Compare commits

...

24 Commits

Author SHA1 Message Date
Dmitry Yusko
5727772bdc Add relatime and lazytime for ext4 mounting 2023-12-14 17:03:38 +03:00
aca2bef15f Add vitastor-disk update-sb command 2023-12-14 01:11:42 +03:00
4dd6e89263 Change qemu to qemu-system-x86 in docs 2023-12-14 01:01:00 +03:00
9bac99ffb6 Fix incorrect error in CSI when searching for the device in /sys 2023-12-14 01:00:32 +03:00
62ed130960 Support building qemu 8.1 from bookworm-backports 2023-12-10 00:34:13 +03:00
9c7755b6e8 Use qemu-storage-daemon from QEMU 8.1.2 for CSI 2023-12-08 00:10:12 +03:00
691ebd991a Move 2 last log printfs to stderr from stdout in etcd_state_client 2023-12-08 00:01:52 +03:00
6d5df908a3 Fix possible out of bounds when checking invalid journal entries 2023-12-08 00:01:07 +03:00
fa87769ed8 Correct config options in vduse docs 2023-12-06 02:09:04 +03:00
2ce8292803 Also log when killing process 2023-12-06 01:06:53 +03:00
7f8f7ded52 Check for empty output of vitastor-nbd map (just in case) 2023-12-06 01:01:14 +03:00
68553eabbb Log executed CLI commands 2023-12-06 00:48:12 +03:00
3147c5c8d5 Remove internal error wrapping 2023-12-06 00:39:42 +03:00
576e2ae608 Fix etcd_address check in CSI 2023-12-06 00:28:21 +03:00
a1c7cc3d8d Release 1.3.1
Hotfix to 1.3.0 - new "journal space reservation" had a bug which
caused OSDs to crash with EC and without immediate_commit.
2023-12-04 18:35:09 +03:00
a5e3dfbc5a Oops, 1.3.0 needs a hotfix 2023-12-04 13:45:54 +03:00
7972502eaf Release 1.3.0
New features:
- RDMA without ODP - much faster and all cards are now supported, not just Mellanox
- VDUSE in CSI - faster, more stable and can even recover after CSI pod restart!
- Reserve journal space for stabilize requests dynamically to prevent stalls under load with EC
- Raise default NBD timeout from 30 to 300 seconds and allow to take it from /etc/vitastor/vitastor.conf
- Remove explicit etcdUrl/etcdPrefix K8S storage class parameter support to prevent
  etcd migration issues for volumes created with these parameters
- Support QEMU 8.1 and pve-qemu 8.1

Bug fixes:
- Fix RDMA connection (and thus memory) leak
- Fix rare crashes under load due to incorrect io_uring queue size tracking
- Fix monitor statistics aggregation in case of empty /osd/stats keys
- Fix crash on unknown long argument to vitastor-disk
- Allow trailing comma in JSONs again
- Fix crash on attempts to dump a long listing of objects "to stabilize" or "to rollback" in a slow op
2023-12-04 02:36:43 +03:00
e57b7203b8 Use cmake3 on RHEL 7 2023-12-04 02:36:29 +03:00
c8a179dcda Note that Proxmox 8.1 is supported 2023-12-04 02:20:33 +03:00
845454742d Fix warning with QEMU 8.1 2023-12-04 01:59:07 +03:00
d65512bd80 Add patches for QEMU 8.1 2023-12-04 01:56:17 +03:00
53de2bbd0f Support VDUSE in CSI
VDUSE has multiple advantages:
- Better performance
- Lack of timeout problems
- And even the ability to recover after restart of the vitastor-csi pod!
2023-12-04 00:41:24 +03:00
628aa59574 Raise default NBD timeout from 30 to 300 seconds and allow to take it from /etc/vitastor/vitastor.conf 2023-12-02 14:11:14 +03:00
037cf64a47 Remove explicit etcdUrl/etcdPrefix from volume parameters 2023-12-02 13:26:00 +03:00
59 changed files with 1193 additions and 202 deletions

View File

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
project(vitastor)
set(VERSION "1.2.0")
set(VERSION "1.3.1")
add_subdirectory(src)

View File

@@ -1,14 +1,15 @@
# Compile stage
FROM golang:buster AS build
FROM golang:bookworm AS build
ADD go.sum go.mod /app/
RUN cd /app; CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go mod download -x
ADD . /app
RUN perl -i -e '$/ = undef; while(<>) { s/\n\s*(\{\s*\n)/$1\n/g; s/\}(\s*\n\s*)else\b/$1} else/g; print; }' `find /app -name '*.go'`
RUN cd /app; CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go build -o vitastor-csi
RUN perl -i -e '$/ = undef; while(<>) { s/\n\s*(\{\s*\n)/$1\n/g; s/\}(\s*\n\s*)else\b/$1} else/g; print; }' `find /app -name '*.go'` && \
cd /app && \
CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go build -o vitastor-csi
# Final stage
FROM debian:buster
FROM debian:bookworm
LABEL maintainers="Vitaliy Filippov <vitalif@yourcmc.ru>"
LABEL description="Vitastor CSI Driver"
@@ -18,19 +19,30 @@ ENV CSI_ENDPOINT=""
RUN apt-get update && \
apt-get install -y wget && \
(echo deb http://deb.debian.org/debian buster-backports main > /etc/apt/sources.list.d/backports.list) && \
(echo "APT::Install-Recommends false;" > /etc/apt/apt.conf) && \
apt-get update && \
apt-get install -y e2fsprogs xfsprogs kmod && \
apt-get install -y e2fsprogs xfsprogs kmod iproute2 \
# dependencies of qemu-storage-daemon
libnuma1 liburing2 libglib2.0-0 libfuse3-3 libaio1 libzstd1 libnettle8 \
libgmp10 libhogweed6 libp11-kit0 libidn2-0 libunistring2 libtasn1-6 libpcre2-8-0 libffi8 && \
apt-get clean && \
(echo options nbd nbds_max=128 > /etc/modprobe.d/nbd.conf)
COPY --from=build /app/vitastor-csi /bin/
RUN (echo deb http://vitastor.io/debian buster main > /etc/apt/sources.list.d/vitastor.list) && \
RUN (echo deb http://vitastor.io/debian bookworm main > /etc/apt/sources.list.d/vitastor.list) && \
((echo 'Package: *'; echo 'Pin: origin "vitastor.io"'; echo 'Pin-Priority: 1000') > /etc/apt/preferences.d/vitastor.pref) && \
wget -q -O /etc/apt/trusted.gpg.d/vitastor.gpg https://vitastor.io/debian/pubkey.gpg && \
apt-get update && \
apt-get install -y vitastor-client && \
wget https://vitastor.io/archive/qemu/qemu-bookworm-8.1.2%2Bds-1%2Bvitastor1/qemu-utils_8.1.2%2Bds-1%2Bvitastor1_amd64.deb && \
wget https://vitastor.io/archive/qemu/qemu-bookworm-8.1.2%2Bds-1%2Bvitastor1/qemu-block-extra_8.1.2%2Bds-1%2Bvitastor1_amd64.deb && \
dpkg -x qemu-utils*.deb tmp1 && \
dpkg -x qemu-block-extra*.deb tmp1 && \
cp -a tmp1/usr/bin/qemu-storage-daemon /usr/bin/ && \
mkdir -p /usr/lib/x86_64-linux-gnu/qemu && \
cp -a tmp1/usr/lib/x86_64-linux-gnu/qemu/block-vitastor.so /usr/lib/x86_64-linux-gnu/qemu/ && \
rm -rf tmp1 *.deb && \
apt-get clean
ENTRYPOINT ["/bin/vitastor-csi"]

View File

@@ -1,4 +1,4 @@
VERSION ?= v1.2.0
VERSION ?= v1.3.1
all: build push

View File

@@ -2,6 +2,7 @@
apiVersion: v1
kind: ConfigMap
data:
# You can add multiple configuration files here to use a multi-cluster setup
vitastor.conf: |-
{"etcd_address":"http://192.168.7.2:2379","etcd_prefix":"/vitastor"}
metadata:

View File

@@ -49,7 +49,7 @@ spec:
capabilities:
add: ["SYS_ADMIN"]
allowPrivilegeEscalation: true
image: vitalif/vitastor-csi:v1.2.0
image: vitalif/vitastor-csi:v1.3.1
args:
- "--node=$(NODE_ID)"
- "--endpoint=$(CSI_ENDPOINT)"
@@ -82,6 +82,8 @@ spec:
name: host-sys
- mountPath: /run/mount
name: host-mount
- mountPath: /run/vitastor-csi
name: run-vitastor-csi
- mountPath: /lib/modules
name: lib-modules
readOnly: true
@@ -132,6 +134,9 @@ spec:
- name: host-mount
hostPath:
path: /run/mount
- name: run-vitastor-csi
hostPath:
path: /run/vitastor-csi
- name: lib-modules
hostPath:
path: /lib/modules

View File

@@ -121,7 +121,7 @@ spec:
privileged: true
capabilities:
add: ["SYS_ADMIN"]
image: vitalif/vitastor-csi:v1.2.0
image: vitalif/vitastor-csi:v1.3.1
args:
- "--node=$(NODE_ID)"
- "--endpoint=$(CSI_ENDPOINT)"

View File

@@ -12,9 +12,6 @@ parameters:
etcdVolumePrefix: ""
poolId: "1"
# you can choose other configuration file if you have it in the config map
# different etcd URLs and prefixes should also be put in the config
#configPath: "/etc/vitastor/vitastor.conf"
# you can also specify etcdUrl here, maybe to connect to another Vitastor cluster
# multiple etcdUrls may be specified, delimited by comma
#etcdUrl: "http://192.168.7.2:2379"
#etcdPrefix: "/vitastor"
allowVolumeExpansion: true

View File

@@ -5,7 +5,7 @@ package vitastor
const (
vitastorCSIDriverName = "csi.vitastor.io"
vitastorCSIDriverVersion = "1.2.0"
vitastorCSIDriverVersion = "1.3.1"
)
// Config struct fills the parameters of request or user input

View File

@@ -62,7 +62,7 @@ func NewControllerServer(driver *Driver) *ControllerServer
}
}
func GetConnectionParams(params map[string]string) (map[string]string, []string, string)
func GetConnectionParams(params map[string]string) (map[string]string, error)
{
ctxVars := make(map[string]string)
configPath := params["configPath"]
@@ -75,71 +75,69 @@ func GetConnectionParams(params map[string]string) (map[string]string, []string,
ctxVars["configPath"] = configPath
}
config := make(map[string]interface{})
if configFD, err := os.Open(configPath); err == nil
configFD, err := os.Open(configPath)
if (err != nil)
{
defer configFD.Close()
data, _ := ioutil.ReadAll(configFD)
json.Unmarshal(data, &config)
return nil, err
}
// Try to load prefix & etcd URL from the config
defer configFD.Close()
data, _ := ioutil.ReadAll(configFD)
json.Unmarshal(data, &config)
// Check etcd URL in the config, but do not use the explicit etcdUrl
// parameter for CLI calls, otherwise users won't be able to later
// change them - storage class parameters are saved in volume IDs
var etcdUrl []string
if (params["etcdUrl"] != "")
switch config["etcd_address"].(type)
{
ctxVars["etcdUrl"] = params["etcdUrl"]
etcdUrl = strings.Split(params["etcdUrl"], ",")
case string:
url := strings.TrimSpace(config["etcd_address"].(string))
if (url != "")
{
etcdUrl = strings.Split(url, ",")
}
case []string:
etcdUrl = config["etcd_address"].([]string)
case []interface{}:
for _, url := range config["etcd_address"].([]interface{})
{
s, ok := url.(string)
if (ok)
{
etcdUrl = append(etcdUrl, s)
}
}
}
if (len(etcdUrl) == 0)
{
switch config["etcd_address"].(type)
{
case string:
etcdUrl = strings.Split(config["etcd_address"].(string), ",")
case []string:
etcdUrl = config["etcd_address"].([]string)
}
return nil, status.Error(codes.InvalidArgument, "etcd_address is missing in "+configPath)
}
etcdPrefix := params["etcdPrefix"]
if (etcdPrefix == "")
return ctxVars, nil
}
func system(program string, args ...string) ([]byte, []byte, error)
{
klog.Infof("Running "+program+" "+strings.Join(args, " "))
c := exec.Command(program, args...)
var stdout, stderr bytes.Buffer
c.Stdout, c.Stderr = &stdout, &stderr
err := c.Run()
if (err != nil)
{
etcdPrefix, _ = config["etcd_prefix"].(string)
if (etcdPrefix == "")
{
etcdPrefix = "/vitastor"
}
stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s, status %s\n", stdoutStr+stderrStr, err)
return nil, nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
}
else
{
ctxVars["etcdPrefix"] = etcdPrefix
}
return ctxVars, etcdUrl, etcdPrefix
return stdout.Bytes(), stderr.Bytes(), nil
}
func invokeCLI(ctxVars map[string]string, args []string) ([]byte, error)
{
if (ctxVars["etcdUrl"] != "")
{
args = append(args, "--etcd_address", ctxVars["etcdUrl"])
}
if (ctxVars["etcdPrefix"] != "")
{
args = append(args, "--etcd_prefix", ctxVars["etcdPrefix"])
}
if (ctxVars["configPath"] != "")
{
args = append(args, "--config_path", ctxVars["configPath"])
}
c := exec.Command("/usr/bin/vitastor-cli", args...)
var stdout, stderr bytes.Buffer
c.Stdout = &stdout
c.Stderr = &stderr
err := c.Run()
stderrStr := string(stderr.Bytes())
if (err != nil)
{
klog.Errorf("vitastor-cli %s failed: %s, status %s\n", strings.Join(args, " "), stderrStr, err)
return nil, status.Error(codes.Internal, stderrStr+" (status "+err.Error()+")")
}
return stdout.Bytes(), nil
stdout, _, err := system("/usr/bin/vitastor-cli", args...)
return stdout, err
}
// Create the volume
@@ -174,10 +172,10 @@ func (cs *ControllerServer) CreateVolume(ctx context.Context, req *csi.CreateVol
volSize = ((capRange.GetRequiredBytes() + MB - 1) / MB) * MB
}
ctxVars, etcdUrl, _ := GetConnectionParams(req.Parameters)
if (len(etcdUrl) == 0)
ctxVars, err := GetConnectionParams(req.Parameters)
if (err != nil)
{
return nil, status.Error(codes.InvalidArgument, "no etcdUrl in storage class configuration and no etcd_address in vitastor.conf")
return nil, err
}
args := []string{ "create", volName, "-s", fmt.Sprintf("%v", volSize), "--pool", fmt.Sprintf("%v", poolId) }
@@ -207,7 +205,7 @@ func (cs *ControllerServer) CreateVolume(ctx context.Context, req *csi.CreateVol
}
// Create image using vitastor-cli
_, err := invokeCLI(ctxVars, args)
_, err = invokeCLI(ctxVars, args)
if (err != nil)
{
if (strings.Index(err.Error(), "already exists") > 0)
@@ -257,7 +255,11 @@ func (cs *ControllerServer) DeleteVolume(ctx context.Context, req *csi.DeleteVol
}
volName := volVars["name"]
ctxVars, _, _ := GetConnectionParams(volVars)
ctxVars, err := GetConnectionParams(volVars)
if (err != nil)
{
return nil, err
}
_, err = invokeCLI(ctxVars, []string{ "rm", volName })
if (err != nil)
@@ -469,7 +471,11 @@ func (cs *ControllerServer) DeleteSnapshot(ctx context.Context, req *csi.DeleteS
volName := volVars["name"]
snapName := volVars["snapshot"]
ctxVars, _, _ := GetConnectionParams(volVars)
ctxVars, err := GetConnectionParams(volVars)
if (err != nil)
{
return nil, err
}
_, err = invokeCLI(ctxVars, []string{ "rm", volName+"@"+snapName })
if (err != nil)
@@ -496,7 +502,11 @@ func (cs *ControllerServer) ListSnapshots(ctx context.Context, req *csi.ListSnap
return nil, status.Error(codes.Internal, "volume ID not in JSON format")
}
volName := volVars["name"]
ctxVars, _, _ := GetConnectionParams(volVars)
ctxVars, err := GetConnectionParams(volVars)
if (err != nil)
{
return nil, err
}
inodeCfg, err := invokeList(ctxVars, volName+"@*", false)
if (err != nil)
@@ -555,7 +565,11 @@ func (cs *ControllerServer) ControllerExpandVolume(ctx context.Context, req *csi
return nil, status.Error(codes.Internal, "volume ID not in JSON format")
}
volName := volVars["name"]
ctxVars, _, _ := GetConnectionParams(volVars)
ctxVars, err := GetConnectionParams(volVars)
if (err != nil)
{
return nil, err
}
inodeCfg, err := invokeList(ctxVars, volName, true)
if (err != nil)

View File

@@ -5,11 +5,15 @@ package vitastor
import (
"context"
"errors"
"encoding/json"
"fmt"
"os"
"os/exec"
"encoding/json"
"path/filepath"
"strconv"
"strings"
"bytes"
"syscall"
"google.golang.org/grpc/codes"
"google.golang.org/grpc/status"
@@ -25,16 +29,91 @@ import (
type NodeServer struct
{
*Driver
useVduse bool
stateDir string
mounter mount.Interface
}
type DeviceState struct
{
ConfigPath string `json:"configPath"`
VdpaId string `json:"vdpaId"`
Image string `json:"image"`
Blockdev string `json:"blockdev"`
Readonly bool `json:"readonly"`
PidFile string `json:"pidFile"`
}
// NewNodeServer create new instance node
func NewNodeServer(driver *Driver) *NodeServer
{
return &NodeServer{
stateDir := os.Getenv("STATE_DIR")
if (stateDir == "")
{
stateDir = "/run/vitastor-csi"
}
if (stateDir[len(stateDir)-1] != '/')
{
stateDir += "/"
}
ns := &NodeServer{
Driver: driver,
useVduse: checkVduseSupport(),
stateDir: stateDir,
mounter: mount.New(""),
}
if (ns.useVduse)
{
ns.restoreVduseDaemons()
}
return ns
}
func checkVduseSupport() bool
{
// Check VDUSE support (vdpa, vduse, virtio-vdpa kernel modules)
vduse := true
for _, mod := range []string{"vdpa", "vduse", "virtio-vdpa"}
{
_, err := os.Stat("/sys/module/"+mod)
if (err != nil)
{
if (!errors.Is(err, os.ErrNotExist))
{
klog.Errorf("failed to check /sys/module/%s: %v", mod, err)
}
c := exec.Command("/sbin/modprobe", mod)
c.Stdout = os.Stderr
c.Stderr = os.Stderr
err := c.Run()
if (err != nil)
{
klog.Errorf("/sbin/modprobe %s failed: %v", mod, err)
vduse = false
break
}
}
}
// Check that vdpa tool functions
if (vduse)
{
c := exec.Command("/sbin/vdpa", "-j", "dev")
c.Stderr = os.Stderr
err := c.Run()
if (err != nil)
{
klog.Errorf("/sbin/vdpa -j dev failed: %v", err)
vduse = false
}
}
if (!vduse)
{
klog.Errorf(
"Your host apparently has no VDUSE support. VDUSE support disabled, NBD will be used to map devices."+
" For VDUSE you need at least Linux 5.15 and the following kernel modules: vdpa, virtio-vdpa, vduse.",
)
}
return vduse
}
// NodeStageVolume mounts the volume to a staging path on the node.
@@ -61,6 +140,303 @@ func Contains(list []string, s string) bool
return false
}
func (ns *NodeServer) mapNbd(volName string, ctxVars map[string]string, readonly bool) (string, error)
{
// Map NBD device
// FIXME: Check if already mapped
args := []string{
"map", "--image", volName,
}
if (ctxVars["configPath"] != "")
{
args = append(args, "--config_path", ctxVars["configPath"])
}
if (readonly)
{
args = append(args, "--readonly", "1")
}
stdout, stderr, err := system("/usr/bin/vitastor-nbd", args...)
dev := strings.TrimSpace(string(stdout))
if (dev == "")
{
return "", fmt.Errorf("vitastor-nbd did not return the name of NBD device. output: %s", stderr)
}
return dev, err
}
func (ns *NodeServer) unmapNbd(devicePath string)
{
// unmap NBD device
unmapOut, unmapErr := exec.Command("/usr/bin/vitastor-nbd", "unmap", devicePath).CombinedOutput()
if (unmapErr != nil)
{
klog.Errorf("failed to unmap NBD device %s: %s, error: %v", devicePath, unmapOut, unmapErr)
}
}
func findByPidFile(pidFile string) (*os.Process, error)
{
klog.Infof("killing process with PID from file %s", pidFile)
pidBuf, err := os.ReadFile(pidFile)
if (err != nil)
{
return nil, err
}
pid, err := strconv.ParseInt(strings.TrimSpace(string(pidBuf)), 0, 64)
if (err != nil)
{
return nil, err
}
proc, err := os.FindProcess(int(pid))
if (err != nil)
{
return nil, err
}
return proc, nil
}
func killByPidFile(pidFile string) error
{
proc, err := findByPidFile(pidFile)
if (err != nil)
{
return err
}
return proc.Signal(syscall.SIGTERM)
}
func startStorageDaemon(vdpaId, volName, pidFile, configPath string, readonly bool) error
{
// Start qemu-storage-daemon
blockSpec := map[string]interface{}{
"node-name": "disk1",
"driver": "vitastor",
"image": volName,
"cache": map[string]bool{
"direct": true,
"no-flush": false,
},
"discard": "unmap",
}
if (configPath != "")
{
blockSpec["config-path"] = configPath
}
blockSpecJson, _ := json.Marshal(blockSpec)
writable := "true"
if (readonly)
{
writable = "false"
}
_, _, err := system(
"/usr/bin/qemu-storage-daemon", "--daemonize", "--pidfile", pidFile, "--blockdev", string(blockSpecJson),
"--export", "vduse-blk,id="+vdpaId+",node-name=disk1,name="+vdpaId+",num-queues=16,queue-size=128,writable="+writable,
)
return err
}
func (ns *NodeServer) mapVduse(volName string, ctxVars map[string]string, readonly bool) (string, string, error)
{
// Generate state file
stateFd, err := os.CreateTemp(ns.stateDir, "vitastor-vduse-*.json")
if (err != nil)
{
return "", "", err
}
stateFile := stateFd.Name()
stateFd.Close()
vdpaId := filepath.Base(stateFile)
vdpaId = vdpaId[0:len(vdpaId)-5] // remove ".json"
pidFile := ns.stateDir + vdpaId + ".pid"
// Map VDUSE device via qemu-storage-daemon
err = startStorageDaemon(vdpaId, volName, pidFile, ctxVars["configPath"], readonly)
if (err == nil)
{
// Add device to VDPA bus
_, _, err = system("/sbin/vdpa", "-j", "dev", "add", "name", vdpaId, "mgmtdev", "vduse")
if (err == nil)
{
// Find block device name
var matches []string
matches, err = filepath.Glob("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/*")
if (err == nil && len(matches) == 0)
{
err = errors.New("/sys/bus/vdpa/devices/"+vdpaId+"/virtio*/block/* is not found")
}
if (err == nil)
{
blockdev := "/dev/"+filepath.Base(matches[0])
_, err = os.Stat(blockdev)
if (err == nil)
{
// Generate state file
stateJSON, _ := json.Marshal(&DeviceState{
ConfigPath: ctxVars["configPath"],
VdpaId: vdpaId,
Image: volName,
Blockdev: blockdev,
Readonly: readonly,
PidFile: pidFile,
})
err = os.WriteFile(stateFile, stateJSON, 0600)
if (err == nil)
{
return blockdev, vdpaId, nil
}
}
}
}
killErr := killByPidFile(pidFile)
if (killErr != nil)
{
klog.Errorf("Failed to kill started qemu-storage-daemon: %v", killErr)
}
os.Remove(stateFile)
os.Remove(pidFile)
}
return "", "", err
}
func (ns *NodeServer) unmapVduse(devicePath string)
{
if (len(devicePath) < 6 || devicePath[0:6] != "/dev/v")
{
klog.Errorf("%s does not start with /dev/v", devicePath)
return
}
vduseDev, err := os.Readlink("/sys/block/"+devicePath[5:])
if (err != nil)
{
klog.Errorf("%s is not a symbolic link to VDUSE device (../devices/virtual/vduse/xxx): %v", devicePath, err)
return
}
vdpaId := ""
p := strings.Index(vduseDev, "/vduse/")
if (p >= 0)
{
vduseDev = vduseDev[p+7:]
p = strings.Index(vduseDev, "/")
if (p >= 0)
{
vdpaId = vduseDev[0:p]
}
}
if (vdpaId == "")
{
klog.Errorf("%s is not a symbolic link to VDUSE device (../devices/virtual/vduse/xxx), but is %v", devicePath, vduseDev)
return
}
ns.unmapVduseById(vdpaId)
}
func (ns *NodeServer) unmapVduseById(vdpaId string)
{
_, err := os.Stat("/sys/bus/vdpa/devices/"+vdpaId)
if (err != nil)
{
klog.Errorf("failed to stat /sys/bus/vdpa/devices/"+vdpaId+": %v", err)
}
else
{
_, _, _ = system("/sbin/vdpa", "-j", "dev", "del", vdpaId)
}
stateFile := ns.stateDir + vdpaId + ".json"
os.Remove(stateFile)
pidFile := ns.stateDir + vdpaId + ".pid"
_, err = os.Stat(pidFile)
if (os.IsNotExist(err))
{
// ok, already killed
}
else if (err != nil)
{
klog.Errorf("Failed to stat %v: %v", pidFile, err)
return
}
else
{
err = killByPidFile(pidFile)
if (err != nil)
{
klog.Errorf("Failed to kill started qemu-storage-daemon: %v", err)
}
os.Remove(pidFile)
}
}
func (ns *NodeServer) restoreVduseDaemons()
{
pattern := ns.stateDir+"vitastor-vduse-*.json"
matches, err := filepath.Glob(pattern)
if (err != nil)
{
klog.Errorf("failed to list %s: %v", pattern, err)
}
if (len(matches) == 0)
{
return
}
devList := make(map[string]interface{})
// example output: {"dev":{"test1":{"type":"block","mgmtdev":"vduse","vendor_id":0,"max_vqs":16,"max_vq_size":128}}}
devListJSON, _, err := system("/sbin/vdpa", "-j", "dev", "list")
if (err != nil)
{
return
}
err = json.Unmarshal(devListJSON, &devList)
devs, ok := devList["dev"].(map[string]interface{})
if (err != nil || !ok)
{
klog.Errorf("/sbin/vdpa -j dev list returned bad JSON (error %v): %v", err, string(devListJSON))
return
}
for _, stateFile := range matches
{
vdpaId := filepath.Base(stateFile)
vdpaId = vdpaId[0:len(vdpaId)-5]
// Check if VDPA device is still added to the bus
if (devs[vdpaId] != nil)
{
// Check if the storage daemon is still active
pidFile := ns.stateDir + vdpaId + ".pid"
exists := false
proc, err := findByPidFile(pidFile)
if (err == nil)
{
exists = proc.Signal(syscall.Signal(0)) == nil
}
if (!exists)
{
// Restart daemon
stateJSON, err := os.ReadFile(stateFile)
if (err != nil)
{
klog.Warningf("error reading state file %v: %v", stateFile, err)
}
else
{
var state DeviceState
err := json.Unmarshal(stateJSON, &state)
if (err != nil)
{
klog.Warningf("state file %v contains invalid JSON (error %v): %v", stateFile, err, string(stateJSON))
}
else
{
klog.Warningf("restarting storage daemon for volume %v (VDPA ID %v)", state.Image, vdpaId)
_ = startStorageDaemon(vdpaId, state.Image, pidFile, state.ConfigPath, state.Readonly)
}
}
}
}
else
{
// Unused, clean it up
ns.unmapVduseById(vdpaId)
}
}
}
// NodePublishVolume mounts the volume mounted to the staging path to the target path
func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublishVolumeRequest) (*csi.NodePublishVolumeResponse, error)
{
@@ -81,13 +457,13 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
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())
return nil, err
}
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())
return nil, err
}
}
else
@@ -96,13 +472,13 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
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, err
}
}
}
else
{
return nil, status.Error(codes.Internal, err.Error())
return nil, err
}
}
@@ -114,38 +490,25 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
}
volName := ctxVars["name"]
_, etcdUrl, etcdPrefix := GetConnectionParams(ctxVars)
if (len(etcdUrl) == 0)
{
return nil, status.Error(codes.InvalidArgument, "no etcdUrl in storage class configuration and no etcd_address in vitastor.conf")
}
// Map NBD device
// FIXME: Check if already mapped
args := []string{
"map", "--etcd_address", strings.Join(etcdUrl, ","),
"--etcd_prefix", etcdPrefix,
"--image", volName,
};
if (ctxVars["configPath"] != "")
{
args = append(args, "--config_path", ctxVars["configPath"])
}
if (req.GetReadonly())
{
args = append(args, "--readonly", "1")
}
c := exec.Command("/usr/bin/vitastor-nbd", args...)
var stdout, stderr bytes.Buffer
c.Stdout, c.Stderr = &stdout, &stderr
err = c.Run()
stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
_, err = GetConnectionParams(ctxVars)
if (err != nil)
{
klog.Errorf("vitastor-nbd map failed: %s, status %s\n", stdoutStr+stderrStr, err)
return nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
return nil, err
}
var devicePath, vdpaId string
if (!ns.useVduse)
{
devicePath, err = ns.mapNbd(volName, ctxVars, req.GetReadonly())
}
else
{
devicePath, vdpaId, err = ns.mapVduse(volName, ctxVars, req.GetReadonly())
}
if (err != nil)
{
return nil, err
}
devicePath := strings.TrimSpace(stdoutStr)
diskMounter := &mount.SafeFormatAndMount{Interface: ns.mounter, Exec: utilexec.New()}
if (isBlock)
@@ -176,6 +539,10 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
{
opt = append(opt, "nouuid")
}
if (fsType == "ext4")
{
opt = append(opt, "relatime","lazytime")
}
readOnly := Contains(opt, "ro")
if (existingFormat == "" && !readOnly)
{
@@ -227,13 +594,15 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
return &csi.NodePublishVolumeResponse{}, nil
unmap:
// unmap NBD device
unmapOut, unmapErr := exec.Command("/usr/bin/vitastor-nbd", "unmap", devicePath).CombinedOutput()
if (unmapErr != nil)
if (!ns.useVduse || len(devicePath) >= 8 && devicePath[0:8] == "/dev/nbd")
{
klog.Errorf("failed to unmap NBD device %s: %s, error: %v", devicePath, unmapOut, unmapErr)
ns.unmapNbd(devicePath)
}
return nil, status.Error(codes.Internal, err.Error())
else
{
ns.unmapVduseById(vdpaId)
}
return nil, err
}
// NodeUnpublishVolume unmounts the volume from the target path
@@ -248,25 +617,31 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
{
return nil, status.Error(codes.NotFound, "Target path not found")
}
return nil, status.Error(codes.Internal, err.Error())
return nil, err
}
if (devicePath == "")
{
return nil, status.Error(codes.NotFound, "Volume not mounted")
// volume not mounted
klog.Warningf("%s is not a mountpoint, deleting", targetPath)
os.Remove(targetPath)
return &csi.NodeUnpublishVolumeResponse{}, nil
}
// unmount
err = mount.CleanupMountPoint(targetPath, ns.mounter, false)
if (err != nil)
{
return nil, status.Error(codes.Internal, err.Error())
return nil, err
}
// unmap NBD device
if (refCount == 1)
{
unmapOut, unmapErr := exec.Command("/usr/bin/vitastor-nbd", "unmap", devicePath).CombinedOutput()
if (unmapErr != nil)
if (!ns.useVduse)
{
klog.Errorf("failed to unmap NBD device %s: %s, error: %v", devicePath, unmapOut, unmapErr)
ns.unmapNbd(devicePath)
}
else
{
ns.unmapVduse(devicePath)
}
}
return &csi.NodeUnpublishVolumeResponse{}, nil

4
debian/changelog vendored
View File

@@ -1,10 +1,10 @@
vitastor (1.2.0-1) unstable; urgency=medium
vitastor (1.3.1-1) unstable; urgency=medium
* Bugfixes
-- Vitaliy Filippov <vitalif@yourcmc.ru> Fri, 03 Jun 2022 02:09:44 +0300
vitastor (1.2.0-1) unstable; urgency=medium
vitastor (0.7.0-1) unstable; urgency=medium
* Implement NFS proxy
* Add documentation

View File

@@ -7,7 +7,7 @@ ARG REL=
WORKDIR /root
RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" ]; then \
RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" -o "$REL" = "bookworm" ]; then \
echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
echo >> /etc/apt/preferences; \
echo 'Package: *' >> /etc/apt/preferences; \
@@ -45,7 +45,7 @@ RUN set -e; \
rm -rf /root/packages/qemu-$REL/*; \
cd /root/packages/qemu-$REL; \
dpkg-source -x /root/qemu*.dsc; \
QEMU_VER=$(ls -d qemu*/ | perl -pe 's!^.*(\d+\.\d+).*!$1!'); \
QEMU_VER=$(ls -d qemu*/ | perl -pe 's!^.*?(\d+\.\d+).*!$1!'); \
D=$(ls -d qemu*/); \
cp /root/vitastor/patches/qemu-$QEMU_VER-vitastor.patch ./qemu-*/debian/patches; \
echo qemu-$QEMU_VER-vitastor.patch >> $D/debian/patches/series; \

View File

@@ -35,8 +35,8 @@ RUN set -e -x; \
mkdir -p /root/packages/vitastor-$REL; \
rm -rf /root/packages/vitastor-$REL/*; \
cd /root/packages/vitastor-$REL; \
cp -r /root/vitastor vitastor-1.2.0; \
cd vitastor-1.2.0; \
cp -r /root/vitastor vitastor-1.3.1; \
cd vitastor-1.3.1; \
ln -s /root/fio-build/fio-*/ ./fio; \
FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -49,8 +49,8 @@ RUN set -e -x; \
rm -rf a b; \
echo "dep:fio=$FIO" > debian/fio_version; \
cd /root/packages/vitastor-$REL; \
tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.2.0.orig.tar.xz vitastor-1.2.0; \
cd vitastor-1.2.0; \
tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_1.3.1.orig.tar.xz vitastor-1.3.1; \
cd vitastor-1.3.1; \
V=$(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; \

View File

@@ -15,6 +15,9 @@ the cluster.
- [client_max_buffered_bytes](#client_max_buffered_bytes)
- [client_max_buffered_ops](#client_max_buffered_ops)
- [client_max_writeback_iodepth](#client_max_writeback_iodepth)
- [nbd_timeout](#nbd_timeout)
- [nbd_max_devices](#nbd_max_devices)
- [nbd_max_part](#nbd_max_part)
## client_max_dirty_bytes
@@ -101,3 +104,34 @@ Multiple consecutive modified data regions are counted as 1 write here.
- Can be changed online: yes
Maximum number of parallel writes when flushing buffered data to the server.
## nbd_timeout
- Type: seconds
- Default: 300
Timeout for I/O operations for [NBD](../usage/nbd.en.md). If an operation
executes for longer than this timeout, including when your cluster is just
temporarily down for more than timeout, the NBD device will detach by itself
(and possibly break the mounted file system).
You can set timeout to 0 to never detach, but in that case you won't be
able to remove the kernel device at all if the NBD process dies - you'll have
to reboot the host.
## nbd_max_devices
- Type: integer
- Default: 64
Maximum number of NBD devices in the system. This value is passed as
`nbds_max` parameter for the nbd kernel module when vitastor-nbd autoloads it.
## nbd_max_part
- Type: integer
- Default: 3
Maximum number of partitions per NBD device. This value is passed as
`max_part` parameter for the nbd kernel module when vitastor-nbd autoloads it.
Note that (nbds_max)*(1+max_part) usually can't exceed 256.

View File

@@ -15,6 +15,9 @@
- [client_max_buffered_bytes](#client_max_buffered_bytes)
- [client_max_buffered_ops](#client_max_buffered_ops)
- [client_max_writeback_iodepth](#client_max_writeback_iodepth)
- [nbd_timeout](#nbd_timeout)
- [nbd_max_devices](#nbd_max_devices)
- [nbd_max_part](#nbd_max_part)
## client_max_dirty_bytes
@@ -101,3 +104,34 @@
- Можно менять на лету: да
Максимальное число параллельных операций записи при сбросе буферов на сервер.
## nbd_timeout
- Тип: секунды
- Значение по умолчанию: 300
Таймаут для операций чтения/записи через [NBD](../usage/nbd.ru.md). Если
операция выполняется дольше таймаута, включая временную недоступность
кластера на время, большее таймаута, NBD-устройство отключится само собой
(и, возможно, сломает примонтированную ФС).
Вы можете установить таймаут в 0, чтобы никогда не отключать устройство по
таймауту, но в этом случае вы вообще не сможете удалить устройство, если
процесс NBD умрёт - вам придётся перезагружать сервер.
## nbd_max_devices
- Тип: целое число
- Значение по умолчанию: 64
Максимальное число NBD-устройств в системе. Данное значение передаётся
модулю ядра nbd как параметр `nbds_max`, когда его загружает vitastor-nbd.
## nbd_max_part
- Тип: целое число
- Значение по умолчанию: 3
Максимальное число разделов на одном NBD-устройстве. Данное значение передаётся
модулю ядра nbd как параметр `max_part`, когда его загружает vitastor-nbd.
Имейте в виду, что (nbds_max)*(1+max_part) обычно не может превышать 256.

View File

@@ -1,4 +1,4 @@
# Client Parameters
These parameters apply only to clients and affect their interaction with
the cluster.
These parameters apply only to Vitastor clients (QEMU, fio, NBD and so on) and
affect their interaction with the cluster.

View File

@@ -1,4 +1,4 @@
# Параметры клиентского кода
Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD) и
Данные параметры применяются только к клиентам Vitastor (QEMU, fio, NBD и т.п.) и
затрагивают логику их работы с кластером.

View File

@@ -122,3 +122,47 @@
Maximum number of parallel writes when flushing buffered data to the server.
info_ru: |
Максимальное число параллельных операций записи при сбросе буферов на сервер.
- name: nbd_timeout
type: sec
default: 300
online: false
info: |
Timeout for I/O operations for [NBD](../usage/nbd.en.md). If an operation
executes for longer than this timeout, including when your cluster is just
temporarily down for more than timeout, the NBD device will detach by itself
(and possibly break the mounted file system).
You can set timeout to 0 to never detach, but in that case you won't be
able to remove the kernel device at all if the NBD process dies - you'll have
to reboot the host.
info_ru: |
Таймаут для операций чтения/записи через [NBD](../usage/nbd.ru.md). Если
операция выполняется дольше таймаута, включая временную недоступность
кластера на время, большее таймаута, NBD-устройство отключится само собой
(и, возможно, сломает примонтированную ФС).
Вы можете установить таймаут в 0, чтобы никогда не отключать устройство по
таймауту, но в этом случае вы вообще не сможете удалить устройство, если
процесс NBD умрёт - вам придётся перезагружать сервер.
- name: nbd_max_devices
type: int
default: 64
online: false
info: |
Maximum number of NBD devices in the system. This value is passed as
`nbds_max` parameter for the nbd kernel module when vitastor-nbd autoloads it.
info_ru: |
Максимальное число NBD-устройств в системе. Данное значение передаётся
модулю ядра nbd как параметр `nbds_max`, когда его загружает vitastor-nbd.
- name: nbd_max_part
type: int
default: 3
online: false
info: |
Maximum number of partitions per NBD device. This value is passed as
`max_part` parameter for the nbd kernel module when vitastor-nbd autoloads it.
Note that (nbds_max)*(1+max_part) usually can't exceed 256.
info_ru: |
Максимальное число разделов на одном NBD-устройстве. Данное значение передаётся
модулю ядра nbd как параметр `max_part`, когда его загружает vitastor-nbd.
Имейте в виду, что (nbds_max)*(1+max_part) обычно не может превышать 256.

View File

@@ -19,6 +19,14 @@ for i in ./???-*.yaml; do kubectl apply -f $i; done
After that you'll be able to create PersistentVolumes.
**Important:** For best experience, use Linux kernel at least 5.15 with [VDUSE](../usage/qemu.en.md#vduse)
kernel modules enabled (vdpa, vduse, virtio-vdpa). If your distribution doesn't
have them pre-built - build them yourself ([instructions](../usage/qemu.en.md#vduse)),
I promise it's worth it :-). When VDUSE is unavailable, CSI driver uses [NBD](../usage/nbd.en.md)
to map Vitastor devices. NBD is slower and prone to timeout issues: if Vitastor
cluster becomes unresponsible for more than [nbd_timeout](../config/client.en.md#nbd_timeout),
the NBD device detaches and breaks pods using it.
## Features
Vitastor CSI supports:
@@ -27,5 +35,8 @@ Vitastor CSI supports:
- Raw block RWX (ReadWriteMany) volumes. Example: [PVC](../../csi/deploy/example-pvc-block.yaml), [pod](../../csi/deploy/example-test-pod-block.yaml)
- Volume expansion
- Volume snapshots. Example: [snapshot class](../../csi/deploy/example-snapshot-class.yaml), [snapshot](../../csi/deploy/example-snapshot.yaml), [clone](../../csi/deploy/example-snapshot-clone.yaml)
- [VDUSE](../usage/qemu.en.md#vduse) (preferred) and [NBD](../usage/nbd.en.md) device mapping methods
- Upgrades with VDUSE - new handler processes are restarted when CSI pods are restarted themselves
- Multiple clusters by using multiple configuration files in ConfigMap.
Remember that to use snapshots with CSI you also have to install [Snapshot Controller and CRDs](https://kubernetes-csi.github.io/docs/snapshot-controller.html#deployment).

View File

@@ -19,6 +19,14 @@ for i in ./???-*.yaml; do kubectl apply -f $i; done
После этого вы сможете создавать PersistentVolume.
**Важно:** Лучше всего использовать ядро Linux версии не менее 5.15 с включёнными модулями
[VDUSE](../usage/qemu.ru.md#vduse) (vdpa, vduse, virtio-vdpa). Если в вашем дистрибутиве
они не собраны из коробки - соберите их сами, обещаю, что это стоит того ([инструкция](../usage/qemu.ru.md#vduse)) :-).
Когда VDUSE недоступно, CSI-плагин использует [NBD](../usage/nbd.ru.md) для подключения
дисков, а NBD медленнее и имеет проблему таймаута - если кластер остаётся недоступным
дольше, чем [nbd_timeout](../config/client.ru.md#nbd_timeout), NBD-устройство отключается
и ломает поды, использующие его.
## Возможности
CSI-плагин Vitastor поддерживает:
@@ -27,5 +35,8 @@ CSI-плагин Vitastor поддерживает:
- Сырые блочные RWX (ReadWriteMany) тома. Пример: [PVC](../../csi/deploy/example-pvc-block.yaml), [под](../../csi/deploy/example-test-pod-block.yaml)
- Расширение размера томов
- Снимки томов. Пример: [класс снимков](../../csi/deploy/example-snapshot-class.yaml), [снимок](../../csi/deploy/example-snapshot.yaml), [клон снимка](../../csi/deploy/example-snapshot-clone.yaml)
- Способы подключения устройств [VDUSE](../usage/qemu.ru.md#vduse) (предпочитаемый) и [NBD](../usage/nbd.ru.md)
- Обновление при использовании VDUSE - новые процессы-обработчики устройств успешно перезапускаются вместе с самими подами CSI
- Несколько кластеров через задание нескольких файлов конфигурации в ConfigMap.
Не забывайте, что для использования снимков нужно сначала установить [контроллер снимков и CRD](https://kubernetes-csi.github.io/docs/snapshot-controller.html#deployment).

View File

@@ -18,7 +18,7 @@
stable version from 0.9.x branch instead of 1.x
- 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`
- Install packages: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
## CentOS

View File

@@ -18,7 +18,7 @@
установить последнюю стабильную версию из ветки 0.9.x вместо 1.x
- Для Debian 10 (Buster) также включите репозиторий backports:
`deb http://deb.debian.org/debian buster-backports main`
- Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu`
- Установите пакеты: `apt update; apt install vitastor lp-solve etcd linux-image-amd64 qemu-system-x86`
## CentOS

View File

@@ -6,10 +6,10 @@
# Proxmox VE
To enable Vitastor support in Proxmox Virtual Environment (6.4-8.0 are supported):
To enable Vitastor support in Proxmox Virtual Environment (6.4-8.1 are supported):
- Add the corresponding Vitastor Debian repository into sources.list on Proxmox hosts:
bookworm for 8.0, bullseye for 7.4, pve7.3 for 7.3, pve7.2 for 7.2, pve7.1 for 7.1, buster for 6.4
bookworm for 8.1, pve8.0 for 8.0, bullseye for 7.4, pve7.3 for 7.3, pve7.2 for 7.2, pve7.1 for 7.1, buster for 6.4
- Install vitastor-client, pve-qemu-kvm, pve-storage-vitastor (* or see note) packages from Vitastor repository
- Define storage in `/etc/pve/storage.cfg` (see below)
- Block network access from VMs to Vitastor network (to OSDs and etcd),

View File

@@ -6,10 +6,10 @@
# Proxmox VE
Чтобы подключить Vitastor к Proxmox Virtual Environment (поддерживаются версии 6.4-8.0):
Чтобы подключить Vitastor к Proxmox Virtual Environment (поддерживаются версии 6.4-8.1):
- Добавьте соответствующий Debian-репозиторий Vitastor в sources.list на хостах Proxmox:
bookworm для 8.0, bullseye для 7.4, pve7.3 для 7.3, pve7.2 для 7.2, pve7.1 для 7.1, buster для 6.4
bookworm для 8.1, pve8.0 для 8.0, bullseye для 7.4, pve7.3 для 7.3, pve7.2 для 7.2, pve7.1 для 7.1, buster для 6.4
- Установите пакеты vitastor-client, pve-qemu-kvm, pve-storage-vitastor (* или см. сноску) из репозитория Vitastor
- Определите тип хранилища в `/etc/pve/storage.cfg` (см. ниже)
- Обязательно заблокируйте доступ от виртуальных машин к сети Vitastor (OSD и etcd), т.к. Vitastor (пока) не поддерживает аутентификацию

View File

@@ -54,7 +54,8 @@
виртуальные диски, их снимки и клоны.
- **Драйвер QEMU** — подключаемый модуль QEMU, позволяющий QEMU/KVM виртуальным машинам работать
с виртуальными дисками Vitastor напрямую из пространства пользователя с помощью клиентской
библиотеки, без необходимости отображения дисков в виде блочных устройств.
библиотеки, без необходимости отображения дисков в виде блочных устройств. Тот же драйвер
позволяет подключать диски в систему через [VDUSE](../usage/qemu.ru.md#vduse).
- **vitastor-nbd** — утилита, позволяющая монтировать образы Vitastor в виде блочных устройств
с помощью NBD (Network Block Device), на самом деле скорее работающего как "BUSE"
(Block Device In Userspace). Модуля ядра Linux для выполнения той же задачи в Vitastor нет

View File

@@ -28,7 +28,8 @@ It supports the following commands:
Global options:
```
--etcd_address ADDR Etcd connection address
--config_file FILE Path to Vitastor configuration file
--etcd_address URL 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)

View File

@@ -27,7 +27,8 @@ vitastor-cli - интерфейс командной строки для адм
Глобальные опции:
```
--etcd_address ADDR Адрес соединения с etcd
--config_file FILE Путь к файлу конфигурации Vitastor
--etcd_address URL Адрес соединения с etcd
--iodepth N Отправлять параллельно N операций на каждый OSD (по умолчанию 32)
--parallel_osds M Работать параллельно с M OSD (по умолчанию 4)
--progress 1|0 Печатать прогресс выполнения (по умолчанию 1)

View File

@@ -17,6 +17,7 @@ It supports the following commands:
- [purge](#purge)
- [read-sb](#read-sb)
- [write-sb](#write-sb)
- [update-sb](#update-sb)
- [udev](#udev)
- [exec-osd](#exec-osd)
- [pre-exec](#pre-exec)
@@ -182,6 +183,14 @@ Try to read Vitastor OSD superblock from `<device>` and print it in JSON format.
Read JSON from STDIN and write it into Vitastor OSD superblock on `<device>`.
## update-sb
`vitastor-disk update-sb <device> [--force] [--<parameter> <value>] [...]`
Read Vitastor OSD superblock from <device>, update parameters in it and write it back.
`--force` allows to ignore validation errors.
## udev
`vitastor-disk udev <device>`

View File

@@ -17,6 +17,7 @@ vitastor-disk - инструмент командной строки для уп
- [purge](#purge)
- [read-sb](#read-sb)
- [write-sb](#write-sb)
- [update-sb](#update-sb)
- [udev](#udev)
- [exec-osd](#exec-osd)
- [pre-exec](#pre-exec)
@@ -187,6 +188,15 @@ throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.
Прочитать JSON со стандартного ввода и записать его в суперблок OSD на диск `<device>`.
## update-sb
`vitastor-disk update-sb <device> [--force] [--<параметр> <значение>] [...]`
Прочитать суперблок OSD с диска `<device>`, изменить в нём заданные параметры и записать обратно.
Опция `--force` позволяет читать суперблок, даже если он считается некорректным
из-за ошибок валидации.
## udev
`vitastor-disk udev <device>`

View File

@@ -11,25 +11,25 @@ NBD stands for "Network Block Device", but in fact it also functions as "BUSE"
NBD slighly lowers the performance due to additional overhead, but performance still
remains decent (see an example [here](../performance/comparison1.en.md#vitastor-0-4-0-nbd)).
Vitastor Kubernetes CSI driver is based on NBD.
See also [VDUSE](qemu.en.md#vduse) as a better alternative to NBD.
See also [VDUSE](qemu.en.md#vduse).
Vitastor Kubernetes CSI driver uses NBD when VDUSE is unavailable.
## Map image
To create a local block device for a Vitastor image run:
```
vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
vitastor-nbd map --image testimg
```
It will output a block device name like /dev/nbd0 which you can then use as a normal disk.
You can also use `--pool <POOL> --inode <INODE> --size <SIZE>` instead of `--image <IMAGE>` if you want.
Additional options for map command:
vitastor-nbd supports all usual Vitastor configuration options like `--config_file <path_to_config>` plus NBD-specific:
* `--nbd_timeout 30` \
* `--nbd_timeout 300` \
Timeout for I/O operations in seconds after exceeding which the kernel stops
the device. You can set it to 0 to disable the timeout, but beware that you
won't be able to stop the device at all if vitastor-nbd process dies.
@@ -44,6 +44,9 @@ Additional options for map command:
* `--foreground 1` \
Stay in foreground, do not daemonize.
Note that `nbd_timeout`, `nbd_max_devices` and `nbd_max_part` options may also be specified
in `/etc/vitastor/vitastor.conf` or in other configuration file specified with `--config_file`.
## Unmap image
To unmap the device run:

View File

@@ -14,16 +14,16 @@ NBD на данный момент необходимо, чтобы монтир
NBD немного снижает производительность из-за дополнительных копирований памяти,
но она всё равно остаётся на неплохом уровне (см. для примера [тест](../performance/comparison1.ru.md#vitastor-0-4-0-nbd)).
CSI-драйвер Kubernetes Vitastor основан на NBD.
Смотрите также [VDUSE](qemu.ru.md#vduse), как лучшую альтернативу NBD.
Смотрите также [VDUSE](qemu.ru.md#vduse).
CSI-драйвер Kubernetes Vitastor использует NBD, когда VDUSE недоступен.
## Подключить устройство
Чтобы создать локальное блочное устройство для образа, выполните команду:
```
vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
vitastor-nbd map --image testimg
```
Команда напечатает название блочного устройства вида /dev/nbd0, которое потом можно
@@ -32,7 +32,8 @@ 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`.
Дополнительные опции для команды подключения NBD-устройства:
vitastor-nbd поддерживает все обычные опции Vitastor, например, `--config_file <path_to_config>`,
плюс специфичные для NBD:
* `--nbd_timeout 30` \
Максимальное время выполнения любой операции чтения/записи в секундах, при
@@ -53,6 +54,10 @@ vitastor-nbd map --etcd_address 10.115.0.10:2379/v3 --image testimg
* `--foreground 1` \
Не уводить процесс в фоновый режим.
Обратите внимание, что опции `nbd_timeout`, `nbd_max_devices` и `nbd_max_part` можно
также задавать в `/etc/vitastor/vitastor.conf` или в другом файле конфигурации,
заданном опцией `--config_file`.
## Отключить устройство
Для отключения устройства выполните:

View File

@@ -23,7 +23,7 @@ balancer or any failover method you want to in that case.
vitastor-nfs usage:
```
vitastor-nfs [--etcd_address ADDR] [OTHER OPTIONS]
vitastor-nfs [STANDARD OPTIONS] [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)

View File

@@ -22,7 +22,7 @@
Использование vitastor-nfs:
```
vitastor-nfs [--etcd_address ADDR] [ДРУГИЕ ОПЦИИ]
vitastor-nfs [СТАНДАРТНЫЕ ОПЦИИ] [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)

View File

@@ -146,7 +146,7 @@ Example performance comparison:
| 4k random read Q1 | 9600 iops | 7640 iops | 7780 iops |
To try VDUSE you need at least Linux 5.15, built with VDUSE support
(CONFIG_VIRTIO_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
(CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
Debian Linux kernels have these options disabled by now, so if you want to try it on Debian,
use a kernel from Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/), Proxmox,

View File

@@ -149,7 +149,7 @@ VDUSE - на данный момент лучший интерфейс для п
| 4k случайное чтение Q1 | 9600 iops | 7640 iops | 7780 iops |
Чтобы попробовать VDUSE, вам нужно ядро Linux как минимум версии 5.15, собранное с поддержкой
VDUSE (CONFIG_VIRTIO_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
VDUSE (CONFIG_VDPA=m, CONFIG_VDPA_USER=m, CONFIG_VIRTIO_VDPA=m).
В ядрах в Debian Linux поддержка пока отключена по умолчанию, так что чтобы попробовать VDUSE
на Debian, поставьте ядро из Ubuntu [kernel-ppa/mainline](https://kernel.ubuntu.com/~kernel-ppa/mainline/),

View File

@@ -1,6 +1,6 @@
{
"name": "vitastor-mon",
"version": "1.2.0",
"version": "1.3.1",
"description": "Vitastor SDS monitor service",
"main": "mon-main.js",
"scripts": {

View File

@@ -50,7 +50,7 @@ from cinder.volume import configuration
from cinder.volume import driver
from cinder.volume import volume_utils
VERSION = '1.2.0'
VERSION = '1.3.1'
LOG = logging.getLogger(__name__)

View File

@@ -0,0 +1,190 @@
Index: pve-qemu-kvm-8.1.2/block/meson.build
===================================================================
--- pve-qemu-kvm-8.1.2.orig/block/meson.build
+++ pve-qemu-kvm-8.1.2/block/meson.build
@@ -123,6 +123,7 @@ foreach m : [
[libnfs, 'nfs', files('nfs.c')],
[libssh, 'ssh', files('ssh.c')],
[rbd, 'rbd', files('rbd.c')],
+ [vitastor, 'vitastor', files('vitastor.c')],
]
if m[0].found()
module_ss = ss.source_set()
Index: pve-qemu-kvm-8.1.2/meson.build
===================================================================
--- pve-qemu-kvm-8.1.2.orig/meson.build
+++ pve-qemu-kvm-8.1.2/meson.build
@@ -1303,6 +1303,26 @@ if not get_option('rbd').auto() or have_
endif
endif
+vitastor = not_found
+if not get_option('vitastor').auto() or have_block
+ libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
+ required: get_option('vitastor'))
+ if libvitastor_client.found()
+ if cc.links('''
+ #include <vitastor_c.h>
+ int main(void) {
+ vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
+ return 0;
+ }''', dependencies: libvitastor_client)
+ vitastor = declare_dependency(dependencies: libvitastor_client)
+ elif get_option('vitastor').enabled()
+ error('could not link libvitastor_client')
+ else
+ warning('could not link libvitastor_client, disabling')
+ endif
+ endif
+endif
+
glusterfs = not_found
glusterfs_ftruncate_has_stat = false
glusterfs_iocb_has_stat = false
@@ -2123,6 +2143,7 @@ if numa.found()
endif
config_host_data.set('CONFIG_OPENGL', opengl.found())
config_host_data.set('CONFIG_RBD', rbd.found())
+config_host_data.set('CONFIG_VITASTOR', vitastor.found())
config_host_data.set('CONFIG_RDMA', rdma.found())
config_host_data.set('CONFIG_SAFESTACK', get_option('safe_stack'))
config_host_data.set('CONFIG_SDL', sdl.found())
@@ -4298,6 +4319,7 @@ summary_info += {'fdt support': fd
summary_info += {'libcap-ng support': libcap_ng}
summary_info += {'bpf support': libbpf}
summary_info += {'rbd support': rbd}
+summary_info += {'vitastor support': vitastor}
summary_info += {'smartcard support': cacard}
summary_info += {'U2F support': u2f}
summary_info += {'libusb': libusb}
Index: pve-qemu-kvm-8.1.2/meson_options.txt
===================================================================
--- pve-qemu-kvm-8.1.2.orig/meson_options.txt
+++ pve-qemu-kvm-8.1.2/meson_options.txt
@@ -186,6 +186,8 @@ option('lzo', type : 'feature', value :
description: 'lzo compression support')
option('rbd', type : 'feature', value : 'auto',
description: 'Ceph block device driver')
+option('vitastor', type : 'feature', value : 'auto',
+ description: 'Vitastor block device driver')
option('opengl', type : 'feature', value : 'auto',
description: 'OpenGL support')
option('rdma', type : 'feature', value : 'auto',
Index: pve-qemu-kvm-8.1.2/qapi/block-core.json
===================================================================
--- pve-qemu-kvm-8.1.2.orig/qapi/block-core.json
+++ pve-qemu-kvm-8.1.2/qapi/block-core.json
@@ -3403,7 +3403,7 @@
'raw', 'rbd',
{ 'name': 'replication', 'if': 'CONFIG_REPLICATION' },
'pbs',
- 'ssh', 'throttle', 'vdi', 'vhdx',
+ 'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor',
{ 'name': 'virtio-blk-vfio-pci', 'if': 'CONFIG_BLKIO' },
{ 'name': 'virtio-blk-vhost-user', 'if': 'CONFIG_BLKIO' },
{ 'name': 'virtio-blk-vhost-vdpa', 'if': 'CONFIG_BLKIO' },
@@ -4465,6 +4465,28 @@
'*server': ['InetSocketAddressBase'] } }
##
+# @BlockdevOptionsVitastor:
+#
+# Driver specific block device options for vitastor
+#
+# @image: Image name
+# @inode: Inode number
+# @pool: Pool ID
+# @size: Desired image size in bytes
+# @config-path: Path to Vitastor configuration
+# @etcd-host: etcd connection address(es)
+# @etcd-prefix: etcd key/value prefix
+##
+{ 'struct': 'BlockdevOptionsVitastor',
+ 'data': { '*inode': 'uint64',
+ '*pool': 'uint64',
+ '*size': 'uint64',
+ '*image': 'str',
+ '*config-path': 'str',
+ '*etcd-host': 'str',
+ '*etcd-prefix': 'str' } }
+
+##
# @ReplicationMode:
#
# An enumeration of replication modes.
@@ -4923,6 +4945,7 @@
'throttle': 'BlockdevOptionsThrottle',
'vdi': 'BlockdevOptionsGenericFormat',
'vhdx': 'BlockdevOptionsGenericFormat',
+ 'vitastor': 'BlockdevOptionsVitastor',
'virtio-blk-vfio-pci':
{ 'type': 'BlockdevOptionsVirtioBlkVfioPci',
'if': 'CONFIG_BLKIO' },
@@ -5360,6 +5383,17 @@
'*encrypt' : 'RbdEncryptionCreateOptions' } }
##
+# @BlockdevCreateOptionsVitastor:
+#
+# Driver specific image creation options for Vitastor.
+#
+# @size: Size of the virtual disk in bytes
+##
+{ 'struct': 'BlockdevCreateOptionsVitastor',
+ 'data': { 'location': 'BlockdevOptionsVitastor',
+ 'size': 'size' } }
+
+##
# @BlockdevVmdkSubformat:
#
# Subformat options for VMDK images
@@ -5581,6 +5615,7 @@
'ssh': 'BlockdevCreateOptionsSsh',
'vdi': 'BlockdevCreateOptionsVdi',
'vhdx': 'BlockdevCreateOptionsVhdx',
+ 'vitastor': 'BlockdevCreateOptionsVitastor',
'vmdk': 'BlockdevCreateOptionsVmdk',
'vpc': 'BlockdevCreateOptionsVpc'
} }
Index: pve-qemu-kvm-8.1.2/scripts/ci/org.centos/stream/8/x86_64/configure
===================================================================
--- pve-qemu-kvm-8.1.2.orig/scripts/ci/org.centos/stream/8/x86_64/configure
+++ pve-qemu-kvm-8.1.2/scripts/ci/org.centos/stream/8/x86_64/configure
@@ -30,7 +30,7 @@
--with-suffix="qemu-kvm" \
--firmwarepath=/usr/share/qemu-firmware \
--target-list="x86_64-softmmu" \
---block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
+--block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,vitastor,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
--audio-drv-list="" \
--block-drv-ro-whitelist="vmdk,vhdx,vpc,https,ssh" \
--with-coroutine=ucontext \
@@ -176,6 +176,7 @@
--enable-opengl \
--enable-pie \
--enable-rbd \
+--enable-vitastor \
--enable-rdma \
--enable-seccomp \
--enable-snappy \
Index: pve-qemu-kvm-8.1.2/scripts/meson-buildoptions.sh
===================================================================
--- pve-qemu-kvm-8.1.2.orig/scripts/meson-buildoptions.sh
+++ pve-qemu-kvm-8.1.2/scripts/meson-buildoptions.sh
@@ -153,6 +153,7 @@ meson_options_help() {
printf "%s\n" ' qed qed image format support'
printf "%s\n" ' qga-vss build QGA VSS support (broken with MinGW)'
printf "%s\n" ' rbd Ceph block device driver'
+ printf "%s\n" ' vitastor Vitastor block device driver'
printf "%s\n" ' rdma Enable RDMA-based migration'
printf "%s\n" ' replication replication support'
printf "%s\n" ' sdl SDL user interface'
@@ -416,6 +417,8 @@ _meson_option_parse() {
--disable-qom-cast-debug) printf "%s" -Dqom_cast_debug=false ;;
--enable-rbd) printf "%s" -Drbd=enabled ;;
--disable-rbd) printf "%s" -Drbd=disabled ;;
+ --enable-vitastor) printf "%s" -Dvitastor=enabled ;;
+ --disable-vitastor) printf "%s" -Dvitastor=disabled ;;
--enable-rdma) printf "%s" -Drdma=enabled ;;
--disable-rdma) printf "%s" -Drdma=disabled ;;
--enable-replication) printf "%s" -Dreplication=enabled ;;

View File

@@ -0,0 +1,190 @@
diff --git a/block/meson.build b/block/meson.build
index 529fc172c6..d542dc0609 100644
--- a/block/meson.build
+++ b/block/meson.build
@@ -110,6 +110,7 @@ foreach m : [
[libnfs, 'nfs', files('nfs.c')],
[libssh, 'ssh', files('ssh.c')],
[rbd, 'rbd', files('rbd.c')],
+ [vitastor, 'vitastor', files('vitastor.c')],
]
if m[0].found()
module_ss = ss.source_set()
diff --git a/meson.build b/meson.build
index a9c4f28247..8496cf13f1 100644
--- a/meson.build
+++ b/meson.build
@@ -1303,6 +1303,26 @@ if not get_option('rbd').auto() or have_block
endif
endif
+vitastor = not_found
+if not get_option('vitastor').auto() or have_block
+ libvitastor_client = cc.find_library('vitastor_client', has_headers: ['vitastor_c.h'],
+ required: get_option('vitastor'))
+ if libvitastor_client.found()
+ if cc.links('''
+ #include <vitastor_c.h>
+ int main(void) {
+ vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
+ return 0;
+ }''', dependencies: libvitastor_client)
+ vitastor = declare_dependency(dependencies: libvitastor_client)
+ elif get_option('vitastor').enabled()
+ error('could not link libvitastor_client')
+ else
+ warning('could not link libvitastor_client, disabling')
+ endif
+ endif
+endif
+
glusterfs = not_found
glusterfs_ftruncate_has_stat = false
glusterfs_iocb_has_stat = false
@@ -2119,6 +2139,7 @@ if numa.found()
endif
config_host_data.set('CONFIG_OPENGL', opengl.found())
config_host_data.set('CONFIG_RBD', rbd.found())
+config_host_data.set('CONFIG_VITASTOR', vitastor.found())
config_host_data.set('CONFIG_RDMA', rdma.found())
config_host_data.set('CONFIG_SAFESTACK', get_option('safe_stack'))
config_host_data.set('CONFIG_SDL', sdl.found())
@@ -4286,6 +4307,7 @@ summary_info += {'fdt support': fdt_opt == 'disabled' ? false : fdt_opt}
summary_info += {'libcap-ng support': libcap_ng}
summary_info += {'bpf support': libbpf}
summary_info += {'rbd support': rbd}
+summary_info += {'vitastor support': vitastor}
summary_info += {'smartcard support': cacard}
summary_info += {'U2F support': u2f}
summary_info += {'libusb': libusb}
diff --git a/meson_options.txt b/meson_options.txt
index ae6d8f469d..e3d9f8404d 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -186,6 +186,8 @@ option('lzo', type : 'feature', value : 'auto',
description: 'lzo compression support')
option('rbd', type : 'feature', value : 'auto',
description: 'Ceph block device driver')
+option('vitastor', type : 'feature', value : 'auto',
+ description: 'Vitastor block device driver')
option('opengl', type : 'feature', value : 'auto',
description: 'OpenGL support')
option('rdma', type : 'feature', value : 'auto',
diff --git a/qapi/block-core.json b/qapi/block-core.json
index 2b1d493d6e..90673fdbdc 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -3146,7 +3146,7 @@
'parallels', 'preallocate', 'qcow', 'qcow2', 'qed', 'quorum',
'raw', 'rbd',
{ 'name': 'replication', 'if': 'CONFIG_REPLICATION' },
- 'ssh', 'throttle', 'vdi', 'vhdx',
+ 'ssh', 'throttle', 'vdi', 'vhdx', 'vitastor',
{ 'name': 'virtio-blk-vfio-pci', 'if': 'CONFIG_BLKIO' },
{ 'name': 'virtio-blk-vhost-user', 'if': 'CONFIG_BLKIO' },
{ 'name': 'virtio-blk-vhost-vdpa', 'if': 'CONFIG_BLKIO' },
@@ -4196,6 +4196,28 @@
'*key-secret': 'str',
'*server': ['InetSocketAddressBase'] } }
+##
+# @BlockdevOptionsVitastor:
+#
+# Driver specific block device options for vitastor
+#
+# @image: Image name
+# @inode: Inode number
+# @pool: Pool ID
+# @size: Desired image size in bytes
+# @config-path: Path to Vitastor configuration
+# @etcd-host: etcd connection address(es)
+# @etcd-prefix: etcd key/value prefix
+##
+{ 'struct': 'BlockdevOptionsVitastor',
+ 'data': { '*inode': 'uint64',
+ '*pool': 'uint64',
+ '*size': 'uint64',
+ '*image': 'str',
+ '*config-path': 'str',
+ '*etcd-host': 'str',
+ '*etcd-prefix': 'str' } }
+
##
# @ReplicationMode:
#
@@ -4654,6 +4676,7 @@
'throttle': 'BlockdevOptionsThrottle',
'vdi': 'BlockdevOptionsGenericFormat',
'vhdx': 'BlockdevOptionsGenericFormat',
+ 'vitastor': 'BlockdevOptionsVitastor',
'virtio-blk-vfio-pci':
{ 'type': 'BlockdevOptionsVirtioBlkVfioPci',
'if': 'CONFIG_BLKIO' },
@@ -5089,6 +5112,17 @@
'*cluster-size' : 'size',
'*encrypt' : 'RbdEncryptionCreateOptions' } }
+##
+# @BlockdevCreateOptionsVitastor:
+#
+# Driver specific image creation options for Vitastor.
+#
+# @size: Size of the virtual disk in bytes
+##
+{ 'struct': 'BlockdevCreateOptionsVitastor',
+ 'data': { 'location': 'BlockdevOptionsVitastor',
+ 'size': 'size' } }
+
##
# @BlockdevVmdkSubformat:
#
@@ -5311,6 +5345,7 @@
'ssh': 'BlockdevCreateOptionsSsh',
'vdi': 'BlockdevCreateOptionsVdi',
'vhdx': 'BlockdevCreateOptionsVhdx',
+ 'vitastor': 'BlockdevCreateOptionsVitastor',
'vmdk': 'BlockdevCreateOptionsVmdk',
'vpc': 'BlockdevCreateOptionsVpc'
} }
diff --git a/scripts/ci/org.centos/stream/8/x86_64/configure b/scripts/ci/org.centos/stream/8/x86_64/configure
index d02b09a4b9..f0b5fbfef3 100755
--- a/scripts/ci/org.centos/stream/8/x86_64/configure
+++ b/scripts/ci/org.centos/stream/8/x86_64/configure
@@ -30,7 +30,7 @@
--with-suffix="qemu-kvm" \
--firmwarepath=/usr/share/qemu-firmware \
--target-list="x86_64-softmmu" \
---block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
+--block-drv-rw-whitelist="qcow2,raw,file,host_device,nbd,iscsi,rbd,vitastor,blkdebug,luks,null-co,nvme,copy-on-read,throttle,gluster" \
--audio-drv-list="" \
--block-drv-ro-whitelist="vmdk,vhdx,vpc,https,ssh" \
--with-coroutine=ucontext \
@@ -176,6 +176,7 @@
--enable-opengl \
--enable-pie \
--enable-rbd \
+--enable-vitastor \
--enable-rdma \
--enable-seccomp \
--enable-snappy \
diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh
index d7020af175..94958eb6fa 100644
--- a/scripts/meson-buildoptions.sh
+++ b/scripts/meson-buildoptions.sh
@@ -153,6 +153,7 @@ meson_options_help() {
printf "%s\n" ' qed qed image format support'
printf "%s\n" ' qga-vss build QGA VSS support (broken with MinGW)'
printf "%s\n" ' rbd Ceph block device driver'
+ printf "%s\n" ' vitastor Vitastor block device driver'
printf "%s\n" ' rdma Enable RDMA-based migration'
printf "%s\n" ' replication replication support'
printf "%s\n" ' sdl SDL user interface'
@@ -416,6 +417,8 @@ _meson_option_parse() {
--disable-qom-cast-debug) printf "%s" -Dqom_cast_debug=false ;;
--enable-rbd) printf "%s" -Drbd=enabled ;;
--disable-rbd) printf "%s" -Drbd=disabled ;;
+ --enable-vitastor) printf "%s" -Dvitastor=enabled ;;
+ --disable-vitastor) printf "%s" -Dvitastor=disabled ;;
--enable-rdma) printf "%s" -Drdma=enabled ;;
--disable-rdma) printf "%s" -Drdma=disabled ;;
--enable-replication) printf "%s" -Dreplication=enabled ;;

View File

@@ -24,4 +24,4 @@ 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-1.2.0/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.2.0$(rpm --eval '%dist').tar.gz *
tar --transform 's#^#vitastor-1.3.1/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-1.3.1$(rpm --eval '%dist').tar.gz *

View File

@@ -15,6 +15,7 @@ RUN yumdownloader --disablerepo=centos-sclo-rh --source fio
RUN rpm --nomd5 -i fio*.src.rpm
RUN rm -f /etc/yum.repos.d/CentOS-Media.repo
RUN cd ~/rpmbuild/SPECS && yum-builddep -y fio.spec
RUN yum -y install cmake3
ADD https://vitastor.io/rpms/liburing-el7/liburing-0.7-2.el7.src.rpm /root
@@ -35,7 +36,7 @@ ADD . /root/vitastor
RUN set -e; \
cd /root/vitastor/rpm; \
sh build-tarball.sh; \
cp /root/vitastor-1.2.0.el7.tar.gz ~/rpmbuild/SOURCES; \
cp /root/vitastor-1.3.1.el7.tar.gz ~/rpmbuild/SOURCES; \
cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
cd ~/rpmbuild/SPECS/; \
rpmbuild -ba vitastor.spec; \

View File

@@ -1,11 +1,11 @@
Name: vitastor
Version: 1.2.0
Version: 1.3.1
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-1.2.0.el7.tar.gz
Source0: vitastor-1.3.1.el7.tar.gz
BuildRequires: liburing-devel >= 0.6
BuildRequires: gperftools-devel
@@ -16,7 +16,7 @@ BuildRequires: jerasure-devel
BuildRequires: libisa-l-devel
BuildRequires: gf-complete-devel
BuildRequires: libibverbs-devel
BuildRequires: cmake
BuildRequires: cmake3
Requires: vitastor-osd = %{version}-%{release}
Requires: vitastor-mon = %{version}-%{release}
Requires: vitastor-client = %{version}-%{release}
@@ -94,7 +94,7 @@ Vitastor fio drivers for benchmarking.
%build
. /opt/rh/devtoolset-9/enable
%cmake .
%cmake3 .
%make_build

View File

@@ -35,7 +35,7 @@ ADD . /root/vitastor
RUN set -e; \
cd /root/vitastor/rpm; \
sh build-tarball.sh; \
cp /root/vitastor-1.2.0.el8.tar.gz ~/rpmbuild/SOURCES; \
cp /root/vitastor-1.3.1.el8.tar.gz ~/rpmbuild/SOURCES; \
cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
cd ~/rpmbuild/SPECS/; \
rpmbuild -ba vitastor.spec; \

View File

@@ -1,11 +1,11 @@
Name: vitastor
Version: 1.2.0
Version: 1.3.1
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-1.2.0.el8.tar.gz
Source0: vitastor-1.3.1.el8.tar.gz
BuildRequires: liburing-devel >= 0.6
BuildRequires: gperftools-devel

View File

@@ -18,7 +18,7 @@ ADD . /root/vitastor
RUN set -e; \
cd /root/vitastor/rpm; \
sh build-tarball.sh; \
cp /root/vitastor-1.2.0.el9.tar.gz ~/rpmbuild/SOURCES; \
cp /root/vitastor-1.3.1.el9.tar.gz ~/rpmbuild/SOURCES; \
cp vitastor-el9.spec ~/rpmbuild/SPECS/vitastor.spec; \
cd ~/rpmbuild/SPECS/; \
rpmbuild -ba vitastor.spec; \

View File

@@ -1,11 +1,11 @@
Name: vitastor
Version: 1.2.0
Version: 1.3.1
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-1.2.0.el9.tar.gz
Source0: vitastor-1.3.1.el9.tar.gz
BuildRequires: liburing-devel >= 0.6
BuildRequires: gperftools-devel

View File

@@ -16,7 +16,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
endif()
add_definitions(-DVERSION="1.2.0")
add_definitions(-DVERSION="1.3.1")
add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -I ${CMAKE_SOURCE_DIR}/src)
add_link_options(-fno-omit-frame-pointer)
if (${WITH_ASAN})

View File

@@ -732,8 +732,9 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
resume:
while (pos < bs->journal.block_size)
{
journal_entry *je = (journal_entry*)((uint8_t*)buf + proc_pos - done_pos + pos);
if (je->magic != JOURNAL_MAGIC || je_crc32(je) != je->crc32 ||
auto buf_pos = proc_pos - done_pos + pos;
journal_entry *je = (journal_entry*)((uint8_t*)buf + buf_pos);
if (je->magic != JOURNAL_MAGIC || buf_pos+je->size > len || je_crc32(je) != je->crc32 ||
je->type < JE_MIN || je->type > JE_MAX || started && je->crc32_prev != crc32_last)
{
if (pos == 0)

View File

@@ -144,8 +144,10 @@ journal_entry* prefill_single_journal_entry(journal_t & journal, uint16_t type,
journal.sector_info[journal.cur_sector].written = false;
journal.sector_info[journal.cur_sector].offset = journal.next_free;
journal.in_sector_pos = 0;
journal.next_free = (journal.next_free+journal.block_size) < journal.len ? journal.next_free + journal.block_size : journal.block_size;
assert(journal.next_free != journal.used_start);
auto next_next_free = (journal.next_free+journal.block_size) < journal.len ? journal.next_free + journal.block_size : journal.block_size;
// double check that next_free doesn't cross used_start from the left
assert(journal.next_free >= journal.used_start || next_next_free < journal.used_start);
journal.next_free = next_next_free;
memset(journal.inmemory
? (uint8_t*)journal.buffer + journal.sector_info[journal.cur_sector].offset
: (uint8_t*)journal.sector_buf + journal.block_size*journal.cur_sector, 0, journal.block_size);

View File

@@ -386,7 +386,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
sqe, dsk.data_fd, PRIV(op)->iov_zerofill, vcnt, dsk.data_offset + (loc << dsk.block_order) + op->offset - stripe_offset
);
PRIV(op)->pending_ops = 1;
if (immediate_commit != IMMEDIATE_ALL && !(dirty_it->second.state & BS_ST_INSTANT))
if (!(dirty_it->second.state & BS_ST_INSTANT))
{
unstable_unsynced++;
}
@@ -412,7 +412,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
sizeof(journal_entry_big_write) + dsk.clean_dyn_size, 0)
|| !space_check.check_available(op, 1,
sizeof(journal_entry_small_write) + dyn_size,
(unstable_writes.size()+unstable_unsynced)*journal.block_size))
op->len + (unstable_writes.size()+unstable_unsynced)*journal.block_size))
{
return 0;
}
@@ -462,6 +462,8 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
exit(1);
}
}
// double check that next_free doesn't cross used_start from the left
assert(journal.next_free >= journal.used_start || next_next_free < journal.used_start);
journal.next_free = next_next_free;
je->oid = op->oid;
je->version = op->version;
@@ -499,13 +501,13 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
}
dirty_it->second.location = journal.next_free;
dirty_it->second.state = (dirty_it->second.state & ~BS_ST_WORKFLOW_MASK) | BS_ST_SUBMITTED;
journal.next_free += op->len;
if (journal.next_free >= journal.len)
{
journal.next_free = dsk.journal_block_size;
assert(journal.next_free != journal.used_start);
}
if (immediate_commit == IMMEDIATE_NONE && !(dirty_it->second.state & BS_ST_INSTANT))
next_next_free = journal.next_free + op->len;
if (next_next_free >= journal.len)
next_next_free = dsk.journal_block_size;
// double check that next_free doesn't cross used_start from the left
assert(journal.next_free >= journal.used_start || next_next_free < journal.used_start);
journal.next_free = next_next_free;
if (!(dirty_it->second.state & BS_ST_INSTANT))
{
unstable_unsynced++;
}
@@ -596,11 +598,11 @@ resume_4:
{
auto & unstab = unstable_writes[op->oid];
unstab = unstab < op->version ? op->version : unstab;
}
else if (!is_instant)
{
unstable_unsynced--;
assert(unstable_unsynced >= 0);
if (!is_instant)
{
unstable_unsynced--;
assert(unstable_unsynced >= 0);
}
}
dirty_it->second.state = (dirty_it->second.state & ~BS_ST_WORKFLOW_MASK)
| (imm ? BS_ST_SYNCED : BS_ST_WRITTEN);

View File

@@ -116,7 +116,8 @@ static const char* help_text =
"Use vitastor-cli --help <command> for command details or vitastor-cli --help --all for all details.\n"
"\n"
"GLOBAL OPTIONS:\n"
" --etcd_address <etcd_address>\n"
" --config_file FILE Path to Vitastor configuration file\n"
" --etcd_address URL Etcd connection address\n"
" --iodepth N Send N operations in parallel to each OSD when possible (default 32)\n"
" --parallel_osds M Work with M osds in parallel when possible (default 4)\n"
" --progress 1|0 Report progress (default 1)\n"

View File

@@ -127,6 +127,10 @@ static const char *help_text =
"vitastor-disk write-sb <device>\n"
" Read JSON from STDIN and write it into Vitastor OSD superblock on <device>.\n"
"\n"
"vitastor-disk update-sb <device> [--force] [--<parameter> <value>] [...]\n"
" Read Vitastor OSD superblock from <device>, update parameters in it and write it back.\n"
" --force allows to ignore validation errors.\n"
"\n"
"vitastor-disk udev <device>\n"
" Try to read Vitastor OSD superblock from <device> and print variables for udev.\n"
"\n"
@@ -363,6 +367,15 @@ int main(int argc, char *argv[])
}
return self.write_sb(cmd[1]);
}
else if (!strcmp(cmd[0], "update-sb"))
{
if (cmd.size() != 2)
{
fprintf(stderr, "Exactly 1 device path argument is required\n");
return 1;
}
return self.update_sb(cmd[1]);
}
else if (!strcmp(cmd[0], "start") || !strcmp(cmd[0], "stop") ||
!strcmp(cmd[0], "restart") || !strcmp(cmd[0], "enable") || !strcmp(cmd[0], "disable"))
{

View File

@@ -109,6 +109,7 @@ struct disk_tool_t
int udev_import(std::string device);
int read_sb(std::string device);
int write_sb(std::string device);
int update_sb(std::string device);
int exec_osd(std::string device);
int systemd_start_stop_osds(const std::vector<std::string> & cmd, const std::vector<std::string> & devices);
int pre_exec_osd(std::string device);

View File

@@ -86,6 +86,24 @@ int disk_tool_t::write_sb(std::string device)
return !write_osd_superblock(device, params);
}
int disk_tool_t::update_sb(std::string device)
{
json11::Json sb = read_osd_superblock(device, true, options.find("force") != options.end());
if (sb.is_null())
{
return 1;
}
auto sb_obj = sb["params"].object_items();
for (auto & kv: options)
{
if (kv.first != "force")
{
sb_obj[kv.first] = kv.second;
}
}
return !write_osd_superblock(device, sb_obj);
}
uint32_t disk_tool_t::write_osd_superblock(std::string device, json11::Json params)
{
std::string json_data = params.dump();

View File

@@ -135,8 +135,8 @@ void etcd_state_client_t::etcd_call(std::string api, json11::Json payload, int t
{
if (this->log_level > 0)
{
printf(
"Warning: etcd request failed: %s, retrying %d more times\n",
fprintf(
stderr, "Warning: etcd request failed: %s, retrying %d more times\n",
err.c_str(), retries
);
}
@@ -333,7 +333,7 @@ void etcd_state_client_t::start_etcd_watcher()
etcd_watch_ws = NULL;
}
if (this->log_level > 1)
printf("Trying to connect to etcd websocket at %s\n", etcd_address.c_str());
fprintf(stderr, "Trying to connect to etcd websocket at %s\n", etcd_address.c_str());
etcd_watch_ws = open_websocket(tfd, etcd_address, etcd_api_path+"/watch", etcd_slow_timeout,
[this, cur_addr = selected_etcd_address](const http_response_t *msg)
{

View File

@@ -30,7 +30,7 @@ protected:
std::string image_name;
uint64_t inode = 0;
uint64_t device_size = 0;
int nbd_timeout = 30;
int nbd_timeout = 300;
int nbd_max_devices = 64;
int nbd_max_part = 3;
inode_watch_t *watch = NULL;
@@ -135,14 +135,16 @@ public:
" %s unmap /dev/nbd0\n"
" %s ls [--json]\n"
"OPTIONS:\n"
" All usual Vitastor config options like --etcd_address <etcd_address> plus NBD-specific:\n"
" --nbd_timeout 30\n"
" All usual Vitastor config options like --config_file <path_to_config> plus NBD-specific:\n"
" --nbd_timeout 300\n"
" Timeout for I/O operations in seconds after exceeding which the kernel stops\n"
" the device. You can set it to 0 to disable the timeout, but beware that you\n"
" won't be able to stop the device at all if vitastor-nbd process dies.\n"
" --nbd_max_devices 64 --nbd_max_part 3\n"
" Options for the \"nbd\" kernel module when modprobing it (nbds_max and max_part).\n"
" note that maximum allowed (nbds_max)*(1+max_part) is 256.\n"
" Note that nbd_timeout, nbd_max_devices and nbd_max_part options may also be specified\n"
" in /etc/vitastor/vitastor.conf or in other configuration file specified with --config_file.\n"
" --logfile /path/to/log/file.txt\n"
" Wite log messages to the specified file instead of dropping them (in background mode)\n"
" or printing them to the standard output (in foreground mode).\n"
@@ -204,17 +206,18 @@ public:
exit(1);
}
}
if (cfg["nbd_max_devices"].is_number() || cfg["nbd_max_devices"].is_string())
auto file_config = osd_messenger_t::read_config(cfg);
if (file_config["nbd_max_devices"].is_number() || file_config["nbd_max_devices"].is_string())
{
nbd_max_devices = cfg["nbd_max_devices"].uint64_value();
nbd_max_devices = file_config["nbd_max_devices"].uint64_value();
}
if (cfg["nbd_max_part"].is_number() || cfg["nbd_max_part"].is_string())
if (file_config["nbd_max_part"].is_number() || file_config["nbd_max_part"].is_string())
{
nbd_max_part = cfg["nbd_max_part"].uint64_value();
nbd_max_part = file_config["nbd_max_part"].uint64_value();
}
if (cfg["nbd_timeout"].is_number() || cfg["nbd_timeout"].is_string())
if (file_config["nbd_timeout"].is_number() || file_config["nbd_timeout"].is_string())
{
nbd_timeout = cfg["nbd_timeout"].uint64_value();
nbd_timeout = file_config["nbd_timeout"].uint64_value();
}
if (cfg["client_writeback_allowed"].is_null())
{
@@ -272,7 +275,7 @@ public:
int i = 0;
while (true)
{
int r = run_nbd(sockfd, i, device_size, NBD_FLAG_SEND_FLUSH, 30, bg);
int r = run_nbd(sockfd, i, device_size, NBD_FLAG_SEND_FLUSH, nbd_timeout, bg);
if (r == 0)
{
printf("/dev/nbd%d\n", i);

View File

@@ -56,7 +56,7 @@ json11::Json::object nfs_proxy_t::parse_args(int narg, const char *args[])
"(c) Vitaliy Filippov, 2021-2022 (VNPL-1.1)\n"
"\n"
"USAGE:\n"
" %s [--etcd_address ADDR] [OTHER OPTIONS]\n"
" %s [STANDARD OPTIONS] [OTHER OPTIONS]\n"
" --subdir <DIR> export images prefixed <DIR>/ (default empty - export all images)\n"
" --portmap 0 do not listen on port 111 (portmap/rpcbind, requires root)\n"
" --bind <IP> bind service to <IP> address (default 0.0.0.0)\n"

View File

@@ -196,10 +196,11 @@ static void vitastor_parse_filename(const char *filename, QDict *options, Error
!strcmp(name, "rdma-gid-index") ||
!strcmp(name, "rdma-mtu"))
{
unsigned long long num_val;
#if QEMU_VERSION_MAJOR < 8 || QEMU_VERSION_MAJOR == 8 && QEMU_VERSION_MINOR < 1
unsigned long long num_val;
if (parse_uint_full(value, &num_val, 0))
#else
uint64_t num_val;
if (parse_uint_full(value, 0, &num_val))
#endif
{

View File

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
Name: Vitastor
Description: Vitastor client library
Version: 1.2.0
Version: 1.3.1
Libs: -L${libdir} -lvitastor_client
Cflags: -I${includedir}