPC_H_RPCGEN
|
||||
|
||||
#include "xdr_impl.h"
|
||||
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
#define RPC_MSG_VERSION 2
|
||||
|
||||
enum rpc_auth_flavor {
|
||||
RPC_AUTH_NONE = 0,
|
||||
RPC_AUTH_SYS = 1,
|
||||
RPC_AUTH_SHORT = 2,
|
||||
RPC_AUTH_DH = 3,
|
||||
RPC_RPCSEC_GSS = 6,
|
||||
};
|
||||
typedef enum rpc_auth_flavor rpc_auth_flavor;
|
||||
|
||||
enum rpc_msg_type {
|
||||
RPC_CALL = 0,
|
||||
RPC_REPLY = 1,
|
||||
};
|
||||
typedef enum rpc_msg_type rpc_msg_type;
|
||||
|
||||
enum rpc_reply_stat {
|
||||
RPC_MSG_ACCEPTED = 0,
|
||||
RPC_MSG_DENIED = 1,
|
||||
};
|
||||
typedef enum rpc_reply_stat rpc_reply_stat;
|
||||
|
||||
enum rpc_accept_stat {
|
||||
RPC_SUCCESS = 0,
|
||||
RPC_PROG_UNAVAIL = 1,
|
||||
RPC_PROG_MISMATCH = 2,
|
||||
RPC_PROC_UNAVAIL = 3,
|
||||
RPC_GARBAGE_ARGS = 4,
|
||||
RPC_SYSTEM_ERR = 5,
|
||||
};
|
||||
typedef enum rpc_accept_stat rpc_accept_stat;
|
||||
|
||||
enum rpc_reject_stat {
|
||||
RPC_MISMATCH = 0,
|
||||
RPC_AUTH_ERROR = 1,
|
||||
};
|
||||
typedef enum rpc_reject_stat rpc_reject_stat;
|
||||
|
||||
enum rpc_auth_stat {
|
||||
RPC_AUTH_OK = 0,
|
||||
RPC_AUTH_BADCRED = 1,
|
||||
RPC_AUTH_REJECTEDCRED = 2,
|
||||
RPC_AUTH_BADVERF = 3,
|
||||
RPC_AUTH_REJECTEDVERF = 4,
|
||||
RPC_AUTH_TOOWEAK = 5,
|
||||
RPC_AUTH_INVALIDRESP = 6,
|
||||
RPC_AUTH_FAILED = 7,
|
||||
};
|
||||
typedef enum rpc_auth_stat rpc_auth_stat;
|
||||
|
||||
struct rpc_opaque_auth {
|
||||
rpc_auth_flavor flavor;
|
||||
xdr_string_t body;
|
||||
};
|
||||
typedef struct rpc_opaque_auth rpc_opaque_auth;
|
||||
|
||||
struct rpc_call_body {
|
||||
u_int rpcvers;
|
||||
u_int prog;
|
||||
u_int vers;
|
||||
u_int proc;
|
||||
rpc_opaque_auth cred;
|
||||
rpc_opaque_auth verf;
|
||||
};
|
||||
typedef struct rpc_call_body rpc_call_body;
|
||||
|
||||
struct rpc_mismatch_info {
|
||||
u_int min_version;
|
||||
u_int max_version;
|
||||
};
|
||||
typedef struct rpc_mismatch_info rpc_mismatch_info;
|
||||
|
||||
struct rpc_accepted_reply_body {
|
||||
rpc_accept_stat stat;
|
||||
union {
|
||||
rpc_mismatch_info mismatch_info;
|
||||
};
|
||||
};
|
||||
typedef struct rpc_accepted_reply_body rpc_accepted_reply_body;
|
||||
|
||||
struct rpc_accepted_reply {
|
||||
rpc_opaque_auth verf;
|
||||
rpc_accepted_reply_body reply_data;
|
||||
};
|
||||
typedef struct rpc_accepted_reply rpc_accepted_reply;
|
||||
|
||||
struct rpc_rejected_reply {
|
||||
rpc_reject_stat stat;
|
||||
union {
|
||||
rpc_mismatch_info mismatch_info;
|
||||
rpc_auth_stat auth_stat;
|
||||
};
|
||||
};
|
||||
typedef struct rpc_rejected_reply rpc_rejected_reply;
|
||||
|
||||
struct rpc_reply_body {
|
||||
rpc_reply_stat stat;
|
||||
union {
|
||||
rpc_accepted_reply areply;
|
||||
rpc_rejected_reply rreply;
|
||||
};
|
||||
};
|
||||
typedef struct rpc_reply_body rpc_reply_body;
|
||||
|
||||
struct rpc_msg_body {
|
||||
rpc_msg_type dir;
|
||||
union {
|
||||
rpc_call_body cbody;
|
||||
rpc_reply_body rbody;
|
||||
};
|
||||
};
|
||||
typedef struct rpc_msg_body rpc_msg_body;
|
||||
|
||||
struct rpc_msg {
|
||||
u_int xid;
|
||||
rpc_msg_body body;
|
||||
};
|
||||
typedef struct rpc_msg rpc_msg;
|
||||
|
||||
/* the xdr functions */
|
||||
|
||||
|
||||
extern bool_t xdr_rpc_auth_flavor (XDR *, rpc_auth_flavor*);
|
||||
extern bool_t xdr_rpc_msg_type (XDR *, rpc_msg_type*);
|
||||
extern bool_t xdr_rpc_reply_stat (XDR *, rpc_reply_stat*);
|
||||
extern bool_t xdr_rpc_accept_stat (XDR *, rpc_accept_stat*);
|
||||
extern bool_t xdr_rpc_reject_stat (XDR *, rpc_reject_stat*);
|
||||
extern bool_t xdr_rpc_auth_stat (XDR *, rpc_auth_stat*);
|
||||
extern bool_t xdr_rpc_opaque_auth (XDR *, rpc_opaque_auth*);
|
||||
extern bool_t xdr_rpc_call_body (XDR *, rpc_call_body*);
|
||||
extern bool_t xdr_rpc_mismatch_info (XDR *, rpc_mismatch_info*);
|
||||
extern bool_t xdr_rpc_accepted_reply_body (XDR *, rpc_accepted_reply_body*);
|
||||
extern bool_t xdr_rpc_accepted_reply (XDR *, rpc_accepted_reply*);
|
||||
extern bool_t xdr_rpc_rejected_reply (XDR *, rpc_rejected_reply*);
|
||||
extern bool_t xdr_rpc_reply_body (XDR *, rpc_reply_body*);
|
||||
extern bool_t xdr_rpc_msg_body (XDR *, rpc_msg_body*);
|
||||
extern bool_t xdr_rpc_msg (XDR *, rpc_msg*);
|
||||
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
|
||||
#endif /* !_RPC_H_RPCGEN */
|
||||
113
src/nfs/rpc.x
113
src/nfs/rpc.x
@@ -1,113 +0,0 @@
|
||||
/* Based on RFC 5531 - RPC: Remote Procedure Call Protocol Specification Version 2 */
|
||||
|
||||
const RPC_MSG_VERSION = 2;
|
||||
|
||||
enum rpc_auth_flavor {
|
||||
RPC_AUTH_NONE = 0,
|
||||
RPC_AUTH_SYS = 1,
|
||||
RPC_AUTH_SHORT = 2,
|
||||
RPC_AUTH_DH = 3,
|
||||
RPC_RPCSEC_GSS = 6
|
||||
};
|
||||
|
||||
enum rpc_msg_type {
|
||||
RPC_CALL = 0,
|
||||
RPC_REPLY = 1
|
||||
};
|
||||
|
||||
enum rpc_reply_stat {
|
||||
RPC_MSG_ACCEPTED = 0,
|
||||
RPC_MSG_DENIED = 1
|
||||
};
|
||||
|
||||
enum rpc_accept_stat {
|
||||
RPC_SUCCESS = 0,
|
||||
RPC_PROG_UNAVAIL = 1,
|
||||
RPC_PROG_MISMATCH = 2,
|
||||
RPC_PROC_UNAVAIL = 3,
|
||||
RPC_GARBAGE_ARGS = 4,
|
||||
RPC_SYSTEM_ERR = 5
|
||||
};
|
||||
|
||||
enum rpc_reject_stat {
|
||||
RPC_MISMATCH = 0,
|
||||
RPC_AUTH_ERROR = 1
|
||||
};
|
||||
|
||||
enum rpc_auth_stat {
|
||||
RPC_AUTH_OK = 0,
|
||||
/*
|
||||
* failed at remote end
|
||||
*/
|
||||
RPC_AUTH_BADCRED = 1, /* bogus credentials (seal broken) */
|
||||
RPC_AUTH_REJECTEDCRED = 2, /* client should begin new session */
|
||||
RPC_AUTH_BADVERF = 3, /* bogus verifier (seal broken) */
|
||||
RPC_AUTH_REJECTEDVERF = 4, /* verifier expired or was replayed */
|
||||
RPC_AUTH_TOOWEAK = 5, /* rejected due to security reasons */
|
||||
/*
|
||||
* failed locally
|
||||
*/
|
||||
RPC_AUTH_INVALIDRESP = 6, /* bogus response verifier */
|
||||
RPC_AUTH_FAILED = 7 /* some unknown reason */
|
||||
};
|
||||
|
||||
struct rpc_opaque_auth {
|
||||
rpc_auth_flavor flavor;
|
||||
opaque body<400>;
|
||||
};
|
||||
|
||||
struct rpc_call_body {
|
||||
u_int rpcvers;
|
||||
u_int prog;
|
||||
u_int vers;
|
||||
u_int proc;
|
||||
rpc_opaque_auth cred;
|
||||
rpc_opaque_auth verf;
|
||||
/* procedure-specific parameters start here */
|
||||
};
|
||||
|
||||
struct rpc_mismatch_info {
|
||||
unsigned int min_version;
|
||||
unsigned int max_version;
|
||||
};
|
||||
|
||||
union rpc_accepted_reply_body switch (rpc_accept_stat stat) {
|
||||
case RPC_SUCCESS:
|
||||
void;
|
||||
/* procedure-specific results start here */
|
||||
case RPC_PROG_MISMATCH:
|
||||
rpc_mismatch_info mismatch_info;
|
||||
default:
|
||||
void;
|
||||
};
|
||||
|
||||
struct rpc_accepted_reply {
|
||||
rpc_opaque_auth verf;
|
||||
rpc_accepted_reply_body reply_data;
|
||||
};
|
||||
|
||||
union rpc_rejected_reply switch (rpc_reject_stat stat) {
|
||||
case RPC_MISMATCH:
|
||||
rpc_mismatch_info mismatch_info;
|
||||
case RPC_AUTH_ERROR:
|
||||
rpc_auth_stat auth_stat;
|
||||
};
|
||||
|
||||
union rpc_reply_body switch (rpc_reply_stat stat) {
|
||||
case RPC_MSG_ACCEPTED:
|
||||
rpc_accepted_reply areply;
|
||||
case RPC_MSG_DENIED:
|
||||
rpc_rejected_reply rreply;
|
||||
};
|
||||
|
||||
union rpc_msg_body switch (rpc_msg_type dir) {
|
||||
case RPC_CALL:
|
||||
rpc_call_body cbody;
|
||||
case RPC_REPLY:
|
||||
rpc_reply_body rbody;
|
||||
};
|
||||
|
||||
struct rpc_msg {
|
||||
u_int xid;
|
||||
rpc_msg_body body;
|
||||
};
|
||||
@@ -1,43 +0,0 @@
|
||||
#pragma once
|
||||
|
||||
#include "rpc.h"
|
||||
|
||||
struct rpc_op_t;
|
||||
|
||||
// Handler should return 1 if the request is processed asynchronously
|
||||
// and requires the incoming message to not be freed until processing ends,
|
||||
// 0 otherwise.
|
||||
typedef int (*rpc_handler_t)(void *opaque, rpc_op_t *rop);
|
||||
|
||||
struct rpc_service_proc_t
|
||||
{
|
||||
uint32_t prog;
|
||||
uint32_t vers;
|
||||
uint32_t proc;
|
||||
rpc_handler_t handler_fn;
|
||||
xdrproc_t req_fn;
|
||||
uint32_t req_size;
|
||||
xdrproc_t resp_fn;
|
||||
uint32_t resp_size;
|
||||
void *opaque;
|
||||
};
|
||||
|
||||
inline bool operator < (const rpc_service_proc_t & a, const rpc_service_proc_t & b)
|
||||
{
|
||||
return a.prog < b.prog || a.prog == b.prog && (a.vers < b.vers || a.vers == b.vers && a.proc < b.proc);
|
||||
}
|
||||
|
||||
struct rpc_op_t
|
||||
{
|
||||
void *client;
|
||||
uint8_t *buffer;
|
||||
XDR *xdrs;
|
||||
rpc_msg in_msg, out_msg;
|
||||
void *request;
|
||||
void *reply;
|
||||
xdrproc_t reply_fn;
|
||||
uint32_t reply_marker;
|
||||
bool referenced;
|
||||
};
|
||||
|
||||
void rpc_queue_reply(rpc_op_t *rop);
|
||||
@@ -1,253 +0,0 @@
|
||||
/*
|
||||
* Please do not edit this file.
|
||||
* It was generated using rpcgen.
|
||||
*/
|
||||
|
||||
#include "rpc.h"
|
||||
#include "xdr_impl_inline.h"
|
||||
|
||||
bool_t
|
||||
xdr_rpc_auth_flavor (XDR *xdrs, rpc_auth_flavor *objp)
|
||||
{
|
||||
|
||||
if (!xdr_enum (xdrs, (enum_t *) objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_msg_type (XDR *xdrs, rpc_msg_type *objp)
|
||||
{
|
||||
|
||||
if (!xdr_enum (xdrs, (enum_t *) objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_reply_stat (XDR *xdrs, rpc_reply_stat *objp)
|
||||
{
|
||||
|
||||
if (!xdr_enum (xdrs, (enum_t *) objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_accept_stat (XDR *xdrs, rpc_accept_stat *objp)
|
||||
{
|
||||
|
||||
if (!xdr_enum (xdrs, (enum_t *) objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_reject_stat (XDR *xdrs, rpc_reject_stat *objp)
|
||||
{
|
||||
|
||||
if (!xdr_enum (xdrs, (enum_t *) objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_auth_stat (XDR *xdrs, rpc_auth_stat *objp)
|
||||
{
|
||||
|
||||
if (!xdr_enum (xdrs, (enum_t *) objp))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_opaque_auth (XDR *xdrs, rpc_opaque_auth *objp)
|
||||
{
|
||||
|
||||
if (!xdr_rpc_auth_flavor (xdrs, &objp->flavor))
|
||||
return FALSE;
|
||||
if (!xdr_bytes(xdrs, &objp->body, 400))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_call_body (XDR *xdrs, rpc_call_body *objp)
|
||||
{
|
||||
|
||||
|
||||
if (xdrs->x_op == XDR_ENCODE) {
|
||||
if (1) {
|
||||
if (!xdr_u_int (xdrs, &objp->rpcvers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->proc))
|
||||
return FALSE;
|
||||
|
||||
} else {
|
||||
IXDR_PUT_U_LONG(buf, objp->rpcvers);
|
||||
IXDR_PUT_U_LONG(buf, objp->prog);
|
||||
IXDR_PUT_U_LONG(buf, objp->vers);
|
||||
IXDR_PUT_U_LONG(buf, objp->proc);
|
||||
}
|
||||
if (!xdr_rpc_opaque_auth (xdrs, &objp->cred))
|
||||
return FALSE;
|
||||
if (!xdr_rpc_opaque_auth (xdrs, &objp->verf))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
} else if (xdrs->x_op == XDR_DECODE) {
|
||||
if (1) {
|
||||
if (!xdr_u_int (xdrs, &objp->rpcvers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->proc))
|
||||
return FALSE;
|
||||
|
||||
} else {
|
||||
objp->rpcvers = IXDR_GET_U_LONG(buf);
|
||||
objp->prog = IXDR_GET_U_LONG(buf);
|
||||
objp->vers = IXDR_GET_U_LONG(buf);
|
||||
objp->proc = IXDR_GET_U_LONG(buf);
|
||||
}
|
||||
if (!xdr_rpc_opaque_auth (xdrs, &objp->cred))
|
||||
return FALSE;
|
||||
if (!xdr_rpc_opaque_auth (xdrs, &objp->verf))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->rpcvers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->prog))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->vers))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->proc))
|
||||
return FALSE;
|
||||
if (!xdr_rpc_opaque_auth (xdrs, &objp->cred))
|
||||
return FALSE;
|
||||
if (!xdr_rpc_opaque_auth (xdrs, &objp->verf))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_mismatch_info (XDR *xdrs, rpc_mismatch_info *objp)
|
||||
{
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->min_version))
|
||||
return FALSE;
|
||||
if (!xdr_u_int (xdrs, &objp->max_version))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_accepted_reply_body (XDR *xdrs, rpc_accepted_reply_body *objp)
|
||||
{
|
||||
|
||||
if (!xdr_rpc_accept_stat (xdrs, &objp->stat))
|
||||
return FALSE;
|
||||
switch (objp->stat) {
|
||||
case RPC_SUCCESS:
|
||||
break;
|
||||
case RPC_PROG_MISMATCH:
|
||||
if (!xdr_rpc_mismatch_info (xdrs, &objp->mismatch_info))
|
||||
return FALSE;
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_accepted_reply (XDR *xdrs, rpc_accepted_reply *objp)
|
||||
{
|
||||
|
||||
if (!xdr_rpc_opaque_auth (xdrs, &objp->verf))
|
||||
return FALSE;
|
||||
if (!xdr_rpc_accepted_reply_body (xdrs, &objp->reply_data))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_rejected_reply (XDR *xdrs, rpc_rejected_reply *objp)
|
||||
{
|
||||
|
||||
if (!xdr_rpc_reject_stat (xdrs, &objp->stat))
|
||||
return FALSE;
|
||||
switch (objp->stat) {
|
||||
case RPC_MISMATCH:
|
||||
if (!xdr_rpc_mismatch_info (xdrs, &objp->mismatch_info))
|
||||
return FALSE;
|
||||
break;
|
||||
case RPC_AUTH_ERROR:
|
||||
if (!xdr_rpc_auth_stat (xdrs, &objp->auth_stat))
|
||||
return FALSE;
|
||||
break;
|
||||
default:
|
||||
return FALSE;
|
||||
}
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_reply_body (XDR *xdrs, rpc_reply_body *objp)
|
||||
{
|
||||
|
||||
if (!xdr_rpc_reply_stat (xdrs, &objp->stat))
|
||||
return FALSE;
|
||||
switch (objp->stat) {
|
||||
case RPC_MSG_ACCEPTED:
|
||||
if (!xdr_rpc_accepted_reply (xdrs, &objp->areply))
|
||||
return FALSE;
|
||||
break;
|
||||
case RPC_MSG_DENIED:
|
||||
if (!xdr_rpc_rejected_reply (xdrs, &objp->rreply))
|
||||
return FALSE;
|
||||
break;
|
||||
default:
|
||||
return FALSE;
|
||||
}
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_msg_body (XDR *xdrs, rpc_msg_body *objp)
|
||||
{
|
||||
|
||||
if (!xdr_rpc_msg_type (xdrs, &objp->dir))
|
||||
return FALSE;
|
||||
switch (objp->dir) {
|
||||
case RPC_CALL:
|
||||
if (!xdr_rpc_call_body (xdrs, &objp->cbody))
|
||||
return FALSE;
|
||||
break;
|
||||
case RPC_REPLY:
|
||||
if (!xdr_rpc_reply_body (xdrs, &objp->rbody))
|
||||
return FALSE;
|
||||
break;
|
||||
default:
|
||||
return FALSE;
|
||||
}
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
bool_t
|
||||
xdr_rpc_msg (XDR *xdrs, rpc_msg *objp)
|
||||
{
|
||||
|
||||
if (!xdr_u_int (xdrs, &objp->xid))
|
||||
return FALSE;
|
||||
if (!xdr_rpc_msg_body (xdrs, &objp->body))
|
||||
return FALSE;
|
||||
return TRUE;
|
||||
}
|
||||
@@ -1,48 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -e
|
||||
|
||||
# 1) remove all extern non-xdr functions (service, client)
|
||||
# 2) use xdr_string_t for strings instead of char*
|
||||
# 3) remove K&R #ifdefs
|
||||
# 4) remove register int32_t* buf
|
||||
# 5) remove union names
|
||||
# 6) use xdr_string_t for opaques instead of u_int + char*
|
||||
# 7) TODO: generate normal procedure stubs
|
||||
run_rpcgen() {
|
||||
rpcgen -h $1.x | \
|
||||
perl -e '
|
||||
{ local $/ = undef; $_ = <>; }
|
||||
s/^extern(?!.*"C"|.*bool_t xdr.*XDR).*\n//gm;
|
||||
s/#include <rpc\/rpc.h>/#include "xdr_impl.h"/;
|
||||
s/^typedef char \*/typedef xdr_string_t /gm;
|
||||
s/^(\s*)char \*(?!.*_val)/$1xdr_string_t /gm;
|
||||
# remove union names
|
||||
s/ \w+_u;/;/gs;
|
||||
# use xdr_string_t for opaques
|
||||
s/struct\s*\{\s*u_int\s+\w+_len;\s*char\s+\*\w+_val;\s*\}\s*/xdr_string_t /gs;
|
||||
# remove stdc/k&r
|
||||
s/^#if.*__STDC__.*//gm;
|
||||
s/\n#else[^\n]*K&R.*?\n#endif[^\n]*K&R[^\n]*//gs;
|
||||
print;' > $1.h
|
||||
rpcgen -c $1.x | \
|
||||
perl -pe '
|
||||
s/register int32_t \*buf;\s*//g;
|
||||
s/\bbuf\s*=[^;]+;\s*//g;
|
||||
s/\bbuf\s*==\s*NULL/1/g;
|
||||
# remove union names
|
||||
s/(\.|->)\w+_u\./$1/g;
|
||||
# use xdr_string_t for opaques
|
||||
# xdr_bytes(xdrs, (char**)&objp->data.data_val, (char**)&objp->data.data_len, 400)
|
||||
# -> xdr_bytes(xdrs, &objp->data, 400)
|
||||
# xdr_bytes(xdrs, (char**)&objp->data_val, (char**)&objp->data_len, 400)
|
||||
# -> xdr_bytes(xdrs, objp, 400)
|
||||
s/xdr_bytes\s*\(\s*xdrs,\s*\(\s*char\s*\*\*\s*\)\s*([^()]+?)\.\w+_val\s*,\s*\(\s*u_int\s*\*\s*\)\s*\1\.\w+_len,/xdr_bytes(xdrs, $1,/gs;
|
||||
s/xdr_bytes\s*\(\s*xdrs,\s*\(\s*char\s*\*\*\s*\)\s*&\s*([^()]+?)->\w+_val\s*,\s*\(\s*u_int\s*\*\s*\)\s*&\s*\1->\w+_len,/xdr_bytes(xdrs, $1,/gs;
|
||||
# add include
|
||||
if (/#include/) { $_ .= "#include \"xdr_impl_inline.h\"\n"; }' > ${1}_xdr.cpp
|
||||
}
|
||||
|
||||
run_rpcgen nfs
|
||||
run_rpcgen rpc
|
||||
run_rpcgen portmap
|
||||
@@ -1,107 +0,0 @@
|
||||
// Copyright (c) Vitaliy Filippov, 2019+
|
||||
// License: VNPL-1.1 (see README.md for details)
|
||||
//
|
||||
// Efficient XDR implementation almost compatible with rpcgen (see run-rpcgen.sh)
|
||||
|
||||
#include "xdr_impl_inline.h"
|
||||
|
||||
XDR* xdr_create()
|
||||
{
|
||||
return new XDR;
|
||||
}
|
||||
|
||||
void xdr_destroy(XDR* xdrs)
|
||||
{
|
||||
xdr_reset(xdrs);
|
||||
delete xdrs;
|
||||
}
|
||||
|
||||
void xdr_reset(XDR *xdrs)
|
||||
{
|
||||
for (auto buf: xdrs->allocs)
|
||||
{
|
||||
free(buf);
|
||||
}
|
||||
xdrs->buf = NULL;
|
||||
xdrs->avail = 0;
|
||||
xdrs->allocs.resize(0);
|
||||
xdrs->in_linked_list.resize(0);
|
||||
xdrs->cur_out.resize(0);
|
||||
xdrs->last_end = 0;
|
||||
xdrs->buf_list.resize(0);
|
||||
}
|
||||
|
||||
int xdr_decode(XDR *xdrs, void *buf, unsigned size, xdrproc_t fn, void *data)
|
||||
{
|
||||
xdrs->x_op = XDR_DECODE;
|
||||
xdrs->buf = (uint8_t*)buf;
|
||||
xdrs->avail = size;
|
||||
return fn(xdrs, data);
|
||||
}
|
||||
|
||||
int xdr_encode(XDR *xdrs, xdrproc_t fn, void *data)
|
||||
{
|
||||
xdrs->x_op = XDR_ENCODE;
|
||||
return fn(xdrs, data);
|
||||
}
|
||||
|
||||
void xdr_encode_finish(XDR *xdrs, iovec **iov_list, unsigned *iov_count)
|
||||
{
|
||||
if (xdrs->last_end < xdrs->cur_out.size())
|
||||
{
|
||||
xdrs->buf_list.push_back((iovec){
|
||||
.iov_base = 0,
|
||||
.iov_len = xdrs->cur_out.size() - xdrs->last_end,
|
||||
});
|
||||
xdrs->last_end = xdrs->cur_out.size();
|
||||
}
|
||||
uint8_t *cur_buf = xdrs->cur_out.data();
|
||||
for (auto & buf: xdrs->buf_list)
|
||||
{
|
||||
if (!buf.iov_base)
|
||||
{
|
||||
buf.iov_base = cur_buf;
|
||||
cur_buf += buf.iov_len;
|
||||
}
|
||||
}
|
||||
*iov_list = xdrs->buf_list.data();
|
||||
*iov_count = xdrs->buf_list.size();
|
||||
}
|
||||
|
||||
void xdr_dump_encoded(XDR *xdrs)
|
||||
{
|
||||
for (auto & buf: xdrs->buf_list)
|
||||
{
|
||||
for (int i = 0; i < buf.iov_len; i++)
|
||||
printf("%02x", ((uint8_t*)buf.iov_base)[i]);
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
|
||||
void xdr_add_malloc(XDR *xdrs, void *buf)
|
||||
{
|
||||
xdrs->allocs.push_back(buf);
|
||||
}
|
||||
|
||||
xdr_string_t xdr_copy_string(XDR *xdrs, const std::string & str)
|
||||
{
|
||||
char *cp = (char*)malloc_or_die(str.size()+1);
|
||||
memcpy(cp, str.data(), str.size());
|
||||
cp[str.size()] = 0;
|
||||
xdr_add_malloc(xdrs, cp);
|
||||
return (xdr_string_t){ str.size(), cp };
|
||||
}
|
||||
|
||||
xdr_string_t xdr_copy_string(XDR *xdrs, const char *str)
|
||||
{
|
||||
return xdr_copy_string(xdrs, str, strlen(str));
|
||||
}
|
||||
|
||||
xdr_string_t xdr_copy_string(XDR *xdrs, const char *str, size_t len)
|
||||
{
|
||||
char *cp = (char*)malloc_or_die(len+1);
|
||||
memcpy(cp, str, len);
|
||||
cp[len] = 0;
|
||||
xdr_add_malloc(xdrs, cp);
|
||||
return (xdr_string_t){ len, cp };
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user