Compare commits

..

24 Commits

Author SHA1 Message Date
Vitaliy Filippov a8d744ca0e Fix wording 2021-03-16 12:48:36 +03:00
Vitaliy Filippov b5ff44fb6f Change Telegram chat link 2021-03-16 12:48:36 +03:00
Vitaliy Filippov f918bc4543 Fix Russian README for CMake build 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 6875a838e0 Capture all by value in qemu_proxy 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 20781abd3d Add LICENSE 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 1f02f645c0 Add Russian version of the README 2021-03-16 12:48:36 +03:00
Vitaliy Filippov ee44f64927 Introduce image names and metadata storage in etcd
Each inode has: image name, parent inode number & pool, size and readonly flag

Snapshots are created by switching image name to a different inode number
while using the older inode as parent.
2021-03-16 12:48:36 +03:00
Vitaliy Filippov abf0611d93 Use clean_entry_bitmap_size instead of entry_attr_size back because of changed bitmap handling 2021-03-16 12:48:36 +03:00
Vitaliy Filippov edbf0eb040 Add a test for snapshots, fix bugs. Now the test passes 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 09725038e7 Begin snapshot test 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 18f71b059a Fix part bitmap addresses 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 2db2ed22ea Fix several snapshot I/O bugs 2021-03-16 12:48:36 +03:00
Vitaliy Filippov aa7699da24 Fix subop generation for snapshot implementation 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 853ecba780 Actual snapshot support (untested) 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 2f9c76b8fc Report inode I/O statistics, aggregate it in the monitor 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 8da7f26459 Report inode space usage statistics to etcd, aggregate it in the monitor 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 9998b50c7e Add inode space usage statistics tracking to blockstore 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 0422d94a70 Send bitmaps with primary-reads, actually read bitmaps for READ ops 2021-03-16 12:48:36 +03:00
Vitaliy Filippov ff2208ae70 Allocate bitmaps along with stripes to avoid memory fragmentation 2021-03-16 12:48:36 +03:00
Vitaliy Filippov ae54dddb0c Remove cryptic bitmap inlining from bs_op_t and osd_op_t, use bitmap in primary OSD code 2021-03-16 12:48:36 +03:00
Vitaliy Filippov bfc175fe0f Add "external" bitmap support to the secondary OSD protocol 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 07e10210b6 Use bitmap granularity for alignment checks 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 221b728fc9 Add "external" bitmap support to blockstore 2021-03-16 12:48:36 +03:00
Vitaliy Filippov 6625aaae00 Add "external" bitmap support to osd_rmw 2021-03-16 12:48:36 +03:00
75 changed files with 2008 additions and 4072 deletions

View File

@ -22,7 +22,6 @@ Vitastor на данный момент находится в статусе п
Однако следующее уже реализовано:
0.5.x (стабильная версия):
- Базовая часть - надёжное кластерное блочное хранилище без единой точки отказа
- Производительность ;-D
- Несколько схем отказоустойчивости: репликация, XOR n+1 (1 диск чётности), коды коррекции ошибок
@ -43,23 +42,20 @@ Vitastor на данный момент находится в статусе п
- NBD-прокси для монтирования образов ядром ("блочное устройство в режиме пользователя")
- Утилита удаления образов/инодов (vitastor-rm)
- Пакеты для Debian и CentOS
0.6.x (master-ветка):
- Статистика операций ввода/вывода и занятого места в разрезе инодов
- Именование инодов через хранение их метаданных в etcd
- Снапшоты и copy-on-write клоны
- Сглаживание производительности случайной записи в SSD+HDD конфигурациях
## Планы развития
## Планы разработки
- Более корректные скрипты разметки дисков и автоматического запуска OSD
- Другие инструменты администрирования
- Плагины для OpenStack, Kubernetes, OpenNebula, Proxmox и других облачных систем
- iSCSI-прокси
- Более быстрое переключение при отказах
- Таймауты операций и более быстрое выявление отказов
- Фоновая проверка целостности без контрольных сумм (сверка реплик)
- Контрольные суммы
- Поддержка SSD-кэширования (tiered storage)
- Оптимизации для гибридных SSD+HDD хранилищ
- Поддержка RDMA и NVDIMM
- Web-интерфейс
- Возможно, сжатие
@ -363,9 +359,9 @@ Vitastor с однопоточной NBD прокси на том же стен
так как в 5.4 есть как минимум 1 известный баг, ведущий к зависанию с io_uring и контроллером HP SmartArray.
- Установите liburing 0.4 или более новый и его заголовки.
- Установите lp_solve.
- Установите etcd, версии не ниже 3.4.15. Более ранние версии работать не будут из-за различных багов,
например [#12402](https://github.com/etcd-io/etcd/pull/12402). Также вы можете взять версию 3.4.13 с
этим конкретным исправлением из ветки release-3.4 репозитория https://github.com/vitalif/etcd/.
- Установите etcd. Внимание: вам нужна версия с исправлением отсюда: https://github.com/vitalif/etcd/,
из ветки release-3.4, так как в etcd есть баг, который [будет](https://github.com/etcd-io/etcd/pull/12402)
исправлен только в 3.4.15. Баг приводит к неспособности Vitastor запустить PG, когда их хотя бы 500 штук.
- Установите node.js 10 или новее.
- Установите gcc и g++ 8.x или новее.
- Склонируйте данный репозиторий с подмодулями: `git clone https://yourcmc.ru/git/vitalif/vitastor/`.

View File

@ -16,7 +16,6 @@ with configurable redundancy (replication or erasure codes/XOR).
Vitastor is currently a pre-release, a lot of features are missing and you can still expect
breaking changes in the future. However, the following is implemented:
0.5.x (stable):
- 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
@ -37,12 +36,9 @@ breaking changes in the future. However, the following is implemented:
- NBD proxy for kernel mounts
- Inode removal tool (vitastor-rm)
- Packaging for Debian and CentOS
0.6.x (master):
- Per-inode I/O and space usage statistics
- Inode metadata storage in etcd
- Snapshots and copy-on-write image clones
- Write throttling to smooth random write workloads in SSD+HDD configurations
## Roadmap
@ -50,10 +46,10 @@ breaking changes in the future. However, the following is implemented:
- Other administrative tools
- Plugins for OpenStack, Kubernetes, OpenNebula, Proxmox and other cloud systems
- iSCSI proxy
- Faster failover
- Operation timeouts and better failure detection
- Scrubbing without checksums (verification of replicas)
- Checksums
- Tiered storage
- SSD+HDD optimizations, possibly including tiered storage and soft journal flushes
- RDMA and NVDIMM support
- Web GUI
- Compression (possibly)
@ -319,9 +315,10 @@ Vitastor with single-thread NBD on the same hardware:
there is at least one known io_uring hang with 5.4 and an HP SmartArray controller.
- Install liburing 0.4 or newer and its headers.
- Install lp_solve.
- Install etcd, at least version 3.4.15. Earlier versions won't work because of various bugs,
for example [#12402](https://github.com/etcd-io/etcd/pull/12402). You can also take 3.4.13
with this specific fix from here: https://github.com/vitalif/etcd/, branch release-3.4.
- Install etcd. Attention: you need a fixed version from here: https://github.com/vitalif/etcd/,
branch release-3.4, because there is a bug in upstream etcd which makes Vitastor OSDs fail to
move PGs out of "starting" state if you have at least around ~500 PGs or so. The custom build
will be unnecessary when etcd merges the fix: https://github.com/etcd-io/etcd/pull/12402.
- Install node.js 10 or newer.
- Install gcc and g++ 8.x or newer.
- Clone https://yourcmc.ru/git/vitalif/vitastor/ with submodules.

2
debian/changelog vendored
View File

@ -1,4 +1,4 @@
vitastor (0.6.0-1) unstable; urgency=medium
vitastor (0.5.10-1) unstable; urgency=medium
* Bugfixes

View File

@ -40,10 +40,10 @@ RUN set -e -x; \
mkdir -p /root/packages/vitastor-$REL; \
rm -rf /root/packages/vitastor-$REL/*; \
cd /root/packages/vitastor-$REL; \
cp -r /root/vitastor vitastor-0.6.0; \
ln -s /root/packages/qemu-$REL/qemu-*/ vitastor-0.6.0/qemu; \
ln -s /root/fio-build/fio-*/ vitastor-0.6.0/fio; \
cd vitastor-0.6.0; \
cp -r /root/vitastor vitastor-0.5.10; \
ln -s /root/packages/qemu-$REL/qemu-*/ vitastor-0.5.10/qemu; \
ln -s /root/fio-build/fio-*/ vitastor-0.5.10/fio; \
cd vitastor-0.5.10; \
FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
QEMU=$(head -n1 qemu/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
sh copy-qemu-includes.sh; \
@ -59,8 +59,8 @@ RUN set -e -x; \
echo "dep:fio=$FIO" > debian/substvars; \
echo "dep:qemu=$QEMU" >> debian/substvars; \
cd /root/packages/vitastor-$REL; \
tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.6.0.orig.tar.xz vitastor-0.6.0; \
cd vitastor-0.6.0; \
tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.5.10.orig.tar.xz vitastor-0.5.10; \
cd vitastor-0.5.10; \
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

@ -104,17 +104,6 @@ async function optimize_initial({ osd_tree, pg_count, pg_size = 3, pg_minsize =
return res;
}
function shuffle(array)
{
for (let i = array.length - 1, j, x; i > 0; i--)
{
j = Math.floor(Math.random() * (i + 1));
x = array[i];
array[i] = array[j];
array[j] = x;
}
}
function make_int_pgs(weights, pg_count)
{
const total_weight = Object.values(weights).reduce((a, c) => Number(a) + Number(c), 0);
@ -131,7 +120,6 @@ function make_int_pgs(weights, pg_count)
weight_left -= weights[pg_name];
pg_left -= n;
}
shuffle(int_pgs);
return int_pgs;
}

View File

@ -53,6 +53,7 @@ ExecStart=/usr/bin/vitastor-osd \\
--osd_num $OSD_NUM \\
--disable_data_fsync 1 \\
--immediate_commit all \\
--flusher_count 256 \\
--disk_alignment 4096 --journal_block_size 4096 --meta_block_size 4096 \\
--journal_no_same_sector_overwrites true \\
--journal_sector_buffer_count 1024 \\

View File

@ -32,8 +32,7 @@ ExecStart=/usr/local/bin/etcd -name etcd$ETCD_NUM --data-dir /var/lib/etcd$ETCD_
--advertise-client-urls http://$IP:2379 --listen-client-urls http://$IP:2379 \\
--initial-advertise-peer-urls http://$IP:2380 --listen-peer-urls http://$IP:2380 \\
--initial-cluster-token vitastor-etcd-1 --initial-cluster $ETCD_HOSTS \\
--initial-cluster-state new --max-txn-ops=100000 --max-request-bytes=104857600 \\
--auto-compaction-retention=10 --auto-compaction-mode=revision
--initial-cluster-state new --max-txn-ops=100000 --auto-compaction-retention=10 --auto-compaction-mode=revision
WorkingDirectory=/var/lib/etcd$ETCD_NUM.etcd
ExecStartPre=+chown -R etcd /var/lib/etcd$ETCD_NUM.etcd
User=etcd

View File

@ -34,7 +34,7 @@ const etcd_allow = new RegExp('^'+[
'pg/stats/[1-9]\\d*/[1-9]\\d*',
'pg/history/[1-9]\\d*/[1-9]\\d*',
'history/last_clean_pgs',
'inode/stats/[1-9]\\d*/[1-9]\\d*',
'inode/stats/[1-9]\\d*',
'stats',
].join('$|^')+'$');
@ -96,8 +96,7 @@ const etcd_tree = {
disable_device_lock,
// blockstore - configurable
max_write_iodepth,
min_flusher_count: 1,
max_flusher_count: 256,
flusher_count,
inmemory_metadata,
inmemory_journal,
journal_sector_buffer_count,
@ -211,7 +210,7 @@ const etcd_tree = {
/* <pool_id>: {
<pg_id>: {
primary: osd_num_t,
state: ("starting"|"peering"|"incomplete"|"active"|"repeering"|"stopping"|"offline"|
state: ("starting"|"peering"|"incomplete"|"active"|"stopping"|"offline"|
"degraded"|"has_incomplete"|"has_degraded"|"has_misplaced"|"has_unclean"|
"has_invalid"|"left_on_dead")[],
}
@ -580,7 +579,7 @@ class Mon
for (const osd_num of this.all_osds().sort((a, b) => a - b))
{
const stat = this.state.osd.stats[osd_num];
if (stat && stat.size && (this.state.osd.state[osd_num] || Number(stat.time) >= down_time))
if (stat.size && (this.state.osd.state[osd_num] || Number(stat.time) >= down_time))
{
// Numeric IDs are reserved for OSDs
const osd_cfg = this.state.config.osd[osd_num];
@ -731,11 +730,6 @@ class Mon
pg_history[i].osd_sets = pg_history[i].osd_sets || [];
pg_history[i].osd_sets.push(prev_pgs[i]);
}
if (pg_history[i] && pg_history[i].osd_sets)
{
pg_history[i].osd_sets = Object.values(pg_history[i].osd_sets
.reduce((a, c) => { a[c.join(' ')] = c; return a; }, {}));
}
});
for (let i = 0; i < new_pgs.length || i < prev_pgs.length; i++)
{
@ -886,7 +880,7 @@ class Mon
{
// Take configuration and state, check it against the stored configuration hash
// Recalculate PGs and save them to etcd if the configuration is changed
// FIXME: Do not change anything if the distribution is good and random enough and no PGs are degraded
// FIXME: Also do not change anything if the distribution is good enough and no PGs are degraded
const { up_osds, levels, osd_tree } = this.get_osd_tree();
const tree_cfg = {
osd_tree,
@ -945,14 +939,7 @@ class Mon
prev_pgs[pg-1] = this.state.history.last_clean_pgs.items[pool_id][pg].osd_set;
}
prev_pgs = JSON.parse(JSON.stringify(prev_pgs.length ? prev_pgs : real_prev_pgs));
const old_pg_count = real_prev_pgs.length;
const optimize_cfg = {
osd_tree: pool_tree,
pg_count: pool_cfg.pg_count,
pg_size: pool_cfg.pg_size,
pg_minsize: pool_cfg.pg_minsize,
max_combinations: pool_cfg.max_osd_combinations,
};
const old_pg_count = prev_pgs.length;
let optimize_result;
if (old_pg_count > 0)
{
@ -979,22 +966,23 @@ class Mon
pg.pop();
}
}
if (!this.state.config.pgs.hash)
{
// Re-shuffle PGs
optimize_result = await LPOptimizer.optimize_initial(optimize_cfg);
}
else
{
optimize_result = await LPOptimizer.optimize_change({
prev_pgs,
...optimize_cfg,
});
}
optimize_result = await LPOptimizer.optimize_change({
prev_pgs,
osd_tree: pool_tree,
pg_size: pool_cfg.pg_size,
pg_minsize: pool_cfg.pg_minsize,
max_combinations: pool_cfg.max_osd_combinations,
});
}
else
{
optimize_result = await LPOptimizer.optimize_initial(optimize_cfg);
optimize_result = await LPOptimizer.optimize_initial({
osd_tree: pool_tree,
pg_count: pool_cfg.pg_count,
pg_size: pool_cfg.pg_size,
pg_minsize: pool_cfg.pg_minsize,
max_combinations: pool_cfg.max_osd_combinations,
});
}
if (old_pg_count != optimize_result.int_pgs.length)
{
@ -1120,7 +1108,7 @@ class Mon
const op_stats = {}, subop_stats = {}, recovery_stats = {};
for (const osd in this.state.osd.stats)
{
const st = this.state.osd.stats[osd]||{};
const st = this.state.osd.stats[osd];
for (const op in st.op_stats||{})
{
op_stats[op] = op_stats[op] || { count: 0n, usec: 0n, bytes: 0n };
@ -1178,31 +1166,23 @@ class Mon
});
for (const osd_num in this.state.osd.space)
{
for (const pool_id in this.state.osd.space[osd_num])
for (const inode_num in this.state.osd.space[osd_num])
{
inode_stats[pool_id] = inode_stats[pool_id] || {};
for (const inode_num in this.state.osd.space[osd_num][pool_id])
{
inode_stats[pool_id][inode_num] = inode_stats[pool_id][inode_num] || inode_stub();
inode_stats[pool_id][inode_num].raw_used += BigInt(this.state.osd.space[osd_num][pool_id][inode_num]||0);
}
inode_stats[inode_num] = inode_stats[inode_num] || inode_stub();
inode_stats[inode_num].raw_used += BigInt(this.state.osd.space[osd_num][inode_num]||0);
}
}
for (const osd_num in this.state.osd.inodestats)
{
const ist = this.state.osd.inodestats[osd_num];
for (const pool_id in ist)
for (const inode_num in ist)
{
inode_stats[pool_id] = inode_stats[pool_id] || {};
for (const inode_num in ist[pool_id])
inode_stats[inode_num] = inode_stats[inode_num] || inode_stub();
for (const op of [ 'read', 'write', 'delete' ])
{
inode_stats[pool_id][inode_num] = inode_stats[pool_id][inode_num] || inode_stub();
for (const op of [ 'read', 'write', 'delete' ])
{
inode_stats[pool_id][inode_num][op].count += BigInt(ist[pool_id][inode_num][op].count||0);
inode_stats[pool_id][inode_num][op].usec += BigInt(ist[pool_id][inode_num][op].usec||0);
inode_stats[pool_id][inode_num][op].bytes += BigInt(ist[pool_id][inode_num][op].bytes||0);
}
inode_stats[inode_num][op].count += BigInt(ist[inode_num][op].count||0);
inode_stats[inode_num][op].usec += BigInt(ist[inode_num][op].usec||0);
inode_stats[inode_num][op].bytes += BigInt(ist[inode_num][op].bytes||0);
}
}
}
@ -1268,15 +1248,12 @@ class Mon
this.serialize_bigints(stats);
this.serialize_bigints(inode_stats);
txn.push({ requestPut: { key: b64(this.etcd_prefix+'/stats'), value: b64(JSON.stringify(stats)) } });
for (const pool_id in inode_stats)
for (const inode_num in inode_stats)
{
for (const inode_num in inode_stats[pool_id])
{
txn.push({ requestPut: {
key: b64(this.etcd_prefix+'/inode/stats/'+pool_id+'/'+inode_num),
value: b64(JSON.stringify(inode_stats[pool_id][inode_num])),
} });
}
txn.push({ requestPut: {
key: b64(this.etcd_prefix+'/inode/stats/'+inode_num),
value: b64(JSON.stringify(inode_stats[inode_num])),
} });
}
if (txn.length)
{

View File

@ -51,7 +51,7 @@ async function run()
const meta_offset = options.journal_offset + Math.ceil(options.journal_size/options.device_block_size)*options.device_block_size;
const entries_per_block = Math.floor(options.device_block_size / (24 + 2*options.object_size/options.bitmap_granularity/8));
const object_count = Math.floor((device_size-meta_offset)/options.object_size);
const meta_size = Math.ceil(1 + object_count / entries_per_block) * options.device_block_size;
const meta_size = Math.ceil(object_count / entries_per_block) * options.device_block_size;
const data_offset = meta_offset + meta_size;
const meta_size_fmt = (meta_size > 1024*1024*1024 ? Math.round(meta_size/1024/1024/1024*100)/100+" GB"
: Math.round(meta_size/1024/1024*100)/100+" MB");
@ -65,9 +65,6 @@ async function run()
);
}
process.stdout.write(
(options.device_block_size != 4096 ?
` --meta_block_size ${options.device}\n`+
` --journal_block-size ${options.device}\n` : '')+
` --data_device ${options.device}\n`+
` --journal_offset ${options.journal_offset}\n`+
` --meta_offset ${meta_offset}\n`+

View File

@ -48,4 +48,4 @@ FIO=`rpm -qi fio | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Ve
QEMU=`rpm -qi qemu qemu-kvm | 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
perl -i -pe 's/(Requires:\s*qemu(?:-kvm)?)([^\n]+)?/$1 = '$QEMU'/' $VITASTOR/rpm/vitastor-el$EL.spec
tar --transform 's#^#vitastor-0.6.0/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.6.0$(rpm --eval '%dist').tar.gz *
tar --transform 's#^#vitastor-0.5.10/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.5.10$(rpm --eval '%dist').tar.gz *

View File

@ -37,7 +37,7 @@ ADD . /root/vitastor
RUN set -e; \
cd /root/vitastor/rpm; \
sh build-tarball.sh; \
cp /root/vitastor-0.6.0.el7.tar.gz ~/rpmbuild/SOURCES; \
cp /root/vitastor-0.5.10.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: 0.6.0
Version: 0.5.10
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-0.6.0.el7.tar.gz
Source0: vitastor-0.5.10.el7.tar.gz
BuildRequires: liburing-devel >= 0.6
BuildRequires: gperftools-devel

View File

@ -35,7 +35,7 @@ ADD . /root/vitastor
RUN set -e; \
cd /root/vitastor/rpm; \
sh build-tarball.sh; \
cp /root/vitastor-0.6.0.el8.tar.gz ~/rpmbuild/SOURCES; \
cp /root/vitastor-0.5.10.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: 0.6.0
Version: 0.5.10
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-0.6.0.el8.tar.gz
Source0: vitastor-0.5.10.el8.tar.gz
BuildRequires: liburing-devel >= 0.6
BuildRequires: gperftools-devel

View File

@ -13,8 +13,8 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
endif()
add_definitions(-DVERSION="0.6.0")
add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -I ${CMAKE_SOURCE_DIR}/src)
add_definitions(-DVERSION="0.6-dev")
add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith)
if (${WITH_ASAN})
add_definitions(-fsanitize=address -fno-omit-frame-pointer)
add_link_options(-fsanitize=address -fno-omit-frame-pointer)
@ -66,8 +66,7 @@ target_link_libraries(fio_vitastor_blk
# vitastor-osd
add_executable(vitastor-osd
osd_main.cpp osd.cpp osd_secondary.cpp msgr_receive.cpp msgr_send.cpp osd_peering.cpp osd_flush.cpp osd_peering_pg.cpp
osd_primary.cpp osd_primary_chain.cpp osd_primary_sync.cpp osd_primary_write.cpp osd_primary_subops.cpp
etcd_state_client.cpp messenger.cpp msgr_stop.cpp msgr_op.cpp osd_cluster.cpp http_client.cpp osd_ops.cpp pg_states.cpp
osd_primary.cpp osd_primary_subops.cpp etcd_state_client.cpp messenger.cpp osd_cluster.cpp http_client.cpp osd_ops.cpp pg_states.cpp
osd_rmw.cpp base64.cpp timerfd_manager.cpp epoll_manager.cpp ../json11/json11.cpp
)
target_link_libraries(vitastor-osd
@ -87,7 +86,7 @@ target_link_libraries(fio_vitastor_sec
# libvitastor_client.so
add_library(vitastor_client SHARED
cluster_client.cpp epoll_manager.cpp etcd_state_client.cpp
messenger.cpp msgr_stop.cpp msgr_op.cpp msgr_send.cpp msgr_receive.cpp ringloop.cpp ../json11/json11.cpp
messenger.cpp msgr_send.cpp msgr_receive.cpp ringloop.cpp ../json11/json11.cpp
http_client.cpp osd_ops.cpp pg_states.cpp timerfd_manager.cpp base64.cpp
)
target_link_libraries(vitastor_client
@ -162,8 +161,7 @@ target_link_libraries(osd_rmw_test Jerasure tcmalloc_minimal)
# stub_uring_osd
add_executable(stub_uring_osd
stub_uring_osd.cpp epoll_manager.cpp messenger.cpp msgr_stop.cpp msgr_op.cpp
msgr_send.cpp msgr_receive.cpp ringloop.cpp timerfd_manager.cpp ../json11/json11.cpp
stub_uring_osd.cpp epoll_manager.cpp messenger.cpp msgr_send.cpp msgr_receive.cpp ringloop.cpp timerfd_manager.cpp ../json11/json11.cpp
)
target_link_libraries(stub_uring_osd
${LIBURING_LIBRARIES}
@ -177,17 +175,8 @@ target_link_libraries(osd_peering_pg_test tcmalloc_minimal)
# test_allocator
add_executable(test_allocator test_allocator.cpp allocator.cpp)
# test_cluster_client
add_executable(test_cluster_client
test_cluster_client.cpp
pg_states.cpp osd_ops.cpp cluster_client.cpp msgr_op.cpp mock/messenger.cpp msgr_stop.cpp
etcd_state_client.cpp timerfd_manager.cpp ../json11/json11.cpp
)
target_compile_definitions(test_cluster_client PUBLIC -D__MOCK__)
target_include_directories(test_cluster_client PUBLIC ${CMAKE_SOURCE_DIR}/src/mock)
## test_blockstore, test_shit
#add_executable(test_blockstore test_blockstore.cpp)
#add_executable(test_blockstore test_blockstore.cpp timerfd_interval.cpp)
#target_link_libraries(test_blockstore blockstore)
#add_executable(test_shit test_shit.cpp osd_peering_pg.cpp)
#target_link_libraries(test_shit ${LIBURING_LIBRARIES} m)

View File

@ -37,21 +37,6 @@ allocator::~allocator()
delete[] mask;
}
bool allocator::get(uint64_t addr)
{
if (addr >= size)
{
return false;
}
uint64_t p2 = 1, offset = 0;
while (p2 * 64 < size)
{
offset += p2;
p2 = p2 * 64;
}
return ((mask[offset + addr/64] >> (addr % 64)) & 1);
}
void allocator::set(uint64_t addr, bool value)
{
if (addr >= size)

View File

@ -16,7 +16,6 @@ class allocator
public:
allocator(uint64_t blocks);
~allocator();
bool get(uint64_t addr);
void set(uint64_t addr, bool value);
uint64_t find_free();
uint64_t get_free_count();

View File

@ -3,9 +3,9 @@
#include "blockstore_impl.h"
blockstore_t::blockstore_t(blockstore_config_t & config, ring_loop_t *ringloop, timerfd_manager_t *tfd)
blockstore_t::blockstore_t(blockstore_config_t & config, ring_loop_t *ringloop)
{
impl = new blockstore_impl_t(config, ringloop, tfd);
impl = new blockstore_impl_t(config, ringloop);
}
blockstore_t::~blockstore_t()
@ -38,11 +38,6 @@ void blockstore_t::enqueue_op(blockstore_op_t *op)
impl->enqueue_op(op);
}
int blockstore_t::read_bitmap(object_id oid, uint64_t target_version, void *bitmap, uint64_t *result_version)
{
return impl->read_bitmap(oid, target_version, bitmap, result_version);
}
std::unordered_map<object_id, uint64_t> & blockstore_t::get_unstable_writes()
{
return impl->unstable_writes;

View File

@ -16,7 +16,6 @@
#include "object_id.h"
#include "ringloop.h"
#include "timerfd_manager.h"
// Memory alignment for direct I/O (usually 512 bytes)
// All other alignments must be a multiple of this one
@ -159,7 +158,7 @@ class blockstore_t
{
blockstore_impl_t *impl;
public:
blockstore_t(blockstore_config_t & config, ring_loop_t *ringloop, timerfd_manager_t *tfd);
blockstore_t(blockstore_config_t & config, ring_loop_t *ringloop);
~blockstore_t();
// Event loop
@ -180,9 +179,6 @@ public:
// Submission
void enqueue_op(blockstore_op_t *op);
// Simplified synchronous operation: get object bitmap & current version
int read_bitmap(object_id oid, uint64_t target_version, void *bitmap, uint64_t *result_version = NULL);
// Unstable writes are added here (map of object_id -> version)
std::unordered_map<object_id, uint64_t> & get_unstable_writes();

View File

@ -3,13 +3,12 @@
#include "blockstore_impl.h"
journal_flusher_t::journal_flusher_t(blockstore_impl_t *bs)
journal_flusher_t::journal_flusher_t(int flusher_count, blockstore_impl_t *bs)
{
this->bs = bs;
this->max_flusher_count = bs->max_flusher_count;
this->min_flusher_count = bs->min_flusher_count;
this->cur_flusher_count = bs->min_flusher_count;
this->target_flusher_count = bs->min_flusher_count;
this->flusher_count = flusher_count;
this->cur_flusher_count = 1;
this->target_flusher_count = 1;
dequeuing = false;
trimming = false;
active_flushers = 0;
@ -17,11 +16,11 @@ journal_flusher_t::journal_flusher_t(blockstore_impl_t *bs)
// FIXME: allow to configure flusher_start_threshold and journal_trim_interval
flusher_start_threshold = bs->journal_block_size / sizeof(journal_entry_stable);
journal_trim_interval = 512;
journal_trim_counter = bs->journal.flush_journal ? 1 : 0;
trim_wanted = bs->journal.flush_journal ? 1 : 0;
journal_trim_counter = 0;
trim_wanted = 0;
journal_superblock = bs->journal.inmemory ? bs->journal.buffer : memalign_or_die(MEM_ALIGNMENT, bs->journal_block_size);
co = new journal_flusher_co[max_flusher_count];
for (int i = 0; i < max_flusher_count; i++)
co = new journal_flusher_co[flusher_count];
for (int i = 0; i < flusher_count; i++)
{
co[i].bs = bs;
co[i].flusher = this;
@ -72,10 +71,10 @@ bool journal_flusher_t::is_active()
void journal_flusher_t::loop()
{
target_flusher_count = bs->write_iodepth*2;
if (target_flusher_count < min_flusher_count)
target_flusher_count = min_flusher_count;
else if (target_flusher_count > max_flusher_count)
target_flusher_count = max_flusher_count;
if (target_flusher_count <= 0)
target_flusher_count = 1;
else if (target_flusher_count > flusher_count)
target_flusher_count = flusher_count;
if (target_flusher_count > cur_flusher_count)
cur_flusher_count = target_flusher_count;
else if (target_flusher_count < cur_flusher_count)
@ -238,8 +237,7 @@ bool journal_flusher_co::loop()
else if (wait_state == 21)
goto resume_21;
resume_0:
if (flusher->flush_queue.size() < flusher->min_flusher_count && !flusher->trim_wanted ||
!flusher->flush_queue.size() || !flusher->dequeuing)
if (!flusher->flush_queue.size() || !flusher->dequeuing)
{
stop_flusher:
if (flusher->trim_wanted > 0 && flusher->journal_trim_counter > 0)
@ -485,13 +483,6 @@ resume_1:
}
if (has_delete)
{
clean_disk_entry *new_entry = (clean_disk_entry*)(meta_new.buf + meta_new.pos*bs->clean_entry_size);
if (new_entry->oid.inode != 0 && new_entry->oid != cur.oid)
{
printf("Fatal error (metadata corruption or bug): tried to delete metadata entry %lu (%lx:%lx) while deleting %lx:%lx\n",
clean_loc >> bs->block_order, new_entry->oid.inode, new_entry->oid.stripe, cur.oid.inode, cur.oid.stripe);
exit(1);
}
// zero out new metadata entry
memset(meta_new.buf + meta_new.pos*bs->clean_entry_size, 0, bs->clean_entry_size);
}
@ -602,7 +593,6 @@ resume_1:
.size = sizeof(journal_entry_start),
.reserved = 0,
.journal_start = new_trim_pos,
.version = JOURNAL_VERSION,
};
((journal_entry_start*)flusher->journal_superblock)->crc32 = je_crc32((journal_entry*)flusher->journal_superblock);
data->iov = (struct iovec){ flusher->journal_superblock, bs->journal_block_size };
@ -634,12 +624,6 @@ resume_1:
#endif
flusher->trimming = false;
}
if (bs->journal.flush_journal && !flusher->flush_queue.size())
{
assert(bs->journal.used_start == bs->journal.next_free);
printf("Journal flushed\n");
exit(0);
}
}
// All done
flusher->active_flushers--;
@ -670,7 +654,7 @@ bool journal_flusher_co::scan_dirty(int wait_base)
{
char err[1024];
snprintf(
err, 1024, "BUG: Unexpected dirty_entry %lx:%lx v%lu unstable state during flush: 0x%x",
err, 1024, "BUG: Unexpected dirty_entry %lx:%lx v%lu unstable state during flush: %d",
dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version, dirty_it->second.state
);
throw std::runtime_error(err);
@ -799,10 +783,7 @@ void journal_flusher_co::update_clean_db()
if (old_clean_loc != UINT64_MAX && old_clean_loc != clean_loc)
{
#ifdef BLOCKSTORE_DEBUG
printf("Free block %lu from %lx:%lx v%lu (new location is %lu)\n",
old_clean_loc >> bs->block_order,
cur.oid.inode, cur.oid.stripe, cur.version,
clean_loc >> bs->block_order);
printf("Free block %lu (new location is %lu)\n", old_clean_loc >> bs->block_order, clean_loc >> bs->block_order);
#endif
bs->data_alloc->set(old_clean_loc >> bs->block_order, false);
}
@ -810,11 +791,6 @@ void journal_flusher_co::update_clean_db()
{
auto clean_it = bs->clean_db.find(cur.oid);
bs->clean_db.erase(clean_it);
#ifdef BLOCKSTORE_DEBUG
printf("Free block %lu from %lx:%lx v%lu (delete)\n",
clean_loc >> bs->block_order,
cur.oid.inode, cur.oid.stripe, cur.version);
#endif
bs->data_alloc->set(clean_loc >> bs->block_order, false);
clean_loc = UINT64_MAX;
}
@ -836,7 +812,7 @@ bool journal_flusher_co::fsync_batch(bool fsync_meta, int wait_base)
goto resume_1;
else if (wait_state == wait_base+2)
goto resume_2;
if (!(fsync_meta ? bs->disable_meta_fsync : bs->disable_data_fsync))
if (!(fsync_meta ? bs->disable_meta_fsync : bs->disable_journal_fsync))
{
cur_sync = flusher->syncs.end();
while (cur_sync != flusher->syncs.begin())

View File

@ -79,7 +79,7 @@ class journal_flusher_t
{
int trim_wanted = 0;
bool dequeuing;
int min_flusher_count, max_flusher_count, cur_flusher_count, target_flusher_count;
int flusher_count, cur_flusher_count, target_flusher_count;
int flusher_start_threshold;
journal_flusher_co *co;
blockstore_impl_t *bs;
@ -98,7 +98,7 @@ class journal_flusher_t
std::deque<object_id> flush_queue;
std::map<object_id, uint64_t> flush_versions;
public:
journal_flusher_t(blockstore_impl_t *bs);
journal_flusher_t(int flusher_count, blockstore_impl_t *bs);
~journal_flusher_t();
void loop();
bool is_active();

View File

@ -3,10 +3,9 @@
#include "blockstore_impl.h"
blockstore_impl_t::blockstore_impl_t(blockstore_config_t & config, ring_loop_t *ringloop, timerfd_manager_t *tfd)
blockstore_impl_t::blockstore_impl_t(blockstore_config_t & config, ring_loop_t *ringloop)
{
assert(sizeof(blockstore_op_private_t) <= BS_OP_PRIVATE_DATA_SIZE);
this->tfd = tfd;
this->ringloop = ringloop;
ring_consumer.loop = [this]() { loop(); };
ringloop->register_consumer(&ring_consumer);
@ -32,7 +31,7 @@ blockstore_impl_t::blockstore_impl_t(blockstore_config_t & config, ring_loop_t *
close(journal.fd);
throw;
}
flusher = new journal_flusher_t(this);
flusher = new journal_flusher_t(flusher_count, this);
}
blockstore_impl_t::~blockstore_impl_t()
@ -93,23 +92,10 @@ void blockstore_impl_t::loop()
{
delete journal_init_reader;
journal_init_reader = NULL;
if (journal.flush_journal)
initialized = 3;
else
initialized = 10;
initialized = 10;
ringloop->wakeup();
}
}
if (initialized == 3)
{
if (readonly)
{
printf("Can't flush the journal in readonly mode\n");
exit(1);
}
flusher->loop();
ringloop->submit();
}
}
else
{
@ -457,7 +443,7 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
}
for (; clean_it != clean_end; clean_it++)
{
if (!pg_count || ((clean_it->first.stripe / pg_stripe_size) % pg_count) == list_pg) // like map_to_pg()
if (!pg_count || ((clean_it->first.inode + clean_it->first.stripe / pg_stripe_size) % pg_count) == list_pg)
{
if (stable_count >= stable_alloc)
{
@ -502,7 +488,7 @@ void blockstore_impl_t::process_list(blockstore_op_t *op)
}
for (; dirty_it != dirty_end; dirty_it++)
{
if (!pg_count || ((dirty_it->first.oid.stripe / pg_stripe_size) % pg_count) == list_pg) // like map_to_pg()
if (!pg_count || ((dirty_it->first.oid.inode + dirty_it->first.oid.stripe / pg_stripe_size) % pg_count) == list_pg)
{
if (IS_DELETE(dirty_it->second.state))
{

View File

@ -9,7 +9,6 @@
#include <sys/ioctl.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <time.h>
#include <unistd.h>
#include <linux/fs.h>
@ -78,23 +77,6 @@
#include "blockstore_journal.h"
// "VITAstor"
#define BLOCKSTORE_META_MAGIC 0x726F747341544956l
#define BLOCKSTORE_META_VERSION 1
// metadata header (superblock)
// FIXME: After adding the OSD superblock, add a key to metadata
// and journal headers to check if they belong to the same OSD
struct __attribute__((__packed__)) blockstore_meta_header_t
{
uint64_t zero;
uint64_t magic;
uint64_t version;
uint32_t meta_block_size;
uint32_t data_block_size;
uint32_t bitmap_granularity;
};
// 32 bytes = 24 bytes + block bitmap (4 bytes by default) + external attributes (also bitmap, 4 bytes by default)
// per "clean" entry on disk with fixed metadata tables
// FIXME: maybe add crc32's to metadata
@ -176,7 +158,6 @@ struct blockstore_op_private_t
struct iovec iov_zerofill[3];
// Warning: must not have a default value here because it's written to before calling constructor in blockstore_write.cpp O_o
uint64_t real_version;
timespec tv_begin;
// Sync
std::vector<obj_ver_id> sync_big_writes, sync_small_writes;
@ -218,18 +199,10 @@ class blockstore_impl_t
// Suitable only for server SSDs with capacitors, requires disabled data and journal fsyncs
int immediate_commit = IMMEDIATE_NONE;
bool inmemory_meta = false;
// Maximum and minimum flusher count
unsigned max_flusher_count, min_flusher_count;
// Maximum flusher count
unsigned flusher_count;
// Maximum queue depth
unsigned max_write_iodepth = 128;
// Enable small (journaled) write throttling, useful for the SSD+HDD case
bool throttle_small_writes = false;
// Target data device iops, bandwidth and parallelism for throttling (100/100/1 is the default for HDD)
int throttle_target_iops = 100;
int throttle_target_mbs = 100;
int throttle_target_parallelism = 1;
// Minimum difference in microseconds between target and real execution times to throttle the response
int throttle_threshold_us = 50;
/******* END OF OPTIONS *******/
struct ring_consumer_t ring_consumer;
@ -239,7 +212,6 @@ class blockstore_impl_t
blockstore_dirty_db_t dirty_db;
std::vector<blockstore_op_t*> submit_queue;
std::vector<obj_ver_id> unsynced_big_writes, unsynced_small_writes;
int unsynced_big_write_count = 0;
allocator *data_alloc = NULL;
uint8_t *zero_object;
@ -260,7 +232,6 @@ class blockstore_impl_t
bool live = false, queue_stall = false;
ring_loop_t *ringloop;
timerfd_manager_t *tfd;
bool stop_sync_submitted;
@ -315,7 +286,7 @@ class blockstore_impl_t
// Stabilize
int dequeue_stable(blockstore_op_t *op);
int continue_stable(blockstore_op_t *op);
void mark_stable(const obj_ver_id & ov, bool forget_dirty = false);
void mark_stable(const obj_ver_id & ov);
void handle_stable_event(ring_data_t *data, blockstore_op_t *op);
void stabilize_object(object_id oid, uint64_t max_ver);
@ -331,7 +302,7 @@ class blockstore_impl_t
public:
blockstore_impl_t(blockstore_config_t & config, ring_loop_t *ringloop, timerfd_manager_t *tfd);
blockstore_impl_t(blockstore_config_t & config, ring_loop_t *ringloop);
~blockstore_impl_t();
// Event loop
@ -352,9 +323,6 @@ public:
// Submission
void enqueue_op(blockstore_op_t *op);
// Simplified synchronous operation: get object bitmap & current version
int read_bitmap(object_id oid, uint64_t target_version, void *bitmap, uint64_t *result_version = NULL);
// Unstable writes are added here (map of object_id -> version)
std::unordered_map<object_id, uint64_t> unstable_writes;

View File

@ -3,20 +3,6 @@
#include "blockstore_impl.h"
#define GET_SQE() \
sqe = bs->get_sqe();\
if (!sqe)\
throw std::runtime_error("io_uring is full during initialization");\
data = ((ring_data_t*)sqe->user_data)
static bool iszero(uint64_t *buf, int len)
{
for (int i = 0; i < len; i++)
if (buf[i] != 0)
return false;
return true;
}
blockstore_init_meta::blockstore_init_meta(blockstore_impl_t *bs)
{
this->bs = bs;
@ -24,7 +10,7 @@ blockstore_init_meta::blockstore_init_meta(blockstore_impl_t *bs)
void blockstore_init_meta::handle_event(ring_data_t *data)
{
if (data->res < 0)
if (data->res <= 0)
{
throw std::runtime_error(
std::string("read metadata failed at offset ") + std::to_string(metadata_read) +
@ -42,12 +28,6 @@ int blockstore_init_meta::loop()
{
if (wait_state == 1)
goto resume_1;
else if (wait_state == 2)
goto resume_2;
else if (wait_state == 3)
goto resume_3;
else if (wait_state == 4)
goto resume_4;
printf("Reading blockstore metadata\n");
if (bs->inmemory_meta)
metadata_buffer = bs->metadata_buffer;
@ -55,98 +35,22 @@ int blockstore_init_meta::loop()
metadata_buffer = memalign(MEM_ALIGNMENT, 2*bs->metadata_buf_size);
if (!metadata_buffer)
throw std::runtime_error("Failed to allocate metadata read buffer");
// Read superblock
GET_SQE();
data->iov = { metadata_buffer, bs->meta_block_size };
data->callback = [this](ring_data_t *data) { handle_event(data); };
my_uring_prep_readv(sqe, bs->meta_fd, &data->iov, 1, bs->meta_offset);
bs->ringloop->submit();
submitted = 1;
resume_1:
if (submitted)
{
wait_state = 1;
return 1;
}
if (iszero((uint64_t*)metadata_buffer, bs->meta_block_size / sizeof(uint64_t)))
{
{
blockstore_meta_header_t *hdr = (blockstore_meta_header_t *)metadata_buffer;
hdr->zero = 0;
hdr->magic = BLOCKSTORE_META_MAGIC;
hdr->version = BLOCKSTORE_META_VERSION;
hdr->meta_block_size = bs->meta_block_size;
hdr->data_block_size = bs->block_size;
hdr->bitmap_granularity = bs->bitmap_granularity;
}
if (bs->readonly)
{
printf("Skipping metadata initialization because blockstore is readonly\n");
}
else
{
printf("Initializing metadata area\n");
GET_SQE();
data->iov = (struct iovec){ metadata_buffer, bs->meta_block_size };
data->callback = [this](ring_data_t *data) { handle_event(data); };
my_uring_prep_writev(sqe, bs->meta_fd, &data->iov, 1, bs->meta_offset);
bs->ringloop->submit();
submitted = 1;
resume_3:
if (submitted > 0)
{
wait_state = 3;
return 1;
}
zero_on_init = true;
}
}
else
{
blockstore_meta_header_t *hdr = (blockstore_meta_header_t *)metadata_buffer;
if (hdr->zero != 0 ||
hdr->magic != BLOCKSTORE_META_MAGIC ||
hdr->version != BLOCKSTORE_META_VERSION)
{
printf(
"Metadata is corrupt or old version.\n"
" If this is a new OSD please zero out the metadata area before starting it.\n"
" If you need to upgrade from 0.5.x please request it via the issue tracker.\n"
);
exit(1);
}
if (hdr->meta_block_size != bs->meta_block_size ||
hdr->data_block_size != bs->block_size ||
hdr->bitmap_granularity != bs->bitmap_granularity)
{
printf(
"Configuration stored in metadata superblock"
" (meta_block_size=%u, data_block_size=%u, bitmap_granularity=%u)"
" differs from OSD configuration (%lu/%u/%lu).\n",
hdr->meta_block_size, hdr->data_block_size, hdr->bitmap_granularity,
bs->meta_block_size, bs->block_size, bs->bitmap_granularity
);
exit(1);
}
}
// Skip superblock
bs->meta_offset += bs->meta_block_size;
prev_done = 0;
done_len = 0;
done_pos = 0;
metadata_read = 0;
// Read the rest of the metadata
while (1)
{
resume_2:
resume_1:
if (submitted)
{
wait_state = 2;
wait_state = 1;
return 1;
}
if (metadata_read < bs->meta_len)
{
GET_SQE();
sqe = bs->get_sqe();
if (!sqe)
{
throw std::runtime_error("io_uring is full while trying to read metadata");
}
data = ((ring_data_t*)sqe->user_data);
data->iov = {
metadata_buffer + (bs->inmemory_meta
? metadata_read
@ -154,14 +58,7 @@ resume_1:
bs->meta_len - metadata_read > bs->metadata_buf_size ? bs->metadata_buf_size : bs->meta_len - metadata_read,
};
data->callback = [this](ring_data_t *data) { handle_event(data); };
if (!zero_on_init)
my_uring_prep_readv(sqe, bs->meta_fd, &data->iov, 1, bs->meta_offset + metadata_read);
else
{
// Fill metadata with zeroes
memset(data->iov.iov_base, 0, data->iov.iov_len);
my_uring_prep_writev(sqe, bs->meta_fd, &data->iov, 1, bs->meta_offset + metadata_read);
}
my_uring_prep_readv(sqe, bs->meta_fd, &data->iov, 1, bs->meta_offset + metadata_read);
bs->ringloop->submit();
submitted = (prev == 1 ? 2 : 1);
prev = submitted;
@ -193,21 +90,6 @@ resume_1:
free(metadata_buffer);
metadata_buffer = NULL;
}
if (zero_on_init && !bs->disable_meta_fsync)
{
GET_SQE();
my_uring_prep_fsync(sqe, bs->meta_fd, IORING_FSYNC_DATASYNC);
data->iov = { 0 };
data->callback = [this](ring_data_t *data) { handle_event(data); };
submitted = 1;
bs->ringloop->submit();
resume_4:
if (submitted > 0)
{
wait_state = 4;
return 1;
}
}
return 0;
}
@ -229,10 +111,7 @@ void blockstore_init_meta::handle_entries(void* entries, unsigned count, int blo
{
// free the previous block
#ifdef BLOCKSTORE_DEBUG
printf("Free block %lu from %lx:%lx v%lu (new location is %lu)\n",
clean_it->second.location >> block_order,
clean_it->first.inode, clean_it->first.stripe, clean_it->second.version,
done_cnt+i);
printf("Free block %lu (new location is %lu)\n", clean_it->second.location >> block_order, done_cnt+i);
#endif
bs->data_alloc->set(clean_it->second.location >> block_order, false);
}
@ -274,6 +153,14 @@ blockstore_init_journal::blockstore_init_journal(blockstore_impl_t *bs)
};
}
bool iszero(uint64_t *buf, int len)
{
for (int i = 0; i < len; i++)
if (buf[i] != 0)
return false;
return true;
}
void blockstore_init_journal::handle_event(ring_data_t *data1)
{
if (data1->res <= 0)
@ -298,6 +185,12 @@ void blockstore_init_journal::handle_event(ring_data_t *data1)
submitted_buf = NULL;
}
#define GET_SQE() \
sqe = bs->get_sqe();\
if (!sqe)\
throw std::runtime_error("io_uring is full while trying to read journal");\
data = ((ring_data_t*)sqe->user_data)
int blockstore_init_journal::loop()
{
if (wait_state == 1)
@ -335,7 +228,7 @@ resume_1:
wait_state = 1;
return 1;
}
if (iszero((uint64_t*)submitted_buf, bs->journal.block_size / sizeof(uint64_t)))
if (iszero((uint64_t*)submitted_buf, 3))
{
// Journal is empty
// FIXME handle this wrapping to journal_block_size better (maybe)
@ -350,7 +243,6 @@ resume_1:
.size = sizeof(journal_entry_start),
.reserved = 0,
.journal_start = bs->journal.block_size,
.version = JOURNAL_VERSION,
};
((journal_entry_start*)submitted_buf)->crc32 = je_crc32((journal_entry*)submitted_buf);
if (bs->readonly)
@ -401,21 +293,11 @@ resume_1:
je_start = (journal_entry_start*)submitted_buf;
if (je_start->magic != JOURNAL_MAGIC ||
je_start->type != JE_START ||
je_crc32((journal_entry*)je_start) != je_start->crc32 ||
je_start->size != sizeof(journal_entry_start) && je_start->size != JE_START_LEGACY_SIZE)
je_start->size != sizeof(journal_entry_start) ||
je_crc32((journal_entry*)je_start) != je_start->crc32)
{
// Entry is corrupt
fprintf(stderr, "First entry of the journal is corrupt\n");
exit(1);
}
if (je_start->size == JE_START_LEGACY_SIZE || je_start->version != JOURNAL_VERSION)
{
fprintf(
stderr, "The code only supports journal version %d, but it is %lu on disk."
" Please use the previous version to flush the journal before upgrading OSD\n",
JOURNAL_VERSION, je_start->size == JE_START_LEGACY_SIZE ? 0 : je_start->version
);
exit(1);
throw std::runtime_error("first entry of the journal is corrupt");
}
next_free = journal_pos = bs->journal.used_start = je_start->journal_start;
if (!bs->journal.inmemory)
@ -521,18 +403,6 @@ resume_1:
}
}
}
for (auto ov: double_allocs)
{
auto dirty_it = bs->dirty_db.find(ov);
if (dirty_it != bs->dirty_db.end() &&
IS_BIG_WRITE(dirty_it->second.state) &&
dirty_it->second.location == UINT64_MAX)
{
printf("Fatal error (bug): %lx:%lx v%lu big_write journal_entry was allocated over another object\n",
dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version);
exit(1);
}
}
bs->flusher->mark_trim_possible();
bs->journal.dirty_start = bs->journal.next_free;
printf(
@ -664,20 +534,20 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
.oid = je->small_write.oid,
.version = je->small_write.version,
};
void *bmp = NULL;
void *bmp_from = (void*)je + sizeof(journal_entry_small_write);
void *bmp = (void*)je + sizeof(journal_entry_small_write);
if (bs->clean_entry_bitmap_size <= sizeof(void*))
{
memcpy(&bmp, bmp_from, bs->clean_entry_bitmap_size);
memcpy(&bmp, bmp, bs->clean_entry_bitmap_size);
}
else
else if (!bs->journal.inmemory)
{
// FIXME Using large blockstore objects will result in a lot of small
// allocations for entry bitmaps. This can only be fixed by using
// a patched map with dynamic entry size, but not the btree_map,
// because it doesn't keep iterators valid all the time.
bmp = malloc_or_die(bs->clean_entry_bitmap_size);
memcpy(bmp, bmp_from, bs->clean_entry_bitmap_size);
// FIXME Using large blockstore objects and not keeping journal in memory
// will result in a lot of small allocations for entry bitmaps. This can
// only be fixed by using a patched map with dynamic entry size, but not
// the btree_map, because it doesn't keep iterators valid all the time.
void *bmp_cp = malloc_or_die(bs->clean_entry_bitmap_size);
memcpy(bmp_cp, bmp, bs->clean_entry_bitmap_size);
bmp = bmp_cp;
}
bs->dirty_db.emplace(ov, (dirty_entry){
.state = (BS_ST_SMALL_WRITE | BS_ST_SYNCED),
@ -699,7 +569,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
unstab = unstab < ov.version ? ov.version : unstab;
if (je->type == JE_SMALL_WRITE_INSTANT)
{
bs->mark_stable(ov, true);
bs->mark_stable(ov);
}
}
}
@ -729,10 +599,32 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
// its data and metadata are already flushed.
// We don't know if newer versions are flushed, but
// the previous delete definitely is.
// So we forget previous dirty entries, but retain the clean one.
// So we flush previous dirty entries, but retain the clean one.
// This feature is required for writes happening shortly
// after deletes.
erase_dirty_object(dirty_it);
auto dirty_end = dirty_it;
dirty_end++;
while (1)
{
if (dirty_it == bs->dirty_db.begin())
{
break;
}
dirty_it--;
if (dirty_it->first.oid != je->big_write.oid)
{
dirty_it++;
break;
}
}
auto clean_it = bs->clean_db.find(je->big_write.oid);
bs->erase_dirty(
dirty_it, dirty_end,
clean_it != bs->clean_db.end() ? clean_it->second.location : UINT64_MAX
);
// Remove it from the flusher's queue, too
// Otherwise it may end up referring to a small unstable write after reading the rest of the journal
bs->flusher->remove_flush(je->big_write.oid);
}
}
auto clean_it = bs->clean_db.find(je->big_write.oid);
@ -744,22 +636,22 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
.oid = je->big_write.oid,
.version = je->big_write.version,
};
void *bmp = NULL;
void *bmp_from = (void*)je + sizeof(journal_entry_big_write);
void *bmp = (void*)je + sizeof(journal_entry_big_write);
if (bs->clean_entry_bitmap_size <= sizeof(void*))
{
memcpy(&bmp, bmp_from, bs->clean_entry_bitmap_size);
memcpy(&bmp, bmp, bs->clean_entry_bitmap_size);
}
else
else if (!bs->journal.inmemory)
{
// FIXME Using large blockstore objects will result in a lot of small
// allocations for entry bitmaps. This can only be fixed by using
// a patched map with dynamic entry size, but not the btree_map,
// because it doesn't keep iterators valid all the time.
bmp = malloc_or_die(bs->clean_entry_bitmap_size);
memcpy(bmp, bmp_from, bs->clean_entry_bitmap_size);
// FIXME Using large blockstore objects and not keeping journal in memory
// will result in a lot of small allocations for entry bitmaps. This can
// only be fixed by using a patched map with dynamic entry size, but not
// the btree_map, because it doesn't keep iterators valid all the time.
void *bmp_cp = malloc_or_die(bs->clean_entry_bitmap_size);
memcpy(bmp_cp, bmp, bs->clean_entry_bitmap_size);
bmp = bmp_cp;
}
auto dirty_it = bs->dirty_db.emplace(ov, (dirty_entry){
bs->dirty_db.emplace(ov, (dirty_entry){
.state = (BS_ST_BIG_WRITE | BS_ST_SYNCED),
.flags = 0,
.location = je->big_write.location,
@ -767,26 +659,11 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
.len = je->big_write.len,
.journal_sector = proc_pos,
.bitmap = bmp,
}).first;
if (bs->data_alloc->get(je->big_write.location >> bs->block_order))
{
// This is probably a big_write that's already flushed and freed, but it may
// also indicate a bug. So we remember such entries and recheck them afterwards.
// If it's not a bug they won't be present after reading the whole journal.
dirty_it->second.location = UINT64_MAX;
double_allocs.push_back(ov);
}
else
{
});
#ifdef BLOCKSTORE_DEBUG
printf(
"Allocate block (journal) %lu: %lx:%lx v%lu\n",
je->big_write.location >> bs->block_order,
ov.oid.inode, ov.oid.stripe, ov.version
);
printf("Allocate block %lu\n", je->big_write.location >> bs->block_order);
#endif
bs->data_alloc->set(je->big_write.location >> bs->block_order, true);
}
bs->data_alloc->set(je->big_write.location >> bs->block_order, true);
bs->journal.used_sectors[proc_pos]++;
#ifdef BLOCKSTORE_DEBUG
printf(
@ -798,7 +675,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
unstab = unstab < ov.version ? ov.version : unstab;
if (je->type == JE_BIG_WRITE_INSTANT)
{
bs->mark_stable(ov, true);
bs->mark_stable(ov);
}
}
}
@ -812,7 +689,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
.oid = je->stable.oid,
.version = je->stable.version,
};
bs->mark_stable(ov, true);
bs->mark_stable(ov);
}
else if (je->type == JE_ROLLBACK)
{
@ -831,26 +708,9 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
#ifdef BLOCKSTORE_DEBUG
printf("je_delete oid=%lx:%lx ver=%lu\n", je->del.oid.inode, je->del.oid.stripe, je->del.version);
#endif
bool dirty_exists = false;
auto dirty_it = bs->dirty_db.upper_bound((obj_ver_id){
.oid = je->del.oid,
.version = UINT64_MAX,
});
if (dirty_it != bs->dirty_db.begin())
{
dirty_it--;
dirty_exists = dirty_it->first.oid == je->del.oid;
}
auto clean_it = bs->clean_db.find(je->del.oid);
bool clean_exists = (clean_it != bs->clean_db.end() &&
clean_it->second.version < je->del.version);
if (!clean_exists && dirty_exists)
{
// Clean entry doesn't exist. This means that the delete is already flushed.
// So we must not flush this object anymore.
erase_dirty_object(dirty_it);
}
else if (clean_exists || dirty_exists)
if (clean_it != bs->clean_db.end() &&
clean_it->second.version < je->del.version)
{
// oid, version
obj_ver_id ov = {
@ -868,9 +728,8 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
bs->journal.used_sectors[proc_pos]++;
// Deletions are treated as immediately stable, because
// "2-phase commit" (write->stabilize) isn't sufficient for them anyway
bs->mark_stable(ov, true);
bs->mark_stable(ov);
}
// Ignore delete if neither preceding dirty entries nor the clean one are present
}
started = true;
pos += je->size;
@ -881,35 +740,3 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
bs->journal.next_free = next_free;
return 1;
}
void blockstore_init_journal::erase_dirty_object(blockstore_dirty_db_t::iterator dirty_it)
{
auto oid = dirty_it->first.oid;
bool exists = !IS_DELETE(dirty_it->second.state);
auto dirty_end = dirty_it;
dirty_end++;
while (1)
{
if (dirty_it == bs->dirty_db.begin())
{
break;
}
dirty_it--;
if (dirty_it->first.oid != oid)
{
dirty_it++;
break;
}
}
auto clean_it = bs->clean_db.find(oid);
uint64_t clean_loc = clean_it != bs->clean_db.end()
? clean_it->second.location : UINT64_MAX;
if (exists && clean_loc == UINT64_MAX)
{
bs->inode_space_stats[oid.inode] -= bs->block_size;
}
bs->erase_dirty(dirty_it, dirty_end, clean_loc);
// Remove it from the flusher's queue, too
// Otherwise it may end up referring to a small unstable write after reading the rest of the journal
bs->flusher->remove_flush(oid);
}

View File

@ -7,7 +7,6 @@ class blockstore_init_meta
{
blockstore_impl_t *bs;
int wait_state = 0, wait_count = 0;
bool zero_on_init = false;
void *metadata_buffer = NULL;
uint64_t metadata_read = 0;
int prev = 0, prev_done = 0, done_len = 0, submitted = 0;
@ -37,7 +36,6 @@ class blockstore_init_journal
bool started = false;
uint64_t next_free;
std::vector<bs_init_journal_done> done;
std::vector<obj_ver_id> double_allocs;
uint64_t journal_pos = 0;
uint64_t continue_pos = 0;
void *init_write_buf = NULL;
@ -50,7 +48,6 @@ class blockstore_init_journal
std::function<void(ring_data_t*)> simple_callback;
int handle_journal_part(void *buf, uint64_t done_pos, uint64_t len);
void handle_event(ring_data_t *data);
void erase_dirty_object(blockstore_dirty_db_t::iterator dirty_it);
public:
blockstore_init_journal(blockstore_impl_t* bs);
int loop();

View File

@ -7,7 +7,6 @@
#define MIN_JOURNAL_SIZE 4*1024*1024
#define JOURNAL_MAGIC 0x4A33
#define JOURNAL_VERSION 1
#define JOURNAL_BUFFER_SIZE 4*1024*1024
// We reserve some extra space for future stabilize requests during writes
@ -38,9 +37,7 @@ struct __attribute__((__packed__)) journal_entry_start
uint32_t size;
uint32_t reserved;
uint64_t journal_start;
uint64_t version;
};
#define JE_START_LEGACY_SIZE 24
struct __attribute__((__packed__)) journal_entry_small_write
{
@ -152,7 +149,6 @@ struct journal_t
int fd;
uint64_t device_size;
bool inmemory = false;
bool flush_journal = false;
void *buffer = NULL;
uint64_t block_size;

View File

@ -42,11 +42,6 @@ void blockstore_impl_t::parse_config(blockstore_config_t & config)
{
disable_flock = true;
}
if (config["flush_journal"] == "true" || config["flush_journal"] == "1" || config["flush_journal"] == "yes")
{
// Only flush journal and exit
journal.flush_journal = true;
}
if (config["immediate_commit"] == "all")
{
immediate_commit = IMMEDIATE_ALL;
@ -74,16 +69,8 @@ void blockstore_impl_t::parse_config(blockstore_config_t & config)
journal_block_size = strtoull(config["journal_block_size"].c_str(), NULL, 10);
meta_block_size = strtoull(config["meta_block_size"].c_str(), NULL, 10);
bitmap_granularity = strtoull(config["bitmap_granularity"].c_str(), NULL, 10);
max_flusher_count = strtoull(config["max_flusher_count"].c_str(), NULL, 10);
if (!max_flusher_count)
max_flusher_count = strtoull(config["flusher_count"].c_str(), NULL, 10);
min_flusher_count = strtoull(config["min_flusher_count"].c_str(), NULL, 10);
flusher_count = strtoull(config["flusher_count"].c_str(), NULL, 10);
max_write_iodepth = strtoull(config["max_write_iodepth"].c_str(), NULL, 10);
throttle_small_writes = config["throttle_small_writes"] == "true" || config["throttle_small_writes"] == "1" || config["throttle_small_writes"] == "yes";
throttle_target_iops = strtoull(config["throttle_target_iops"].c_str(), NULL, 10);
throttle_target_mbs = strtoull(config["throttle_target_mbs"].c_str(), NULL, 10);
throttle_target_parallelism = strtoull(config["throttle_target_parallelism"].c_str(), NULL, 10);
throttle_threshold_us = strtoull(config["throttle_threshold_us"].c_str(), NULL, 10);
// Validate
if (!block_size)
{
@ -93,13 +80,9 @@ void blockstore_impl_t::parse_config(blockstore_config_t & config)
{
throw std::runtime_error("Bad block size");
}
if (!max_flusher_count)
if (!flusher_count)
{
max_flusher_count = 256;
}
if (!min_flusher_count || journal.flush_journal)
{
min_flusher_count = 1;
flusher_count = 32;
}
if (!max_write_iodepth)
{
@ -185,22 +168,6 @@ void blockstore_impl_t::parse_config(blockstore_config_t & config)
{
throw std::runtime_error("immediate_commit=all requires disable_journal_fsync and disable_data_fsync");
}
if (!throttle_target_iops)
{
throttle_target_iops = 100;
}
if (!throttle_target_mbs)
{
throttle_target_mbs = 100;
}
if (!throttle_target_parallelism)
{
throttle_target_parallelism = 1;
}
if (!throttle_threshold_us)
{
throttle_threshold_us = 50;
}
// init some fields
clean_entry_bitmap_size = block_size / bitmap_granularity / 8;
clean_entry_size = sizeof(clean_disk_entry) + 2*clean_entry_bitmap_size;
@ -257,7 +224,7 @@ void blockstore_impl_t::calc_lengths()
}
// required metadata size
block_count = data_len / block_size;
meta_len = (1 + (block_count - 1 + meta_block_size / clean_entry_size) / (meta_block_size / clean_entry_size)) * meta_block_size;
meta_len = ((block_count - 1 + meta_block_size / clean_entry_size) / (meta_block_size / clean_entry_size)) * meta_block_size;
if (meta_area < meta_len)
{
throw std::runtime_error("Metadata area is too small, need at least "+std::to_string(meta_len)+" bytes");

View File

@ -268,50 +268,3 @@ void blockstore_impl_t::handle_read_event(ring_data_t *data, blockstore_op_t *op
FINISH_OP(op);
}
}
int blockstore_impl_t::read_bitmap(object_id oid, uint64_t target_version, void *bitmap, uint64_t *result_version)
{
auto dirty_it = dirty_db.upper_bound((obj_ver_id){
.oid = oid,
.version = UINT64_MAX,
});
if (dirty_it != dirty_db.begin())
dirty_it--;
if (dirty_it != dirty_db.end())
{
while (dirty_it->first.oid == oid)
{
if (target_version >= dirty_it->first.version)
{
if (result_version)
*result_version = dirty_it->first.version;
if (bitmap)
{
void *bmp_ptr = (clean_entry_bitmap_size > sizeof(void*) ? dirty_it->second.bitmap : &dirty_it->second.bitmap);
memcpy(bitmap, bmp_ptr, clean_entry_bitmap_size);
}
return 0;
}
if (dirty_it == dirty_db.begin())
break;
dirty_it--;
}
}
auto clean_it = clean_db.find(oid);
if (clean_it != clean_db.end())
{
if (result_version)
*result_version = clean_it->second.version;
if (bitmap)
{
void *bmp_ptr = get_clean_entry_bitmap(clean_it->second.location, clean_entry_bitmap_size);
memcpy(bitmap, bmp_ptr, clean_entry_bitmap_size);
}
return 0;
}
if (result_version)
*result_version = 0;
if (bitmap)
memset(bitmap, 0, clean_entry_bitmap_size);
return -ENOENT;
}

View File

@ -248,12 +248,10 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
}
while (1)
{
if (IS_BIG_WRITE(dirty_it->second.state) && dirty_it->second.location != clean_loc &&
dirty_it->second.location != UINT64_MAX)
if (IS_BIG_WRITE(dirty_it->second.state) && dirty_it->second.location != clean_loc)
{
#ifdef BLOCKSTORE_DEBUG
printf("Free block %lu from %lx:%lx v%lu\n", dirty_it->second.location >> block_order,
dirty_it->first.oid.inode, dirty_it->first.oid.stripe, dirty_it->first.version);
printf("Free block %lu\n", dirty_it->second.location >> block_order);
#endif
data_alloc->set(dirty_it->second.location >> block_order, false);
}

View File

@ -168,9 +168,6 @@ resume_5:
for (i = 0, v = (obj_ver_id*)op->buf; i < op->len; i++, v++)
{
// Mark all dirty_db entries up to op->version as stable
#ifdef BLOCKSTORE_DEBUG
printf("Stabilize %lx:%lx v%lu\n", v->oid.inode, v->oid.stripe, v->version);
#endif
mark_stable(*v);
}
// Acknowledge op
@ -179,66 +176,31 @@ resume_5:
return 2;
}
void blockstore_impl_t::mark_stable(const obj_ver_id & v, bool forget_dirty)
void blockstore_impl_t::mark_stable(const obj_ver_id & v)
{
auto dirty_it = dirty_db.find(v);
if (dirty_it != dirty_db.end())
{
while (1)
{
bool was_stable = IS_STABLE(dirty_it->second.state);
if ((dirty_it->second.state & BS_ST_WORKFLOW_MASK) == BS_ST_SYNCED)
{
dirty_it->second.state = (dirty_it->second.state & ~BS_ST_WORKFLOW_MASK) | BS_ST_STABLE;
// Allocations and deletions are counted when they're stabilized
if (IS_BIG_WRITE(dirty_it->second.state))
{
int exists = -1;
if (dirty_it != dirty_db.begin())
{
auto prev_it = dirty_it;
prev_it--;
if (prev_it->first.oid == v.oid)
{
exists = IS_DELETE(prev_it->second.state) ? 0 : 1;
}
}
if (exists == -1)
{
auto clean_it = clean_db.find(v.oid);
exists = clean_it != clean_db.end() ? 1 : 0;
}
if (!exists)
{
inode_space_stats[dirty_it->first.oid.inode] += block_size;
}
inode_space_stats[dirty_it->first.oid.inode] += block_size;
}
else if (IS_DELETE(dirty_it->second.state))
{
inode_space_stats[dirty_it->first.oid.inode] -= block_size;
}
}
if (forget_dirty && (IS_BIG_WRITE(dirty_it->second.state) ||
IS_DELETE(dirty_it->second.state)))
else if (IS_STABLE(dirty_it->second.state))
{
// Big write overrides all previous dirty entries
auto erase_end = dirty_it;
while (dirty_it != dirty_db.begin())
{
dirty_it--;
if (dirty_it->first.oid != v.oid)
{
dirty_it++;
break;
}
}
auto clean_it = clean_db.find(v.oid);
uint64_t clean_loc = clean_it != clean_db.end()
? clean_it->second.location : UINT64_MAX;
erase_dirty(dirty_it, erase_end, clean_loc);
break;
}
if (was_stable || dirty_it == dirty_db.begin())
if (dirty_it == dirty_db.begin())
{
break;
}

View File

@ -24,7 +24,6 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op, bool queue_has_in_prog
if (PRIV(op)->op_state == 0)
{
stop_sync_submitted = false;
unsynced_big_write_count -= unsynced_big_writes.size();
PRIV(op)->sync_big_writes.swap(unsynced_big_writes);
PRIV(op)->sync_small_writes.swap(unsynced_small_writes);
PRIV(op)->sync_small_checked = 0;
@ -80,8 +79,7 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op, bool queue_has_in_prog
// 2nd step: Data device is synced, prepare & write journal entries
// Check space in the journal and journal memory buffers
blockstore_journal_check_t space_check(this);
if (!space_check.check_available(op, PRIV(op)->sync_big_writes.size(),
sizeof(journal_entry_big_write) + clean_entry_bitmap_size, JOURNAL_STABILIZE_RESERVATION))
if (!space_check.check_available(op, PRIV(op)->sync_big_writes.size(), sizeof(journal_entry_big_write), JOURNAL_STABILIZE_RESERVATION))
{
return 0;
}
@ -96,7 +94,7 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op, bool queue_has_in_prog
int s = 0, cur_sector = -1;
while (it != PRIV(op)->sync_big_writes.end())
{
if (!journal.entry_fits(sizeof(journal_entry_big_write) + clean_entry_bitmap_size) &&
if (!journal.entry_fits(sizeof(journal_entry_big_write)) &&
journal.sector_info[journal.cur_sector].dirty)
{
if (cur_sector == -1)
@ -104,27 +102,24 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op, bool queue_has_in_prog
prepare_journal_sector_write(journal, journal.cur_sector, sqe[s++], [this, op](ring_data_t *data) { handle_sync_event(data, op); });
cur_sector = journal.cur_sector;
}
auto & dirty_entry = dirty_db.at(*it);
journal_entry_big_write *je = (journal_entry_big_write*)prefill_single_journal_entry(
journal, (dirty_entry.state & BS_ST_INSTANT) ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
sizeof(journal_entry_big_write) + clean_entry_bitmap_size
journal, (dirty_db[*it].state & BS_ST_INSTANT) ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
sizeof(journal_entry_big_write)
);
dirty_entry.journal_sector = journal.sector_info[journal.cur_sector].offset;
dirty_db[*it].journal_sector = journal.sector_info[journal.cur_sector].offset;
journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
#ifdef BLOCKSTORE_DEBUG
printf(
"journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
dirty_entry.journal_sector, it->oid.inode, it->oid.stripe, it->version,
dirty_db[*it].journal_sector, it->oid.inode, it->oid.stripe, it->version,
journal.used_sectors[journal.sector_info[journal.cur_sector].offset]
);
#endif
je->oid = it->oid;
je->version = it->version;
je->offset = dirty_entry.offset;
je->len = dirty_entry.len;
je->location = dirty_entry.location;
memcpy((void*)(je+1), (clean_entry_bitmap_size > sizeof(void*)
? dirty_entry.bitmap : &dirty_entry.bitmap), clean_entry_bitmap_size);
je->offset = dirty_db[*it].offset;
je->len = dirty_db[*it].len;
je->location = dirty_db[*it].location;
je->crc32 = je_crc32((journal_entry*)je);
journal.crc32_last = je->crc32;
it++;

View File

@ -30,13 +30,10 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
wait_big = (dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_BIG_WRITE
? !IS_SYNCED(dirty_it->second.state)
: ((dirty_it->second.state & BS_ST_WORKFLOW_MASK) == BS_ST_WAIT_BIG);
if (!is_del && !deleted)
{
if (clean_entry_bitmap_size > sizeof(void*))
memcpy(bmp, dirty_it->second.bitmap, clean_entry_bitmap_size);
else
bmp = dirty_it->second.bitmap;
}
if (clean_entry_bitmap_size > sizeof(void*))
memcpy(bmp, dirty_it->second.bitmap, clean_entry_bitmap_size);
else
bmp = dirty_it->second.bitmap;
}
}
if (!found)
@ -45,11 +42,8 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
if (clean_it != clean_db.end())
{
version = clean_it->second.version + 1;
if (!is_del)
{
void *bmp_ptr = get_clean_entry_bitmap(clean_it->second.location, clean_entry_bitmap_size);
memcpy((clean_entry_bitmap_size > sizeof(void*) ? bmp : &bmp), bmp_ptr, clean_entry_bitmap_size);
}
void *bmp_ptr = get_clean_entry_bitmap(clean_it->second.location, clean_entry_bitmap_size);
memcpy((clean_entry_bitmap_size > sizeof(void*) ? bmp : &bmp), bmp_ptr, clean_entry_bitmap_size);
}
else
{
@ -122,8 +116,6 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
else
{
state = (op->len == block_size || deleted ? BS_ST_BIG_WRITE : BS_ST_SMALL_WRITE);
if (state == BS_ST_SMALL_WRITE && throttle_small_writes)
clock_gettime(CLOCK_REALTIME, &PRIV(op)->tv_begin);
if (wait_del)
state |= BS_ST_WAIT_DEL;
else if (state == BS_ST_SMALL_WRITE && wait_big)
@ -249,8 +241,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
if ((dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_BIG_WRITE)
{
blockstore_journal_check_t space_check(this);
if (!space_check.check_available(op, unsynced_big_write_count + 1,
sizeof(journal_entry_big_write) + clean_entry_bitmap_size, JOURNAL_STABILIZE_RESERVATION))
if (!space_check.check_available(op, unsynced_big_writes.size() + 1, sizeof(journal_entry_big_write), JOURNAL_STABILIZE_RESERVATION))
{
return 0;
}
@ -273,10 +264,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
dirty_it->second.location = loc << block_order;
dirty_it->second.state = (dirty_it->second.state & ~BS_ST_WORKFLOW_MASK) | BS_ST_SUBMITTED;
#ifdef BLOCKSTORE_DEBUG
printf(
"Allocate block %lu for %lx:%lx v%lu\n",
loc, op->oid.inode, op->oid.stripe, op->version
);
printf("Allocate block %lu\n", loc);
#endif
data_alloc->set(loc, true);
uint64_t stripe_offset = (op->offset % bitmap_granularity);
@ -302,8 +290,11 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
PRIV(op)->min_flushed_journal_sector = PRIV(op)->max_flushed_journal_sector = 0;
if (immediate_commit != IMMEDIATE_ALL)
{
// Increase the counter, but don't save into unsynced_writes yet (can't sync until the write is finished)
unsynced_big_write_count++;
// Remember big write as unsynced
unsynced_big_writes.push_back((obj_ver_id){
.oid = op->oid,
.version = op->version,
});
PRIV(op)->op_state = 3;
}
else
@ -316,11 +307,8 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
// Small (journaled) write
// First check if the journal has sufficient space
blockstore_journal_check_t space_check(this);
if (unsynced_big_write_count &&
!space_check.check_available(op, unsynced_big_write_count,
sizeof(journal_entry_big_write) + clean_entry_bitmap_size, 0)
|| !space_check.check_available(op, 1,
sizeof(journal_entry_small_write) + clean_entry_bitmap_size, op->len + JOURNAL_STABILIZE_RESERVATION))
if (unsynced_big_writes.size() && !space_check.check_available(op, unsynced_big_writes.size(), sizeof(journal_entry_big_write), 0)
|| !space_check.check_available(op, 1, sizeof(journal_entry_small_write), op->len + JOURNAL_STABILIZE_RESERVATION))
{
return 0;
}
@ -328,7 +316,8 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
// There is sufficient space. Get SQE(s)
struct io_uring_sqe *sqe1 = NULL;
if (immediate_commit != IMMEDIATE_NONE ||
!journal.entry_fits(sizeof(journal_entry_small_write) + clean_entry_bitmap_size))
(journal_block_size - journal.in_sector_pos) < sizeof(journal_entry_small_write) &&
journal.sector_info[journal.cur_sector].dirty)
{
// Write current journal sector only if it's dirty and full, or in the immediate_commit mode
BS_SUBMIT_GET_SQE_DECL(sqe1);
@ -411,6 +400,14 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
{
journal.next_free = journal_block_size;
}
if (immediate_commit == IMMEDIATE_NONE)
{
// Remember small write as unsynced
unsynced_small_writes.push_back((obj_ver_id){
.oid = op->oid,
.version = op->version,
});
}
if (!PRIV(op)->pending_ops)
{
PRIV(op)->op_state = 4;
@ -426,148 +423,85 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
int blockstore_impl_t::continue_write(blockstore_op_t *op)
{
io_uring_sqe *sqe = NULL;
journal_entry_big_write *je;
int op_state = PRIV(op)->op_state;
if (op_state == 2)
goto resume_2;
else if (op_state == 4)
goto resume_4;
else if (op_state == 6)
goto resume_6;
else
if (op_state != 2 && op_state != 4)
{
// In progress
return 1;
}
auto dirty_it = dirty_db.find((obj_ver_id){
.oid = op->oid,
.version = op->version,
});
assert(dirty_it != dirty_db.end());
if (op_state == 2)
goto resume_2;
else if (op_state == 4)
goto resume_4;
resume_2:
// Only for the immediate_commit mode: prepare and submit big_write journal entry
{
auto dirty_it = dirty_db.find((obj_ver_id){
.oid = op->oid,
.version = op->version,
});
assert(dirty_it != dirty_db.end());
io_uring_sqe *sqe = NULL;
BS_SUBMIT_GET_SQE_DECL(sqe);
journal_entry_big_write *je = (journal_entry_big_write*)prefill_single_journal_entry(
journal, op->opcode == BS_OP_WRITE_STABLE ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
sizeof(journal_entry_big_write) + clean_entry_bitmap_size
);
dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
BS_SUBMIT_GET_SQE_DECL(sqe);
je = (journal_entry_big_write*)prefill_single_journal_entry(
journal, op->opcode == BS_OP_WRITE_STABLE ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
sizeof(journal_entry_big_write) + clean_entry_bitmap_size
);
dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
#ifdef BLOCKSTORE_DEBUG
printf(
"journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
journal.sector_info[journal.cur_sector].offset, op->oid.inode, op->oid.stripe, op->version,
journal.used_sectors[journal.sector_info[journal.cur_sector].offset]
);
printf(
"journal offset %08lx is used by %lx:%lx v%lu (%lu refs)\n",
journal.sector_info[journal.cur_sector].offset, op->oid.inode, op->oid.stripe, op->version,
journal.used_sectors[journal.sector_info[journal.cur_sector].offset]
);
#endif
je->oid = op->oid;
je->version = op->version;
je->offset = op->offset;
je->len = op->len;
je->location = dirty_it->second.location;
memcpy((void*)(je+1), (clean_entry_bitmap_size > sizeof(void*) ? dirty_it->second.bitmap : &dirty_it->second.bitmap), clean_entry_bitmap_size);
je->crc32 = je_crc32((journal_entry*)je);
journal.crc32_last = je->crc32;
prepare_journal_sector_write(journal, journal.cur_sector, sqe,
[this, op](ring_data_t *data) { handle_write_event(data, op); });
PRIV(op)->min_flushed_journal_sector = PRIV(op)->max_flushed_journal_sector = 1 + journal.cur_sector;
PRIV(op)->pending_ops = 1;
PRIV(op)->op_state = 3;
return 1;
}
je->oid = op->oid;
je->version = op->version;
je->offset = op->offset;
je->len = op->len;
je->location = dirty_it->second.location;
memcpy((void*)(je+1), (clean_entry_bitmap_size > sizeof(void*) ? dirty_it->second.bitmap : &dirty_it->second.bitmap), clean_entry_bitmap_size);
je->crc32 = je_crc32((journal_entry*)je);
journal.crc32_last = je->crc32;
prepare_journal_sector_write(journal, journal.cur_sector, sqe,
[this, op](ring_data_t *data) { handle_write_event(data, op); });
PRIV(op)->min_flushed_journal_sector = PRIV(op)->max_flushed_journal_sector = 1 + journal.cur_sector;
PRIV(op)->pending_ops = 1;
PRIV(op)->op_state = 3;
return 1;
resume_4:
// Switch object state
#ifdef BLOCKSTORE_DEBUG
printf("Ack write %lx:%lx v%lu = state 0x%x\n", op->oid.inode, op->oid.stripe, op->version, dirty_it->second.state);
printf("Ack write %lx:%lx v%lu = state %x\n", op->oid.inode, op->oid.stripe, op->version, dirty_it->second.state);
#endif
bool imm = (dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_BIG_WRITE
? (immediate_commit == IMMEDIATE_ALL)
: (immediate_commit != IMMEDIATE_NONE);
if (imm)
{
auto dirty_it = dirty_db.find((obj_ver_id){
.oid = op->oid,
.version = op->version,
});
assert(dirty_it != dirty_db.end());
bool is_big = (dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_BIG_WRITE;
bool imm = is_big ? (immediate_commit == IMMEDIATE_ALL) : (immediate_commit != IMMEDIATE_NONE);
if (imm)
auto & unstab = unstable_writes[op->oid];
unstab = unstab < op->version ? op->version : unstab;
}
dirty_it->second.state = (dirty_it->second.state & ~BS_ST_WORKFLOW_MASK)
| (imm ? BS_ST_SYNCED : BS_ST_WRITTEN);
if (imm && ((dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_DELETE || (dirty_it->second.state & BS_ST_INSTANT)))
{
// Deletions are treated as immediately stable
mark_stable(dirty_it->first);
}
if (immediate_commit == IMMEDIATE_ALL)
{
dirty_it++;
while (dirty_it != dirty_db.end() && dirty_it->first.oid == op->oid)
{
auto & unstab = unstable_writes[op->oid];
unstab = unstab < op->version ? op->version : unstab;
}
dirty_it->second.state = (dirty_it->second.state & ~BS_ST_WORKFLOW_MASK)
| (imm ? BS_ST_SYNCED : BS_ST_WRITTEN);
if (imm && ((dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_DELETE || (dirty_it->second.state & BS_ST_INSTANT)))
{
// Deletions and 'instant' operations are treated as immediately stable
mark_stable(dirty_it->first);
}
if (!imm)
{
if (is_big)
if ((dirty_it->second.state & BS_ST_WORKFLOW_MASK) == BS_ST_WAIT_BIG)
{
// Remember big write as unsynced
unsynced_big_writes.push_back((obj_ver_id){
.oid = op->oid,
.version = op->version,
});
dirty_it->second.state = (dirty_it->second.state & ~BS_ST_WORKFLOW_MASK) | BS_ST_IN_FLIGHT;
}
else
{
// Remember small write as unsynced
unsynced_small_writes.push_back((obj_ver_id){
.oid = op->oid,
.version = op->version,
});
}
}
if (imm && (dirty_it->second.state & BS_ST_TYPE_MASK) == BS_ST_BIG_WRITE)
{
// Unblock small writes
dirty_it++;
while (dirty_it != dirty_db.end() && dirty_it->first.oid == op->oid)
{
if ((dirty_it->second.state & BS_ST_WORKFLOW_MASK) == BS_ST_WAIT_BIG)
{
dirty_it->second.state = (dirty_it->second.state & ~BS_ST_WORKFLOW_MASK) | BS_ST_IN_FLIGHT;
}
dirty_it++;
}
}
// Apply throttling to not fill the journal too fast for the SSD+HDD case
if (!is_big && throttle_small_writes)
{
// Apply throttling
timespec tv_end;
clock_gettime(CLOCK_REALTIME, &tv_end);
uint64_t exec_us =
(tv_end.tv_sec - PRIV(op)->tv_begin.tv_sec)*1000000 +
(tv_end.tv_nsec - PRIV(op)->tv_begin.tv_nsec)/1000;
// Compare with target execution time
// 100% free -> target time = 0
// 0% free -> target time = iodepth/parallelism * (iops + size/bw) / write per second
uint64_t used_start = journal.get_trim_pos();
uint64_t journal_free_space = journal.next_free < used_start
? (used_start - journal.next_free)
: (journal.len - journal.next_free + used_start - journal.block_size);
uint64_t ref_us =
(write_iodepth <= throttle_target_parallelism ? 100 : 100*write_iodepth/throttle_target_parallelism)
* (1000000/throttle_target_iops + op->len*1000000/throttle_target_mbs/1024/1024)
/ 100;
ref_us -= ref_us * journal_free_space / journal.len;
if (ref_us > exec_us + throttle_threshold_us)
{
// Pause reply
tfd->set_timer_us(ref_us-exec_us, false, [this, op](int timer_id)
{
PRIV(op)->op_state++;
ringloop->wakeup();
});
PRIV(op)->op_state = 5;
return 1;
}
}
}
resume_6:
// Acknowledge write
op->retval = op->len;
write_iodepth--;
@ -691,6 +625,14 @@ int blockstore_impl_t::dequeue_del(blockstore_op_t *op)
PRIV(op)->min_flushed_journal_sector = PRIV(op)->max_flushed_journal_sector = 1 + journal.cur_sector;
PRIV(op)->pending_ops++;
}
else
{
// Remember delete as unsynced
unsynced_small_writes.push_back((obj_ver_id){
.oid = op->oid,
.version = op->version,
});
}
if (!PRIV(op)->pending_ops)
{
PRIV(op)->op_state = 4;

File diff suppressed because it is too large Load Diff

View File

@ -8,8 +8,7 @@
#define MIN_BLOCK_SIZE 4*1024
#define MAX_BLOCK_SIZE 128*1024*1024
#define DEFAULT_CLIENT_MAX_DIRTY_BYTES 32*1024*1024
#define DEFAULT_CLIENT_MAX_DIRTY_OPS 1024
#define DEFAULT_CLIENT_DIRTY_LIMIT 32*1024*1024
struct cluster_op_t;
@ -21,7 +20,8 @@ struct cluster_op_part_t
pg_num_t pg_num;
osd_num_t osd_num;
osd_op_buf_list_t iov;
unsigned flags;
bool sent;
bool done;
osd_op_t op;
};
@ -36,28 +36,19 @@ struct cluster_op_t
std::function<void(cluster_op_t*)> callback;
~cluster_op_t();
protected:
int flags = 0;
int state = 0;
uint64_t cur_inode; // for snapshot reads
void *buf = NULL;
cluster_op_t *orig_op = NULL;
bool is_internal = false;
bool needs_reslice = false;
bool up_wait = false;
int inflight_count = 0, done_count = 0;
int sent_count = 0, done_count = 0;
std::vector<cluster_op_part_t> parts;
void *bitmap_buf = NULL, *part_bitmaps = NULL;
unsigned bitmap_buf_size = 0;
friend class cluster_client_t;
};
struct cluster_buffer_t
{
void *buf;
uint64_t len;
int state;
};
// FIXME: Split into public and private interfaces
class cluster_client_t
{
timerfd_manager_t *tfd;
@ -68,27 +59,28 @@ class cluster_client_t
std::map<pool_id_t, uint64_t> pg_counts;
bool immediate_commit = false;
// FIXME: Implement inmemory_commit mode. Note that it requires to return overlapping reads from memory.
uint64_t client_max_dirty_bytes = 0;
uint64_t client_max_dirty_ops = 0;
uint64_t client_dirty_limit = 0;
int log_level;
int up_wait_retry_interval = 500; // ms
int retry_timeout_id = 0;
uint64_t op_id = 1;
ring_consumer_t consumer;
// operations currently in progress
std::set<cluster_op_t*> cur_ops;
int retry_timeout_id = 0;
// unsynced operations are copied in memory to allow replay when cluster isn't in the immediate_commit mode
// unsynced_writes are replayed in any order (because only the SYNC operation guarantees ordering)
std::vector<cluster_op_t*> unsynced_writes;
std::vector<cluster_op_t*> syncing_writes;
cluster_op_t* cur_sync = NULL;
std::vector<cluster_op_t*> next_writes;
std::vector<cluster_op_t*> offline_ops;
std::vector<cluster_op_t*> op_queue;
std::map<object_id, cluster_buffer_t> dirty_buffers;
std::set<osd_num_t> dirty_osds;
uint64_t dirty_bytes = 0, dirty_ops = 0;
uint64_t queued_bytes = 0;
void *scrap_buffer = NULL;
unsigned scrap_buffer_size = 0;
bool pgs_loaded = false;
ring_consumer_t consumer;
std::vector<std::function<void(void)>> on_ready_hooks;
int continuing_ops = 0;
int op_queue_pos = 0;
public:
etcd_state_client_t st_cli;
@ -101,20 +93,19 @@ public:
bool is_ready();
void on_ready(std::function<void(void)> fn);
static void copy_write(cluster_op_t *op, std::map<object_id, cluster_buffer_t> & dirty_buffers);
void continue_ops(bool up_retry = false);
protected:
bool affects_osd(uint64_t inode, uint64_t offset, uint64_t len, osd_num_t osd);
void flush_buffer(const object_id & oid, cluster_buffer_t *wr);
void continue_ops(bool up_retry = false);
void on_load_config_hook(json11::Json::object & config);
void on_load_pgs_hook(bool success);
void on_change_hook(std::map<std::string, etcd_kv_t> & changes);
void on_change_hook(json11::Json::object & changes);
void on_change_osd_state_hook(uint64_t peer_osd);
int continue_rw(cluster_op_t *op);
cluster_op_t *copy_write(cluster_op_t *op);
void continue_rw(cluster_op_t *op);
void slice_rw(cluster_op_t *op);
bool try_send(cluster_op_t *op, int i);
int continue_sync(cluster_op_t *op);
void execute_sync(cluster_op_t *op);
void continue_sync();
void finish_sync();
void send_sync(cluster_op_t *op, cluster_op_part_t *part);
void handle_op_part(cluster_op_part_t *part);
void copy_part_bitmap(cluster_op_t *op, cluster_op_part_t *part);
};

View File

@ -4,10 +4,8 @@
#include "osd_ops.h"
#include "pg_states.h"
#include "etcd_state_client.h"
#ifndef __MOCK__
#include "http_client.h"
#include "base64.h"
#endif
etcd_state_client_t::~etcd_state_client_t()
{
@ -17,19 +15,16 @@ etcd_state_client_t::~etcd_state_client_t()
}
watches.clear();
etcd_watches_initialised = -1;
#ifndef __MOCK__
if (etcd_watch_ws)
{
etcd_watch_ws->close();
etcd_watch_ws = NULL;
}
#endif
}
#ifndef __MOCK__
etcd_kv_t etcd_state_client_t::parse_etcd_kv(const json11::Json & kv_json)
json_kv_t etcd_state_client_t::parse_etcd_kv(const json11::Json & kv_json)
{
etcd_kv_t kv;
json_kv_t kv;
kv.key = base64_decode(kv_json["key"].string_value());
std::string json_err, json_text = base64_decode(kv_json["value"].string_value());
kv.value = json_text == "" ? json11::Json() : json11::Json::parse(json_text, json_err);
@ -38,8 +33,6 @@ etcd_kv_t etcd_state_client_t::parse_etcd_kv(const json11::Json & kv_json)
printf("Bad JSON in etcd key %s: %s (value: %s)\n", kv.key.c_str(), json_err.c_str(), json_text.c_str());
kv.key = "";
}
else
kv.mod_revision = kv_json["mod_revision"].uint64_value();
return kv;
}
@ -152,22 +145,22 @@ void etcd_state_client_t::start_etcd_watcher()
etcd_watch_revision = data["result"]["header"]["revision"].uint64_value();
}
// First gather all changes into a hash to remove multiple overwrites
std::map<std::string, etcd_kv_t> changes;
json11::Json::object changes;
for (auto & ev: data["result"]["events"].array_items())
{
auto kv = parse_etcd_kv(ev["kv"]);
if (kv.key != "")
{
changes[kv.key] = kv;
changes[kv.key] = kv.value;
}
}
for (auto & kv: changes)
{
if (this->log_level > 3)
{
printf("Incoming event: %s -> %s\n", kv.first.c_str(), kv.second.value.dump().c_str());
printf("Incoming event: %s -> %s\n", kv.first.c_str(), kv.second.dump().c_str());
}
parse_state(kv.second);
parse_state(kv.first, kv.second);
}
// React to changes
if (on_change_hook != NULL)
@ -334,33 +327,16 @@ void etcd_state_client_t::load_pgs()
for (auto & kv_json: res["response_range"]["kvs"].array_items())
{
auto kv = parse_etcd_kv(kv_json);
parse_state(kv);
parse_state(kv.key, kv.value);
}
}
on_load_pgs_hook(true);
start_etcd_watcher();
});
}
#else
void etcd_state_client_t::parse_config(json11::Json & config)
{
}
void etcd_state_client_t::load_global_config()
void etcd_state_client_t::parse_state(const std::string & key, const json11::Json & value)
{
json11::Json::object global_config;
on_load_config_hook(global_config);
}
void etcd_state_client_t::load_pgs()
{
}
#endif
void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
{
const std::string & key = kv.key;
const json11::Json & value = kv.value;
if (key == etcd_prefix+"/config/pools")
{
for (auto & pool_item: this->pool_config)
@ -371,10 +347,8 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
{
pool_config_t pc;
// ID
pool_id_t pool_id;
char null_byte = 0;
sscanf(pool_item.first.c_str(), "%u%c", &pool_id, &null_byte);
if (!pool_id || pool_id >= POOL_ID_MAX || null_byte != 0)
pool_id_t pool_id = stoull_full(pool_item.first);
if (!pool_id || pool_id >= POOL_ID_MAX)
{
printf("Pool ID %s is invalid (must be a number less than 0x%x), skipping pool\n", pool_item.first.c_str(), POOL_ID_MAX);
continue;
@ -486,19 +460,16 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
}
for (auto & pool_item: value["items"].object_items())
{
pool_id_t pool_id;
char null_byte = 0;
sscanf(pool_item.first.c_str(), "%u%c", &pool_id, &null_byte);
if (!pool_id || pool_id >= POOL_ID_MAX || null_byte != 0)
pool_id_t pool_id = stoull_full(pool_item.first);
if (!pool_id || pool_id >= POOL_ID_MAX)
{
printf("Pool ID %s is invalid in PG configuration (must be a number less than 0x%x), skipping pool\n", pool_item.first.c_str(), POOL_ID_MAX);
continue;
}
for (auto & pg_item: pool_item.second.object_items())
{
pg_num_t pg_num = 0;
sscanf(pg_item.first.c_str(), "%u%c", &pg_num, &null_byte);
if (!pg_num || null_byte != 0)
pg_num_t pg_num = stoull_full(pg_item.first);
if (!pg_num)
{
printf("Bad key in pool %u PG configuration: %s (must be a number), skipped\n", pool_id, pg_item.first.c_str());
continue;
@ -711,7 +682,6 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
.size = value["size"].uint64_value(),
.parent_id = parent_inode_num,
.readonly = value["readonly"].bool_value(),
.mod_revision = kv.mod_revision,
};
this->inode_config[inode_num] = cfg;
if (cfg.name != "")

View File

@ -3,8 +3,8 @@
#pragma once
#include "json11/json11.hpp"
#include "osd_id.h"
#include "http_client.h"
#include "timerfd_manager.h"
#define ETCD_CONFIG_WATCH_ID 1
@ -18,11 +18,10 @@
#define DEFAULT_BLOCK_SIZE 128*1024
struct etcd_kv_t
struct json_kv_t
{
std::string key;
json11::Json value;
uint64_t mod_revision;
};
struct pg_config_t
@ -60,8 +59,6 @@ struct inode_config_t
uint64_t size;
inode_t parent_id;
bool readonly;
// Change revision of the metadata in etcd
uint64_t mod_revision;
};
struct inode_watch_t
@ -70,14 +67,12 @@ struct inode_watch_t
inode_config_t cfg;
};
struct websocket_t;
struct etcd_state_client_t
{
protected:
std::vector<inode_watch_t*> watches;
websocket_t *etcd_watch_ws = NULL;
uint64_t bs_block_size = DEFAULT_BLOCK_SIZE;
uint64_t bs_block_size = 0;
void add_etcd_url(std::string);
public:
std::vector<std::string> etcd_addresses;
@ -92,20 +87,20 @@ public:
std::map<inode_t, inode_config_t> inode_config;
std::map<std::string, inode_t> inode_by_name;
std::function<void(std::map<std::string, etcd_kv_t> &)> on_change_hook;
std::function<void(json11::Json::object &)> on_change_hook;
std::function<void(json11::Json::object &)> on_load_config_hook;
std::function<json11::Json()> load_pgs_checks_hook;
std::function<void(bool)> on_load_pgs_hook;
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;
etcd_kv_t parse_etcd_kv(const json11::Json & kv_json);
json_kv_t parse_etcd_kv(const json11::Json & kv_json);
void etcd_call(std::string api, json11::Json payload, int timeout, std::function<void(std::string, json11::Json)> callback);
void etcd_txn(json11::Json txn, int timeout, std::function<void(std::string, json11::Json)> callback);
void start_etcd_watcher();
void load_global_config();
void load_pgs();
void parse_state(const etcd_kv_t & kv);
void parse_state(const std::string & key, const json11::Json & value);
void parse_config(json11::Json & config);
inode_watch_t* watch_inode(std::string name);
void close_watch(inode_watch_t* watch);

View File

@ -25,7 +25,6 @@
// -bs_config='{"data_device":"./test_data.bin"}' -size=1000M
#include "blockstore.h"
#include "epoll_manager.h"
#include "fio_headers.h"
#include "json11/json11.hpp"
@ -33,7 +32,6 @@
struct bs_data
{
blockstore_t *bs;
epoll_manager_t *epmgr;
ring_loop_t *ringloop;
/* The list of completed io_u structs. */
std::vector<io_u*> completed;
@ -106,7 +104,6 @@ static void bs_cleanup(struct thread_data *td)
}
safe:
delete bsd->bs;
delete bsd->epmgr;
delete bsd->ringloop;
delete bsd;
}
@ -132,8 +129,7 @@ static int bs_init(struct thread_data *td)
}
}
bsd->ringloop = new ring_loop_t(512);
bsd->epmgr = new epoll_manager_t(bsd->ringloop);
bsd->bs = new blockstore_t(config, bsd->ringloop, bsd->epmgr->tfd);
bsd->bs = new blockstore_t(config, bsd->ringloop);
while (1)
{
bsd->ringloop->loop();

View File

@ -10,16 +10,30 @@
#include "messenger.h"
osd_op_t::~osd_op_t()
{
assert(!bs_op);
assert(!op_data);
if (rmw_buf)
{
free(rmw_buf);
}
if (buf)
{
// Note: reusing osd_op_t WILL currently lead to memory leaks
// So we don't reuse it, but free it every time
free(buf);
}
}
void osd_messenger_t::init()
{
keepalive_timer_id = tfd->set_timer(1000, true, [this](int)
{
std::vector<int> to_stop;
std::vector<osd_op_t*> to_ping;
for (auto cl_it = clients.begin(); cl_it != clients.end(); cl_it++)
for (auto cl_it = clients.begin(); cl_it != clients.end();)
{
auto cl = cl_it->second;
if (!cl->osd_num || cl->peer_state != PEER_CONNECTED)
auto cl = (cl_it++)->second;
if (!cl->osd_num)
{
// Do not run keepalive on regular clients
continue;
@ -30,8 +44,7 @@ void osd_messenger_t::init()
if (!cl->ping_time_remaining)
{
// Ping timed out, stop the client
printf("Ping timed out for OSD %lu (client %d), disconnecting peer\n", cl->osd_num, cl->peer_fd);
to_stop.push_back(cl->peer_fd);
stop_client(cl->peer_fd, true);
}
}
else if (cl->idle_time_remaining > 0)
@ -57,11 +70,10 @@ void osd_messenger_t::init()
delete op;
if (fail_fd >= 0)
{
printf("Ping failed for OSD %lu (client %d), disconnecting peer\n", cl->osd_num, cl->peer_fd);
stop_client(fail_fd, true);
}
};
to_ping.push_back(op);
outbox_push(op);
cl->ping_time_remaining = osd_ping_timeout;
cl->idle_time_remaining = osd_idle_timeout;
}
@ -71,15 +83,6 @@ void osd_messenger_t::init()
cl->idle_time_remaining = osd_idle_timeout;
}
}
// Don't stop clients while a 'clients' iterator is still active
for (int peer_fd: to_stop)
{
stop_client(peer_fd, true);
}
for (auto op: to_ping)
{
outbox_push(op);
}
});
}
@ -138,14 +141,17 @@ void osd_messenger_t::connect_peer(uint64_t peer_osd, json11::Json peer_state)
wanted_peers[peer_osd].port = (int)peer_state["port"].int64_value();
}
wanted_peers[peer_osd].address_changed = true;
try_connect_peer(peer_osd);
if (!wanted_peers[peer_osd].connecting &&
(time(NULL) - wanted_peers[peer_osd].last_connect_attempt) >= peer_connect_interval)
{
try_connect_peer(peer_osd);
}
}
void osd_messenger_t::try_connect_peer(uint64_t peer_osd)
{
auto wp_it = wanted_peers.find(peer_osd);
if (wp_it == wanted_peers.end() || wp_it->second.connecting ||
(time(NULL) - wp_it->second.last_connect_attempt) < peer_connect_interval)
if (wp_it == wanted_peers.end())
{
return;
}
@ -191,22 +197,10 @@ void osd_messenger_t::try_connect_peer_addr(osd_num_t peer_osd, const char *peer
on_connect_peer(peer_osd, -errno);
return;
}
clients[peer_fd] = new osd_client_t();
clients[peer_fd]->peer_addr = addr;
clients[peer_fd]->peer_port = peer_port;
clients[peer_fd]->peer_fd = peer_fd;
clients[peer_fd]->peer_state = PEER_CONNECTING;
clients[peer_fd]->connect_timeout_id = -1;
clients[peer_fd]->osd_num = peer_osd;
clients[peer_fd]->in_buf = malloc_or_die(receive_buffer_size);
tfd->set_fd_handler(peer_fd, true, [this](int peer_fd, int epoll_events)
{
// Either OUT (connected) or HUP
handle_connect_epoll(peer_fd);
});
int timeout_id = -1;
if (peer_connect_timeout > 0)
{
clients[peer_fd]->connect_timeout_id = tfd->set_timer(1000*peer_connect_timeout, false, [this, peer_fd](int timer_id)
timeout_id = tfd->set_timer(1000*peer_connect_timeout, false, [this, peer_fd](int timer_id)
{
osd_num_t peer_osd = clients.at(peer_fd)->osd_num;
stop_client(peer_fd, true);
@ -214,6 +208,20 @@ void osd_messenger_t::try_connect_peer_addr(osd_num_t peer_osd, const char *peer
return;
});
}
clients[peer_fd] = new osd_client_t((osd_client_t){
.peer_addr = addr,
.peer_port = peer_port,
.peer_fd = peer_fd,
.peer_state = PEER_CONNECTING,
.connect_timeout_id = timeout_id,
.osd_num = peer_osd,
.in_buf = malloc_or_die(receive_buffer_size),
});
tfd->set_fd_handler(peer_fd, true, [this](int peer_fd, int epoll_events)
{
// Either OUT (connected) or HUP
handle_connect_epoll(peer_fd);
});
}
void osd_messenger_t::handle_connect_epoll(int peer_fd)
@ -349,15 +357,6 @@ void osd_messenger_t::check_peer_config(osd_client_t *cl)
err = true;
printf("Connected to OSD %lu instead of OSD %lu, peer state is outdated, disconnecting peer\n", config["osd_num"].uint64_value(), cl->osd_num);
}
else if (config["protocol_version"].uint64_value() != OSD_PROTOCOL_VERSION)
{
err = true;
printf(
"OSD %lu protocol version is %lu, but only version %u is supported.\n"
" If you need to upgrade from 0.5.x please request it via the issue tracker.\n",
cl->osd_num, config["protocol_version"].uint64_value(), OSD_PROTOCOL_VERSION
);
}
}
if (err)
{
@ -374,6 +373,123 @@ void osd_messenger_t::check_peer_config(osd_client_t *cl)
outbox_push(op);
}
void osd_messenger_t::cancel_osd_ops(osd_client_t *cl)
{
for (auto p: cl->sent_ops)
{
cancel_op(p.second);
}
cl->sent_ops.clear();
cl->outbox.clear();
}
void osd_messenger_t::cancel_op(osd_op_t *op)
{
if (op->op_type == OSD_OP_OUT)
{
op->reply.hdr.magic = SECONDARY_OSD_REPLY_MAGIC;
op->reply.hdr.id = op->req.hdr.id;
op->reply.hdr.opcode = op->req.hdr.opcode;
op->reply.hdr.retval = -EPIPE;
// Copy lambda to be unaffected by `delete op`
std::function<void(osd_op_t*)>(op->callback)(op);
}
else
{
// This function is only called in stop_client(), so it's fine to destroy the operation
delete op;
}
}
void osd_messenger_t::stop_client(int peer_fd, bool force)
{
assert(peer_fd != 0);
auto it = clients.find(peer_fd);
if (it == clients.end())
{
return;
}
uint64_t repeer_osd = 0;
osd_client_t *cl = it->second;
if (cl->peer_state == PEER_CONNECTED)
{
if (cl->osd_num)
{
// Reload configuration from etcd when the connection is dropped
if (log_level > 0)
printf("[OSD %lu] Stopping client %d (OSD peer %lu)\n", osd_num, peer_fd, cl->osd_num);
repeer_osd = cl->osd_num;
}
else
{
if (log_level > 0)
printf("[OSD %lu] Stopping client %d (regular client)\n", osd_num, peer_fd);
}
}
else if (!force)
{
return;
}
cl->peer_state = PEER_STOPPED;
clients.erase(it);
tfd->set_fd_handler(peer_fd, false, NULL);
if (cl->connect_timeout_id >= 0)
{
tfd->clear_timer(cl->connect_timeout_id);
cl->connect_timeout_id = -1;
}
if (cl->osd_num)
{
osd_peer_fds.erase(cl->osd_num);
}
if (cl->read_op)
{
if (cl->read_op->callback)
{
cancel_op(cl->read_op);
}
else
{
delete cl->read_op;
}
cl->read_op = NULL;
}
for (auto rit = read_ready_clients.begin(); rit != read_ready_clients.end(); rit++)
{
if (*rit == peer_fd)
{
read_ready_clients.erase(rit);
break;
}
}
for (auto wit = write_ready_clients.begin(); wit != write_ready_clients.end(); wit++)
{
if (*wit == peer_fd)
{
write_ready_clients.erase(wit);
break;
}
}
free(cl->in_buf);
cl->in_buf = NULL;
close(peer_fd);
if (repeer_osd)
{
// First repeer PGs as canceling OSD ops may push new operations
// and we need correct PG states when we do that
repeer_pgs(repeer_osd);
}
if (cl->osd_num)
{
// Cancel outbound operations
cancel_osd_ops(cl);
}
if (cl->refs <= 0)
{
delete cl;
}
}
void osd_messenger_t::accept_connections(int listen_fd)
{
// Accept new connections
@ -389,12 +505,13 @@ void osd_messenger_t::accept_connections(int listen_fd)
fcntl(peer_fd, F_SETFL, fcntl(peer_fd, F_GETFL, 0) | O_NONBLOCK);
int one = 1;
setsockopt(peer_fd, SOL_TCP, TCP_NODELAY, &one, sizeof(one));
clients[peer_fd] = new osd_client_t();
clients[peer_fd]->peer_addr = addr;
clients[peer_fd]->peer_port = ntohs(addr.sin_port);
clients[peer_fd]->peer_fd = peer_fd;
clients[peer_fd]->peer_state = PEER_CONNECTED;
clients[peer_fd]->in_buf = malloc_or_die(receive_buffer_size);
clients[peer_fd] = new osd_client_t((osd_client_t){
.peer_addr = addr,
.peer_port = ntohs(addr.sin_port),
.peer_fd = peer_fd,
.peer_state = PEER_CONNECTED,
.in_buf = malloc_or_die(receive_buffer_size),
});
// Add FD to epoll
tfd->set_fd_handler(peer_fd, false, [this](int peer_fd, int epoll_events)
{

View File

@ -14,15 +14,19 @@
#include "malloc_or_die.h"
#include "json11/json11.hpp"
#include "msgr_op.h"
#include "osd_ops.h"
#include "timerfd_manager.h"
#include <ringloop.h>
#include "ringloop.h"
#define OSD_OP_IN 0
#define OSD_OP_OUT 1
#define CL_READ_HDR 1
#define CL_READ_DATA 2
#define CL_READ_REPLY_DATA 3
#define CL_WRITE_READY 1
#define CL_WRITE_REPLY 2
#define OSD_OP_INLINE_BUF_COUNT 16
#define PEER_CONNECTING 1
#define PEER_CONNECTED 2
@ -33,6 +37,164 @@
#define DEFAULT_OSD_PING_TIMEOUT 5
#define DEFAULT_BITMAP_GRANULARITY 4096
// Kind of a vector with small-list-optimisation
struct osd_op_buf_list_t
{
int count = 0, alloc = OSD_OP_INLINE_BUF_COUNT, done = 0;
iovec *buf = NULL;
iovec inline_buf[OSD_OP_INLINE_BUF_COUNT];
inline osd_op_buf_list_t()
{
buf = inline_buf;
}
inline osd_op_buf_list_t(const osd_op_buf_list_t & other)
{
buf = inline_buf;
append(other);
}
inline osd_op_buf_list_t & operator = (const osd_op_buf_list_t & other)
{
reset();
append(other);
return *this;
}
inline ~osd_op_buf_list_t()
{
if (buf && buf != inline_buf)
{
free(buf);
}
}
inline void reset()
{
count = 0;
done = 0;
}
inline iovec* get_iovec()
{
return buf + done;
}
inline int get_size()
{
return count - done;
}
inline void append(const osd_op_buf_list_t & other)
{
if (count+other.count > alloc)
{
if (buf == inline_buf)
{
int old = alloc;
alloc = (((count+other.count+15)/16)*16);
buf = (iovec*)malloc(sizeof(iovec) * alloc);
if (!buf)
{
printf("Failed to allocate %lu bytes\n", sizeof(iovec) * alloc);
exit(1);
}
memcpy(buf, inline_buf, sizeof(iovec) * old);
}
else
{
alloc = (((count+other.count+15)/16)*16);
buf = (iovec*)realloc(buf, sizeof(iovec) * alloc);
if (!buf)
{
printf("Failed to allocate %lu bytes\n", sizeof(iovec) * alloc);
exit(1);
}
}
}
for (int i = 0; i < other.count; i++)
{
buf[count++] = other.buf[i];
}
}
inline void push_back(void *nbuf, size_t len)
{
if (count >= alloc)
{
if (buf == inline_buf)
{
int old = alloc;
alloc = ((alloc/16)*16 + 1);
buf = (iovec*)malloc(sizeof(iovec) * alloc);
if (!buf)
{
printf("Failed to allocate %lu bytes\n", sizeof(iovec) * alloc);
exit(1);
}
memcpy(buf, inline_buf, sizeof(iovec)*old);
}
else
{
alloc = alloc < 16 ? 16 : (alloc+16);
buf = (iovec*)realloc(buf, sizeof(iovec) * alloc);
if (!buf)
{
printf("Failed to allocate %lu bytes\n", sizeof(iovec) * alloc);
exit(1);
}
}
}
buf[count++] = { .iov_base = nbuf, .iov_len = len };
}
inline void eat(int result)
{
while (result > 0 && done < count)
{
iovec & iov = buf[done];
if (iov.iov_len <= result)
{
result -= iov.iov_len;
done++;
}
else
{
iov.iov_len -= result;
iov.iov_base += result;
break;
}
}
}
};
struct blockstore_op_t;
struct osd_primary_op_data_t;
struct osd_op_t
{
timespec tv_begin = { 0 }, tv_end = { 0 };
uint64_t op_type = OSD_OP_IN;
int peer_fd;
osd_any_op_t req;
osd_any_reply_t reply;
blockstore_op_t *bs_op = NULL;
void *buf = NULL;
// bitmap, bitmap_len, bmp_data are only meaningful for reads
void *bitmap = NULL;
unsigned bitmap_len = 0;
unsigned bmp_data = 0;
void *rmw_buf = NULL;
osd_primary_op_data_t* op_data = NULL;
std::function<void(osd_op_t*)> callback;
osd_op_buf_list_t iov;
~osd_op_t();
};
struct osd_client_t
{
int refs = 0;
@ -71,12 +233,6 @@ struct osd_client_t
int write_state = 0;
std::vector<iovec> send_list, next_send_list;
std::vector<osd_op_t*> outbox, next_outbox;
~osd_client_t()
{
free(in_buf);
in_buf = NULL;
}
};
struct osd_wanted_peer_t
@ -101,9 +257,12 @@ struct osd_op_stats_t
struct osd_messenger_t
{
protected:
timerfd_manager_t *tfd;
ring_loop_t *ringloop;
int keepalive_timer_id = -1;
// osd_num_t is only for logging and asserts
osd_num_t osd_num;
// FIXME: make receive_buffer_size configurable
int receive_buffer_size = 64*1024;
int peer_connect_interval = DEFAULT_PEER_CONNECT_INTERVAL;
@ -113,22 +272,19 @@ protected:
int log_level = 0;
bool use_sync_send_recv = false;
std::map<osd_num_t, osd_wanted_peer_t> wanted_peers;
std::map<uint64_t, int> osd_peer_fds;
uint64_t next_subop_id = 1;
std::map<int, osd_client_t*> clients;
std::vector<int> read_ready_clients;
std::vector<int> write_ready_clients;
std::vector<std::function<void()>> set_immediate;
public:
timerfd_manager_t *tfd;
ring_loop_t *ringloop;
// osd_num_t is only for logging and asserts
osd_num_t osd_num;
uint64_t next_subop_id = 1;
std::map<int, osd_client_t*> clients;
std::map<osd_num_t, osd_wanted_peer_t> wanted_peers;
std::map<uint64_t, int> osd_peer_fds;
// op statistics
osd_op_stats_t stats;
public:
void init();
void parse_config(const json11::Json & config);
void connect_peer(uint64_t osd_num, json11::Json peer_state);
@ -136,6 +292,7 @@ public:
void outbox_push(osd_op_t *cur_op);
std::function<void(osd_op_t*)> exec_op;
std::function<void(osd_num_t)> repeer_pgs;
void handle_peer_epoll(int peer_fd, int epoll_events);
void read_requests();
void send_replies();
void accept_connections(int listen_fd);
@ -144,7 +301,6 @@ public:
protected:
void try_connect_peer(uint64_t osd_num);
void try_connect_peer_addr(osd_num_t peer_osd, const char *peer_host, int peer_port);
void handle_peer_epoll(int peer_fd, int epoll_events);
void handle_connect_epoll(int peer_fd);
void on_connect_peer(osd_num_t peer_osd, int peer_fd);
void check_peer_config(osd_client_t *cl);

View File

@ -1 +0,0 @@
g++ -D__MOCK__ -fsanitize=address -g -Wno-pointer-arith pg_states.cpp osd_ops.cpp test_cluster_client.cpp cluster_client.cpp msgr_op.cpp msgr_stop.cpp mock/messenger.cpp etcd_state_client.cpp timerfd_manager.cpp ../json11/json11.cpp -I mock -I . -I ..; ./a.out

View File

@ -1,44 +0,0 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
#include <unistd.h>
#include <stdexcept>
#include <assert.h>
#include "messenger.h"
void osd_messenger_t::init()
{
}
osd_messenger_t::~osd_messenger_t()
{
while (clients.size() > 0)
{
stop_client(clients.begin()->first, true);
}
}
void osd_messenger_t::outbox_push(osd_op_t *cur_op)
{
clients[cur_op->peer_fd]->sent_ops[cur_op->req.hdr.id] = cur_op;
}
void osd_messenger_t::parse_config(const json11::Json & config)
{
}
void osd_messenger_t::connect_peer(uint64_t peer_osd, json11::Json peer_state)
{
wanted_peers[peer_osd] = (osd_wanted_peer_t){
.port = 1,
};
}
void osd_messenger_t::read_requests()
{
}
void osd_messenger_t::send_replies()
{
}

View File

@ -1,25 +0,0 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
#pragma once
#include <functional>
struct ring_consumer_t
{
std::function<void(void)> loop;
};
class ring_loop_t
{
public:
void register_consumer(ring_consumer_t *consumer)
{
}
void unregister_consumer(ring_consumer_t *consumer)
{
}
void submit()
{
}
};

View File

@ -1,22 +0,0 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
#include <assert.h>
#include "msgr_op.h"
osd_op_t::~osd_op_t()
{
assert(!bs_op);
assert(!op_data);
if (rmw_buf)
{
free(rmw_buf);
}
if (buf)
{
// Note: reusing osd_op_t WILL currently lead to memory leaks
// So we don't reuse it, but free it every time
free(buf);
}
}

View File

@ -1,175 +0,0 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
#pragma once
#include <sys/uio.h>
#include <stdint.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include "osd_ops.h"
#define OSD_OP_IN 0
#define OSD_OP_OUT 1
#define OSD_OP_INLINE_BUF_COUNT 16
// Kind of a vector with small-list-optimisation
struct osd_op_buf_list_t
{
int count = 0, alloc = OSD_OP_INLINE_BUF_COUNT, done = 0;
iovec *buf = NULL;
iovec inline_buf[OSD_OP_INLINE_BUF_COUNT];
inline osd_op_buf_list_t()
{
buf = inline_buf;
}
inline osd_op_buf_list_t(const osd_op_buf_list_t & other)
{
buf = inline_buf;
append(other);
}
inline osd_op_buf_list_t & operator = (const osd_op_buf_list_t & other)
{
reset();
append(other);
return *this;
}
inline ~osd_op_buf_list_t()
{
if (buf && buf != inline_buf)
{
free(buf);
}
}
inline void reset()
{
count = 0;
done = 0;
}
inline iovec* get_iovec()
{
return buf + done;
}
inline int get_size()
{
return count - done;
}
inline void append(const osd_op_buf_list_t & other)
{
if (count+other.count > alloc)
{
if (buf == inline_buf)
{
int old = alloc;
alloc = (((count+other.count+15)/16)*16);
buf = (iovec*)malloc(sizeof(iovec) * alloc);
if (!buf)
{
printf("Failed to allocate %lu bytes\n", sizeof(iovec) * alloc);
exit(1);
}
memcpy(buf, inline_buf, sizeof(iovec) * old);
}
else
{
alloc = (((count+other.count+15)/16)*16);
buf = (iovec*)realloc(buf, sizeof(iovec) * alloc);
if (!buf)
{
printf("Failed to allocate %lu bytes\n", sizeof(iovec) * alloc);
exit(1);
}
}
}
for (int i = 0; i < other.count; i++)
{
buf[count++] = other.buf[i];
}
}
inline void push_back(void *nbuf, size_t len)
{
if (count >= alloc)
{
if (buf == inline_buf)
{
int old = alloc;
alloc = ((alloc/16)*16 + 1);
buf = (iovec*)malloc(sizeof(iovec) * alloc);
if (!buf)
{
printf("Failed to allocate %lu bytes\n", sizeof(iovec) * alloc);
exit(1);
}
memcpy(buf, inline_buf, sizeof(iovec)*old);
}
else
{
alloc = alloc < 16 ? 16 : (alloc+16);
buf = (iovec*)realloc(buf, sizeof(iovec) * alloc);
if (!buf)
{
printf("Failed to allocate %lu bytes\n", sizeof(iovec) * alloc);
exit(1);
}
}
}
buf[count++] = { .iov_base = nbuf, .iov_len = len };
}
inline void eat(int result)
{
while (result > 0 && done < count)
{
iovec & iov = buf[done];
if (iov.iov_len <= result)
{
result -= iov.iov_len;
done++;
}
else
{
iov.iov_len -= result;
iov.iov_base += result;
break;
}
}
}
};
struct blockstore_op_t;
struct osd_primary_op_data_t;
struct osd_op_t
{
timespec tv_begin = { 0 }, tv_end = { 0 };
uint64_t op_type = OSD_OP_IN;
int peer_fd;
osd_any_op_t req;
osd_any_reply_t reply;
blockstore_op_t *bs_op = NULL;
void *buf = NULL;
// bitmap, bitmap_len, bmp_data are only meaningful for reads
void *bitmap = NULL;
unsigned bitmap_len = 0;
unsigned bmp_data = 0;
void *rmw_buf = NULL;
osd_primary_op_data_t* op_data = NULL;
std::function<void(osd_op_t*)> callback;
osd_op_buf_list_t iov;
~osd_op_t();
};

View File

@ -232,15 +232,6 @@ void osd_messenger_t::handle_op_hdr(osd_client_t *cl)
}
cl->read_remaining = cur_op->req.sec_stab.len;
}
else if (cur_op->req.hdr.opcode == OSD_OP_SEC_READ_BMP)
{
if (cur_op->req.sec_read_bmp.len > 0)
{
cur_op->buf = memalign_or_die(MEM_ALIGNMENT, cur_op->req.sec_read_bmp.len);
cl->recv_list.push_back(cur_op->buf, cur_op->req.sec_read_bmp.len);
}
cl->read_remaining = cur_op->req.sec_read_bmp.len;
}
else if (cur_op->req.hdr.opcode == OSD_OP_READ)
{
cl->read_remaining = 0;
@ -286,19 +277,17 @@ bool osd_messenger_t::handle_reply_hdr(osd_client_t *cl)
{
// Read data. In this case we assume that the buffer is preallocated by the caller (!)
unsigned bmp_len = (op->reply.hdr.opcode == OSD_OP_SEC_READ ? op->reply.sec_rw.attr_len : op->reply.rw.bitmap_len);
unsigned expected_size = (op->reply.hdr.opcode == OSD_OP_SEC_READ ? op->req.sec_rw.len : op->req.rw.len);
if (op->reply.hdr.retval >= 0 && (op->reply.hdr.retval != expected_size || bmp_len > op->bitmap_len))
if (op->reply.hdr.retval != (op->reply.hdr.opcode == OSD_OP_SEC_READ ? op->req.sec_rw.len : op->req.rw.len) ||
bmp_len > op->bitmap_len)
{
// Check reply length to not overflow the buffer
printf("Client %d read reply of different length: expected %u+%u, got %ld+%u\n",
cl->peer_fd, expected_size, op->bitmap_len, op->reply.hdr.retval, bmp_len);
printf("Client %d read reply of different length\n", cl->peer_fd);
cl->sent_ops[op->req.hdr.id] = op;
stop_client(cl->peer_fd);
return false;
}
if (op->reply.hdr.retval >= 0 && bmp_len > 0)
if (bmp_len > 0)
{
assert(op->bitmap);
cl->recv_list.push_back(op->bitmap, bmp_len);
}
if (op->reply.hdr.retval > 0)
@ -325,16 +314,6 @@ bool osd_messenger_t::handle_reply_hdr(osd_client_t *cl)
op->buf = memalign_or_die(MEM_ALIGNMENT, cl->read_remaining);
cl->recv_list.push_back(op->buf, cl->read_remaining);
}
else if (op->reply.hdr.opcode == OSD_OP_SEC_READ_BMP && op->reply.hdr.retval > 0)
{
assert(!op->iov.count);
delete cl->read_op;
cl->read_op = op;
cl->read_state = CL_READ_REPLY_DATA;
cl->read_remaining = op->reply.hdr.retval;
op->buf = memalign_or_die(MEM_ALIGNMENT, cl->read_remaining);
cl->recv_list.push_back(op->buf, cl->read_remaining);
}
else if (op->reply.hdr.opcode == OSD_OP_SHOW_CONFIG && op->reply.hdr.retval > 0)
{
assert(!op->iov.count);

View File

@ -87,14 +87,6 @@ void osd_messenger_t::outbox_push(osd_op_t *cur_op)
to_outbox.push_back(NULL);
}
}
if (cur_op->req.hdr.opcode == OSD_OP_SEC_READ_BMP)
{
if (cur_op->op_type == OSD_OP_IN && cur_op->reply.hdr.retval > 0)
to_send_list.push_back((iovec){ .iov_base = cur_op->buf, .iov_len = (size_t)cur_op->reply.hdr.retval });
else if (cur_op->op_type == OSD_OP_OUT && cur_op->req.sec_read_bmp.len > 0)
to_send_list.push_back((iovec){ .iov_base = cur_op->buf, .iov_len = (size_t)cur_op->req.sec_read_bmp.len });
to_outbox.push_back(NULL);
}
if (cur_op->op_type == OSD_OP_IN)
{
// To free it later
@ -211,7 +203,7 @@ void osd_messenger_t::handle_send(int result, osd_client_t *cl)
cl->refs--;
if (cl->peer_state == PEER_STOPPED)
{
if (cl->refs <= 0)
if (!cl->refs)
{
delete cl;
}

View File

@ -1,137 +0,0 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
#include <unistd.h>
#include <assert.h>
#include "messenger.h"
void osd_messenger_t::cancel_osd_ops(osd_client_t *cl)
{
std::vector<osd_op_t*> cancel_ops;
cancel_ops.resize(cl->sent_ops.size());
int i = 0;
for (auto p: cl->sent_ops)
{
cancel_ops[i++] = p.second;
}
cl->sent_ops.clear();
cl->outbox.clear();
for (auto op: cancel_ops)
{
cancel_op(op);
}
}
void osd_messenger_t::cancel_op(osd_op_t *op)
{
if (op->op_type == OSD_OP_OUT)
{
op->reply.hdr.magic = SECONDARY_OSD_REPLY_MAGIC;
op->reply.hdr.id = op->req.hdr.id;
op->reply.hdr.opcode = op->req.hdr.opcode;
op->reply.hdr.retval = -EPIPE;
// Copy lambda to be unaffected by `delete op`
std::function<void(osd_op_t*)>(op->callback)(op);
}
else
{
// This function is only called in stop_client(), so it's fine to destroy the operation
delete op;
}
}
void osd_messenger_t::stop_client(int peer_fd, bool force)
{
assert(peer_fd != 0);
auto it = clients.find(peer_fd);
if (it == clients.end())
{
return;
}
osd_client_t *cl = it->second;
if (cl->peer_state == PEER_CONNECTING && !force || cl->peer_state == PEER_STOPPED)
{
return;
}
if (log_level > 0)
{
if (cl->osd_num)
{
printf("[OSD %lu] Stopping client %d (OSD peer %lu)\n", osd_num, peer_fd, cl->osd_num);
}
else
{
printf("[OSD %lu] Stopping client %d (regular client)\n", osd_num, peer_fd);
}
}
// First set state to STOPPED so another stop_client() call doesn't try to free it again
cl->refs++;
cl->peer_state = PEER_STOPPED;
if (cl->osd_num)
{
// ...and forget OSD peer
osd_peer_fds.erase(cl->osd_num);
}
#ifndef __MOCK__
// Then remove FD from the eventloop so we don't accidentally read something
tfd->set_fd_handler(peer_fd, false, NULL);
if (cl->connect_timeout_id >= 0)
{
tfd->clear_timer(cl->connect_timeout_id);
cl->connect_timeout_id = -1;
}
for (auto rit = read_ready_clients.begin(); rit != read_ready_clients.end(); rit++)
{
if (*rit == peer_fd)
{
read_ready_clients.erase(rit);
break;
}
}
for (auto wit = write_ready_clients.begin(); wit != write_ready_clients.end(); wit++)
{
if (*wit == peer_fd)
{
write_ready_clients.erase(wit);
break;
}
}
#endif
if (cl->osd_num)
{
// Then repeer PGs because cancel_op() callbacks can try to perform
// some actions and we need correct PG states to not do something silly
repeer_pgs(cl->osd_num);
}
// Then cancel all operations
if (cl->read_op)
{
if (!cl->read_op->callback)
{
delete cl->read_op;
}
cl->read_op = NULL;
}
if (cl->osd_num)
{
// Cancel outbound operations
cancel_osd_ops(cl);
}
#ifndef __MOCK__
// And close the FD only when everything is done
// ...because peer_fd number can get reused after close()
close(peer_fd);
#endif
// Find the item again because it can be invalidated at this point
it = clients.find(peer_fd);
if (it != clients.end())
{
clients.erase(it);
}
cl->refs--;
if (cl->refs <= 0)
{
delete cl;
}
}

View File

@ -8,7 +8,6 @@
#include <arpa/inet.h>
#include "osd.h"
#include "http_client.h"
osd_t::osd_t(blockstore_config_t & config, ring_loop_t *ringloop)
{
@ -20,22 +19,17 @@ osd_t::osd_t(blockstore_config_t & config, ring_loop_t *ringloop)
bs_bitmap_granularity = DEFAULT_BITMAP_GRANULARITY;
clean_entry_bitmap_size = bs_block_size / bs_bitmap_granularity / 8;
zero_buffer_size = 1<<20;
zero_buffer = malloc_or_die(zero_buffer_size);
memset(zero_buffer, 0, zero_buffer_size);
this->config = config;
this->ringloop = ringloop;
epmgr = new epoll_manager_t(ringloop);
// FIXME: Use timerfd_interval based directly on io_uring
this->tfd = epmgr->tfd;
// FIXME: Create Blockstore from on-disk superblock config and check it against the OSD cluster config
this->bs = new blockstore_t(config, ringloop, tfd);
this->bs = new blockstore_t(config, ringloop);
parse_config(config);
epmgr = new epoll_manager_t(ringloop);
this->tfd = epmgr->tfd;
this->tfd->set_timer(print_stats_interval*1000, true, [this](int timer_id)
{
print_stats();
@ -63,7 +57,6 @@ osd_t::~osd_t()
delete epmgr;
delete bs;
close(listen_fd);
free(zero_buffer);
}
void osd_t::parse_config(blockstore_config_t & config)
@ -205,8 +198,6 @@ void osd_t::exec_op(osd_op_t *cur_op)
delete cur_op;
return;
}
// Clear the reply buffer
memset(cur_op->reply.buf, 0, OSD_PACKET_SIZE);
inflight_ops++;
if (cur_op->req.hdr.magic != SECONDARY_OSD_OP_MAGIC ||
cur_op->req.hdr.opcode < OSD_OP_MIN || cur_op->req.hdr.opcode > OSD_OP_MAX ||
@ -237,7 +228,6 @@ void osd_t::exec_op(osd_op_t *cur_op)
cur_op->req.hdr.opcode != OSD_OP_SEC_READ &&
cur_op->req.hdr.opcode != OSD_OP_SEC_LIST &&
cur_op->req.hdr.opcode != OSD_OP_READ &&
cur_op->req.hdr.opcode != OSD_OP_SEC_READ_BMP &&
cur_op->req.hdr.opcode != OSD_OP_SHOW_CONFIG)
{
// Readonly mode

View File

@ -66,28 +66,6 @@ struct inode_stats_t
uint64_t op_bytes[3] = { 0 };
};
struct bitmap_request_t
{
osd_num_t osd_num;
object_id oid;
uint64_t version;
void *bmp_buf;
};
inline bool operator < (const bitmap_request_t & a, const bitmap_request_t & b)
{
return a.osd_num < b.osd_num || a.osd_num == b.osd_num && a.oid < b.oid;
}
struct osd_chain_read_t
{
int chain_pos;
inode_t inode;
uint32_t offset, len;
};
struct osd_rmw_stripe_t;
class osd_t
{
// config
@ -148,8 +126,6 @@ class osd_t
bool stopping = false;
int inflight_ops = 0;
blockstore_t *bs;
void *zero_buffer = NULL;
uint64_t zero_buffer_size = 0;
uint32_t bs_block_size, bs_bitmap_granularity, clean_entry_bitmap_size;
ring_loop_t *ringloop;
timerfd_manager_t *tfd = NULL;
@ -171,7 +147,7 @@ class osd_t
void init_cluster();
void on_change_osd_state_hook(osd_num_t peer_osd);
void on_change_pg_history_hook(pool_id_t pool_id, pg_num_t pg_num);
void on_change_etcd_state_hook(std::map<std::string, etcd_kv_t> & changes);
void on_change_etcd_state_hook(json11::Json::object & changes);
void on_load_config_hook(json11::Json::object & changes);
json11::Json on_load_pgs_checks_hook();
void on_load_pgs_hook(bool success);
@ -234,37 +210,23 @@ class osd_t
void continue_primary_del(osd_op_t *cur_op);
bool check_write_queue(osd_op_t *cur_op, pg_t & pg);
void remove_object_from_state(object_id & oid, pg_osd_set_state_t *object_state, pg_t &pg);
void free_object_state(pg_t & pg, pg_osd_set_state_t **object_state);
bool remember_unstable_write(osd_op_t *cur_op, pg_t & pg, pg_osd_set_t & loc_set, int base_state);
void handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op);
void handle_primary_bs_subop(osd_op_t *subop);
void add_bs_subop_stats(osd_op_t *subop);
void pg_cancel_write_queue(pg_t & pg, osd_op_t *first_op, object_id oid, int retval);
void submit_primary_subops(int submit_type, uint64_t op_version, const uint64_t* osd_set, osd_op_t *cur_op);
int submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t op_version,
osd_rmw_stripe_t *stripes, const uint64_t* osd_set, osd_op_t *cur_op, int subop_idx, int zero_read);
void submit_primary_subops(int submit_type, uint64_t op_version, int pg_size, const uint64_t* osd_set, osd_op_t *cur_op);
void submit_primary_del_subops(osd_op_t *cur_op, uint64_t *cur_set, uint64_t set_size, pg_osd_set_t & loc_set);
void submit_primary_del_batch(osd_op_t *cur_op, obj_ver_osd_t *chunks_to_delete, int chunks_to_delete_count);
int submit_primary_sync_subops(osd_op_t *cur_op);
void submit_primary_sync_subops(osd_op_t *cur_op);
void submit_primary_stab_subops(osd_op_t *cur_op);
uint64_t* get_object_osd_set(pg_t &pg, object_id &oid, uint64_t *def, pg_osd_set_state_t **object_state);
void continue_chained_read(osd_op_t *cur_op);
int submit_chained_read_requests(pg_t & pg, osd_op_t *cur_op);
void send_chained_read_results(pg_t & pg, osd_op_t *cur_op);
std::vector<osd_chain_read_t> collect_chained_read_requests(osd_op_t *cur_op);
int collect_bitmap_requests(osd_op_t *cur_op, pg_t & pg, std::vector<bitmap_request_t> & bitmap_requests);
int submit_bitmap_subops(osd_op_t *cur_op, pg_t & pg);
int read_bitmaps(osd_op_t *cur_op, pg_t & pg, int base_state);
inline pg_num_t map_to_pg(object_id oid, uint64_t pg_stripe_size)
{
uint64_t pg_count = pg_counts[INODE_POOL(oid.inode)];
if (!pg_count)
pg_count = 1;
return (oid.stripe / pg_stripe_size) % pg_count + 1;
return (oid.inode + oid.stripe / pg_stripe_size) % pg_count + 1;
}
public:

View File

@ -4,7 +4,6 @@
#include "osd.h"
#include "base64.h"
#include "etcd_state_client.h"
#include "http_client.h"
#include "osd_rmw.h"
// Startup sequence:
@ -65,7 +64,7 @@ void osd_t::init_cluster()
st_cli.log_level = log_level;
st_cli.on_change_osd_state_hook = [this](osd_num_t peer_osd) { on_change_osd_state_hook(peer_osd); };
st_cli.on_change_pg_history_hook = [this](pool_id_t pool_id, pg_num_t pg_num) { on_change_pg_history_hook(pool_id, pg_num); };
st_cli.on_change_hook = [this](std::map<std::string, etcd_kv_t> & changes) { on_change_etcd_state_hook(changes); };
st_cli.on_change_hook = [this](json11::Json::object & changes) { on_change_etcd_state_hook(changes); };
st_cli.on_load_config_hook = [this](json11::Json::object & cfg) { on_load_config_hook(cfg); };
st_cli.load_pgs_checks_hook = [this]() { return on_load_pgs_checks_hook(); };
st_cli.on_load_pgs_hook = [this](bool success) { on_load_pgs_hook(success); };
@ -183,38 +182,14 @@ void osd_t::report_statistics()
// Report space usage statistics as a whole
// Maybe we'll report it using deltas if we tune for a lot of inodes at some point
json11::Json::object inode_space;
json11::Json::object last_stat;
pool_id_t last_pool = 0;
for (auto kv: bs->get_inode_space_stats())
{
pool_id_t pool_id = INODE_POOL(kv.first);
uint64_t only_inode_num = (kv.first & ((1l << (64-POOL_ID_BITS)) - 1));
if (!last_pool || pool_id != last_pool)
{
if (last_pool)
inode_space[std::to_string(last_pool)] = last_stat;
last_stat = json11::Json::object();
last_pool = pool_id;
}
last_stat[std::to_string(only_inode_num)] = kv.second;
inode_space[std::to_string(kv.first)] = kv.second;
}
if (last_pool)
inode_space[std::to_string(last_pool)] = last_stat;
last_stat = json11::Json::object();
last_pool = 0;
json11::Json::object inode_ops;
for (auto kv: inode_stats)
{
pool_id_t pool_id = INODE_POOL(kv.first);
uint64_t only_inode_num = (kv.first & ((1l << (64-POOL_ID_BITS)) - 1));
if (!last_pool || pool_id != last_pool)
{
if (last_pool)
inode_ops[std::to_string(last_pool)] = last_stat;
last_stat = json11::Json::object();
last_pool = pool_id;
}
last_stat[std::to_string(only_inode_num)] = json11::Json::object {
inode_ops[std::to_string(kv.first)] = json11::Json::object {
{ "read", json11::Json::object {
{ "count", kv.second.op_count[INODE_STATS_READ] },
{ "usec", kv.second.op_sum[INODE_STATS_READ] },
@ -232,28 +207,20 @@ void osd_t::report_statistics()
} },
};
}
if (last_pool)
inode_ops[std::to_string(last_pool)] = last_stat;
json11::Json::array txn = {
json11::Json::object {
{ "request_put", json11::Json::object {
{ "key", base64_encode(st_cli.etcd_prefix+"/osd/stats/"+std::to_string(osd_num)) },
{ "value", base64_encode(get_statistics().dump()) },
} },
},
json11::Json::object {
{ "request_put", json11::Json::object {
{ "key", base64_encode(st_cli.etcd_prefix+"/osd/space/"+std::to_string(osd_num)) },
{ "value", base64_encode(json11::Json(inode_space).dump()) },
} },
},
json11::Json::object {
{ "request_put", json11::Json::object {
{ "key", base64_encode(st_cli.etcd_prefix+"/osd/inodestats/"+std::to_string(osd_num)) },
{ "value", base64_encode(json11::Json(inode_ops).dump()) },
} },
},
};
json11::Json::array txn = { json11::Json::object {
{ "request_put", json11::Json::object {
{ "key", base64_encode(st_cli.etcd_prefix+"/osd/stats/"+std::to_string(osd_num)) },
{ "value", base64_encode(get_statistics().dump()) },
} },
{ "request_put", json11::Json::object {
{ "key", base64_encode(st_cli.etcd_prefix+"/osd/space/"+std::to_string(osd_num)) },
{ "value", base64_encode(json11::Json(inode_space).dump()) },
} },
{ "request_put", json11::Json::object {
{ "key", base64_encode(st_cli.etcd_prefix+"/osd/inodestats/"+std::to_string(osd_num)) },
{ "value", base64_encode(json11::Json(inode_ops).dump()) },
} },
} };
for (auto & p: pgs)
{
auto & pg = p.second;
@ -304,7 +271,7 @@ void osd_t::on_change_osd_state_hook(osd_num_t peer_osd)
}
}
void osd_t::on_change_etcd_state_hook(std::map<std::string, etcd_kv_t> & changes)
void osd_t::on_change_etcd_state_hook(json11::Json::object & changes)
{
// FIXME apply config changes in runtime (maybe, some)
if (run_primary)
@ -626,7 +593,7 @@ void osd_t::apply_pg_config()
}
if (currently_taken)
{
if (pg_it->second.state & (PG_ACTIVE | PG_INCOMPLETE | PG_PEERING | PG_REPEERING))
if (pg_it->second.state & (PG_ACTIVE | PG_INCOMPLETE | PG_PEERING))
{
if (pg_it->second.target_set == pg_cfg.target_set)
{

View File

@ -149,14 +149,10 @@ void osd_t::handle_flush_op(bool rollback, pool_id_t pool_id, pg_num_t pg_num, p
{
continue_primary_write(op);
}
if ((pg.state & PG_STOPPING) && pg.inflight == 0 && !pg.flush_batch)
if (pg.inflight == 0 && (pg.state & PG_STOPPING))
{
finish_stop_pg(pg);
}
else if ((pg.state & PG_REPEERING) && pg.inflight == 0 && !pg.flush_batch)
{
start_pg_peering(pg);
}
}
}
@ -235,8 +231,7 @@ bool osd_t::pick_next_recovery(osd_recovery_op_t &op)
{
for (auto pg_it = pgs.begin(); pg_it != pgs.end(); pg_it++)
{
// Don't try to "recover" misplaced objects if "recovery" would make them degraded
if ((pg_it->second.state & (PG_ACTIVE | PG_DEGRADED | PG_HAS_MISPLACED)) == (PG_ACTIVE | PG_HAS_MISPLACED))
if ((pg_it->second.state & (PG_ACTIVE | PG_HAS_MISPLACED)) == (PG_ACTIVE | PG_HAS_MISPLACED))
{
for (auto obj_it = pg_it->second.misplaced_objects.begin(); obj_it != pg_it->second.misplaced_objects.end(); obj_it++)
{

View File

@ -20,5 +20,4 @@ const char* osd_op_names[] = {
"primary_sync",
"primary_delete",
"ping",
"sec_read_bmp",
};

View File

@ -28,14 +28,12 @@
#define OSD_OP_SYNC 13
#define OSD_OP_DELETE 14
#define OSD_OP_PING 15
#define OSD_OP_SEC_READ_BMP 16
#define OSD_OP_MAX 16
#define OSD_OP_MAX 15
// Alignment & limit for read/write operations
#ifndef MEM_ALIGNMENT
#define MEM_ALIGNMENT 512
#endif
#define OSD_RW_MAX 64*1024*1024
#define OSD_PROTOCOL_VERSION 1
// common request and reply headers
struct __attribute__((__packed__)) osd_op_header_t
@ -61,7 +59,7 @@ struct __attribute__((__packed__)) osd_reply_header_t
};
// read or write to the secondary OSD
struct __attribute__((__packed__)) osd_op_sec_rw_t
struct __attribute__((__packed__)) osd_op_secondary_rw_t
{
osd_op_header_t header;
// object
@ -78,7 +76,7 @@ struct __attribute__((__packed__)) osd_op_sec_rw_t
uint32_t pad0;
};
struct __attribute__((__packed__)) osd_reply_sec_rw_t
struct __attribute__((__packed__)) osd_reply_secondary_rw_t
{
osd_reply_header_t header;
// for reads and writes: assigned or read version number
@ -89,7 +87,7 @@ struct __attribute__((__packed__)) osd_reply_sec_rw_t
};
// delete object on the secondary OSD
struct __attribute__((__packed__)) osd_op_sec_del_t
struct __attribute__((__packed__)) osd_op_secondary_del_t
{
osd_op_header_t header;
// object
@ -98,51 +96,37 @@ struct __attribute__((__packed__)) osd_op_sec_del_t
uint64_t version;
};
struct __attribute__((__packed__)) osd_reply_sec_del_t
struct __attribute__((__packed__)) osd_reply_secondary_del_t
{
osd_reply_header_t header;
uint64_t version;
};
// sync to the secondary OSD
struct __attribute__((__packed__)) osd_op_sec_sync_t
struct __attribute__((__packed__)) osd_op_secondary_sync_t
{
osd_op_header_t header;
};
struct __attribute__((__packed__)) osd_reply_sec_sync_t
struct __attribute__((__packed__)) osd_reply_secondary_sync_t
{
osd_reply_header_t header;
};
// stabilize or rollback objects on the secondary OSD
struct __attribute__((__packed__)) osd_op_sec_stab_t
struct __attribute__((__packed__)) osd_op_secondary_stabilize_t
{
osd_op_header_t header;
// obj_ver_id array length in bytes
uint64_t len;
};
typedef osd_op_sec_stab_t osd_op_sec_rollback_t;
typedef osd_op_secondary_stabilize_t osd_op_secondary_rollback_t;
struct __attribute__((__packed__)) osd_reply_sec_stab_t
struct __attribute__((__packed__)) osd_reply_secondary_stabilize_t
{
osd_reply_header_t header;
};
typedef osd_reply_sec_stab_t osd_reply_sec_rollback_t;
// bulk read bitmaps from a secondary OSD
struct __attribute__((__packed__)) osd_op_sec_read_bmp_t
{
osd_op_header_t header;
// obj_ver_id array length in bytes
uint64_t len;
};
struct __attribute__((__packed__)) osd_reply_sec_read_bmp_t
{
// retval is payload length in bytes. payload is {version,bitmap}[]
osd_reply_header_t header;
};
typedef osd_reply_secondary_stabilize_t osd_reply_secondary_rollback_t;
// show configuration
struct __attribute__((__packed__)) osd_op_show_config_t
@ -156,7 +140,7 @@ struct __attribute__((__packed__)) osd_reply_show_config_t
};
// list objects on replica
struct __attribute__((__packed__)) osd_op_sec_list_t
struct __attribute__((__packed__)) osd_op_secondary_list_t
{
osd_op_header_t header;
// placement group total number and total count
@ -167,7 +151,7 @@ struct __attribute__((__packed__)) osd_op_sec_list_t
uint64_t min_inode, max_inode;
};
struct __attribute__((__packed__)) osd_reply_sec_list_t
struct __attribute__((__packed__)) osd_reply_secondary_list_t
{
osd_reply_header_t header;
// stable object version count. header.retval = total object version count
@ -185,10 +169,6 @@ struct __attribute__((__packed__)) osd_op_rw_t
uint64_t offset;
// length
uint32_t len;
// flags (for future)
uint32_t flags;
// inode metadata revision
uint64_t meta_revision;
};
struct __attribute__((__packed__)) osd_reply_rw_t
@ -214,12 +194,11 @@ struct __attribute__((__packed__)) osd_reply_sync_t
union osd_any_op_t
{
osd_op_header_t hdr;
osd_op_sec_rw_t sec_rw;
osd_op_sec_del_t sec_del;
osd_op_sec_sync_t sec_sync;
osd_op_sec_stab_t sec_stab;
osd_op_sec_read_bmp_t sec_read_bmp;
osd_op_sec_list_t sec_list;
osd_op_secondary_rw_t sec_rw;
osd_op_secondary_del_t sec_del;
osd_op_secondary_sync_t sec_sync;
osd_op_secondary_stabilize_t sec_stab;
osd_op_secondary_list_t sec_list;
osd_op_show_config_t show_conf;
osd_op_rw_t rw;
osd_op_sync_t sync;
@ -229,12 +208,11 @@ union osd_any_op_t
union osd_any_reply_t
{
osd_reply_header_t hdr;
osd_reply_sec_rw_t sec_rw;
osd_reply_sec_del_t sec_del;
osd_reply_sec_sync_t sec_sync;
osd_reply_sec_stab_t sec_stab;
osd_reply_sec_read_bmp_t sec_read_bmp;
osd_reply_sec_list_t sec_list;
osd_reply_secondary_rw_t sec_rw;
osd_reply_secondary_del_t sec_del;
osd_reply_secondary_sync_t sec_sync;
osd_reply_secondary_stabilize_t sec_stab;
osd_reply_secondary_list_t sec_list;
osd_reply_show_config_t show_conf;
osd_reply_rw_t rw;
osd_reply_sync_t sync;

View File

@ -77,11 +77,10 @@ void osd_t::repeer_pgs(osd_num_t peer_osd)
// Re-peer affected PGs
for (auto & p: pgs)
{
auto & pg = p.second;
bool repeer = false;
if (pg.state & (PG_PEERING | PG_ACTIVE | PG_INCOMPLETE))
if (p.second.state & (PG_PEERING | PG_ACTIVE | PG_INCOMPLETE))
{
for (osd_num_t pg_osd: pg.all_peers)
for (osd_num_t pg_osd: p.second.all_peers)
{
if (pg_osd == peer_osd)
{
@ -92,17 +91,8 @@ void osd_t::repeer_pgs(osd_num_t peer_osd)
if (repeer)
{
// Repeer this pg
printf("[PG %u/%u] Repeer because of OSD %lu\n", pg.pool_id, pg.pg_num, peer_osd);
if (!(pg.state & (PG_ACTIVE | PG_REPEERING)) || pg.inflight == 0 && !pg.flush_batch)
{
start_pg_peering(pg);
}
else
{
// Stop accepting new operations, wait for current ones to finish or fail
pg.state = pg.state & ~PG_ACTIVE | PG_REPEERING;
report_pg_state(pg);
}
printf("[PG %u/%u] Repeer because of OSD %lu\n", p.second.pool_id, p.second.pg_num, peer_osd);
start_pg_peering(p.second);
}
}
}
@ -344,10 +334,9 @@ void osd_t::submit_sync_and_list_subop(osd_num_t role_osd, pg_peering_state_t *p
{
// FIXME: Mark peer as failed and don't reconnect immediately after dropping the connection
printf("Failed to sync OSD %lu: %ld (%s), disconnecting peer\n", role_osd, op->reply.hdr.retval, strerror(-op->reply.hdr.retval));
int fail_fd = op->peer_fd;
ps->list_ops.erase(role_osd);
c_cli.stop_client(op->peer_fd);
delete op;
c_cli.stop_client(fail_fd);
return;
}
delete op;
@ -424,10 +413,9 @@ void osd_t::submit_list_subop(osd_num_t role_osd, pg_peering_state_t *ps)
if (op->reply.hdr.retval < 0)
{
printf("Failed to get object list from OSD %lu (retval=%ld), disconnecting peer\n", role_osd, op->reply.hdr.retval);
int fail_fd = op->peer_fd;
ps->list_ops.erase(role_osd);
c_cli.stop_client(op->peer_fd);
delete op;
c_cli.stop_client(fail_fd);
return;
}
printf(
@ -496,13 +484,15 @@ bool osd_t::stop_pg(pg_t & pg)
{
return false;
}
if (!(pg.state & (PG_ACTIVE | PG_REPEERING)))
if (!(pg.state & PG_ACTIVE))
{
finish_stop_pg(pg);
return true;
}
pg.state = pg.state & ~PG_ACTIVE & ~PG_REPEERING | PG_STOPPING;
if (pg.inflight == 0 && !pg.flush_batch)
pg.state = pg.state & ~PG_ACTIVE | PG_STOPPING;
if (pg.inflight == 0 && !pg.flush_batch &&
// We must either forget all PG's unstable writes or wait for it to become clean
dirty_pgs.find({ .pool_id = pg.pool_id, .pg_num = pg.pg_num }) == dirty_pgs.end())
{
finish_stop_pg(pg);
}

View File

@ -430,13 +430,12 @@ void pg_t::calc_object_states(int log_level)
void pg_t::print_state()
{
printf(
"[PG %u/%u] is %s%s%s%s%s%s%s%s%s%s%s%s%s%s (%lu objects)\n", pool_id, pg_num,
"[PG %u/%u] is %s%s%s%s%s%s%s%s%s%s%s%s%s (%lu objects)\n", pool_id, pg_num,
(state & PG_STARTING) ? "starting" : "",
(state & PG_OFFLINE) ? "offline" : "",
(state & PG_PEERING) ? "peering" : "",
(state & PG_INCOMPLETE) ? "incomplete" : "",
(state & PG_ACTIVE) ? "active" : "",
(state & PG_REPEERING) ? "repeering" : "",
(state & PG_STOPPING) ? "stopping" : "",
(state & PG_DEGRADED) ? " + degraded" : "",
(state & PG_HAS_INCOMPLETE) ? " + has_incomplete" : "",

View File

@ -19,7 +19,7 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
// Our EC scheme stores data in fixed chunks equal to (K*block size)
// K = (pg_size-parity_chunks) in case of EC/XOR, or 1 for replicated pools
pool_id_t pool_id = INODE_POOL(cur_op->req.rw.inode);
// Note: We read pool config here, so we must NOT change it when PGs are active
// FIXME: We have to access pool config here, so make sure that it doesn't change while its PGs are active...
auto pool_cfg_it = st_cli.pool_config.find(pool_id);
if (pool_cfg_it == st_cli.pool_config.end())
{
@ -28,7 +28,6 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
return false;
}
auto & pool_cfg = pool_cfg_it->second;
// FIXME: op_data->pg_data_size can probably be removed (there's pg.pg_data_size)
uint64_t pg_data_size = (pool_cfg.scheme == POOL_SCHEME_REPLICATED ? 1 : pool_cfg.pg_size-pool_cfg.parity_chunks);
uint64_t pg_block_size = bs_block_size * pg_data_size;
object_id oid = {
@ -36,7 +35,7 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
// oid.stripe = starting offset of the parity stripe
.stripe = (cur_op->req.rw.offset/pg_block_size)*pg_block_size,
};
pg_num_t pg_num = (oid.stripe/pool_cfg.pg_stripe_size) % pg_counts[pool_id] + 1; // like map_to_pg()
pg_num_t pg_num = (cur_op->req.rw.inode + oid.stripe/pool_cfg.pg_stripe_size) % pg_counts[pool_id] + 1;
auto pg_it = pgs.find({ .pool_id = pool_id, .pg_num = pg_num });
if (pg_it == pgs.end() || !(pg_it->second.state & PG_ACTIVE))
{
@ -53,87 +52,26 @@ bool osd_t::prepare_primary_rw(osd_op_t *cur_op)
return false;
}
int stripe_count = (pool_cfg.scheme == POOL_SCHEME_REPLICATED ? 1 : pg_it->second.pg_size);
int chain_size = 0;
if (cur_op->req.hdr.opcode == OSD_OP_READ && cur_op->req.rw.meta_revision > 0)
{
// Chained read
auto inode_it = st_cli.inode_config.find(cur_op->req.rw.inode);
if (inode_it->second.mod_revision != cur_op->req.rw.meta_revision)
{
// Client view of the metadata differs from OSD's view
// Operation can't be completed correctly, client should retry later
finish_op(cur_op, -EPIPE);
return false;
}
// Find parents from the same pool. Optimized reads only work within pools
while (inode_it != st_cli.inode_config.end() && inode_it->second.parent_id &&
INODE_POOL(inode_it->second.parent_id) == pg_it->second.pool_id)
{
chain_size++;
inode_it = st_cli.inode_config.find(inode_it->second.parent_id);
}
if (chain_size)
{
// Add the original inode
chain_size++;
}
}
osd_primary_op_data_t *op_data = (osd_primary_op_data_t*)calloc_or_die(
// Allocate:
// - op_data
1, sizeof(osd_primary_op_data_t) +
// - stripes
// - resulting bitmap buffers
stripe_count * (clean_entry_bitmap_size + sizeof(osd_rmw_stripe_t)) +
chain_size * (
// - copy of the chain
sizeof(inode_t) +
// - bitmap buffers for chained read
stripe_count * clean_entry_bitmap_size +
// - 'missing' flags for chained reads
(pool_cfg.scheme == POOL_SCHEME_REPLICATED ? 0 : pg_it->second.pg_size)
)
1, sizeof(osd_primary_op_data_t) + (clean_entry_bitmap_size + sizeof(osd_rmw_stripe_t)) * stripe_count
);
void *data_buf = ((void*)op_data) + sizeof(osd_primary_op_data_t);
op_data->pg_num = pg_num;
op_data->oid = oid;
op_data->stripes = (osd_rmw_stripe_t*)data_buf;
data_buf += sizeof(osd_rmw_stripe_t) * stripe_count;
op_data->stripes = ((osd_rmw_stripe_t*)(op_data+1));
op_data->scheme = pool_cfg.scheme;
op_data->pg_data_size = pg_data_size;
op_data->pg_size = pg_it->second.pg_size;
cur_op->op_data = op_data;
split_stripes(pg_data_size, bs_block_size, (uint32_t)(cur_op->req.rw.offset - oid.stripe), cur_op->req.rw.len, op_data->stripes);
// Allocate bitmaps along with stripes to avoid extra allocations and fragmentation
for (int i = 0; i < stripe_count; i++)
{
op_data->stripes[i].bmp_buf = data_buf;
data_buf += clean_entry_bitmap_size;
}
op_data->chain_size = chain_size;
if (chain_size > 0)
{
op_data->read_chain = (inode_t*)data_buf;
data_buf += sizeof(inode_t) * chain_size;
op_data->snapshot_bitmaps = data_buf;
data_buf += chain_size * stripe_count * clean_entry_bitmap_size;
op_data->missing_flags = (uint8_t*)data_buf;
data_buf += chain_size * (pool_cfg.scheme == POOL_SCHEME_REPLICATED ? 0 : pg_it->second.pg_size);
// Copy chain
int chain_num = 0;
op_data->read_chain[chain_num++] = cur_op->req.rw.inode;
auto inode_it = st_cli.inode_config.find(cur_op->req.rw.inode);
while (inode_it != st_cli.inode_config.end() && inode_it->second.parent_id)
{
op_data->read_chain[chain_num++] = inode_it->second.parent_id;
inode_it = st_cli.inode_config.find(inode_it->second.parent_id);
}
op_data->stripes[i].bmp_buf = (void*)(op_data->stripes+stripe_count) + clean_entry_bitmap_size*i;
}
pg_it->second.inflight++;
return true;
}
uint64_t* osd_t::get_object_osd_set(pg_t &pg, object_id &oid, uint64_t *def, pg_osd_set_state_t **object_state)
static uint64_t* get_object_osd_set(pg_t &pg, object_id &oid, uint64_t *def, pg_osd_set_state_t **object_state)
{
if (!(pg.state & (PG_HAS_INCOMPLETE | PG_HAS_DEGRADED | PG_HAS_MISPLACED)))
{
@ -168,17 +106,10 @@ void osd_t::continue_primary_read(osd_op_t *cur_op)
{
return;
}
osd_primary_op_data_t *op_data = cur_op->op_data;
if (op_data->chain_size)
{
continue_chained_read(cur_op);
return;
}
if (op_data->st == 1)
goto resume_1;
else if (op_data->st == 2)
goto resume_2;
cur_op->reply.rw.bitmap_len = 0;
osd_primary_op_data_t *op_data = cur_op->op_data;
if (op_data->st == 1) goto resume_1;
else if (op_data->st == 2) goto resume_2;
{
auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
for (int role = 0; role < op_data->pg_data_size; role++)
@ -193,7 +124,8 @@ void osd_t::continue_primary_read(osd_op_t *cur_op)
{
// Fast happy-path
cur_op->buf = alloc_read_buffer(op_data->stripes, op_data->pg_data_size, 0);
submit_primary_subops(SUBMIT_READ, op_data->target_ver, pg.cur_set.data(), cur_op);
submit_primary_subops(SUBMIT_READ, op_data->target_ver,
(op_data->scheme == POOL_SCHEME_REPLICATED ? pg.pg_size : op_data->pg_data_size), pg.cur_set.data(), cur_op);
op_data->st = 1;
}
else
@ -210,7 +142,7 @@ void osd_t::continue_primary_read(osd_op_t *cur_op)
op_data->scheme = pg.scheme;
op_data->degraded = 1;
cur_op->buf = alloc_read_buffer(op_data->stripes, pg.pg_size, 0);
submit_primary_subops(SUBMIT_READ, op_data->target_ver, cur_set, cur_op);
submit_primary_subops(SUBMIT_READ, op_data->target_ver, pg.pg_size, cur_set, cur_op);
op_data->st = 1;
}
}
@ -256,6 +188,612 @@ resume_2:
finish_op(cur_op, cur_op->req.rw.len);
}
bool osd_t::check_write_queue(osd_op_t *cur_op, pg_t & pg)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
// Check if actions are pending for this object
auto act_it = pg.flush_actions.lower_bound((obj_piece_id_t){
.oid = op_data->oid,
.osd_num = 0,
});
if (act_it != pg.flush_actions.end() &&
act_it->first.oid.inode == op_data->oid.inode &&
(act_it->first.oid.stripe & ~STRIPE_MASK) == op_data->oid.stripe)
{
pg.write_queue.emplace(op_data->oid, cur_op);
return false;
}
// Check if there are other write requests to the same object
auto vo_it = pg.write_queue.find(op_data->oid);
if (vo_it != pg.write_queue.end())
{
op_data->st = 1;
pg.write_queue.emplace(op_data->oid, cur_op);
return false;
}
pg.write_queue.emplace(op_data->oid, cur_op);
return true;
}
void osd_t::continue_primary_write(osd_op_t *cur_op)
{
if (!cur_op->op_data && !prepare_primary_rw(cur_op))
{
return;
}
osd_primary_op_data_t *op_data = cur_op->op_data;
auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
if (op_data->st == 1) goto resume_1;
else if (op_data->st == 2) goto resume_2;
else if (op_data->st == 3) goto resume_3;
else if (op_data->st == 4) goto resume_4;
else if (op_data->st == 5) goto resume_5;
else if (op_data->st == 6) goto resume_6;
else if (op_data->st == 7) goto resume_7;
else if (op_data->st == 8) goto resume_8;
else if (op_data->st == 9) goto resume_9;
else if (op_data->st == 10) goto resume_10;
assert(op_data->st == 0);
if (!check_write_queue(cur_op, pg))
{
return;
}
resume_1:
// Determine blocks to read and write
// Missing chunks are allowed to be overwritten even in incomplete objects
// FIXME: Allow to do small writes to the old (degraded/misplaced) OSD set for lower performance impact
op_data->prev_set = get_object_osd_set(pg, op_data->oid, pg.cur_set.data(), &op_data->object_state);
if (op_data->scheme == POOL_SCHEME_REPLICATED)
{
// Simplified algorithm
op_data->stripes[0].write_start = op_data->stripes[0].req_start;
op_data->stripes[0].write_end = op_data->stripes[0].req_end;
op_data->stripes[0].write_buf = cur_op->buf;
op_data->stripes[0].bmp_buf = (void*)(op_data->stripes+1);
if (pg.cur_set.data() != op_data->prev_set && (op_data->stripes[0].write_start != 0 ||
op_data->stripes[0].write_end != bs_block_size))
{
// Object is degraded/misplaced and will be moved to <write_osd_set>
op_data->stripes[0].read_start = 0;
op_data->stripes[0].read_end = bs_block_size;
cur_op->rmw_buf = op_data->stripes[0].read_buf = memalign_or_die(MEM_ALIGNMENT, bs_block_size);
}
}
else
{
cur_op->rmw_buf = calc_rmw(cur_op->buf, op_data->stripes, op_data->prev_set,
pg.pg_size, op_data->pg_data_size, pg.pg_cursize, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
if (!cur_op->rmw_buf)
{
// Refuse partial overwrite of an incomplete object
cur_op->reply.hdr.retval = -EINVAL;
goto continue_others;
}
}
// Read required blocks
submit_primary_subops(SUBMIT_RMW_READ, UINT64_MAX, pg.pg_size, op_data->prev_set, cur_op);
resume_2:
op_data->st = 2;
return;
resume_3:
if (op_data->errors > 0)
{
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->epipe > 0 ? -EPIPE : -EIO);
return;
}
// Save version override for parallel reads
pg.ver_override[op_data->oid] = op_data->fact_ver;
if (op_data->scheme == POOL_SCHEME_REPLICATED)
{
// Set bitmap bits
bitmap_set(op_data->stripes[0].bmp_buf, op_data->stripes[0].write_start, op_data->stripes[0].write_end, bs_bitmap_granularity);
// Possibly copy new data from the request into the recovery buffer
if (pg.cur_set.data() != op_data->prev_set && (op_data->stripes[0].write_start != 0 ||
op_data->stripes[0].write_end != bs_block_size))
{
memcpy(
op_data->stripes[0].read_buf + op_data->stripes[0].req_start,
op_data->stripes[0].write_buf,
op_data->stripes[0].req_end - op_data->stripes[0].req_start
);
op_data->stripes[0].write_buf = op_data->stripes[0].read_buf;
op_data->stripes[0].write_start = 0;
op_data->stripes[0].write_end = bs_block_size;
}
}
else
{
// Recover missing stripes, calculate parity
if (pg.scheme == POOL_SCHEME_XOR)
{
calc_rmw_parity_xor(op_data->stripes, pg.pg_size, op_data->prev_set, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
}
else if (pg.scheme == POOL_SCHEME_JERASURE)
{
calc_rmw_parity_jerasure(op_data->stripes, pg.pg_size, op_data->pg_data_size, op_data->prev_set, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
}
}
// Send writes
if ((op_data->fact_ver >> (64-PG_EPOCH_BITS)) < pg.epoch)
{
op_data->target_ver = ((uint64_t)pg.epoch << (64-PG_EPOCH_BITS)) | 1;
}
else
{
if ((op_data->fact_ver & (1ul<<(64-PG_EPOCH_BITS) - 1)) == (1ul<<(64-PG_EPOCH_BITS) - 1))
{
assert(pg.epoch != ((1ul << PG_EPOCH_BITS)-1));
pg.epoch++;
}
op_data->target_ver = op_data->fact_ver + 1;
}
if (pg.epoch > pg.reported_epoch)
{
// Report newer epoch before writing
// FIXME: We may report only one PG state here...
this->pg_state_dirty.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
pg.history_changed = true;
report_pg_states();
resume_10:
if (pg.epoch > pg.reported_epoch)
{
op_data->st = 10;
return;
}
}
submit_primary_subops(SUBMIT_WRITE, op_data->target_ver, pg.pg_size, pg.cur_set.data(), cur_op);
resume_4:
op_data->st = 4;
return;
resume_5:
if (op_data->errors > 0)
{
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->epipe > 0 ? -EPIPE : -EIO);
return;
}
resume_6:
resume_7:
if (!remember_unstable_write(cur_op, pg, pg.cur_loc_set, 6))
{
// FIXME: Check for immediate_commit == IMMEDIATE_SMALL
return;
}
if (op_data->fact_ver == 1)
{
// Object is created
pg.clean_count++;
pg.total_count++;
}
if (op_data->object_state)
{
{
int recovery_type = op_data->object_state->state & (OBJ_DEGRADED|OBJ_INCOMPLETE) ? 0 : 1;
recovery_stat_count[0][recovery_type]++;
if (!recovery_stat_count[0][recovery_type])
{
recovery_stat_count[0][recovery_type]++;
recovery_stat_bytes[0][recovery_type] = 0;
}
for (int role = 0; role < (op_data->scheme == POOL_SCHEME_REPLICATED ? 1 : pg.pg_size); role++)
{
recovery_stat_bytes[0][recovery_type] += op_data->stripes[role].write_end - op_data->stripes[role].write_start;
}
}
// Any kind of a non-clean object can have extra chunks, because we don't record objects
// as degraded & misplaced or incomplete & misplaced at the same time. So try to remove extra chunks
if (immediate_commit != IMMEDIATE_ALL)
{
// We can't remove extra chunks yet if fsyncs are explicit, because
// new copies may not be committed to stable storage yet
// We can only remove extra chunks after a successful SYNC for this PG
for (auto & chunk: op_data->object_state->osd_set)
{
// Check is the same as in submit_primary_del_subops()
if (op_data->scheme == POOL_SCHEME_REPLICATED
? !contains_osd(pg.cur_set.data(), pg.pg_size, chunk.osd_num)
: (chunk.osd_num != pg.cur_set[chunk.role]))
{
pg.copies_to_delete_after_sync.push_back((obj_ver_osd_t){
.osd_num = chunk.osd_num,
.oid = {
.inode = op_data->oid.inode,
.stripe = op_data->oid.stripe | (op_data->scheme == POOL_SCHEME_REPLICATED ? 0 : chunk.role),
},
.version = op_data->fact_ver,
});
copies_to_delete_after_sync_count++;
}
}
}
else
{
submit_primary_del_subops(cur_op, pg.cur_set.data(), pg.pg_size, op_data->object_state->osd_set);
if (op_data->n_subops > 0)
{
resume_8:
op_data->st = 8;
return;
resume_9:
if (op_data->errors > 0)
{
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->epipe > 0 ? -EPIPE : -EIO);
return;
}
}
}
// Clear object state
remove_object_from_state(op_data->oid, op_data->object_state, pg);
pg.clean_count++;
}
cur_op->reply.hdr.retval = cur_op->req.rw.len;
continue_others:
// Remove version override
pg.ver_override.erase(op_data->oid);
object_id oid = op_data->oid;
// Remove the operation from queue before calling finish_op so it doesn't see the completed operation in queue
auto next_it = pg.write_queue.find(oid);
if (next_it != pg.write_queue.end() && next_it->second == cur_op)
{
pg.write_queue.erase(next_it++);
}
// finish_op would invalidate next_it if it cleared pg.write_queue, but it doesn't do that :)
finish_op(cur_op, cur_op->reply.hdr.retval);
// Continue other write operations to the same object
if (next_it != pg.write_queue.end() && next_it->first == oid)
{
osd_op_t *next_op = next_it->second;
continue_primary_write(next_op);
}
}
bool osd_t::remember_unstable_write(osd_op_t *cur_op, pg_t & pg, pg_osd_set_t & loc_set, int base_state)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
if (op_data->st == base_state)
{
goto resume_6;
}
else if (op_data->st == base_state+1)
{
goto resume_7;
}
// FIXME: Check for immediate_commit == IMMEDIATE_SMALL
if (immediate_commit == IMMEDIATE_ALL)
{
if (op_data->scheme != POOL_SCHEME_REPLICATED)
{
// Send STABILIZE ops immediately
op_data->unstable_write_osds = new std::vector<unstable_osd_num_t>();
op_data->unstable_writes = new obj_ver_id[loc_set.size()];
{
int last_start = 0;
for (auto & chunk: loc_set)
{
op_data->unstable_writes[last_start] = (obj_ver_id){
.oid = {
.inode = op_data->oid.inode,
.stripe = op_data->oid.stripe | chunk.role,
},
.version = op_data->fact_ver,
};
op_data->unstable_write_osds->push_back((unstable_osd_num_t){
.osd_num = chunk.osd_num,
.start = last_start,
.len = 1,
});
last_start++;
}
}
submit_primary_stab_subops(cur_op);
resume_6:
op_data->st = 6;
return false;
resume_7:
// FIXME: Free those in the destructor?
delete op_data->unstable_write_osds;
delete[] op_data->unstable_writes;
op_data->unstable_writes = NULL;
op_data->unstable_write_osds = NULL;
if (op_data->errors > 0)
{
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->epipe > 0 ? -EPIPE : -EIO);
return false;
}
}
}
else
{
if (op_data->scheme != POOL_SCHEME_REPLICATED)
{
// Remember version as unstable for EC/XOR
for (auto & chunk: loc_set)
{
this->dirty_osds.insert(chunk.osd_num);
this->unstable_writes[(osd_object_id_t){
.osd_num = chunk.osd_num,
.oid = {
.inode = op_data->oid.inode,
.stripe = op_data->oid.stripe | chunk.role,
},
}] = op_data->fact_ver;
}
}
else
{
// Only remember to sync OSDs for replicated pools
for (auto & chunk: loc_set)
{
this->dirty_osds.insert(chunk.osd_num);
}
}
// Remember PG as dirty to drop the connection when PG goes offline
// (this is required because of the "lazy sync")
auto cl_it = c_cli.clients.find(cur_op->peer_fd);
if (cl_it != c_cli.clients.end())
{
cl_it->second->dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
}
dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
}
return true;
}
// Save and clear unstable_writes -> SYNC all -> STABLE all
void osd_t::continue_primary_sync(osd_op_t *cur_op)
{
if (!cur_op->op_data)
{
cur_op->op_data = (osd_primary_op_data_t*)calloc_or_die(1, sizeof(osd_primary_op_data_t));
}
osd_primary_op_data_t *op_data = cur_op->op_data;
if (op_data->st == 1) goto resume_1;
else if (op_data->st == 2) goto resume_2;
else if (op_data->st == 3) goto resume_3;
else if (op_data->st == 4) goto resume_4;
else if (op_data->st == 5) goto resume_5;
else if (op_data->st == 6) goto resume_6;
else if (op_data->st == 7) goto resume_7;
else if (op_data->st == 8) goto resume_8;
assert(op_data->st == 0);
if (syncs_in_progress.size() > 0)
{
// Wait for previous syncs, if any
// FIXME: We may try to execute the current one in parallel, like in Blockstore, but I'm not sure if it matters at all
syncs_in_progress.push_back(cur_op);
op_data->st = 1;
resume_1:
return;
}
else
{
syncs_in_progress.push_back(cur_op);
}
resume_2:
if (dirty_osds.size() == 0)
{
// Nothing to sync
goto finish;
}
// Save and clear unstable_writes
// In theory it is possible to do in on a per-client basis, but this seems to be an unnecessary complication
// It would be cool not to copy these here at all, but someone has to deduplicate them by object IDs anyway
if (unstable_writes.size() > 0)
{
op_data->unstable_write_osds = new std::vector<unstable_osd_num_t>();
op_data->unstable_writes = new obj_ver_id[this->unstable_writes.size()];
osd_num_t last_osd = 0;
int last_start = 0, last_end = 0;
for (auto it = this->unstable_writes.begin(); it != this->unstable_writes.end(); it++)
{
if (last_osd != it->first.osd_num)
{
if (last_osd != 0)
{
op_data->unstable_write_osds->push_back((unstable_osd_num_t){
.osd_num = last_osd,
.start = last_start,
.len = last_end - last_start,
});
}
last_osd = it->first.osd_num;
last_start = last_end;
}
op_data->unstable_writes[last_end] = (obj_ver_id){
.oid = it->first.oid,
.version = it->second,
};
last_end++;
}
if (last_osd != 0)
{
op_data->unstable_write_osds->push_back((unstable_osd_num_t){
.osd_num = last_osd,
.start = last_start,
.len = last_end - last_start,
});
}
this->unstable_writes.clear();
}
{
void *dirty_buf = malloc_or_die(
sizeof(pool_pg_num_t)*dirty_pgs.size() +
sizeof(osd_num_t)*dirty_osds.size() +
sizeof(obj_ver_osd_t)*this->copies_to_delete_after_sync_count
);
op_data->dirty_pgs = (pool_pg_num_t*)dirty_buf;
op_data->dirty_osds = (osd_num_t*)(dirty_buf + sizeof(pool_pg_num_t)*dirty_pgs.size());
op_data->dirty_pg_count = dirty_pgs.size();
op_data->dirty_osd_count = dirty_osds.size();
if (this->copies_to_delete_after_sync_count)
{
op_data->copies_to_delete_count = 0;
op_data->copies_to_delete = (obj_ver_osd_t*)(op_data->dirty_osds + op_data->dirty_osd_count);
for (auto dirty_pg_num: dirty_pgs)
{
auto & pg = pgs.at(dirty_pg_num);
assert(pg.copies_to_delete_after_sync.size() <= this->copies_to_delete_after_sync_count);
memcpy(
op_data->copies_to_delete + op_data->copies_to_delete_count,
pg.copies_to_delete_after_sync.data(),
sizeof(obj_ver_osd_t)*pg.copies_to_delete_after_sync.size()
);
op_data->copies_to_delete_count += pg.copies_to_delete_after_sync.size();
this->copies_to_delete_after_sync_count -= pg.copies_to_delete_after_sync.size();
pg.copies_to_delete_after_sync.clear();
}
assert(this->copies_to_delete_after_sync_count == 0);
}
int dpg = 0;
for (auto dirty_pg_num: dirty_pgs)
{
pgs.at(dirty_pg_num).inflight++;
op_data->dirty_pgs[dpg++] = dirty_pg_num;
}
dirty_pgs.clear();
dpg = 0;
for (auto osd_num: dirty_osds)
{
op_data->dirty_osds[dpg++] = osd_num;
}
dirty_osds.clear();
}
if (immediate_commit != IMMEDIATE_ALL)
{
// SYNC
submit_primary_sync_subops(cur_op);
resume_3:
op_data->st = 3;
return;
resume_4:
if (op_data->errors > 0)
{
goto resume_6;
}
}
if (op_data->unstable_writes)
{
// Stabilize version sets, if any
submit_primary_stab_subops(cur_op);
resume_5:
op_data->st = 5;
return;
}
resume_6:
if (op_data->errors > 0)
{
// Return PGs and OSDs back into their dirty sets
for (int i = 0; i < op_data->dirty_pg_count; i++)
{
dirty_pgs.insert(op_data->dirty_pgs[i]);
}
for (int i = 0; i < op_data->dirty_osd_count; i++)
{
dirty_osds.insert(op_data->dirty_osds[i]);
}
if (op_data->unstable_writes)
{
// Return objects back into the unstable write set
for (auto unstable_osd: *(op_data->unstable_write_osds))
{
for (int i = 0; i < unstable_osd.len; i++)
{
// Except those from peered PGs
auto & w = op_data->unstable_writes[i];
pool_pg_num_t wpg = {
.pool_id = INODE_POOL(w.oid.inode),
.pg_num = map_to_pg(w.oid, st_cli.pool_config.at(INODE_POOL(w.oid.inode)).pg_stripe_size),
};
if (pgs.at(wpg).state & PG_ACTIVE)
{
uint64_t & dest = this->unstable_writes[(osd_object_id_t){
.osd_num = unstable_osd.osd_num,
.oid = w.oid,
}];
dest = dest < w.version ? w.version : dest;
dirty_pgs.insert(wpg);
}
}
}
}
if (op_data->copies_to_delete)
{
// Return 'copies to delete' back into respective PGs
for (int i = 0; i < op_data->copies_to_delete_count; i++)
{
auto & w = op_data->copies_to_delete[i];
auto & pg = pgs.at((pool_pg_num_t){
.pool_id = INODE_POOL(w.oid.inode),
.pg_num = map_to_pg(w.oid, st_cli.pool_config.at(INODE_POOL(w.oid.inode)).pg_stripe_size),
});
if (pg.state & PG_ACTIVE)
{
pg.copies_to_delete_after_sync.push_back(w);
copies_to_delete_after_sync_count++;
}
}
}
}
else if (op_data->copies_to_delete)
{
// Actually delete copies which we wanted to delete
submit_primary_del_batch(cur_op, op_data->copies_to_delete, op_data->copies_to_delete_count);
resume_7:
op_data->st = 7;
return;
resume_8:
if (op_data->errors > 0)
{
goto resume_6;
}
}
for (int i = 0; i < op_data->dirty_pg_count; i++)
{
auto & pg = pgs.at(op_data->dirty_pgs[i]);
pg.inflight--;
if ((pg.state & PG_STOPPING) && pg.inflight == 0 && !pg.flush_batch &&
// We must either forget all PG's unstable writes or wait for it to become clean
dirty_pgs.find({ .pool_id = pg.pool_id, .pg_num = pg.pg_num }) == dirty_pgs.end())
{
finish_stop_pg(pg);
}
}
// FIXME: Free those in the destructor?
free(op_data->dirty_pgs);
op_data->dirty_pgs = NULL;
op_data->dirty_osds = NULL;
if (op_data->unstable_writes)
{
delete op_data->unstable_write_osds;
delete[] op_data->unstable_writes;
op_data->unstable_writes = NULL;
op_data->unstable_write_osds = NULL;
}
if (op_data->errors > 0)
{
finish_op(cur_op, op_data->epipe > 0 ? -EPIPE : -EIO);
}
else
{
finish:
if (cur_op->peer_fd)
{
auto it = c_cli.clients.find(cur_op->peer_fd);
if (it != c_cli.clients.end())
it->second->dirty_pgs.clear();
}
finish_op(cur_op, 0);
}
assert(syncs_in_progress.front() == cur_op);
syncs_in_progress.pop_front();
if (syncs_in_progress.size() > 0)
{
cur_op = syncs_in_progress.front();
op_data = cur_op->op_data;
op_data->st++;
goto resume_2;
}
}
// Decrement pg_osd_set_state_t's object_count and change PG state accordingly
void osd_t::remove_object_from_state(object_id & oid, pg_osd_set_state_t *object_state, pg_t & pg)
{
@ -294,14 +832,10 @@ void osd_t::remove_object_from_state(object_id & oid, pg_osd_set_state_t *object
{
throw std::runtime_error("BUG: Invalid object state: "+std::to_string(object_state->state));
}
}
void osd_t::free_object_state(pg_t & pg, pg_osd_set_state_t **object_state)
{
if (*object_state && !(--(*object_state)->object_count))
object_state->object_count--;
if (!object_state->object_count)
{
pg.state_dict.erase((*object_state)->osd_set);
*object_state = NULL;
pg.state_dict.erase(object_state->osd_set);
}
}
@ -333,7 +867,7 @@ resume_1:
// Determine which OSDs contain this object and delete it
op_data->prev_set = get_object_osd_set(pg, op_data->oid, pg.cur_set.data(), &op_data->object_state);
// Submit 1 read to determine the actual version number
submit_primary_subops(SUBMIT_RMW_READ, UINT64_MAX, op_data->prev_set, cur_op);
submit_primary_subops(SUBMIT_RMW_READ, UINT64_MAX, pg.pg_size, op_data->prev_set, cur_op);
resume_2:
op_data->st = 2;
return;
@ -367,21 +901,22 @@ resume_5:
else
{
remove_object_from_state(op_data->oid, op_data->object_state, pg);
free_object_state(pg, &op_data->object_state);
}
pg.total_count--;
osd_op_t *next_op = NULL;
auto next_it = pg.write_queue.find(op_data->oid);
if (next_it != pg.write_queue.end() && next_it->second == cur_op)
{
pg.write_queue.erase(next_it++);
if (next_it != pg.write_queue.end() && next_it->first == op_data->oid)
next_op = next_it->second;
}
object_id oid = op_data->oid;
finish_op(cur_op, cur_op->req.rw.len);
if (next_op)
// Continue other write operations to the same object
auto next_it = pg.write_queue.find(oid);
auto this_it = next_it;
if (this_it != pg.write_queue.end() && this_it->second == cur_op)
{
// Continue next write to the same object
continue_primary_write(next_op);
next_it++;
pg.write_queue.erase(this_it);
if (next_it != pg.write_queue.end() &&
next_it->first == oid)
{
osd_op_t *next_op = next_it->second;
continue_primary_write(next_op);
}
}
}

View File

@ -31,31 +31,15 @@ struct osd_primary_op_data_t
uint64_t *prev_set = NULL;
pg_osd_set_state_t *object_state = NULL;
union
{
struct
{
// for sync. oops, requires freeing
std::vector<unstable_osd_num_t> *unstable_write_osds;
pool_pg_num_t *dirty_pgs;
int dirty_pg_count;
osd_num_t *dirty_osds;
int dirty_osd_count;
obj_ver_id *unstable_writes;
obj_ver_osd_t *copies_to_delete;
int copies_to_delete_count;
};
struct
{
// for read_bitmaps
void *snapshot_bitmaps;
inode_t *read_chain;
uint8_t *missing_flags;
int chain_size;
osd_chain_read_t *chain_reads;
int chain_read_count;
};
};
// for sync. oops, requires freeing
std::vector<unstable_osd_num_t> *unstable_write_osds = NULL;
pool_pg_num_t *dirty_pgs = NULL;
int dirty_pg_count = 0;
osd_num_t *dirty_osds = NULL;
int dirty_osd_count = 0;
obj_ver_id *unstable_writes = NULL;
obj_ver_osd_t *copies_to_delete = NULL;
int copies_to_delete_count = 0;
};
bool contains_osd(osd_num_t *osd_set, uint64_t size, osd_num_t osd_num);

View File

@ -1,549 +0,0 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 (see README.md for details)
#include "osd_primary.h"
#include "allocator.h"
void osd_t::continue_chained_read(osd_op_t *cur_op)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
if (op_data->st == 1)
goto resume_1;
else if (op_data->st == 2)
goto resume_2;
else if (op_data->st == 3)
goto resume_3;
else if (op_data->st == 4)
goto resume_4;
cur_op->reply.rw.bitmap_len = 0;
for (int role = 0; role < op_data->pg_data_size; role++)
{
op_data->stripes[role].read_start = op_data->stripes[role].req_start;
op_data->stripes[role].read_end = op_data->stripes[role].req_end;
}
resume_1:
resume_2:
// Read bitmaps
if (read_bitmaps(cur_op, pg, 1) != 0)
return;
// Prepare & submit reads
if (submit_chained_read_requests(pg, cur_op) != 0)
return;
if (op_data->n_subops > 0)
{
// Wait for reads
op_data->st = 3;
resume_3:
return;
}
resume_4:
if (op_data->errors > 0)
{
free(op_data->chain_reads);
op_data->chain_reads = NULL;
finish_op(cur_op, op_data->epipe > 0 ? -EPIPE : -EIO);
return;
}
send_chained_read_results(pg, cur_op);
finish_op(cur_op, cur_op->req.rw.len);
}
int osd_t::read_bitmaps(osd_op_t *cur_op, pg_t & pg, int base_state)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
if (op_data->st == base_state)
goto resume_0;
else if (op_data->st == base_state+1)
goto resume_1;
if (pg.state == PG_ACTIVE && pg.scheme == POOL_SCHEME_REPLICATED)
{
// Happy path for clean replicated PGs (all bitmaps are available locally)
for (int chain_num = 0; chain_num < op_data->chain_size; chain_num++)
{
object_id cur_oid = { .inode = op_data->read_chain[chain_num], .stripe = op_data->oid.stripe };
auto vo_it = pg.ver_override.find(cur_oid);
auto read_version = (vo_it != pg.ver_override.end() ? vo_it->second : UINT64_MAX);
// Read bitmap synchronously from the local database
bs->read_bitmap(cur_oid, read_version, op_data->snapshot_bitmaps + chain_num*clean_entry_bitmap_size, NULL);
}
}
else
{
if (submit_bitmap_subops(cur_op, pg) < 0)
{
// Failure
finish_op(cur_op, -EIO);
return -1;
}
resume_0:
if (op_data->n_subops > 0)
{
// Wait for subops
op_data->st = base_state;
return 1;
}
resume_1:
if (pg.scheme != POOL_SCHEME_REPLICATED)
{
for (int chain_num = 0; chain_num < op_data->chain_size; chain_num++)
{
// Check if we need to reconstruct any bitmaps
for (int i = 0; i < pg.pg_size; i++)
{
if (op_data->missing_flags[chain_num*pg.pg_size + i])
{
osd_rmw_stripe_t local_stripes[pg.pg_size] = { 0 };
for (i = 0; i < pg.pg_size; i++)
{
local_stripes[i].missing = op_data->missing_flags[chain_num*pg.pg_size + i] && true;
local_stripes[i].bmp_buf = op_data->snapshot_bitmaps + (chain_num*pg.pg_size + i)*clean_entry_bitmap_size;
local_stripes[i].read_start = local_stripes[i].read_end = 1;
}
if (pg.scheme == POOL_SCHEME_XOR)
{
reconstruct_stripes_xor(local_stripes, pg.pg_size, clean_entry_bitmap_size);
}
else if (pg.scheme == POOL_SCHEME_JERASURE)
{
reconstruct_stripes_jerasure(local_stripes, pg.pg_size, pg.pg_data_size, clean_entry_bitmap_size);
}
break;
}
}
}
}
}
return 0;
}
int osd_t::collect_bitmap_requests(osd_op_t *cur_op, pg_t & pg, std::vector<bitmap_request_t> & bitmap_requests)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
for (int chain_num = 0; chain_num < op_data->chain_size; chain_num++)
{
object_id cur_oid = { .inode = op_data->read_chain[chain_num], .stripe = op_data->oid.stripe };
auto vo_it = pg.ver_override.find(cur_oid);
uint64_t target_version = vo_it != pg.ver_override.end() ? vo_it->second : UINT64_MAX;
pg_osd_set_state_t *object_state;
uint64_t* cur_set = get_object_osd_set(pg, cur_oid, pg.cur_set.data(), &object_state);
if (pg.scheme == POOL_SCHEME_REPLICATED)
{
osd_num_t read_target = 0;
for (int i = 0; i < pg.pg_size; i++)
{
if (cur_set[i] == this->osd_num || cur_set[i] != 0 && read_target == 0)
{
// Select local or any other available OSD for reading
read_target = cur_set[i];
}
}
assert(read_target != 0);
bitmap_requests.push_back((bitmap_request_t){
.osd_num = read_target,
.oid = cur_oid,
.version = target_version,
.bmp_buf = op_data->snapshot_bitmaps + chain_num*clean_entry_bitmap_size,
});
}
else
{
osd_rmw_stripe_t local_stripes[pg.pg_size];
memcpy(local_stripes, op_data->stripes, sizeof(osd_rmw_stripe_t) * pg.pg_size);
if (extend_missing_stripes(local_stripes, cur_set, pg.pg_data_size, pg.pg_size) < 0)
{
free(op_data->snapshot_bitmaps);
return -1;
}
int need_at_least = 0;
for (int i = 0; i < pg.pg_size; i++)
{
if (local_stripes[i].read_end != 0 && cur_set[i] == 0)
{
// We need this part of the bitmap, but it's unavailable
need_at_least = pg.pg_data_size;
op_data->missing_flags[chain_num*pg.pg_size + i] = 1;
}
else
{
op_data->missing_flags[chain_num*pg.pg_size + i] = 0;
}
}
int found = 0;
for (int i = 0; i < pg.pg_size; i++)
{
if (cur_set[i] != 0 && (local_stripes[i].read_end != 0 || found < need_at_least))
{
// Read part of the bitmap
bitmap_requests.push_back((bitmap_request_t){
.osd_num = cur_set[i],
.oid = {
.inode = cur_oid.inode,
.stripe = cur_oid.stripe | i,
},
.version = target_version,
.bmp_buf = op_data->snapshot_bitmaps + (chain_num*pg.pg_size + i)*clean_entry_bitmap_size,
});
found++;
}
}
// Already checked by extend_missing_stripes, so it's fine to use assert
assert(found >= need_at_least);
}
}
std::sort(bitmap_requests.begin(), bitmap_requests.end());
return 0;
}
int osd_t::submit_bitmap_subops(osd_op_t *cur_op, pg_t & pg)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
std::vector<bitmap_request_t> *bitmap_requests = new std::vector<bitmap_request_t>();
if (collect_bitmap_requests(cur_op, pg, *bitmap_requests) < 0)
{
return -1;
}
op_data->n_subops = 0;
for (int i = 0; i < bitmap_requests->size(); i++)
{
if ((i == bitmap_requests->size()-1 || (*bitmap_requests)[i+1].osd_num != (*bitmap_requests)[i].osd_num) &&
(*bitmap_requests)[i].osd_num != this->osd_num)
{
op_data->n_subops++;
}
}
if (op_data->n_subops)
{
op_data->fact_ver = 0;
op_data->done = op_data->errors = 0;
op_data->subops = new osd_op_t[op_data->n_subops];
}
for (int i = 0, subop_idx = 0, prev = 0; i < bitmap_requests->size(); i++)
{
if (i == bitmap_requests->size()-1 || (*bitmap_requests)[i+1].osd_num != (*bitmap_requests)[i].osd_num)
{
osd_num_t subop_osd_num = (*bitmap_requests)[i].osd_num;
if (subop_osd_num == this->osd_num)
{
// Read bitmap synchronously from the local database
for (int j = prev; j <= i; j++)
{
bs->read_bitmap((*bitmap_requests)[j].oid, (*bitmap_requests)[j].version, (*bitmap_requests)[j].bmp_buf, NULL);
}
}
else
{
// Send to a remote OSD
osd_op_t *subop = op_data->subops+subop_idx;
subop->op_type = OSD_OP_OUT;
subop->peer_fd = c_cli.osd_peer_fds.at(subop_osd_num);
// FIXME: Use the pre-allocated buffer
subop->buf = malloc_or_die(sizeof(obj_ver_id)*(i+1-prev));
subop->req = (osd_any_op_t){
.sec_read_bmp = {
.header = {
.magic = SECONDARY_OSD_OP_MAGIC,
.id = c_cli.next_subop_id++,
.opcode = OSD_OP_SEC_READ_BMP,
},
.len = sizeof(obj_ver_id)*(i+1-prev),
}
};
obj_ver_id *ov = (obj_ver_id*)subop->buf;
for (int j = prev; j <= i; j++, ov++)
{
ov->oid = (*bitmap_requests)[j].oid;
ov->version = (*bitmap_requests)[j].version;
}
subop->callback = [cur_op, bitmap_requests, prev, i, this](osd_op_t *subop)
{
int requested_count = subop->req.sec_read_bmp.len / sizeof(obj_ver_id);
if (subop->reply.hdr.retval == requested_count * (8 + clean_entry_bitmap_size))
{
void *cur_buf = subop->buf + 8;
for (int j = prev; j <= i; j++)
{
memcpy((*bitmap_requests)[j].bmp_buf, cur_buf, clean_entry_bitmap_size);
cur_buf += 8 + clean_entry_bitmap_size;
}
}
if ((cur_op->op_data->errors + cur_op->op_data->done + 1) >= cur_op->op_data->n_subops)
{
delete bitmap_requests;
}
handle_primary_subop(subop, cur_op);
};
c_cli.outbox_push(subop);
subop_idx++;
}
prev = i+1;
}
}
if (!op_data->n_subops)
{
delete bitmap_requests;
}
return 0;
}
std::vector<osd_chain_read_t> osd_t::collect_chained_read_requests(osd_op_t *cur_op)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
std::vector<osd_chain_read_t> chain_reads;
int stripe_count = (op_data->scheme == POOL_SCHEME_REPLICATED ? 1 : op_data->pg_size);
memset(op_data->stripes[0].bmp_buf, 0, stripe_count * clean_entry_bitmap_size);
uint8_t *global_bitmap = (uint8_t*)op_data->stripes[0].bmp_buf;
// We always use at most 1 read request per layer
for (int chain_pos = 0; chain_pos < op_data->chain_size; chain_pos++)
{
uint8_t *part_bitmap = ((uint8_t*)op_data->snapshot_bitmaps) + chain_pos*stripe_count*clean_entry_bitmap_size;
int start = (cur_op->req.rw.offset - op_data->oid.stripe)/bs_bitmap_granularity;
int end = start + cur_op->req.rw.len/bs_bitmap_granularity;
// Skip unneeded part in the beginning
while (start < end && (
((global_bitmap[start>>3] >> (start&7)) & 1) ||
!((part_bitmap[start>>3] >> (start&7)) & 1)))
{
start++;
}
// Skip unneeded part in the end
while (start < end && (
((global_bitmap[(end-1)>>3] >> ((end-1)&7)) & 1) ||
!((part_bitmap[(end-1)>>3] >> ((end-1)&7)) & 1)))
{
end--;
}
if (start < end)
{
// Copy (OR) bits in between
int cur = start;
for (; cur < end && (cur & 0x7); cur++)
{
global_bitmap[cur>>3] = global_bitmap[cur>>3] | (part_bitmap[cur>>3] & (1 << (cur&7)));
}
for (; cur <= end-8; cur += 8)
{
global_bitmap[cur>>3] = global_bitmap[cur>>3] | part_bitmap[cur>>3];
}
for (; cur < end; cur++)
{
global_bitmap[cur>>3] = global_bitmap[cur>>3] | (part_bitmap[cur>>3] & (1 << (cur&7)));
}
// Add request
chain_reads.push_back((osd_chain_read_t){
.chain_pos = chain_pos,
.inode = op_data->read_chain[chain_pos],
.offset = start*bs_bitmap_granularity,
.len = (end-start)*bs_bitmap_granularity,
});
}
}
return chain_reads;
}
int osd_t::submit_chained_read_requests(pg_t & pg, osd_op_t *cur_op)
{
// Decide which parts of which objects we need to read based on bitmaps
osd_primary_op_data_t *op_data = cur_op->op_data;
auto chain_reads = collect_chained_read_requests(cur_op);
int stripe_count = (pg.scheme == POOL_SCHEME_REPLICATED ? 1 : pg.pg_size);
op_data->chain_read_count = chain_reads.size();
op_data->chain_reads = (osd_chain_read_t*)calloc_or_die(
1, (sizeof(osd_chain_read_t) + sizeof(osd_rmw_stripe_t)*stripe_count) * chain_reads.size()
);
osd_rmw_stripe_t *chain_stripes = (osd_rmw_stripe_t*)(((void*)op_data->chain_reads) + sizeof(osd_chain_read_t) * op_data->chain_read_count);
// Now process each subrequest as a separate read, including reconstruction if needed
// Prepare reads
int n_subops = 0;
uint64_t read_buffer_size = 0;
for (int cri = 0; cri < chain_reads.size(); cri++)
{
op_data->chain_reads[cri] = chain_reads[cri];
object_id cur_oid = { .inode = chain_reads[cri].inode, .stripe = op_data->oid.stripe };
// FIXME: maybe introduce split_read_stripes to shorten these lines and to remove read_start=req_start
osd_rmw_stripe_t *stripes = chain_stripes + cri*stripe_count;
split_stripes(pg.pg_data_size, bs_block_size, chain_reads[cri].offset, chain_reads[cri].len, stripes);
if (op_data->scheme == POOL_SCHEME_REPLICATED && !stripes[0].req_end)
{
continue;
}
for (int role = 0; role < op_data->pg_data_size; role++)
{
stripes[role].read_start = stripes[role].req_start;
stripes[role].read_end = stripes[role].req_end;
}
uint64_t *cur_set = pg.cur_set.data();
if (pg.state != PG_ACTIVE && op_data->scheme != POOL_SCHEME_REPLICATED)
{
pg_osd_set_state_t *object_state;
cur_set = get_object_osd_set(pg, cur_oid, pg.cur_set.data(), &object_state);
if (extend_missing_stripes(stripes, cur_set, pg.pg_data_size, pg.pg_size) < 0)
{
free(op_data->chain_reads);
op_data->chain_reads = NULL;
finish_op(cur_op, -EIO);
return -1;
}
op_data->degraded = 1;
}
if (op_data->scheme == POOL_SCHEME_REPLICATED)
{
n_subops++;
read_buffer_size += stripes[0].read_end - stripes[0].read_start;
}
else
{
for (int role = 0; role < pg.pg_size; role++)
{
if (stripes[role].read_end > 0 && cur_set[role] != 0)
n_subops++;
if (stripes[role].read_end > 0)
read_buffer_size += stripes[role].read_end - stripes[role].read_start;
}
}
}
cur_op->buf = memalign_or_die(MEM_ALIGNMENT, read_buffer_size);
void *cur_buf = cur_op->buf;
for (int cri = 0; cri < chain_reads.size(); cri++)
{
osd_rmw_stripe_t *stripes = chain_stripes + cri*stripe_count;
for (int role = 0; role < stripe_count; role++)
{
if (stripes[role].read_end > 0)
{
stripes[role].read_buf = cur_buf;
stripes[role].bmp_buf = op_data->snapshot_bitmaps + (chain_reads[cri].chain_pos*stripe_count + role)*clean_entry_bitmap_size;
cur_buf += stripes[role].read_end - stripes[role].read_start;
}
}
}
// Submit all reads
op_data->fact_ver = UINT64_MAX;
op_data->done = op_data->errors = 0;
op_data->n_subops = n_subops;
if (!n_subops)
{
return 0;
}
op_data->subops = new osd_op_t[n_subops];
int cur_subops = 0;
for (int cri = 0; cri < chain_reads.size(); cri++)
{
osd_rmw_stripe_t *stripes = chain_stripes + cri*stripe_count;
if (op_data->scheme == POOL_SCHEME_REPLICATED && !stripes[0].req_end)
{
continue;
}
object_id cur_oid = { .inode = chain_reads[cri].inode, .stripe = op_data->oid.stripe };
auto vo_it = pg.ver_override.find(cur_oid);
uint64_t target_ver = vo_it != pg.ver_override.end() ? vo_it->second : UINT64_MAX;
uint64_t *cur_set = pg.cur_set.data();
if (pg.state != PG_ACTIVE && op_data->scheme != POOL_SCHEME_REPLICATED)
{
pg_osd_set_state_t *object_state;
cur_set = get_object_osd_set(pg, cur_oid, pg.cur_set.data(), &object_state);
}
int zero_read = -1;
if (op_data->scheme == POOL_SCHEME_REPLICATED)
{
for (int role = 0; role < op_data->pg_size; role++)
if (cur_set[role] == this->osd_num || zero_read == -1)
zero_read = role;
}
cur_subops += submit_primary_subop_batch(SUBMIT_READ, chain_reads[cri].inode, target_ver, stripes, cur_set, cur_op, cur_subops, zero_read);
}
assert(cur_subops == n_subops);
return 0;
}
void osd_t::send_chained_read_results(pg_t & pg, osd_op_t *cur_op)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
int stripe_count = (pg.scheme == POOL_SCHEME_REPLICATED ? 1 : pg.pg_size);
osd_rmw_stripe_t *chain_stripes = (osd_rmw_stripe_t*)(((void*)op_data->chain_reads) + sizeof(osd_chain_read_t) * op_data->chain_read_count);
// Reconstruct parts if needed
if (op_data->degraded)
{
int stripe_count = (pg.scheme == POOL_SCHEME_REPLICATED ? 1 : pg.pg_size);
for (int cri = 0; cri < op_data->chain_read_count; cri++)
{
// Reconstruct missing stripes
osd_rmw_stripe_t *stripes = chain_stripes + cri*stripe_count;
if (op_data->scheme == POOL_SCHEME_XOR)
{
reconstruct_stripes_xor(stripes, pg.pg_size, clean_entry_bitmap_size);
}
else if (op_data->scheme == POOL_SCHEME_JERASURE)
{
reconstruct_stripes_jerasure(stripes, pg.pg_size, pg.pg_data_size, clean_entry_bitmap_size);
}
}
}
// Send bitmap
cur_op->reply.rw.bitmap_len = op_data->pg_data_size * clean_entry_bitmap_size;
cur_op->iov.push_back(op_data->stripes[0].bmp_buf, cur_op->reply.rw.bitmap_len);
// And finally compose the result
uint64_t sent = 0;
int prev_pos = 0, pos = 0;
bool prev_set = false;
int prev = (cur_op->req.rw.offset - op_data->oid.stripe) / bs_bitmap_granularity;
int end = prev + cur_op->req.rw.len/bs_bitmap_granularity;
int cur = prev;
while (cur <= end)
{
bool has_bit = false;
if (cur < end)
{
for (pos = 0; pos < op_data->chain_size; pos++)
{
has_bit = (((uint8_t*)op_data->snapshot_bitmaps)[pos*stripe_count*clean_entry_bitmap_size + cur/8] >> (cur%8)) & 1;
if (has_bit)
break;
}
}
if (has_bit != prev_set || pos != prev_pos || cur == end)
{
if (cur > prev)
{
// Send buffer in parts to avoid copying
if (!prev_set)
{
while ((cur-prev) > zero_buffer_size/bs_bitmap_granularity)
{
cur_op->iov.push_back(zero_buffer, zero_buffer_size);
sent += zero_buffer_size;
prev += zero_buffer_size/bs_bitmap_granularity;
}
cur_op->iov.push_back(zero_buffer, (cur-prev)*bs_bitmap_granularity);
sent += (cur-prev)*bs_bitmap_granularity;
}
else
{
osd_rmw_stripe_t *stripes = chain_stripes + prev_pos*stripe_count;
while (cur > prev)
{
int role = prev*bs_bitmap_granularity/bs_block_size;
int role_start = prev*bs_bitmap_granularity - role*bs_block_size;
int role_end = cur*bs_bitmap_granularity - role*bs_block_size;
if (role_end > bs_block_size)
role_end = bs_block_size;
assert(stripes[role].read_buf);
cur_op->iov.push_back(
stripes[role].read_buf + (role_start - stripes[role].read_start),
role_end - role_start
);
sent += role_end - role_start;
prev += (role_end - role_start)/bs_bitmap_granularity;
}
}
}
prev = cur;
prev_pos = pos;
prev_set = has_bit;
}
cur++;
}
assert(sent == cur_op->req.rw.len);
free(op_data->chain_reads);
op_data->chain_reads = NULL;
}

View File

@ -66,16 +66,17 @@ void osd_t::finish_op(osd_op_t *cur_op, int retval)
auto & pg = pgs.at({ .pool_id = INODE_POOL(cur_op->op_data->oid.inode), .pg_num = cur_op->op_data->pg_num });
pg.inflight--;
assert(pg.inflight >= 0);
if ((pg.state & PG_STOPPING) && pg.inflight == 0 && !pg.flush_batch)
if ((pg.state & PG_STOPPING) && pg.inflight == 0 && !pg.flush_batch &&
// We must either forget all PG's unstable writes or wait for it to become clean
dirty_pgs.find({ .pool_id = pg.pool_id, .pg_num = pg.pg_num }) == dirty_pgs.end())
{
finish_stop_pg(pg);
}
else if ((pg.state & PG_REPEERING) && pg.inflight == 0 && !pg.flush_batch)
{
start_pg_peering(pg);
}
}
assert(!cur_op->op_data->subops);
assert(!cur_op->op_data->unstable_write_osds);
assert(!cur_op->op_data->unstable_writes);
assert(!cur_op->op_data->dirty_pgs);
free(cur_op->op_data);
cur_op->op_data = NULL;
}
@ -103,7 +104,7 @@ void osd_t::finish_op(osd_op_t *cur_op, int retval)
}
}
void osd_t::submit_primary_subops(int submit_type, uint64_t op_version, const uint64_t* osd_set, osd_op_t *cur_op)
void osd_t::submit_primary_subops(int submit_type, uint64_t op_version, int pg_size, const uint64_t* osd_set, osd_op_t *cur_op)
{
bool wr = submit_type == SUBMIT_WRITE;
osd_primary_op_data_t *op_data = cur_op->op_data;
@ -111,34 +112,32 @@ void osd_t::submit_primary_subops(int submit_type, uint64_t op_version, const ui
bool rep = op_data->scheme == POOL_SCHEME_REPLICATED;
// Allocate subops
int n_subops = 0, zero_read = -1;
for (int role = 0; role < op_data->pg_size; role++)
for (int role = 0; role < pg_size; role++)
{
if (osd_set[role] == this->osd_num || osd_set[role] != 0 && zero_read == -1)
{
zero_read = role;
}
if (osd_set[role] != 0 && (wr || !rep && stripes[role].read_end != 0))
{
n_subops++;
}
}
if (!n_subops && (submit_type == SUBMIT_RMW_READ || rep))
{
n_subops = 1;
}
else
{
zero_read = -1;
}
osd_op_t *subops = new osd_op_t[n_subops];
op_data->fact_ver = 0;
op_data->done = op_data->errors = 0;
op_data->n_subops = n_subops;
op_data->subops = subops;
int sent = submit_primary_subop_batch(submit_type, op_data->oid.inode, op_version, op_data->stripes, osd_set, cur_op, 0, zero_read);
assert(sent == n_subops);
}
int osd_t::submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t op_version,
osd_rmw_stripe_t *stripes, const uint64_t* osd_set, osd_op_t *cur_op, int subop_idx, int zero_read)
{
bool wr = submit_type == SUBMIT_WRITE;
osd_primary_op_data_t *op_data = cur_op->op_data;
bool rep = op_data->scheme == POOL_SCHEME_REPLICATED;
int i = subop_idx;
for (int role = 0; role < op_data->pg_size; role++)
int i = 0;
for (int role = 0; role < pg_size; role++)
{
// We always submit zero-length writes to all replicas, even if the stripe is not modified
if (!(wr || !rep && stripes[role].read_end != 0 || zero_read == role))
@ -149,21 +148,20 @@ int osd_t::submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t o
if (role_osd_num != 0)
{
int stripe_num = rep ? 0 : role;
osd_op_t *subop = op_data->subops + i;
if (role_osd_num == this->osd_num)
{
clock_gettime(CLOCK_REALTIME, &subop->tv_begin);
subop->op_type = (uint64_t)cur_op;
subop->bitmap = stripes[stripe_num].bmp_buf;
subop->bitmap_len = clean_entry_bitmap_size;
subop->bs_op = new blockstore_op_t({
clock_gettime(CLOCK_REALTIME, &subops[i].tv_begin);
subops[i].op_type = (uint64_t)cur_op;
subops[i].bitmap = stripes[stripe_num].bmp_buf;
subops[i].bitmap_len = clean_entry_bitmap_size;
subops[i].bs_op = new blockstore_op_t({
.opcode = (uint64_t)(wr ? (rep ? BS_OP_WRITE_STABLE : BS_OP_WRITE) : BS_OP_READ),
.callback = [subop, this](blockstore_op_t *bs_subop)
.callback = [subop = &subops[i], this](blockstore_op_t *bs_subop)
{
handle_primary_bs_subop(subop);
},
.oid = {
.inode = inode,
.inode = op_data->oid.inode,
.stripe = op_data->oid.stripe | stripe_num,
},
.version = op_version,
@ -175,26 +173,26 @@ int osd_t::submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t o
#ifdef OSD_DEBUG
printf(
"Submit %s to local: %lx:%lx v%lu %u-%u\n", wr ? "write" : "read",
inode, op_data->oid.stripe | stripe_num, op_version,
subop->bs_op->offset, subop->bs_op->len
op_data->oid.inode, op_data->oid.stripe | stripe_num, op_version,
subops[i].bs_op->offset, subops[i].bs_op->len
);
#endif
bs->enqueue_op(subop->bs_op);
bs->enqueue_op(subops[i].bs_op);
}
else
{
subop->op_type = OSD_OP_OUT;
subop->peer_fd = c_cli.osd_peer_fds.at(role_osd_num);
subop->bitmap = stripes[stripe_num].bmp_buf;
subop->bitmap_len = clean_entry_bitmap_size;
subop->req.sec_rw = {
subops[i].op_type = OSD_OP_OUT;
subops[i].peer_fd = c_cli.osd_peer_fds.at(role_osd_num);
subops[i].bitmap = stripes[stripe_num].bmp_buf;
subops[i].bitmap_len = clean_entry_bitmap_size;
subops[i].req.sec_rw = {
.header = {
.magic = SECONDARY_OSD_OP_MAGIC,
.id = c_cli.next_subop_id++,
.opcode = (uint64_t)(wr ? (rep ? OSD_OP_SEC_WRITE_STABLE : OSD_OP_SEC_WRITE) : OSD_OP_SEC_READ),
},
.oid = {
.inode = inode,
.inode = op_data->oid.inode,
.stripe = op_data->oid.stripe | stripe_num,
},
.version = op_version,
@ -205,34 +203,40 @@ int osd_t::submit_primary_subop_batch(int submit_type, inode_t inode, uint64_t o
#ifdef OSD_DEBUG
printf(
"Submit %s to osd %lu: %lx:%lx v%lu %u-%u\n", wr ? "write" : "read", role_osd_num,
inode, op_data->oid.stripe | stripe_num, op_version,
subop->req.sec_rw.offset, subop->req.sec_rw.len
op_data->oid.inode, op_data->oid.stripe | stripe_num, op_version,
subops[i].req.sec_rw.offset, subops[i].req.sec_rw.len
);
#endif
if (wr)
{
if (stripes[stripe_num].write_end > stripes[stripe_num].write_start)
{
subop->iov.push_back(stripes[stripe_num].write_buf, stripes[stripe_num].write_end - stripes[stripe_num].write_start);
subops[i].iov.push_back(stripes[stripe_num].write_buf, stripes[stripe_num].write_end - stripes[stripe_num].write_start);
}
}
else
{
if (stripes[stripe_num].read_end > stripes[stripe_num].read_start)
{
subop->iov.push_back(stripes[stripe_num].read_buf, stripes[stripe_num].read_end - stripes[stripe_num].read_start);
subops[i].iov.push_back(stripes[stripe_num].read_buf, stripes[stripe_num].read_end - stripes[stripe_num].read_start);
}
}
subop->callback = [cur_op, this](osd_op_t *subop)
subops[i].callback = [cur_op, this](osd_op_t *subop)
{
int fail_fd = subop->req.hdr.opcode == OSD_OP_SEC_WRITE &&
subop->reply.hdr.retval != subop->req.sec_rw.len ? subop->peer_fd : -1;
handle_primary_subop(subop, cur_op);
if (fail_fd >= 0)
{
// write operation failed, drop the connection
c_cli.stop_client(fail_fd);
}
};
c_cli.outbox_push(subop);
c_cli.outbox_push(&subops[i]);
}
i++;
}
}
return i-subop_idx;
}
static uint64_t bs_op_to_osd_op[] = {
@ -272,7 +276,6 @@ void osd_t::handle_primary_bs_subop(osd_op_t *subop)
}
delete bs_op;
subop->bs_op = NULL;
subop->peer_fd = -1;
handle_primary_subop(subop, cur_op);
}
@ -303,13 +306,8 @@ void osd_t::handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op)
{
uint64_t opcode = subop->req.hdr.opcode;
int retval = subop->reply.hdr.retval;
int expected;
if (opcode == OSD_OP_SEC_READ || opcode == OSD_OP_SEC_WRITE || opcode == OSD_OP_SEC_WRITE_STABLE)
expected = subop->req.sec_rw.len;
else if (opcode == OSD_OP_SEC_READ_BMP)
expected = subop->req.sec_read_bmp.len / sizeof(obj_ver_id) * (8 + clean_entry_bitmap_size);
else
expected = 0;
int expected = opcode == OSD_OP_SEC_READ || opcode == OSD_OP_SEC_WRITE
|| opcode == OSD_OP_SEC_WRITE_STABLE ? subop->req.sec_rw.len : 0;
osd_primary_op_data_t *op_data = cur_op->op_data;
if (retval != expected)
{
@ -319,11 +317,6 @@ void osd_t::handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op)
op_data->epipe++;
}
op_data->errors++;
if (subop->peer_fd >= 0)
{
// Drop connection on any error
c_cli.stop_client(subop->peer_fd);
}
}
else
{
@ -336,17 +329,14 @@ void osd_t::handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op)
? c_cli.clients[subop->peer_fd]->osd_num : osd_num;
printf("subop %lu from osd %lu: version = %lu\n", opcode, peer_osd, version);
#endif
if (op_data->fact_ver != UINT64_MAX)
if (op_data->fact_ver != 0 && op_data->fact_ver != version)
{
if (op_data->fact_ver != 0 && op_data->fact_ver != version)
{
throw std::runtime_error(
"different fact_versions returned from "+std::string(osd_op_names[opcode])+
" subops: "+std::to_string(version)+" vs "+std::to_string(op_data->fact_ver)
);
}
op_data->fact_ver = version;
throw std::runtime_error(
"different fact_versions returned from "+std::string(osd_op_names[opcode])+
" subops: "+std::to_string(version)+" vs "+std::to_string(op_data->fact_ver)
);
}
op_data->fact_ver = version;
}
}
if ((op_data->errors + op_data->done) >= op_data->n_subops)
@ -466,7 +456,7 @@ void osd_t::submit_primary_del_batch(osd_op_t *cur_op, obj_ver_osd_t *chunks_to_
{
subops[i].op_type = OSD_OP_OUT;
subops[i].peer_fd = c_cli.osd_peer_fds.at(chunk.osd_num);
subops[i].req = (osd_any_op_t){ .sec_del = {
subops[i].req.sec_del = {
.header = {
.magic = SECONDARY_OSD_OP_MAGIC,
.id = c_cli.next_subop_id++,
@ -474,17 +464,23 @@ void osd_t::submit_primary_del_batch(osd_op_t *cur_op, obj_ver_osd_t *chunks_to_
},
.oid = chunk.oid,
.version = chunk.version,
} };
};
subops[i].callback = [cur_op, this](osd_op_t *subop)
{
int fail_fd = subop->reply.hdr.retval != 0 ? subop->peer_fd : -1;
handle_primary_subop(subop, cur_op);
if (fail_fd >= 0)
{
// delete operation failed, drop the connection
c_cli.stop_client(fail_fd);
}
};
c_cli.outbox_push(&subops[i]);
}
}
}
int osd_t::submit_primary_sync_subops(osd_op_t *cur_op)
void osd_t::submit_primary_sync_subops(osd_op_t *cur_op)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
int n_osds = op_data->dirty_osd_count;
@ -492,7 +488,6 @@ int osd_t::submit_primary_sync_subops(osd_op_t *cur_op)
op_data->done = op_data->errors = 0;
op_data->n_subops = n_osds;
op_data->subops = subops;
std::map<uint64_t, int>::iterator peer_it;
for (int i = 0; i < n_osds; i++)
{
osd_num_t sync_osd = op_data->dirty_osds[i];
@ -509,35 +504,30 @@ int osd_t::submit_primary_sync_subops(osd_op_t *cur_op)
});
bs->enqueue_op(subops[i].bs_op);
}
else if ((peer_it = c_cli.osd_peer_fds.find(sync_osd)) != c_cli.osd_peer_fds.end())
else
{
subops[i].op_type = OSD_OP_OUT;
subops[i].peer_fd = peer_it->second;
subops[i].req = (osd_any_op_t){ .sec_sync = {
subops[i].peer_fd = c_cli.osd_peer_fds.at(sync_osd);
subops[i].req.sec_sync = {
.header = {
.magic = SECONDARY_OSD_OP_MAGIC,
.id = c_cli.next_subop_id++,
.opcode = OSD_OP_SEC_SYNC,
},
} };
};
subops[i].callback = [cur_op, this](osd_op_t *subop)
{
int fail_fd = subop->reply.hdr.retval != 0 ? subop->peer_fd : -1;
handle_primary_subop(subop, cur_op);
if (fail_fd >= 0)
{
// sync operation failed, drop the connection
c_cli.stop_client(fail_fd);
}
};
c_cli.outbox_push(&subops[i]);
}
else
{
op_data->done++;
}
}
if (op_data->done >= op_data->n_subops)
{
delete[] op_data->subops;
op_data->subops = NULL;
return 0;
}
return 1;
}
void osd_t::submit_primary_stab_subops(osd_op_t *cur_op)
@ -570,18 +560,24 @@ void osd_t::submit_primary_stab_subops(osd_op_t *cur_op)
{
subops[i].op_type = OSD_OP_OUT;
subops[i].peer_fd = c_cli.osd_peer_fds.at(stab_osd.osd_num);
subops[i].req = (osd_any_op_t){ .sec_stab = {
subops[i].req.sec_stab = {
.header = {
.magic = SECONDARY_OSD_OP_MAGIC,
.id = c_cli.next_subop_id++,
.opcode = OSD_OP_SEC_STABILIZE,
},
.len = (uint64_t)(stab_osd.len * sizeof(obj_ver_id)),
} };
};
subops[i].iov.push_back(op_data->unstable_writes + stab_osd.start, stab_osd.len * sizeof(obj_ver_id));
subops[i].callback = [cur_op, this](osd_op_t *subop)
{
int fail_fd = subop->reply.hdr.retval != 0 ? subop->peer_fd : -1;
handle_primary_subop(subop, cur_op);
if (fail_fd >= 0)
{
// sync operation failed, drop the connection
c_cli.stop_client(fail_fd);
}
};
c_cli.outbox_push(&subops[i]);
}
@ -599,7 +595,7 @@ void osd_t::pg_cancel_write_queue(pg_t & pg, osd_op_t *first_op, object_id oid,
return;
}
std::vector<osd_op_t*> cancel_ops;
while (it != pg.write_queue.end() && it->first == oid)
while (it != pg.write_queue.end())
{
cancel_ops.push_back(it->second);
it++;

View File

@ -1,265 +0,0 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 (see README.md for details)
#include "osd_primary.h"
// Save and clear unstable_writes -> SYNC all -> STABLE all
void osd_t::continue_primary_sync(osd_op_t *cur_op)
{
if (!cur_op->op_data)
{
cur_op->op_data = (osd_primary_op_data_t*)calloc_or_die(1, sizeof(osd_primary_op_data_t));
}
osd_primary_op_data_t *op_data = cur_op->op_data;
if (op_data->st == 1) goto resume_1;
else if (op_data->st == 2) goto resume_2;
else if (op_data->st == 3) goto resume_3;
else if (op_data->st == 4) goto resume_4;
else if (op_data->st == 5) goto resume_5;
else if (op_data->st == 6) goto resume_6;
else if (op_data->st == 7) goto resume_7;
else if (op_data->st == 8) goto resume_8;
assert(op_data->st == 0);
if (syncs_in_progress.size() > 0)
{
// Wait for previous syncs, if any
// FIXME: We may try to execute the current one in parallel, like in Blockstore, but I'm not sure if it matters at all
syncs_in_progress.push_back(cur_op);
op_data->st = 1;
resume_1:
return;
}
else
{
syncs_in_progress.push_back(cur_op);
}
resume_2:
if (dirty_osds.size() == 0)
{
// Nothing to sync
goto finish;
}
// Save and clear unstable_writes
// In theory it is possible to do in on a per-client basis, but this seems to be an unnecessary complication
// It would be cool not to copy these here at all, but someone has to deduplicate them by object IDs anyway
if (unstable_writes.size() > 0)
{
op_data->unstable_write_osds = new std::vector<unstable_osd_num_t>();
op_data->unstable_writes = new obj_ver_id[this->unstable_writes.size()];
osd_num_t last_osd = 0;
int last_start = 0, last_end = 0;
for (auto it = this->unstable_writes.begin(); it != this->unstable_writes.end(); it++)
{
if (last_osd != it->first.osd_num)
{
if (last_osd != 0)
{
op_data->unstable_write_osds->push_back((unstable_osd_num_t){
.osd_num = last_osd,
.start = last_start,
.len = last_end - last_start,
});
}
last_osd = it->first.osd_num;
last_start = last_end;
}
op_data->unstable_writes[last_end] = (obj_ver_id){
.oid = it->first.oid,
.version = it->second,
};
last_end++;
}
if (last_osd != 0)
{
op_data->unstable_write_osds->push_back((unstable_osd_num_t){
.osd_num = last_osd,
.start = last_start,
.len = last_end - last_start,
});
}
this->unstable_writes.clear();
}
{
void *dirty_buf = malloc_or_die(
sizeof(pool_pg_num_t)*dirty_pgs.size() +
sizeof(osd_num_t)*dirty_osds.size() +
sizeof(obj_ver_osd_t)*this->copies_to_delete_after_sync_count
);
op_data->dirty_pgs = (pool_pg_num_t*)dirty_buf;
op_data->dirty_osds = (osd_num_t*)(dirty_buf + sizeof(pool_pg_num_t)*dirty_pgs.size());
op_data->dirty_pg_count = dirty_pgs.size();
op_data->dirty_osd_count = dirty_osds.size();
if (this->copies_to_delete_after_sync_count)
{
op_data->copies_to_delete_count = 0;
op_data->copies_to_delete = (obj_ver_osd_t*)(op_data->dirty_osds + op_data->dirty_osd_count);
for (auto dirty_pg_num: dirty_pgs)
{
auto & pg = pgs.at(dirty_pg_num);
assert(pg.copies_to_delete_after_sync.size() <= this->copies_to_delete_after_sync_count);
memcpy(
op_data->copies_to_delete + op_data->copies_to_delete_count,
pg.copies_to_delete_after_sync.data(),
sizeof(obj_ver_osd_t)*pg.copies_to_delete_after_sync.size()
);
op_data->copies_to_delete_count += pg.copies_to_delete_after_sync.size();
this->copies_to_delete_after_sync_count -= pg.copies_to_delete_after_sync.size();
pg.copies_to_delete_after_sync.clear();
}
assert(this->copies_to_delete_after_sync_count == 0);
}
int dpg = 0;
for (auto dirty_pg_num: dirty_pgs)
{
pgs.at(dirty_pg_num).inflight++;
op_data->dirty_pgs[dpg++] = dirty_pg_num;
}
dirty_pgs.clear();
dpg = 0;
for (auto osd_num: dirty_osds)
{
op_data->dirty_osds[dpg++] = osd_num;
}
dirty_osds.clear();
}
if (immediate_commit != IMMEDIATE_ALL)
{
// SYNC
if (!submit_primary_sync_subops(cur_op))
{
goto resume_4;
}
resume_3:
op_data->st = 3;
return;
resume_4:
if (op_data->errors > 0)
{
goto resume_6;
}
}
if (op_data->unstable_writes)
{
// Stabilize version sets, if any
submit_primary_stab_subops(cur_op);
resume_5:
op_data->st = 5;
return;
}
resume_6:
if (op_data->errors > 0)
{
// Return PGs and OSDs back into their dirty sets
for (int i = 0; i < op_data->dirty_pg_count; i++)
{
dirty_pgs.insert(op_data->dirty_pgs[i]);
}
for (int i = 0; i < op_data->dirty_osd_count; i++)
{
dirty_osds.insert(op_data->dirty_osds[i]);
}
if (op_data->unstable_writes)
{
// Return objects back into the unstable write set
for (auto unstable_osd: *(op_data->unstable_write_osds))
{
for (int i = 0; i < unstable_osd.len; i++)
{
// Except those from peered PGs
auto & w = op_data->unstable_writes[i];
pool_pg_num_t wpg = {
.pool_id = INODE_POOL(w.oid.inode),
.pg_num = map_to_pg(w.oid, st_cli.pool_config.at(INODE_POOL(w.oid.inode)).pg_stripe_size),
};
if (pgs.at(wpg).state & PG_ACTIVE)
{
uint64_t & dest = this->unstable_writes[(osd_object_id_t){
.osd_num = unstable_osd.osd_num,
.oid = w.oid,
}];
dest = dest < w.version ? w.version : dest;
dirty_pgs.insert(wpg);
}
}
}
}
if (op_data->copies_to_delete)
{
// Return 'copies to delete' back into respective PGs
for (int i = 0; i < op_data->copies_to_delete_count; i++)
{
auto & w = op_data->copies_to_delete[i];
auto & pg = pgs.at((pool_pg_num_t){
.pool_id = INODE_POOL(w.oid.inode),
.pg_num = map_to_pg(w.oid, st_cli.pool_config.at(INODE_POOL(w.oid.inode)).pg_stripe_size),
});
if (pg.state & PG_ACTIVE)
{
pg.copies_to_delete_after_sync.push_back(w);
copies_to_delete_after_sync_count++;
}
}
}
}
else if (op_data->copies_to_delete)
{
// Actually delete copies which we wanted to delete
submit_primary_del_batch(cur_op, op_data->copies_to_delete, op_data->copies_to_delete_count);
resume_7:
op_data->st = 7;
return;
resume_8:
if (op_data->errors > 0)
{
goto resume_6;
}
}
for (int i = 0; i < op_data->dirty_pg_count; i++)
{
auto & pg = pgs.at(op_data->dirty_pgs[i]);
pg.inflight--;
if ((pg.state & PG_STOPPING) && pg.inflight == 0 && !pg.flush_batch)
{
finish_stop_pg(pg);
}
else if ((pg.state & PG_REPEERING) && pg.inflight == 0 && !pg.flush_batch)
{
start_pg_peering(pg);
}
}
// FIXME: Free those in the destructor?
free(op_data->dirty_pgs);
op_data->dirty_pgs = NULL;
op_data->dirty_osds = NULL;
if (op_data->unstable_writes)
{
delete op_data->unstable_write_osds;
delete[] op_data->unstable_writes;
op_data->unstable_writes = NULL;
op_data->unstable_write_osds = NULL;
}
if (op_data->errors > 0)
{
finish_op(cur_op, op_data->epipe > 0 ? -EPIPE : -EIO);
}
else
{
finish:
if (cur_op->peer_fd)
{
auto it = c_cli.clients.find(cur_op->peer_fd);
if (it != c_cli.clients.end())
it->second->dirty_pgs.clear();
}
finish_op(cur_op, 0);
}
assert(syncs_in_progress.front() == cur_op);
syncs_in_progress.pop_front();
if (syncs_in_progress.size() > 0)
{
cur_op = syncs_in_progress.front();
op_data = cur_op->op_data;
op_data->st++;
goto resume_2;
}
}

View File

@ -1,381 +0,0 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 (see README.md for details)
#include "osd_primary.h"
#include "allocator.h"
bool osd_t::check_write_queue(osd_op_t *cur_op, pg_t & pg)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
// Check if actions are pending for this object
auto act_it = pg.flush_actions.lower_bound((obj_piece_id_t){
.oid = op_data->oid,
.osd_num = 0,
});
if (act_it != pg.flush_actions.end() &&
act_it->first.oid.inode == op_data->oid.inode &&
(act_it->first.oid.stripe & ~STRIPE_MASK) == op_data->oid.stripe)
{
pg.write_queue.emplace(op_data->oid, cur_op);
return false;
}
// Check if there are other write requests to the same object
auto vo_it = pg.write_queue.find(op_data->oid);
if (vo_it != pg.write_queue.end())
{
op_data->st = 1;
pg.write_queue.emplace(op_data->oid, cur_op);
return false;
}
pg.write_queue.emplace(op_data->oid, cur_op);
return true;
}
void osd_t::continue_primary_write(osd_op_t *cur_op)
{
if (!cur_op->op_data && !prepare_primary_rw(cur_op))
{
return;
}
osd_primary_op_data_t *op_data = cur_op->op_data;
auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
if (op_data->st == 1) goto resume_1;
else if (op_data->st == 2) goto resume_2;
else if (op_data->st == 3) goto resume_3;
else if (op_data->st == 4) goto resume_4;
else if (op_data->st == 5) goto resume_5;
else if (op_data->st == 6) goto resume_6;
else if (op_data->st == 7) goto resume_7;
else if (op_data->st == 8) goto resume_8;
else if (op_data->st == 9) goto resume_9;
else if (op_data->st == 10) goto resume_10;
assert(op_data->st == 0);
if (!check_write_queue(cur_op, pg))
{
return;
}
resume_1:
// Determine blocks to read and write
// Missing chunks are allowed to be overwritten even in incomplete objects
// FIXME: Allow to do small writes to the old (degraded/misplaced) OSD set for lower performance impact
op_data->prev_set = get_object_osd_set(pg, op_data->oid, pg.cur_set.data(), &op_data->object_state);
if (op_data->scheme == POOL_SCHEME_REPLICATED)
{
// Simplified algorithm
op_data->stripes[0].write_start = op_data->stripes[0].req_start;
op_data->stripes[0].write_end = op_data->stripes[0].req_end;
op_data->stripes[0].write_buf = cur_op->buf;
if (pg.cur_set.data() != op_data->prev_set && (op_data->stripes[0].write_start != 0 ||
op_data->stripes[0].write_end != bs_block_size))
{
// Object is degraded/misplaced and will be moved to <write_osd_set>
op_data->stripes[0].read_start = 0;
op_data->stripes[0].read_end = bs_block_size;
cur_op->rmw_buf = op_data->stripes[0].read_buf = memalign_or_die(MEM_ALIGNMENT, bs_block_size);
}
}
else
{
cur_op->rmw_buf = calc_rmw(cur_op->buf, op_data->stripes, op_data->prev_set,
pg.pg_size, op_data->pg_data_size, pg.pg_cursize, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
if (!cur_op->rmw_buf)
{
// Refuse partial overwrite of an incomplete object
cur_op->reply.hdr.retval = -EINVAL;
goto continue_others;
}
}
// Read required blocks
submit_primary_subops(SUBMIT_RMW_READ, UINT64_MAX, op_data->prev_set, cur_op);
resume_2:
op_data->st = 2;
return;
resume_3:
if (op_data->errors > 0)
{
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->epipe > 0 ? -EPIPE : -EIO);
return;
}
if (op_data->scheme == POOL_SCHEME_REPLICATED)
{
// Set bitmap bits
bitmap_set(op_data->stripes[0].bmp_buf, op_data->stripes[0].write_start,
op_data->stripes[0].write_end-op_data->stripes[0].write_start, bs_bitmap_granularity);
// Possibly copy new data from the request into the recovery buffer
if (pg.cur_set.data() != op_data->prev_set && (op_data->stripes[0].write_start != 0 ||
op_data->stripes[0].write_end != bs_block_size))
{
memcpy(
op_data->stripes[0].read_buf + op_data->stripes[0].req_start,
op_data->stripes[0].write_buf,
op_data->stripes[0].req_end - op_data->stripes[0].req_start
);
op_data->stripes[0].write_buf = op_data->stripes[0].read_buf;
op_data->stripes[0].write_start = 0;
op_data->stripes[0].write_end = bs_block_size;
}
}
else
{
// For EC/XOR pools, save version override to make it impossible
// for parallel reads to read different versions of data and parity
pg.ver_override[op_data->oid] = op_data->fact_ver;
// Recover missing stripes, calculate parity
if (pg.scheme == POOL_SCHEME_XOR)
{
calc_rmw_parity_xor(op_data->stripes, pg.pg_size, op_data->prev_set, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
}
else if (pg.scheme == POOL_SCHEME_JERASURE)
{
calc_rmw_parity_jerasure(op_data->stripes, pg.pg_size, op_data->pg_data_size, op_data->prev_set, pg.cur_set.data(), bs_block_size, clean_entry_bitmap_size);
}
}
// Send writes
if ((op_data->fact_ver >> (64-PG_EPOCH_BITS)) < pg.epoch)
{
op_data->target_ver = ((uint64_t)pg.epoch << (64-PG_EPOCH_BITS)) | 1;
}
else
{
if ((op_data->fact_ver & (1ul<<(64-PG_EPOCH_BITS) - 1)) == (1ul<<(64-PG_EPOCH_BITS) - 1))
{
assert(pg.epoch != ((1ul << PG_EPOCH_BITS)-1));
pg.epoch++;
}
op_data->target_ver = op_data->fact_ver + 1;
}
if (pg.epoch > pg.reported_epoch)
{
// Report newer epoch before writing
// FIXME: We may report only one PG state here...
this->pg_state_dirty.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
pg.history_changed = true;
report_pg_states();
resume_10:
if (pg.epoch > pg.reported_epoch)
{
op_data->st = 10;
return;
}
}
submit_primary_subops(SUBMIT_WRITE, op_data->target_ver, pg.cur_set.data(), cur_op);
resume_4:
op_data->st = 4;
return;
resume_5:
if (op_data->scheme != POOL_SCHEME_REPLICATED)
{
// Remove version override just after the write, but before stabilizing
pg.ver_override.erase(op_data->oid);
}
if (op_data->errors > 0)
{
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->epipe > 0 ? -EPIPE : -EIO);
return;
}
if (op_data->object_state)
{
// We must forget the unclean state of the object before deleting it
// so the next reads don't accidentally read a deleted version
// And it should be done at the same time as the removal of the version override
remove_object_from_state(op_data->oid, op_data->object_state, pg);
pg.clean_count++;
}
resume_6:
resume_7:
if (!remember_unstable_write(cur_op, pg, pg.cur_loc_set, 6))
{
return;
}
if (op_data->fact_ver == 1)
{
// Object is created
pg.clean_count++;
pg.total_count++;
}
if (op_data->object_state)
{
{
int recovery_type = op_data->object_state->state & (OBJ_DEGRADED|OBJ_INCOMPLETE) ? 0 : 1;
recovery_stat_count[0][recovery_type]++;
if (!recovery_stat_count[0][recovery_type])
{
recovery_stat_count[0][recovery_type]++;
recovery_stat_bytes[0][recovery_type] = 0;
}
for (int role = 0; role < (op_data->scheme == POOL_SCHEME_REPLICATED ? 1 : pg.pg_size); role++)
{
recovery_stat_bytes[0][recovery_type] += op_data->stripes[role].write_end - op_data->stripes[role].write_start;
}
}
// Any kind of a non-clean object can have extra chunks, because we don't record objects
// as degraded & misplaced or incomplete & misplaced at the same time. So try to remove extra chunks
if (immediate_commit != IMMEDIATE_ALL)
{
// We can't remove extra chunks yet if fsyncs are explicit, because
// new copies may not be committed to stable storage yet
// We can only remove extra chunks after a successful SYNC for this PG
for (auto & chunk: op_data->object_state->osd_set)
{
// Check is the same as in submit_primary_del_subops()
if (op_data->scheme == POOL_SCHEME_REPLICATED
? !contains_osd(pg.cur_set.data(), pg.pg_size, chunk.osd_num)
: (chunk.osd_num != pg.cur_set[chunk.role]))
{
pg.copies_to_delete_after_sync.push_back((obj_ver_osd_t){
.osd_num = chunk.osd_num,
.oid = {
.inode = op_data->oid.inode,
.stripe = op_data->oid.stripe | (op_data->scheme == POOL_SCHEME_REPLICATED ? 0 : chunk.role),
},
.version = op_data->fact_ver,
});
copies_to_delete_after_sync_count++;
}
}
free_object_state(pg, &op_data->object_state);
}
else
{
submit_primary_del_subops(cur_op, pg.cur_set.data(), pg.pg_size, op_data->object_state->osd_set);
free_object_state(pg, &op_data->object_state);
if (op_data->n_subops > 0)
{
resume_8:
op_data->st = 8;
return;
resume_9:
if (op_data->errors > 0)
{
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->epipe > 0 ? -EPIPE : -EIO);
return;
}
}
}
}
cur_op->reply.hdr.retval = cur_op->req.rw.len;
continue_others:
osd_op_t *next_op = NULL;
auto next_it = pg.write_queue.find(op_data->oid);
// Remove the operation from queue before calling finish_op so it doesn't see the completed operation in queue
if (next_it != pg.write_queue.end() && next_it->second == cur_op)
{
pg.write_queue.erase(next_it++);
if (next_it != pg.write_queue.end() && next_it->first == op_data->oid)
next_op = next_it->second;
}
// finish_op would invalidate next_it if it cleared pg.write_queue, but it doesn't do that :)
finish_op(cur_op, cur_op->req.rw.len);
if (next_op)
{
// Continue next write to the same object
continue_primary_write(next_op);
}
}
bool osd_t::remember_unstable_write(osd_op_t *cur_op, pg_t & pg, pg_osd_set_t & loc_set, int base_state)
{
osd_primary_op_data_t *op_data = cur_op->op_data;
if (op_data->st == base_state)
{
goto resume_6;
}
else if (op_data->st == base_state+1)
{
goto resume_7;
}
if (immediate_commit == IMMEDIATE_ALL)
{
immediate:
if (op_data->scheme != POOL_SCHEME_REPLICATED)
{
// Send STABILIZE ops immediately
op_data->unstable_write_osds = new std::vector<unstable_osd_num_t>();
op_data->unstable_writes = new obj_ver_id[loc_set.size()];
{
int last_start = 0;
for (auto & chunk: loc_set)
{
op_data->unstable_writes[last_start] = (obj_ver_id){
.oid = {
.inode = op_data->oid.inode,
.stripe = op_data->oid.stripe | chunk.role,
},
.version = op_data->fact_ver,
};
op_data->unstable_write_osds->push_back((unstable_osd_num_t){
.osd_num = chunk.osd_num,
.start = last_start,
.len = 1,
});
last_start++;
}
}
submit_primary_stab_subops(cur_op);
resume_6:
op_data->st = 6;
return false;
resume_7:
// FIXME: Free those in the destructor?
delete op_data->unstable_write_osds;
delete[] op_data->unstable_writes;
op_data->unstable_writes = NULL;
op_data->unstable_write_osds = NULL;
if (op_data->errors > 0)
{
pg_cancel_write_queue(pg, cur_op, op_data->oid, op_data->epipe > 0 ? -EPIPE : -EIO);
return false;
}
}
}
else if (immediate_commit == IMMEDIATE_SMALL)
{
int stripe_count = (op_data->scheme == POOL_SCHEME_REPLICATED ? 1 : op_data->pg_size);
for (int role = 0; role < stripe_count; role++)
{
if (op_data->stripes[role].write_start == 0 &&
op_data->stripes[role].write_end == bs_block_size)
{
// Big write. Treat write as unsynced
goto lazy;
}
}
goto immediate;
}
else
{
lazy:
if (op_data->scheme != POOL_SCHEME_REPLICATED)
{
// Remember version as unstable for EC/XOR
for (auto & chunk: loc_set)
{
this->dirty_osds.insert(chunk.osd_num);
this->unstable_writes[(osd_object_id_t){
.osd_num = chunk.osd_num,
.oid = {
.inode = op_data->oid.inode,
.stripe = op_data->oid.stripe | chunk.role,
},
}] = op_data->fact_ver;
}
}
else
{
// Only remember to sync OSDs for replicated pools
for (auto & chunk: loc_set)
{
this->dirty_osds.insert(chunk.osd_num);
}
}
// Remember PG as dirty to drop the connection when PG goes offline
// (this is required because of the "lazy sync")
auto cl_it = c_cli.clients.find(cur_op->peer_fd);
if (cl_it != c_cli.clients.end())
{
cl_it->second->dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
}
dirty_pgs.insert({ .pool_id = pg.pool_id, .pg_num = pg.pg_num });
}
return true;
}

View File

@ -246,23 +246,20 @@ void reconstruct_stripes_jerasure(osd_rmw_stripe_t *stripes, int pg_size, int pg
{
if (stripes[role].read_end != 0 && stripes[role].missing)
{
if (stripes[role].read_end > stripes[role].read_start)
for (int other = 0; other < pg_size; other++)
{
for (int other = 0; other < pg_size; other++)
if (stripes[other].read_end != 0 && !stripes[other].missing)
{
if (stripes[other].read_end != 0 && !stripes[other].missing)
{
assert(stripes[other].read_start <= stripes[role].read_start);
assert(stripes[other].read_end >= stripes[role].read_end);
data_ptrs[other] = (char*)(stripes[other].read_buf + (stripes[role].read_start - stripes[other].read_start));
}
assert(stripes[other].read_start <= stripes[role].read_start);
assert(stripes[other].read_end >= stripes[role].read_end);
data_ptrs[other] = (char*)(stripes[other].read_buf + (stripes[role].read_start - stripes[other].read_start));
}
data_ptrs[role] = (char*)stripes[role].read_buf;
jerasure_matrix_dotprod(
pg_minsize, OSD_JERASURE_W, decoding_matrix+(role*pg_minsize), dm_ids, role,
data_ptrs, data_ptrs+pg_minsize, stripes[role].read_end - stripes[role].read_start
);
}
data_ptrs[role] = (char*)stripes[role].read_buf;
jerasure_matrix_dotprod(
pg_minsize, OSD_JERASURE_W, decoding_matrix+(role*pg_minsize), dm_ids, role,
data_ptrs, data_ptrs+pg_minsize, stripes[role].read_end - stripes[role].read_start
);
for (int other = 0; other < pg_size; other++)
{
if (stripes[other].read_end != 0 && !stripes[other].missing)

View File

@ -44,25 +44,6 @@ void osd_t::secondary_op_callback(osd_op_t *op)
void osd_t::exec_secondary(osd_op_t *cur_op)
{
if (cur_op->req.hdr.opcode == OSD_OP_SEC_READ_BMP)
{
int n = cur_op->req.sec_read_bmp.len / sizeof(obj_ver_id);
if (n > 0)
{
obj_ver_id *ov = (obj_ver_id*)cur_op->buf;
void *reply_buf = malloc_or_die(n * (8 + clean_entry_bitmap_size));
void *cur_buf = reply_buf;
for (int i = 0; i < n; i++)
{
bs->read_bitmap(ov[i].oid, ov[i].version, cur_buf + sizeof(uint64_t), (uint64_t*)cur_buf);
cur_buf += (8 + clean_entry_bitmap_size);
}
free(cur_op->buf);
cur_op->buf = reply_buf;
}
finish_op(cur_op, n * (8 + clean_entry_bitmap_size));
return;
}
cur_op->bs_op = new blockstore_op_t();
cur_op->bs_op->callback = [this, cur_op](blockstore_op_t* bs_op) { secondary_op_callback(cur_op); };
cur_op->bs_op->opcode = (cur_op->req.hdr.opcode == OSD_OP_SEC_READ ? BS_OP_READ
@ -145,9 +126,7 @@ void osd_t::exec_secondary(osd_op_t *cur_op)
void osd_t::exec_show_config(osd_op_t *cur_op)
{
// FIXME: Send the real config, not its source
auto cfg_copy = config;
cfg_copy["protocol_version"] = std::to_string(OSD_PROTOCOL_VERSION);
std::string cfg_str = json11::Json(cfg_copy).dump();
std::string cfg_str = json11::Json(config).dump();
cur_op->buf = malloc_or_die(cfg_str.size()+1);
memcpy(cur_op->buf, cfg_str.c_str(), cfg_str.size()+1);
cur_op->iov.push_back(cur_op->buf, cfg_str.size()+1);

View File

@ -3,14 +3,13 @@
#include "pg_states.h"
const int pg_state_bit_count = 15;
const int pg_state_bit_count = 14;
const int pg_state_bits[15] = {
const int pg_state_bits[14] = {
PG_STARTING,
PG_PEERING,
PG_INCOMPLETE,
PG_ACTIVE,
PG_REPEERING,
PG_STOPPING,
PG_OFFLINE,
PG_DEGRADED,
@ -22,12 +21,11 @@ const int pg_state_bits[15] = {
PG_LEFT_ON_DEAD,
};
const char *pg_state_names[15] = {
const char *pg_state_names[14] = {
"starting",
"peering",
"incomplete",
"active",
"repeering",
"stopping",
"offline",
"degraded",

View File

@ -10,17 +10,16 @@
#define PG_PEERING (1<<1)
#define PG_INCOMPLETE (1<<2)
#define PG_ACTIVE (1<<3)
#define PG_REPEERING (1<<4)
#define PG_STOPPING (1<<5)
#define PG_OFFLINE (1<<6)
#define PG_STOPPING (1<<4)
#define PG_OFFLINE (1<<5)
// Plus any of these:
#define PG_DEGRADED (1<<7)
#define PG_HAS_INCOMPLETE (1<<8)
#define PG_HAS_DEGRADED (1<<9)
#define PG_HAS_MISPLACED (1<<10)
#define PG_HAS_UNCLEAN (1<<11)
#define PG_HAS_INVALID (1<<12)
#define PG_LEFT_ON_DEAD (1<<13)
#define PG_DEGRADED (1<<6)
#define PG_HAS_INCOMPLETE (1<<7)
#define PG_HAS_DEGRADED (1<<8)
#define PG_HAS_MISPLACED (1<<9)
#define PG_HAS_UNCLEAN (1<<10)
#define PG_HAS_INVALID (1<<11)
#define PG_LEFT_ON_DEAD (1<<12)
// Lower bits that represent object role (EC 0/1/2... or always 0 with replication)
// 12 bits is a safe default that doesn't depend on pg_stripe_size or pg_block_size

View File

@ -20,15 +20,7 @@ void alloc_all(int size)
{
printf("incorrect block allocated: expected %d, got %lu\n", i, x);
}
if (a->get(x))
{
printf("not free before set at %d\n", i);
}
a->set(x, true);
if (!a->get(x))
{
printf("free after set at %d\n", i);
}
}
uint64_t x = a->find_free();
if (x != UINT64_MAX)

View File

@ -2,8 +2,8 @@
// License: VNPL-1.1 (see README.md for details)
#include <malloc.h>
#include "timerfd_interval.h"
#include "blockstore.h"
#include "epoll_manager.h"
int main(int narg, char *args[])
{
@ -12,8 +12,11 @@ int main(int narg, char *args[])
config["journal_device"] = "./test_journal.bin";
config["data_device"] = "./test_data.bin";
ring_loop_t *ringloop = new ring_loop_t(512);
epoll_manager_t *epmgr = new epoll_manager_t(ringloop);
blockstore_t *bs = new blockstore_t(config, ringloop, epmgr->tfd);
blockstore_t *bs = new blockstore_t(config, ringloop);
timerfd_interval tick_tfd(ringloop, 1, []()
{
printf("tick 1s\n");
});
blockstore_op_t op;
int main_state = 0;
@ -122,7 +125,6 @@ int main(int narg, char *args[])
ringloop->wait();
}
delete bs;
delete epmgr;
delete ringloop;
return 0;
}

View File

@ -1,407 +0,0 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 (see README.md for details)
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
#include "cluster_client.h"
void configure_single_pg_pool(cluster_client_t *cli)
{
cli->st_cli.on_load_pgs_hook(true);
cli->st_cli.parse_state((etcd_kv_t){
.key = "/config/pools",
.value = json11::Json::object {
{ "1", json11::Json::object {
{ "name", "hddpool" },
{ "scheme", "replicated" },
{ "pg_size", 2 },
{ "pg_minsize", 1 },
{ "pg_count", 1 },
{ "failure_domain", "osd" },
} }
},
});
cli->st_cli.parse_state((etcd_kv_t){
.key = "/config/pgs",
.value = json11::Json::object {
{ "items", json11::Json::object {
{ "1", json11::Json::object {
{ "1", json11::Json::object {
{ "osd_set", json11::Json::array { 1, 2 } },
{ "primary", 1 },
} }
} }
} }
},
});
cli->st_cli.parse_state((etcd_kv_t){
.key = "/pg/state/1/1",
.value = json11::Json::object {
{ "peers", json11::Json::array { 1, 2 } },
{ "primary", 1 },
{ "state", json11::Json::array { "active" } },
},
});
std::map<std::string, etcd_kv_t> changes;
cli->st_cli.on_change_hook(changes);
}
int *test_write(cluster_client_t *cli, uint64_t offset, uint64_t len, uint8_t c, std::function<void()> cb = NULL)
{
printf("Post write %lx+%lx\n", offset, len);
int *r = new int;
*r = -1;
cluster_op_t *op = new cluster_op_t();
op->opcode = OSD_OP_WRITE;
op->inode = 0x1000000000001;
op->offset = offset;
op->len = len;
op->iov.push_back(malloc_or_die(len), len);
memset(op->iov.buf[0].iov_base, c, len);
op->callback = [r, cb](cluster_op_t *op)
{
if (*r == -1)
printf("Error: Not allowed to complete yet\n");
assert(*r != -1);
*r = op->retval == op->len ? 1 : 0;
free(op->iov.buf[0].iov_base);
printf("Done write %lx+%lx r=%d\n", op->offset, op->len, op->retval);
delete op;
if (cb != NULL)
cb();
};
cli->execute(op);
return r;
}
int *test_sync(cluster_client_t *cli)
{
printf("Post sync\n");
int *r = new int;
*r = -1;
cluster_op_t *op = new cluster_op_t();
op->opcode = OSD_OP_SYNC;
op->callback = [r](cluster_op_t *op)
{
if (*r == -1)
printf("Error: Not allowed to complete yet\n");
assert(*r != -1);
*r = op->retval == 0 ? 1 : 0;
printf("Done sync r=%d\n", op->retval);
delete op;
};
cli->execute(op);
return r;
}
void can_complete(int *r)
{
// Allow the operation to proceed so the test verifies
// that it doesn't complete earlier than expected
*r = -2;
}
void check_completed(int *r)
{
assert(*r == 1);
delete r;
}
void pretend_connected(cluster_client_t *cli, osd_num_t osd_num)
{
printf("OSD %lu connected\n", osd_num);
int peer_fd = cli->msgr.clients.size() ? std::prev(cli->msgr.clients.end())->first+1 : 10;
cli->msgr.osd_peer_fds[osd_num] = peer_fd;
cli->msgr.clients[peer_fd] = new osd_client_t();
cli->msgr.clients[peer_fd]->osd_num = osd_num;
cli->msgr.clients[peer_fd]->peer_state = PEER_CONNECTED;
cli->msgr.wanted_peers.erase(osd_num);
cli->msgr.repeer_pgs(osd_num);
}
void pretend_disconnected(cluster_client_t *cli, osd_num_t osd_num)
{
printf("OSD %lu disconnected\n", osd_num);
cli->msgr.stop_client(cli->msgr.osd_peer_fds.at(osd_num));
}
void check_disconnected(cluster_client_t *cli, osd_num_t osd_num)
{
if (cli->msgr.osd_peer_fds.find(osd_num) != cli->msgr.osd_peer_fds.end())
{
printf("OSD %lu not disconnected as it ought to be\n", osd_num);
assert(0);
}
}
void check_op_count(cluster_client_t *cli, osd_num_t osd_num, int ops)
{
int peer_fd = cli->msgr.osd_peer_fds.at(osd_num);
int real_ops = cli->msgr.clients[peer_fd]->sent_ops.size();
if (real_ops != ops)
{
printf("error: %d ops expected, but %d queued\n", ops, real_ops);
assert(0);
}
}
osd_op_t *find_op(cluster_client_t *cli, osd_num_t osd_num, uint64_t opcode, uint64_t offset, uint64_t len)
{
int peer_fd = cli->msgr.osd_peer_fds.at(osd_num);
auto op_it = cli->msgr.clients[peer_fd]->sent_ops.begin();
while (op_it != cli->msgr.clients[peer_fd]->sent_ops.end())
{
auto op = op_it->second;
if (op->req.hdr.opcode == opcode && (opcode == OSD_OP_SYNC ||
op->req.rw.inode == 0x1000000000001 && op->req.rw.offset == offset && op->req.rw.len == len))
{
return op;
}
op_it++;
}
return NULL;
}
void pretend_op_completed(cluster_client_t *cli, osd_op_t *op, int64_t retval)
{
assert(op);
printf("Pretend completed %s %lx+%x\n", op->req.hdr.opcode == OSD_OP_SYNC
? "sync" : (op->req.hdr.opcode == OSD_OP_WRITE ? "write" : "read"), op->req.rw.offset, op->req.rw.len);
uint64_t op_id = op->req.hdr.id;
int peer_fd = op->peer_fd;
cli->msgr.clients[peer_fd]->sent_ops.erase(op_id);
op->reply.hdr.magic = SECONDARY_OSD_REPLY_MAGIC;
op->reply.hdr.id = op->req.hdr.id;
op->reply.hdr.opcode = op->req.hdr.opcode;
op->reply.hdr.retval = retval < 0 ? retval : (op->req.hdr.opcode == OSD_OP_SYNC ? 0 : op->req.rw.len);
// Copy lambda to be unaffected by `delete op`
std::function<void(osd_op_t*)>(op->callback)(op);
}
void test1()
{
json11::Json config;
timerfd_manager_t *tfd = new timerfd_manager_t([](int fd, bool wr, std::function<void(int, int)> callback){});
cluster_client_t *cli = new cluster_client_t(NULL, tfd, config);
int *r1 = test_write(cli, 0, 4096, 0x55);
configure_single_pg_pool(cli);
pretend_connected(cli, 1);
cli->continue_ops(true);
can_complete(r1);
check_op_count(cli, 1, 1);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0, 4096), 0);
check_completed(r1);
pretend_disconnected(cli, 1);
int *r2 = test_sync(cli);
pretend_connected(cli, 1);
check_op_count(cli, 1, 0);
cli->continue_ops(true);
check_op_count(cli, 1, 1);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0, 4096), 0);
check_op_count(cli, 1, 1);
can_complete(r2);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_SYNC, 0, 0), 0);
check_completed(r2);
// Check that the client doesn't repeat operations once more
pretend_disconnected(cli, 1);
pretend_connected(cli, 1);
check_op_count(cli, 1, 0);
// Case:
// Write(1) -> Complete Write(1) -> Overwrite(2) -> Complete Write(2)
// -> Overwrite(3) -> Drop OSD connection -> Reestablish OSD connection
// -> Complete All Posted Writes -> Sync -> Complete Sync
// The resulting state of the block must be (3) over (2) over (1).
// I.e. the part overwritten by (3) must remain as in (3) and so on.
// More interesting case:
// Same, but both Write(2) and Write(3) must consist of two parts:
// one from an OSD 2 that drops connection and other from OSD 1 that doesn't.
// The idea is that if the whole Write(2) is repeated when OSD 2 drops connection
// then it may also overwrite a part in OSD 1 which shouldn't be overwritten.
// Another interesting case:
// A new operation added during replay (would also break with the previous implementation)
r1 = test_write(cli, 0, 0x10000, 0x56);
can_complete(r1);
check_op_count(cli, 1, 1);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0, 0x10000), 0);
check_completed(r1);
r1 = test_write(cli, 0xE000, 0x4000, 0x57);
can_complete(r1);
check_op_count(cli, 1, 1);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0xE000, 0x4000), 0);
check_completed(r1);
r1 = test_write(cli, 0x10000, 0x4000, 0x58);
pretend_disconnected(cli, 1);
pretend_connected(cli, 1);
cli->continue_ops(true);
// Check replay
{
uint64_t replay_start = UINT64_MAX;
uint64_t replay_end = 0;
std::vector<osd_op_t*> replay_ops;
auto osd_cl = cli->msgr.clients.at(cli->msgr.osd_peer_fds.at(1));
for (auto & op_p: osd_cl->sent_ops)
{
auto op = op_p.second;
assert(op->req.hdr.opcode == OSD_OP_WRITE);
uint64_t offset = op->req.rw.offset;
if (op->req.rw.offset < replay_start)
replay_start = op->req.rw.offset;
if (op->req.rw.offset+op->req.rw.len > replay_end)
replay_end = op->req.rw.offset+op->req.rw.len;
for (int buf_idx = 0; buf_idx < op->iov.count; buf_idx++)
{
for (int i = 0; i < op->iov.buf[buf_idx].iov_len; i++, offset++)
{
uint8_t c = offset < 0xE000 ? 0x56 : (offset < 0x10000 ? 0x57 : 0x58);
if (((uint8_t*)op->iov.buf[buf_idx].iov_base)[i] != c)
{
printf("Write replay: mismatch at %lu\n", offset-op->req.rw.offset);
goto fail;
}
}
}
fail:
assert(offset == op->req.rw.offset+op->req.rw.len);
replay_ops.push_back(op);
}
if (replay_start != 0 || replay_end != 0x14000)
{
printf("Write replay: range mismatch: %lx-%lx\n", replay_start, replay_end);
assert(0);
}
for (auto op: replay_ops)
{
pretend_op_completed(cli, op, 0);
}
}
// Check that the following write finally proceeds
check_op_count(cli, 1, 1);
can_complete(r1);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0x10000, 0x4000), 0);
check_completed(r1);
check_op_count(cli, 1, 0);
// Check sync
r2 = test_sync(cli);
can_complete(r2);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_SYNC, 0, 0), 0);
check_completed(r2);
// Check disconnect during write
r1 = test_write(cli, 0, 4096, 0x59);
check_op_count(cli, 1, 1);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0, 0x1000), -EPIPE);
check_disconnected(cli, 1);
pretend_connected(cli, 1);
check_op_count(cli, 1, 0);
cli->continue_ops(true);
check_op_count(cli, 1, 1);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0, 0x1000), 0);
check_op_count(cli, 1, 1);
can_complete(r1);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0, 0x1000), 0);
check_completed(r1);
// Check disconnect inside operation callback (reenterability)
// Probably doesn't happen too often, but possible in theory
r1 = test_write(cli, 0, 0x1000, 0x60, [cli]()
{
pretend_disconnected(cli, 1);
});
r2 = test_write(cli, 0x1000, 0x1000, 0x61);
check_op_count(cli, 1, 2);
can_complete(r1);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0, 0x1000), 0);
check_completed(r1);
check_disconnected(cli, 1);
pretend_connected(cli, 1);
cli->continue_ops(true);
check_op_count(cli, 1, 2);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0, 0x1000), 0);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0x1000, 0x1000), 0);
check_op_count(cli, 1, 1);
can_complete(r2);
pretend_op_completed(cli, find_op(cli, 1, OSD_OP_WRITE, 0x1000, 0x1000), 0);
check_completed(r2);
// Free client
delete cli;
delete tfd;
printf("[ok] write replay test\n");
}
void test2()
{
std::map<object_id, cluster_buffer_t> unsynced_writes;
cluster_op_t *op = new cluster_op_t();
op->opcode = OSD_OP_WRITE;
op->inode = 1;
op->offset = 0;
op->len = 4096;
op->iov.push_back(malloc_or_die(4096*1024), 4096);
// 0-4k = 0x55
memset(op->iov.buf[0].iov_base, 0x55, op->iov.buf[0].iov_len);
cluster_client_t::copy_write(op, unsynced_writes);
// 8k-12k = 0x66
op->offset = 8192;
memset(op->iov.buf[0].iov_base, 0x66, op->iov.buf[0].iov_len);
cluster_client_t::copy_write(op, unsynced_writes);
// 4k-1M+4k = 0x77
op->len = op->iov.buf[0].iov_len = 1048576;
op->offset = 4096;
memset(op->iov.buf[0].iov_base, 0x77, op->iov.buf[0].iov_len);
cluster_client_t::copy_write(op, unsynced_writes);
// check it
assert(unsynced_writes.size() == 4);
auto uit = unsynced_writes.begin();
int i;
assert(uit->first.inode == 1);
assert(uit->first.stripe == 0);
assert(uit->second.len == 4096);
for (i = 0; i < uit->second.len && ((uint8_t*)uit->second.buf)[i] == 0x55; i++) {}
assert(i == uit->second.len);
uit++;
assert(uit->first.inode == 1);
assert(uit->first.stripe == 4096);
assert(uit->second.len == 4096);
for (i = 0; i < uit->second.len && ((uint8_t*)uit->second.buf)[i] == 0x77; i++) {}
assert(i == uit->second.len);
uit++;
assert(uit->first.inode == 1);
assert(uit->first.stripe == 8192);
assert(uit->second.len == 4096);
for (i = 0; i < uit->second.len && ((uint8_t*)uit->second.buf)[i] == 0x77; i++) {}
assert(i == uit->second.len);
uit++;
assert(uit->first.inode == 1);
assert(uit->first.stripe == 12*1024);
assert(uit->second.len == 1016*1024);
for (i = 0; i < uit->second.len && ((uint8_t*)uit->second.buf)[i] == 0x77; i++) {}
assert(i == uit->second.len);
uit++;
// free memory
free(op->iov.buf[0].iov_base);
delete op;
for (auto p: unsynced_writes)
{
free(p.second.buf);
}
printf("[ok] copy_write test\n");
}
int main(int narg, char *args[])
{
test1();
test2();
return 0;
}

64
src/timerfd_interval.cpp Normal file
View File

@ -0,0 +1,64 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
#include <sys/timerfd.h>
#include <sys/poll.h>
#include <unistd.h>
#include "timerfd_interval.h"
timerfd_interval::timerfd_interval(ring_loop_t *ringloop, int seconds, std::function<void(void)> cb)
{
wait_state = 0;
timerfd = timerfd_create(CLOCK_MONOTONIC, TFD_NONBLOCK);
if (timerfd < 0)
{
throw std::runtime_error(std::string("timerfd_create: ") + strerror(errno));
}
struct itimerspec exp = {
.it_interval = { seconds, 0 },
.it_value = { seconds, 0 },
};
if (timerfd_settime(timerfd, 0, &exp, NULL))
{
throw std::runtime_error(std::string("timerfd_settime: ") + strerror(errno));
}
consumer.loop = [this]() { loop(); };
ringloop->register_consumer(&consumer);
this->ringloop = ringloop;
this->callback = cb;
}
timerfd_interval::~timerfd_interval()
{
ringloop->unregister_consumer(&consumer);
close(timerfd);
}
void timerfd_interval::loop()
{
if (wait_state == 1)
{
return;
}
struct io_uring_sqe *sqe = ringloop->get_sqe();
if (!sqe)
{
wait_state = 0;
return;
}
struct ring_data_t *data = ((ring_data_t*)sqe->user_data);
my_uring_prep_poll_add(sqe, timerfd, POLLIN);
data->callback = [&](ring_data_t *data)
{
if (data->res < 0)
{
throw std::runtime_error(std::string("waiting for timer failed: ") + strerror(-data->res));
}
uint64_t n;
read(timerfd, &n, 8);
wait_state = 0;
callback();
};
wait_state = 1;
ringloop->submit();
}

19
src/timerfd_interval.h Normal file
View File

@ -0,0 +1,19 @@
// Copyright (c) Vitaliy Filippov, 2019+
// License: VNPL-1.1 or GNU GPL-2.0+ (see README.md for details)
#pragma once
#include "ringloop.h"
class timerfd_interval
{
int wait_state;
int timerfd;
ring_loop_t *ringloop;
ring_consumer_t consumer;
std::function<void(void)> callback;
public:
timerfd_interval(ring_loop_t *ringloop, int seconds, std::function<void(void)> cb);
~timerfd_interval();
void loop();
};

View File

@ -34,8 +34,8 @@ timerfd_manager_t::~timerfd_manager_t()
void timerfd_manager_t::inc_timer(timerfd_timer_t & t)
{
t.next.tv_sec += t.micros/1000000;
t.next.tv_nsec += (t.micros%1000000)*1000;
t.next.tv_sec += t.millis/1000;
t.next.tv_nsec += (t.millis%1000)*1000000;
if (t.next.tv_nsec > 1000000000)
{
t.next.tv_sec++;
@ -44,18 +44,13 @@ void timerfd_manager_t::inc_timer(timerfd_timer_t & t)
}
int timerfd_manager_t::set_timer(uint64_t millis, bool repeat, std::function<void(int)> callback)
{
return set_timer_us(millis*1000, repeat, callback);
}
int timerfd_manager_t::set_timer_us(uint64_t micros, bool repeat, std::function<void(int)> callback)
{
int timer_id = id++;
timespec start;
clock_gettime(CLOCK_MONOTONIC, &start);
timers.push_back({
.id = timer_id,
.micros = micros,
.millis = millis,
.start = start,
.next = start,
.repeat = repeat,
@ -126,7 +121,7 @@ again:
exp.it_value.tv_sec--;
exp.it_value.tv_nsec += 1000000000;
}
if (exp.it_value.tv_sec < 0 || exp.it_value.tv_sec == 0 && exp.it_value.tv_nsec <= 0)
if (exp.it_value.tv_sec < 0 || !exp.it_value.tv_sec && !exp.it_value.tv_nsec)
{
// It already happened
trigger_nearest();
@ -164,6 +159,6 @@ void timerfd_manager_t::trigger_nearest()
{
timers.erase(timers.begin()+nearest, timers.begin()+nearest+1);
}
nearest = -1;
cb(nearest_id);
nearest = -1;
}

View File

@ -10,7 +10,7 @@
struct timerfd_timer_t
{
int id;
uint64_t micros;
uint64_t millis;
timespec start, next;
bool repeat;
std::function<void(int)> callback;
@ -34,6 +34,5 @@ public:
timerfd_manager_t(std::function<void(int, bool, std::function<void(int, int)>)> set_fd_handler);
~timerfd_manager_t();
int set_timer(uint64_t millis, bool repeat, std::function<void(int)> callback);
int set_timer_us(uint64_t micros, bool repeat, std::function<void(int)> callback);
void clear_timer(int timer_id);
};

View File

@ -2,14 +2,6 @@
. `dirname $0`/common.sh
if [ "$EC" != "" ]; then
POOLCFG='"scheme":"xor","pg_size":3,"pg_minsize":2,"parity_chunks":1'
NOBJ=512
else
POOLCFG='"scheme":"replicated","pg_size":2,"pg_minsize":2'
NOBJ=1024
fi
dd if=/dev/zero of=./testdata/test_osd1.bin bs=1024 count=1 seek=$((1024*1024-1))
dd if=/dev/zero of=./testdata/test_osd2.bin bs=1024 count=1 seek=$((1024*1024-1))
dd if=/dev/zero of=./testdata/test_osd3.bin bs=1024 count=1 seek=$((1024*1024-1))
@ -36,7 +28,7 @@ cd ..
node mon/mon-main.js --etcd_url http://$ETCD_URL --etcd_prefix "/vitastor" --verbose 1 &>./testdata/mon.log &
MON_PID=$!
$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool",'$POOLCFG',"pg_count":16,"failure_domain":"osd"}}'
$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":2,"pg_count":16,"failure_domain":"osd"}}'
sleep 2
@ -60,7 +52,7 @@ try_change()
echo --- Change PG count to $n --- >>testdata/osd$i.log
done
$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool",'$POOLCFG',"pg_count":'$n',"failure_domain":"osd"}}'
$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":2,"pg_count":'$n',"failure_domain":"osd"}}'
for i in {1..10}; do
($ETCDCTL get /vitastor/config/pgs --print-value-only | jq -s -e '(.[0].items["1"] | map((.osd_set | select(. > 0)) | length == 2) | length) == '$n) && \
@ -90,8 +82,8 @@ try_change()
# Check that no objects are lost !
nobj=`$ETCDCTL get --prefix '/vitastor/pg/stats' --print-value-only | jq -s '[ .[].object_count ] | reduce .[] as $num (0; .+$num)'`
if [ "$nobj" -ne $NOBJ ]; then
format_error "Data lost after changing PG count to $n: $NOBJ objects expected, but got $nobj"
if [ "$nobj" -ne 1024 ]; then
format_error "Data lost after changing PG count to $n: 1024 objects expected, but got $nobj"
fi
}

View File

@ -1,75 +0,0 @@
#!/bin/bash -ex
. `dirname $0`/common.sh
dd if=/dev/zero of=./testdata/test_osd1.bin bs=1024 count=1 seek=$((1024*1024-1))
dd if=/dev/zero of=./testdata/test_osd2.bin bs=1024 count=1 seek=$((1024*1024-1))
dd if=/dev/zero of=./testdata/test_osd3.bin bs=1024 count=1 seek=$((1024*1024-1))
build/src/vitastor-osd --osd_num 1 --bind_address 127.0.0.1 --etcd_address $ETCD_URL $(node mon/simple-offsets.js --format options --device ./testdata/test_osd1.bin 2>/dev/null) &>./testdata/osd1.log &
OSD1_PID=$!
build/src/vitastor-osd --osd_num 2 --bind_address 127.0.0.1 --etcd_address $ETCD_URL $(node mon/simple-offsets.js --format options --device ./testdata/test_osd2.bin 2>/dev/null) &>./testdata/osd2.log &
OSD2_PID=$!
build/src/vitastor-osd --osd_num 3 --bind_address 127.0.0.1 --etcd_address $ETCD_URL $(node mon/simple-offsets.js --format options --device ./testdata/test_osd3.bin 2>/dev/null) &>./testdata/osd3.log &
OSD3_PID=$!
cd mon
npm install
cd ..
node mon/mon-main.js --etcd_url http://$ETCD_URL --etcd_prefix "/vitastor" &>./testdata/mon.log &
MON_PID=$!
$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"xor","pg_size":3,"pg_minsize":2,"parity_chunks":1,"pg_count":1,"failure_domain":"osd"}}'
sleep 2
if ! ($ETCDCTL get /vitastor/config/pgs --print-value-only | jq -s -e '(. | length) != 0 and (.[0].items["1"]["1"].osd_set | sort) == ["1","2","3"]'); then
format_error "FAILED: 1 PG NOT CONFIGURED"
fi
if ! ($ETCDCTL get /vitastor/pg/state/1/1 --print-value-only | jq -s -e '(. | length) != 0 and .[0].state == ["active"]'); then
format_error "FAILED: 1 PG NOT UP"
fi
if ! cmp build/src/block-vitastor.so /usr/lib/x86_64-linux-gnu/qemu/block-vitastor.so; then
sudo rm -f /usr/lib/x86_64-linux-gnu/qemu/block-vitastor.so
sudo ln -s "$(realpath .)/build/src/block-vitastor.so" /usr/lib/x86_64-linux-gnu/qemu/block-vitastor.so
fi
# Test basic write and snapshot
$ETCDCTL put /vitastor/config/inode/1/2 '{"name":"testimg","size":'$((32*1024*1024))'}'
LD_PRELOAD=libasan.so.5 \
fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -fsync=1 -rw=write \
-etcd=$ETCD_URL -pool=1 -inode=2 -size=32M -cluster_log_level=10
$ETCDCTL put /vitastor/config/inode/1/2 '{"name":"testimg@0","size":'$((32*1024*1024))'}'
$ETCDCTL put /vitastor/config/inode/1/3 '{"parent_id":2,"name":"testimg","size":'$((32*1024*1024))'}'
LD_PRELOAD=libasan.so.5 \
fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4k -direct=1 -iodepth=1 -fsync=32 -buffer_pattern=0xdeadface \
-rw=randwrite -etcd=$ETCD_URL -image=testimg -number_ios=1024
LD_PRELOAD=libasan.so.5 \
fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -rw=read -etcd=$ETCD_URL -pool=1 -inode=3 -size=32M
qemu-img convert -S 4096 -p \
-f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:pool=1:inode=3:size=$((32*1024*1024))" \
-O raw ./testdata/merged.bin
qemu-img convert -S 4096 -p \
-f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testimg@0" \
-O raw ./testdata/layer0.bin
$ETCDCTL put /vitastor/config/inode/1/3 '{"name":"testimg","size":'$((32*1024*1024))'}'
qemu-img convert -S 4096 -p \
-f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testimg" \
-O raw ./testdata/layer1.bin
node mon/merge.js ./testdata/layer0.bin ./testdata/layer1.bin ./testdata/check.bin
cmp ./testdata/merged.bin ./testdata/check.bin
format_green OK

View File

@ -34,24 +34,40 @@ fi
#LD_PRELOAD=libasan.so.5 \
# fio -thread -name=test -ioengine=build/src/libfio_vitastor_sec.so -bs=4k -fsync=128 `$ETCDCTL get /vitastor/osd/state/1 --print-value-only | jq -r '"-host="+.addresses[0]+" -port="+(.port|tostring)'` -rw=write -size=32M
if ! cmp build/src/block-vitastor.so /usr/lib/x86_64-linux-gnu/qemu/block-vitastor.so; then
sudo rm -f /usr/lib/x86_64-linux-gnu/qemu/block-vitastor.so
sudo ln -s "$(realpath .)/build/src/block-vitastor.so" /usr/lib/x86_64-linux-gnu/qemu/block-vitastor.so
fi
# Test basic write and snapshot
$ETCDCTL put /vitastor/config/inode/1/2 '{"name":"testimg","size":'$((32*1024*1024))'}'
LD_PRELOAD=libasan.so.5 \
fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -fsync=1 -rw=write -etcd=$ETCD_URL -pool=1 -inode=1 -size=128M -cluster_log_level=10
fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -fsync=1 -rw=write \
-etcd=$ETCD_URL -pool=1 -inode=2 -size=32M -cluster_log_level=10
$ETCDCTL put /vitastor/config/inode/1/2 '{"name":"testimg@0","size":'$((32*1024*1024))'}'
$ETCDCTL put /vitastor/config/inode/1/3 '{"parent_id":2,"name":"testimg","size":'$((32*1024*1024))'}'
LD_PRELOAD=libasan.so.5 \
fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4k -direct=1 -iodepth=1 -fsync=32 -buffer_pattern=0xdeadface \
-rw=randwrite -etcd=$ETCD_URL -pool=1 -inode=1 -size=128M -number_ios=1024
fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4k -direct=1 -iodepth=1 -fsync=32 -buffer_pattern=0xdeadface \
-rw=randwrite -etcd=$ETCD_URL -image=testimg -number_ios=1024
LD_PRELOAD=libasan.so.5 \
fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -rw=read -etcd=$ETCD_URL -pool=1 -inode=3 -size=32M
qemu-img convert -S 4096 -p \
-f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:pool=1:inode=1:size=$((128*1024*1024))" \
-O raw ./testdata/read.bin
-f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:pool=1:inode=3:size=$((32*1024*1024))" \
-O raw ./testdata/merged.bin
qemu-img convert -S 4096 -p \
-f raw ./testdata/read.bin \
-O raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:pool=1:inode=1:size=$((128*1024*1024))"
-f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testimg@0" \
-O raw ./testdata/layer0.bin
$ETCDCTL put /vitastor/config/inode/1/3 '{"name":"testimg","size":'$((32*1024*1024))'}'
qemu-img convert -S 4096 -p \
-f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testimg" \
-O raw ./testdata/layer1.bin
node mon/merge.js ./testdata/layer0.bin ./testdata/layer1.bin ./testdata/check.bin
cmp ./testdata/merged.bin ./testdata/check.bin
format_green OK