Compare commits
1 Commits
90a56a0519
...
a6bf6a2cf0
Author | SHA1 | Date |
---|---|---|
Vitaliy Filippov | a6bf6a2cf0 |
|
@ -288,24 +288,6 @@ jobs:
|
||||||
echo ""
|
echo ""
|
||||||
done
|
done
|
||||||
|
|
||||||
test_create_halfhost:
|
|
||||||
runs-on: ubuntu-latest
|
|
||||||
needs: build
|
|
||||||
container: ${{env.TEST_IMAGE}}:${{github.sha}}
|
|
||||||
steps:
|
|
||||||
- name: Run test
|
|
||||||
id: test
|
|
||||||
timeout-minutes: 3
|
|
||||||
run: /root/vitastor/tests/test_create_halfhost.sh
|
|
||||||
- name: Print logs
|
|
||||||
if: always() && steps.test.outcome == 'failure'
|
|
||||||
run: |
|
|
||||||
for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
|
|
||||||
echo "-------- $i --------"
|
|
||||||
cat $i
|
|
||||||
echo ""
|
|
||||||
done
|
|
||||||
|
|
||||||
test_failure_domain:
|
test_failure_domain:
|
||||||
runs-on: ubuntu-latest
|
runs-on: ubuntu-latest
|
||||||
needs: build
|
needs: build
|
||||||
|
|
|
@ -68,17 +68,11 @@ but they are not connected to the cluster.
|
||||||
- Type: string
|
- Type: string
|
||||||
|
|
||||||
RDMA device name to use for Vitastor OSD communications (for example,
|
RDMA device name to use for Vitastor OSD communications (for example,
|
||||||
"rocep5s0f0"). If not specified, Vitastor will try to find an RoCE
|
"rocep5s0f0"). Now Vitastor supports all adapters, even ones without
|
||||||
device matching [osd_network](osd.en.md#osd_network), preferring RoCEv2,
|
ODP support, like Mellanox ConnectX-3 and non-Mellanox cards.
|
||||||
or choose the first available RDMA device if no RoCE devices are
|
|
||||||
found or if `osd_network` is not specified. Auto-selection is also
|
|
||||||
unsupported with old libibverbs < v32, like in Debian 10 Buster or
|
|
||||||
CentOS 7.
|
|
||||||
|
|
||||||
Vitastor supports all adapters, even ones without ODP support, like
|
Versions up to Vitastor 1.2.0 required ODP which is only present in
|
||||||
Mellanox ConnectX-3 and non-Mellanox cards. Versions up to Vitastor
|
Mellanox ConnectX >= 4. See also [rdma_odp](#rdma_odp).
|
||||||
1.2.0 required ODP which is only present in Mellanox ConnectX >= 4.
|
|
||||||
See also [rdma_odp](#rdma_odp).
|
|
||||||
|
|
||||||
Run `ibv_devinfo -v` as root to list available RDMA devices and their
|
Run `ibv_devinfo -v` as root to list available RDMA devices and their
|
||||||
features.
|
features.
|
||||||
|
@ -101,17 +95,15 @@ your device has.
|
||||||
## rdma_gid_index
|
## rdma_gid_index
|
||||||
|
|
||||||
- Type: integer
|
- Type: integer
|
||||||
|
- Default: 0
|
||||||
|
|
||||||
Global address identifier index of the RDMA device to use. Different GID
|
Global address identifier index of the RDMA device to use. Different GID
|
||||||
indexes may correspond to different protocols like RoCEv1, RoCEv2 and iWARP.
|
indexes may correspond to different protocols like RoCEv1, RoCEv2 and iWARP.
|
||||||
Search for "GID" in `ibv_devinfo -v` output to determine which GID index
|
Search for "GID" in `ibv_devinfo -v` output to determine which GID index
|
||||||
you need.
|
you need.
|
||||||
|
|
||||||
If not specified, Vitastor will try to auto-select a RoCEv2 IPv4 GID, then
|
**IMPORTANT:** If you want to use RoCEv2 (as recommended) then the correct
|
||||||
RoCEv2 IPv6 GID, then RoCEv1 IPv4 GID, then RoCEv1 IPv6 GID, then IB GID.
|
rdma_gid_index is usually 1 (IPv6) or 3 (IPv4).
|
||||||
GID auto-selection is unsupported with libibverbs < v32.
|
|
||||||
|
|
||||||
A correct rdma_gid_index for RoCEv2 is usually 1 (IPv6) or 3 (IPv4).
|
|
||||||
|
|
||||||
## rdma_mtu
|
## rdma_mtu
|
||||||
|
|
||||||
|
|
|
@ -71,17 +71,12 @@ RDMA может быть нужно только если у клиентов е
|
||||||
- Тип: строка
|
- Тип: строка
|
||||||
|
|
||||||
Название RDMA-устройства для связи с Vitastor OSD (например, "rocep5s0f0").
|
Название RDMA-устройства для связи с Vitastor OSD (например, "rocep5s0f0").
|
||||||
Если не указано, Vitastor попробует найти RoCE-устройство, соответствующее
|
Сейчас Vitastor поддерживает все модели адаптеров, включая те, у которых
|
||||||
[osd_network](osd.en.md#osd_network), предпочитая RoCEv2, или выбрать первое
|
|
||||||
попавшееся RDMA-устройство, если RoCE-устройств нет или если сеть `osd_network`
|
|
||||||
не задана. Также автовыбор не поддерживается со старыми версиями библиотеки
|
|
||||||
libibverbs < v32, например в Debian 10 Buster или CentOS 7.
|
|
||||||
|
|
||||||
Vitastor поддерживает все модели адаптеров, включая те, у которых
|
|
||||||
нет поддержки ODP, то есть вы можете использовать RDMA с ConnectX-3 и
|
нет поддержки ODP, то есть вы можете использовать RDMA с ConnectX-3 и
|
||||||
картами производства не Mellanox. Версии Vitastor до 1.2.0 включительно
|
картами производства не Mellanox.
|
||||||
требовали ODP, который есть только на Mellanox ConnectX 4 и более новых.
|
|
||||||
См. также [rdma_odp](#rdma_odp).
|
Версии Vitastor до 1.2.0 включительно требовали ODP, который есть только
|
||||||
|
на Mellanox ConnectX 4 и более новых. См. также [rdma_odp](#rdma_odp).
|
||||||
|
|
||||||
Запустите `ibv_devinfo -v` от имени суперпользователя, чтобы посмотреть
|
Запустите `ibv_devinfo -v` от имени суперпользователя, чтобы посмотреть
|
||||||
список доступных RDMA-устройств, их параметры и возможности.
|
список доступных RDMA-устройств, их параметры и возможности.
|
||||||
|
@ -106,18 +101,15 @@ Control) и ECN (Explicit Congestion Notification).
|
||||||
## rdma_gid_index
|
## rdma_gid_index
|
||||||
|
|
||||||
- Тип: целое число
|
- Тип: целое число
|
||||||
|
- Значение по умолчанию: 0
|
||||||
|
|
||||||
Номер глобального идентификатора адреса RDMA-устройства, который следует
|
Номер глобального идентификатора адреса RDMA-устройства, который следует
|
||||||
использовать. Разным gid_index могут соответствовать разные протоколы связи:
|
использовать. Разным gid_index могут соответствовать разные протоколы связи:
|
||||||
RoCEv1, RoCEv2, iWARP. Чтобы понять, какой нужен вам - смотрите строчки со
|
RoCEv1, RoCEv2, iWARP. Чтобы понять, какой нужен вам - смотрите строчки со
|
||||||
словом "GID" в выводе команды `ibv_devinfo -v`.
|
словом "GID" в выводе команды `ibv_devinfo -v`.
|
||||||
|
|
||||||
Если не указан, Vitastor попробует автоматически выбрать сначала GID,
|
**ВАЖНО:** Если вы хотите использовать RoCEv2 (как мы и рекомендуем), то
|
||||||
соответствующий RoCEv2 IPv4, потом RoCEv2 IPv6, потом RoCEv1 IPv4, потом
|
правильный rdma_gid_index, как правило, 1 (IPv6) или 3 (IPv4).
|
||||||
RoCEv1 IPv6, потом IB. Авто-выбор GID не поддерживается со старыми версиями
|
|
||||||
libibverbs < v32.
|
|
||||||
|
|
||||||
Правильный rdma_gid_index для RoCEv2, как правило, 1 (IPv6) или 3 (IPv4).
|
|
||||||
|
|
||||||
## rdma_mtu
|
## rdma_mtu
|
||||||
|
|
||||||
|
|
|
@ -48,17 +48,11 @@
|
||||||
type: string
|
type: string
|
||||||
info: |
|
info: |
|
||||||
RDMA device name to use for Vitastor OSD communications (for example,
|
RDMA device name to use for Vitastor OSD communications (for example,
|
||||||
"rocep5s0f0"). If not specified, Vitastor will try to find an RoCE
|
"rocep5s0f0"). Now Vitastor supports all adapters, even ones without
|
||||||
device matching [osd_network](osd.en.md#osd_network), preferring RoCEv2,
|
ODP support, like Mellanox ConnectX-3 and non-Mellanox cards.
|
||||||
or choose the first available RDMA device if no RoCE devices are
|
|
||||||
found or if `osd_network` is not specified. Auto-selection is also
|
|
||||||
unsupported with old libibverbs < v32, like in Debian 10 Buster or
|
|
||||||
CentOS 7.
|
|
||||||
|
|
||||||
Vitastor supports all adapters, even ones without ODP support, like
|
Versions up to Vitastor 1.2.0 required ODP which is only present in
|
||||||
Mellanox ConnectX-3 and non-Mellanox cards. Versions up to Vitastor
|
Mellanox ConnectX >= 4. See also [rdma_odp](#rdma_odp).
|
||||||
1.2.0 required ODP which is only present in Mellanox ConnectX >= 4.
|
|
||||||
See also [rdma_odp](#rdma_odp).
|
|
||||||
|
|
||||||
Run `ibv_devinfo -v` as root to list available RDMA devices and their
|
Run `ibv_devinfo -v` as root to list available RDMA devices and their
|
||||||
features.
|
features.
|
||||||
|
@ -70,17 +64,12 @@
|
||||||
PFC (Priority Flow Control) and ECN (Explicit Congestion Notification).
|
PFC (Priority Flow Control) and ECN (Explicit Congestion Notification).
|
||||||
info_ru: |
|
info_ru: |
|
||||||
Название RDMA-устройства для связи с Vitastor OSD (например, "rocep5s0f0").
|
Название RDMA-устройства для связи с Vitastor OSD (например, "rocep5s0f0").
|
||||||
Если не указано, Vitastor попробует найти RoCE-устройство, соответствующее
|
Сейчас Vitastor поддерживает все модели адаптеров, включая те, у которых
|
||||||
[osd_network](osd.en.md#osd_network), предпочитая RoCEv2, или выбрать первое
|
|
||||||
попавшееся RDMA-устройство, если RoCE-устройств нет или если сеть `osd_network`
|
|
||||||
не задана. Также автовыбор не поддерживается со старыми версиями библиотеки
|
|
||||||
libibverbs < v32, например в Debian 10 Buster или CentOS 7.
|
|
||||||
|
|
||||||
Vitastor поддерживает все модели адаптеров, включая те, у которых
|
|
||||||
нет поддержки ODP, то есть вы можете использовать RDMA с ConnectX-3 и
|
нет поддержки ODP, то есть вы можете использовать RDMA с ConnectX-3 и
|
||||||
картами производства не Mellanox. Версии Vitastor до 1.2.0 включительно
|
картами производства не Mellanox.
|
||||||
требовали ODP, который есть только на Mellanox ConnectX 4 и более новых.
|
|
||||||
См. также [rdma_odp](#rdma_odp).
|
Версии Vitastor до 1.2.0 включительно требовали ODP, который есть только
|
||||||
|
на Mellanox ConnectX 4 и более новых. См. также [rdma_odp](#rdma_odp).
|
||||||
|
|
||||||
Запустите `ibv_devinfo -v` от имени суперпользователя, чтобы посмотреть
|
Запустите `ibv_devinfo -v` от имени суперпользователя, чтобы посмотреть
|
||||||
список доступных RDMA-устройств, их параметры и возможности.
|
список доступных RDMA-устройств, их параметры и возможности.
|
||||||
|
@ -105,29 +94,23 @@
|
||||||
`ibv_devinfo -v`.
|
`ibv_devinfo -v`.
|
||||||
- name: rdma_gid_index
|
- name: rdma_gid_index
|
||||||
type: int
|
type: int
|
||||||
|
default: 0
|
||||||
info: |
|
info: |
|
||||||
Global address identifier index of the RDMA device to use. Different GID
|
Global address identifier index of the RDMA device to use. Different GID
|
||||||
indexes may correspond to different protocols like RoCEv1, RoCEv2 and iWARP.
|
indexes may correspond to different protocols like RoCEv1, RoCEv2 and iWARP.
|
||||||
Search for "GID" in `ibv_devinfo -v` output to determine which GID index
|
Search for "GID" in `ibv_devinfo -v` output to determine which GID index
|
||||||
you need.
|
you need.
|
||||||
|
|
||||||
If not specified, Vitastor will try to auto-select a RoCEv2 IPv4 GID, then
|
**IMPORTANT:** If you want to use RoCEv2 (as recommended) then the correct
|
||||||
RoCEv2 IPv6 GID, then RoCEv1 IPv4 GID, then RoCEv1 IPv6 GID, then IB GID.
|
rdma_gid_index is usually 1 (IPv6) or 3 (IPv4).
|
||||||
GID auto-selection is unsupported with libibverbs < v32.
|
|
||||||
|
|
||||||
A correct rdma_gid_index for RoCEv2 is usually 1 (IPv6) or 3 (IPv4).
|
|
||||||
info_ru: |
|
info_ru: |
|
||||||
Номер глобального идентификатора адреса RDMA-устройства, который следует
|
Номер глобального идентификатора адреса RDMA-устройства, который следует
|
||||||
использовать. Разным gid_index могут соответствовать разные протоколы связи:
|
использовать. Разным gid_index могут соответствовать разные протоколы связи:
|
||||||
RoCEv1, RoCEv2, iWARP. Чтобы понять, какой нужен вам - смотрите строчки со
|
RoCEv1, RoCEv2, iWARP. Чтобы понять, какой нужен вам - смотрите строчки со
|
||||||
словом "GID" в выводе команды `ibv_devinfo -v`.
|
словом "GID" в выводе команды `ibv_devinfo -v`.
|
||||||
|
|
||||||
Если не указан, Vitastor попробует автоматически выбрать сначала GID,
|
**ВАЖНО:** Если вы хотите использовать RoCEv2 (как мы и рекомендуем), то
|
||||||
соответствующий RoCEv2 IPv4, потом RoCEv2 IPv6, потом RoCEv1 IPv4, потом
|
правильный rdma_gid_index, как правило, 1 (IPv6) или 3 (IPv4).
|
||||||
RoCEv1 IPv6, потом IB. Авто-выбор GID не поддерживается со старыми версиями
|
|
||||||
libibverbs < v32.
|
|
||||||
|
|
||||||
Правильный rdma_gid_index для RoCEv2, как правило, 1 (IPv6) или 3 (IPv4).
|
|
||||||
- name: rdma_mtu
|
- name: rdma_mtu
|
||||||
type: int
|
type: int
|
||||||
default: 4096
|
default: 4096
|
||||||
|
|
|
@ -232,7 +232,6 @@ class EtcdAdapter
|
||||||
async become_master()
|
async become_master()
|
||||||
{
|
{
|
||||||
const state = { ...this.mon.get_mon_state(), id: ''+this.mon.etcd_lease_id };
|
const state = { ...this.mon.get_mon_state(), id: ''+this.mon.etcd_lease_id };
|
||||||
console.log('Waiting to become master');
|
|
||||||
// eslint-disable-next-line no-constant-condition
|
// eslint-disable-next-line no-constant-condition
|
||||||
while (1)
|
while (1)
|
||||||
{
|
{
|
||||||
|
@ -244,6 +243,7 @@ class EtcdAdapter
|
||||||
{
|
{
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
|
console.log('Waiting to become master');
|
||||||
await new Promise(ok => setTimeout(ok, this.mon.config.etcd_start_timeout));
|
await new Promise(ok => setTimeout(ok, this.mon.config.etcd_start_timeout));
|
||||||
}
|
}
|
||||||
console.log('Became master');
|
console.log('Became master');
|
||||||
|
|
|
@ -56,7 +56,6 @@ const etcd_tree = {
|
||||||
osd_out_time: 600, // seconds. min: 0
|
osd_out_time: 600, // seconds. min: 0
|
||||||
placement_levels: { datacenter: 1, rack: 2, host: 3, osd: 4, ... },
|
placement_levels: { datacenter: 1, rack: 2, host: 3, osd: 4, ... },
|
||||||
use_old_pg_combinator: false,
|
use_old_pg_combinator: false,
|
||||||
osd_backfillfull_ratio: 0.99,
|
|
||||||
// client and osd
|
// client and osd
|
||||||
tcp_header_buffer_size: 65536,
|
tcp_header_buffer_size: 65536,
|
||||||
use_sync_send_recv: false,
|
use_sync_send_recv: false,
|
||||||
|
|
52
mon/mon.js
52
mon/mon.js
|
@ -74,7 +74,6 @@ class Mon
|
||||||
this.state = JSON.parse(JSON.stringify(etcd_tree));
|
this.state = JSON.parse(JSON.stringify(etcd_tree));
|
||||||
this.prev_stats = { osd_stats: {}, osd_diff: {} };
|
this.prev_stats = { osd_stats: {}, osd_diff: {} };
|
||||||
this.recheck_pgs_active = false;
|
this.recheck_pgs_active = false;
|
||||||
this.updating_total_stats = false;
|
|
||||||
this.watcher_active = false;
|
this.watcher_active = false;
|
||||||
this.old_pg_config = false;
|
this.old_pg_config = false;
|
||||||
this.old_pg_stats_seen = false;
|
this.old_pg_stats_seen = false;
|
||||||
|
@ -659,19 +658,7 @@ class Mon
|
||||||
this.etcd_watch_revision, pool_id, up_osds, osd_tree, real_prev_pgs, pool_res.pgs, pg_history);
|
this.etcd_watch_revision, pool_id, up_osds, osd_tree, real_prev_pgs, pool_res.pgs, pg_history);
|
||||||
}
|
}
|
||||||
new_pg_config.hash = tree_hash;
|
new_pg_config.hash = tree_hash;
|
||||||
const { backfillfull_pools, backfillfull_osds } = sum_object_counts(
|
return await this.save_pg_config(new_pg_config, etcd_request);
|
||||||
{ ...this.state, pg: { ...this.state.pg, config: new_pg_config } }, this.config
|
|
||||||
);
|
|
||||||
if (backfillfull_pools.join(',') != ((this.state.pg.config||{}).backfillfull_pools||[]).join(','))
|
|
||||||
{
|
|
||||||
this.log_backfillfull(backfillfull_osds, backfillfull_pools);
|
|
||||||
}
|
|
||||||
new_pg_config.backfillfull_pools = backfillfull_pools.length ? backfillfull_pools : undefined;
|
|
||||||
if (!await this.save_pg_config(new_pg_config, etcd_request))
|
|
||||||
{
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
return true;
|
|
||||||
}
|
}
|
||||||
|
|
||||||
async save_pg_config(new_pg_config, etcd_request = { compare: [], success: [] })
|
async save_pg_config(new_pg_config, etcd_request = { compare: [], success: [] })
|
||||||
|
@ -743,7 +730,7 @@ class Mon
|
||||||
async update_total_stats()
|
async update_total_stats()
|
||||||
{
|
{
|
||||||
const txn = [];
|
const txn = [];
|
||||||
const { object_counts, object_bytes, backfillfull_pools, backfillfull_osds } = sum_object_counts(this.state, this.config);
|
const { object_counts, object_bytes } = sum_object_counts(this.state, this.config);
|
||||||
let stats = sum_op_stats(this.state.osd, this.prev_stats);
|
let stats = sum_op_stats(this.state.osd, this.prev_stats);
|
||||||
let { inode_stats, seen_pools } = sum_inode_stats(this.state, this.prev_stats);
|
let { inode_stats, seen_pools } = sum_inode_stats(this.state, this.prev_stats);
|
||||||
stats.object_counts = object_counts;
|
stats.object_counts = object_counts;
|
||||||
|
@ -796,27 +783,6 @@ class Mon
|
||||||
{
|
{
|
||||||
await this.etcd.etcd_call('/kv/txn', { success: txn }, this.config.etcd_mon_timeout, 0);
|
await this.etcd.etcd_call('/kv/txn', { success: txn }, this.config.etcd_mon_timeout, 0);
|
||||||
}
|
}
|
||||||
if (!this.recheck_pgs_active &&
|
|
||||||
backfillfull_pools.join(',') != ((this.state.pg.config||{}).backfillfull_pools||[]).join(','))
|
|
||||||
{
|
|
||||||
this.log_backfillfull(backfillfull_osds, backfillfull_pools);
|
|
||||||
const new_pg_config = { ...this.state.pg.config, backfillfull_pools: backfillfull_pools.length ? backfillfull_pools : undefined };
|
|
||||||
await this.save_pg_config(new_pg_config);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
log_backfillfull(osds, pools)
|
|
||||||
{
|
|
||||||
for (const osd in osds)
|
|
||||||
{
|
|
||||||
const bf = osds[osd];
|
|
||||||
console.log('OSD '+osd+' may fill up during rebalance: capacity '+(bf.cap/1024n/1024n)+
|
|
||||||
' MB, target user data '+(bf.clean/1024n/1024n)+' MB');
|
|
||||||
}
|
|
||||||
console.log(
|
|
||||||
(pools.length ? 'Pool(s) '+pools.join(', ') : 'No pools')+
|
|
||||||
' are backfillfull now, applying rebalance configuration'
|
|
||||||
);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
schedule_update_stats()
|
schedule_update_stats()
|
||||||
|
@ -828,21 +794,7 @@ class Mon
|
||||||
this.stats_timer = setTimeout(() =>
|
this.stats_timer = setTimeout(() =>
|
||||||
{
|
{
|
||||||
this.stats_timer = null;
|
this.stats_timer = null;
|
||||||
if (this.updating_total_stats)
|
|
||||||
{
|
|
||||||
this.schedule_update_stats();
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
this.updating_total_stats = true;
|
|
||||||
try
|
|
||||||
{
|
|
||||||
this.update_total_stats().catch(console.error);
|
this.update_total_stats().catch(console.error);
|
||||||
}
|
|
||||||
catch (e)
|
|
||||||
{
|
|
||||||
console.error(e);
|
|
||||||
}
|
|
||||||
this.updating_total_stats = false;
|
|
||||||
}, this.config.mon_stats_timeout);
|
}, this.config.mon_stats_timeout);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
39
mon/stats.js
39
mon/stats.js
|
@ -109,8 +109,6 @@ function sum_object_counts(state, global_config)
|
||||||
pgstats[pool_id] = { ...(state.pg.stats[pool_id] || {}), ...(pgstats[pool_id] || {}) };
|
pgstats[pool_id] = { ...(state.pg.stats[pool_id] || {}), ...(pgstats[pool_id] || {}) };
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
const pool_per_osd = {};
|
|
||||||
const clean_per_osd = {};
|
|
||||||
for (const pool_id in pgstats)
|
for (const pool_id in pgstats)
|
||||||
{
|
{
|
||||||
let object_size = 0;
|
let object_size = 0;
|
||||||
|
@ -145,45 +143,10 @@ function sum_object_counts(state, global_config)
|
||||||
object_bytes[k] += BigInt(st[k+'_count']) * object_size;
|
object_bytes[k] += BigInt(st[k+'_count']) * object_size;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
if (st.object_count)
|
|
||||||
{
|
|
||||||
for (const pg_osd of (((state.pg.config.items||{})[pool_id]||{})[pg_num]||{}).osd_set||[])
|
|
||||||
{
|
|
||||||
if (!(pg_osd in clean_per_osd))
|
|
||||||
{
|
|
||||||
clean_per_osd[pg_osd] = 0n;
|
|
||||||
}
|
|
||||||
clean_per_osd[pg_osd] += BigInt(st.object_count);
|
|
||||||
pool_per_osd[pg_osd] = pool_per_osd[pg_osd]||{};
|
|
||||||
pool_per_osd[pg_osd][pool_id] = true;
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
return { object_counts, object_bytes };
|
||||||
}
|
|
||||||
// If clean_per_osd[osd] is larger than osd capacity then it will fill up during rebalance
|
|
||||||
let backfillfull_pools = {};
|
|
||||||
let backfillfull_osds = {};
|
|
||||||
for (const osd in clean_per_osd)
|
|
||||||
{
|
|
||||||
const st = state.osd.stats[osd];
|
|
||||||
if (!st || !st.size || !st.data_block_size)
|
|
||||||
{
|
|
||||||
continue;
|
|
||||||
}
|
|
||||||
let cap = BigInt(st.size)/BigInt(st.data_block_size);
|
|
||||||
cap = cap * BigInt((global_config.osd_backfillfull_ratio||0.99)*1000000) / 1000000n;
|
|
||||||
if (cap < clean_per_osd[osd])
|
|
||||||
{
|
|
||||||
backfillfull_osds[osd] = { cap: BigInt(st.size), clean: clean_per_osd[osd]*BigInt(st.data_block_size) };
|
|
||||||
for (const pool_id in pool_per_osd[osd])
|
|
||||||
{
|
|
||||||
backfillfull_pools[pool_id] = true;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
backfillfull_pools = Object.keys(backfillfull_pools).sort();
|
|
||||||
return { object_counts, object_bytes, backfillfull_pools, backfillfull_osds };
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// sum_inode_stats(this.state, this.prev_stats)
|
// sum_inode_stats(this.state, this.prev_stats)
|
||||||
|
|
|
@ -785,7 +785,7 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
|
||||||
}
|
}
|
||||||
for (auto & pool_item: value.object_items())
|
for (auto & pool_item: value.object_items())
|
||||||
{
|
{
|
||||||
pool_config_t pc = {};
|
pool_config_t pc;
|
||||||
// ID
|
// ID
|
||||||
pool_id_t pool_id;
|
pool_id_t pool_id;
|
||||||
char null_byte = 0;
|
char null_byte = 0;
|
||||||
|
@ -931,28 +931,12 @@ void etcd_state_client_t::parse_state(const etcd_kv_t & kv)
|
||||||
// Ignore old key if the new one is present
|
// Ignore old key if the new one is present
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
for (auto & pool_id_json: value["backfillfull_pools"].array_items())
|
|
||||||
{
|
|
||||||
auto pool_id = pool_id_json.uint64_value();
|
|
||||||
auto pool_it = this->pool_config.find(pool_id);
|
|
||||||
if (pool_it != this->pool_config.end())
|
|
||||||
{
|
|
||||||
pool_it->second.backfillfull |= 2;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
for (auto & pool_item: this->pool_config)
|
for (auto & pool_item: this->pool_config)
|
||||||
{
|
{
|
||||||
for (auto & pg_item: pool_item.second.pg_config)
|
for (auto & pg_item: pool_item.second.pg_config)
|
||||||
{
|
{
|
||||||
pg_item.second.config_exists = false;
|
pg_item.second.config_exists = false;
|
||||||
}
|
}
|
||||||
// 3 = was 1 and became 1, 0 = was 0 and became 0
|
|
||||||
if (pool_item.second.backfillfull == 2 || pool_item.second.backfillfull == 1)
|
|
||||||
{
|
|
||||||
if (on_change_backfillfull_hook)
|
|
||||||
on_change_backfillfull_hook(pool_item.first);
|
|
||||||
}
|
|
||||||
pool_item.second.backfillfull = pool_item.second.backfillfull >> 1;
|
|
||||||
}
|
}
|
||||||
for (auto & pool_item: value["items"].object_items())
|
for (auto & pool_item: value["items"].object_items())
|
||||||
{
|
{
|
||||||
|
|
|
@ -62,7 +62,6 @@ struct pool_config_t
|
||||||
std::map<pg_num_t, pg_config_t> pg_config;
|
std::map<pg_num_t, pg_config_t> pg_config;
|
||||||
uint64_t scrub_interval;
|
uint64_t scrub_interval;
|
||||||
std::string used_for_fs;
|
std::string used_for_fs;
|
||||||
int backfillfull;
|
|
||||||
};
|
};
|
||||||
|
|
||||||
struct inode_config_t
|
struct inode_config_t
|
||||||
|
@ -132,7 +131,6 @@ public:
|
||||||
std::function<json11::Json()> load_pgs_checks_hook;
|
std::function<json11::Json()> load_pgs_checks_hook;
|
||||||
std::function<void(bool)> on_load_pgs_hook;
|
std::function<void(bool)> on_load_pgs_hook;
|
||||||
std::function<void()> on_change_pool_config_hook;
|
std::function<void()> on_change_pool_config_hook;
|
||||||
std::function<void(pool_id_t)> on_change_backfillfull_hook;
|
|
||||||
std::function<void(pool_id_t, pg_num_t, osd_num_t)> on_change_pg_state_hook;
|
std::function<void(pool_id_t, pg_num_t, osd_num_t)> on_change_pg_state_hook;
|
||||||
std::function<void(pool_id_t, pg_num_t)> on_change_pg_history_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;
|
std::function<void(osd_num_t)> on_change_osd_state_hook;
|
||||||
|
|
|
@ -70,7 +70,6 @@ msgr_rdma_connection_t::~msgr_rdma_connection_t()
|
||||||
send_out_size = 0;
|
send_out_size = 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
#ifdef IBV_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT
|
|
||||||
static bool is_ipv4_gid(ibv_gid_entry *gidx)
|
static bool is_ipv4_gid(ibv_gid_entry *gidx)
|
||||||
{
|
{
|
||||||
return (((uint64_t*)gidx->gid.raw)[0] == 0 &&
|
return (((uint64_t*)gidx->gid.raw)[0] == 0 &&
|
||||||
|
@ -132,7 +131,6 @@ static matched_dev match_device(ibv_device **dev_list, addr_mask_t *networks, in
|
||||||
ibv_port_attr portinfo;
|
ibv_port_attr portinfo;
|
||||||
ibv_gid_entry best_gidx;
|
ibv_gid_entry best_gidx;
|
||||||
int res;
|
int res;
|
||||||
bool have_non_roce = false, have_roce = false;
|
|
||||||
for (int i = 0; dev_list[i]; ++i)
|
for (int i = 0; dev_list[i]; ++i)
|
||||||
{
|
{
|
||||||
auto dev = dev_list[i];
|
auto dev = dev_list[i];
|
||||||
|
@ -163,11 +161,6 @@ static matched_dev match_device(ibv_device **dev_list, addr_mask_t *networks, in
|
||||||
else
|
else
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
if (gidx.gid_type != IBV_GID_TYPE_ROCE_V1 &&
|
|
||||||
gidx.gid_type != IBV_GID_TYPE_ROCE_V2)
|
|
||||||
have_non_roce = true;
|
|
||||||
else
|
|
||||||
have_roce = true;
|
|
||||||
if (match_gid(&gidx, networks, nnet))
|
if (match_gid(&gidx, networks, nnet))
|
||||||
{
|
{
|
||||||
// Prefer RoCEv2
|
// Prefer RoCEv2
|
||||||
|
@ -193,13 +186,8 @@ cleanup:
|
||||||
{
|
{
|
||||||
log_rdma_dev_port_gid(dev_list[best.dev], best.port, best.gid, best_gidx);
|
log_rdma_dev_port_gid(dev_list[best.dev], best.port, best.gid, best_gidx);
|
||||||
}
|
}
|
||||||
if (best.dev < 0 && have_non_roce && !have_roce)
|
|
||||||
{
|
|
||||||
best.dev = -2;
|
|
||||||
}
|
|
||||||
return best;
|
return best;
|
||||||
}
|
}
|
||||||
#endif
|
|
||||||
|
|
||||||
msgr_rdma_context_t *msgr_rdma_context_t::create(std::vector<std::string> osd_networks, const char *ib_devname, uint8_t ib_port, uint8_t gid_index, uint32_t mtu, bool odp, int log_level)
|
msgr_rdma_context_t *msgr_rdma_context_t::create(std::vector<std::string> osd_networks, const char *ib_devname, uint8_t ib_port, uint8_t gid_index, uint32_t mtu, bool odp, int log_level)
|
||||||
{
|
{
|
||||||
|
@ -241,7 +229,6 @@ msgr_rdma_context_t *msgr_rdma_context_t::create(std::vector<std::string> osd_ne
|
||||||
goto cleanup;
|
goto cleanup;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
#ifdef IBV_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT
|
|
||||||
else if (osd_networks.size())
|
else if (osd_networks.size())
|
||||||
{
|
{
|
||||||
std::vector<addr_mask_t> nets;
|
std::vector<addr_mask_t> nets;
|
||||||
|
@ -250,17 +237,11 @@ msgr_rdma_context_t *msgr_rdma_context_t::create(std::vector<std::string> osd_ne
|
||||||
nets.push_back(cidr_parse(netstr));
|
nets.push_back(cidr_parse(netstr));
|
||||||
}
|
}
|
||||||
auto best = match_device(dev_list, nets.data(), nets.size(), log_level);
|
auto best = match_device(dev_list, nets.data(), nets.size(), log_level);
|
||||||
if (best.dev == -2)
|
if (best.dev < 0)
|
||||||
{
|
{
|
||||||
|
if (log_level > 0)
|
||||||
|
fprintf(stderr, "RDMA device matching osd_network is not found, using first available device\n");
|
||||||
best.dev = 0;
|
best.dev = 0;
|
||||||
if (log_level > 0)
|
|
||||||
fprintf(stderr, "No RoCE devices found, using first available RDMA device %s\n", ibv_get_device_name(*dev_list));
|
|
||||||
}
|
|
||||||
else if (best.dev < 0)
|
|
||||||
{
|
|
||||||
if (log_level > 0)
|
|
||||||
fprintf(stderr, "RDMA device matching osd_network is not found, disabling RDMA\n");
|
|
||||||
goto cleanup;
|
|
||||||
}
|
}
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
|
@ -269,7 +250,6 @@ msgr_rdma_context_t *msgr_rdma_context_t::create(std::vector<std::string> osd_ne
|
||||||
}
|
}
|
||||||
ctx->dev = dev_list[best.dev];
|
ctx->dev = dev_list[best.dev];
|
||||||
}
|
}
|
||||||
#endif
|
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
ctx->dev = *dev_list;
|
ctx->dev = *dev_list;
|
||||||
|
@ -295,22 +275,18 @@ msgr_rdma_context_t *msgr_rdma_context_t::create(std::vector<std::string> osd_ne
|
||||||
goto cleanup;
|
goto cleanup;
|
||||||
}
|
}
|
||||||
|
|
||||||
#ifdef IBV_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT
|
|
||||||
if (gid_index != -1)
|
if (gid_index != -1)
|
||||||
#endif
|
|
||||||
{
|
{
|
||||||
ctx->gid_index = gid_index < 0 ? 0 : gid_index;
|
ctx->gid_index = gid_index;
|
||||||
if (ibv_query_gid(ctx->context, ib_port, gid_index, &ctx->my_gid))
|
if (ibv_query_gid_ex(ctx->context, ib_port, gid_index, &ctx->my_gid, 0))
|
||||||
{
|
{
|
||||||
fprintf(stderr, "Couldn't read RDMA device %s GID index %d\n", ibv_get_device_name(ctx->dev), gid_index);
|
fprintf(stderr, "Couldn't read RDMA device %s GID index %d\n", ibv_get_device_name(ctx->dev), gid_index);
|
||||||
goto cleanup;
|
goto cleanup;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
#ifdef IBV_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT
|
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
// Auto-guess GID
|
// Auto-guess GID
|
||||||
ibv_gid_entry best_gidx;
|
|
||||||
for (int k = 0; k < ctx->portinfo.gid_tbl_len; k++)
|
for (int k = 0; k < ctx->portinfo.gid_tbl_len; k++)
|
||||||
{
|
{
|
||||||
ibv_gid_entry gidx;
|
ibv_gid_entry gidx;
|
||||||
|
@ -325,24 +301,21 @@ msgr_rdma_context_t *msgr_rdma_context_t::create(std::vector<std::string> osd_ne
|
||||||
{
|
{
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
// Prefer IPv4 RoCEv2 -> IPv6 RoCEv2 -> IPv4 RoCEv1 -> IPv6 RoCEv1 -> IB
|
// Prefer IPv4 RoCEv2 GID by default
|
||||||
if (gid_index == -1 ||
|
if (gid_index == -1 ||
|
||||||
gidx.gid_type == IBV_GID_TYPE_ROCE_V2 && best_gidx.gid_type != IBV_GID_TYPE_ROCE_V2 ||
|
gidx.gid_type == IBV_GID_TYPE_ROCE_V2 &&
|
||||||
gidx.gid_type == IBV_GID_TYPE_ROCE_V1 && best_gidx.gid_type == IBV_GID_TYPE_IB ||
|
(ctx->my_gid.gid_type != IBV_GID_TYPE_ROCE_V2 || is_ipv4_gid(&gidx)))
|
||||||
gidx.gid_type == best_gidx.gid_type && is_ipv4_gid(&gidx))
|
|
||||||
{
|
{
|
||||||
gid_index = k;
|
gid_index = k;
|
||||||
best_gidx = gidx;
|
ctx->my_gid = gidx;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
ctx->gid_index = gid_index = (gid_index == -1 ? 0 : gid_index);
|
ctx->gid_index = gid_index = (gid_index == -1 ? 0 : gid_index);
|
||||||
if (log_level > 0)
|
if (log_level > 0)
|
||||||
{
|
{
|
||||||
log_rdma_dev_port_gid(ctx->dev, ctx->ib_port, ctx->gid_index, best_gidx);
|
log_rdma_dev_port_gid(ctx->dev, ctx->ib_port, ctx->gid_index, ctx->my_gid);
|
||||||
}
|
}
|
||||||
ctx->my_gid = best_gidx.gid;
|
|
||||||
}
|
}
|
||||||
#endif
|
|
||||||
|
|
||||||
ctx->pd = ibv_alloc_pd(ctx->context);
|
ctx->pd = ibv_alloc_pd(ctx->context);
|
||||||
if (!ctx->pd)
|
if (!ctx->pd)
|
||||||
|
@ -458,7 +431,7 @@ msgr_rdma_connection_t *msgr_rdma_connection_t::create(msgr_rdma_context_t *ctx,
|
||||||
}
|
}
|
||||||
|
|
||||||
conn->addr.lid = ctx->my_lid;
|
conn->addr.lid = ctx->my_lid;
|
||||||
conn->addr.gid = ctx->my_gid;
|
conn->addr.gid = ctx->my_gid.gid;
|
||||||
conn->addr.qpn = conn->qp->qp_num;
|
conn->addr.qpn = conn->qp->qp_num;
|
||||||
conn->addr.psn = lrand48() & 0xffffff;
|
conn->addr.psn = lrand48() & 0xffffff;
|
||||||
|
|
||||||
|
|
|
@ -31,7 +31,7 @@ struct msgr_rdma_context_t
|
||||||
uint8_t ib_port;
|
uint8_t ib_port;
|
||||||
uint8_t gid_index;
|
uint8_t gid_index;
|
||||||
uint16_t my_lid;
|
uint16_t my_lid;
|
||||||
ibv_gid my_gid;
|
ibv_gid_entry my_gid;
|
||||||
uint32_t mtu;
|
uint32_t mtu;
|
||||||
int max_cqe = 0;
|
int max_cqe = 0;
|
||||||
int used_max_cqe = 0;
|
int used_max_cqe = 0;
|
||||||
|
|
|
@ -64,7 +64,7 @@ static void netlink_sock_alloc(struct netlink_ctx *ctx)
|
||||||
if (nl_driver_id < 0)
|
if (nl_driver_id < 0)
|
||||||
{
|
{
|
||||||
nl_socket_free(sk);
|
nl_socket_free(sk);
|
||||||
fail("Couldn't resolve the nbd netlink family: %s (code %d)\n", nl_geterror(nl_driver_id), nl_driver_id);
|
fail("Couldn't resolve the nbd netlink family\n");
|
||||||
}
|
}
|
||||||
|
|
||||||
ctx->driver_id = nl_driver_id;
|
ctx->driver_id = nl_driver_id;
|
||||||
|
@ -555,12 +555,7 @@ help:
|
||||||
fcntl(sockfd[0], F_SETFL, fcntl(sockfd[0], F_GETFL, 0) | O_NONBLOCK);
|
fcntl(sockfd[0], F_SETFL, fcntl(sockfd[0], F_GETFL, 0) | O_NONBLOCK);
|
||||||
nbd_fd = sockfd[0];
|
nbd_fd = sockfd[0];
|
||||||
load_module();
|
load_module();
|
||||||
|
|
||||||
bool bg = cfg["foreground"].is_null();
|
bool bg = cfg["foreground"].is_null();
|
||||||
if (cfg["logfile"].string_value() != "")
|
|
||||||
{
|
|
||||||
logfile = cfg["logfile"].string_value();
|
|
||||||
}
|
|
||||||
|
|
||||||
if (netlink)
|
if (netlink)
|
||||||
{
|
{
|
||||||
|
@ -593,10 +588,6 @@ help:
|
||||||
}
|
}
|
||||||
close(sockfd[1]);
|
close(sockfd[1]);
|
||||||
printf("/dev/nbd%d\n", err);
|
printf("/dev/nbd%d\n", err);
|
||||||
if (bg)
|
|
||||||
{
|
|
||||||
daemonize_reopen_stdio();
|
|
||||||
}
|
|
||||||
#else
|
#else
|
||||||
fprintf(stderr, "netlink support is disabled in this build\n");
|
fprintf(stderr, "netlink support is disabled in this build\n");
|
||||||
exit(1);
|
exit(1);
|
||||||
|
@ -640,11 +631,15 @@ help:
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
if (cfg["logfile"].string_value() != "")
|
||||||
|
{
|
||||||
|
logfile = cfg["logfile"].string_value();
|
||||||
|
}
|
||||||
if (bg)
|
if (bg)
|
||||||
{
|
{
|
||||||
daemonize();
|
daemonize();
|
||||||
}
|
}
|
||||||
}
|
|
||||||
// Initialize read state
|
// Initialize read state
|
||||||
read_state = CL_READ_HDR;
|
read_state = CL_READ_HDR;
|
||||||
recv_buf = malloc_or_die(receive_buffer_size);
|
recv_buf = malloc_or_die(receive_buffer_size);
|
||||||
|
@ -721,17 +716,13 @@ help:
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
void daemonize_fork()
|
void daemonize()
|
||||||
{
|
{
|
||||||
if (fork())
|
if (fork())
|
||||||
exit(0);
|
exit(0);
|
||||||
setsid();
|
setsid();
|
||||||
if (fork())
|
if (fork())
|
||||||
exit(0);
|
exit(0);
|
||||||
}
|
|
||||||
|
|
||||||
void daemonize_reopen_stdio()
|
|
||||||
{
|
|
||||||
close(0);
|
close(0);
|
||||||
close(1);
|
close(1);
|
||||||
close(2);
|
close(2);
|
||||||
|
@ -742,12 +733,6 @@ help:
|
||||||
fprintf(stderr, "Warning: Failed to chdir into /\n");
|
fprintf(stderr, "Warning: Failed to chdir into /\n");
|
||||||
}
|
}
|
||||||
|
|
||||||
void daemonize()
|
|
||||||
{
|
|
||||||
daemonize_fork();
|
|
||||||
daemonize_reopen_stdio();
|
|
||||||
}
|
|
||||||
|
|
||||||
json11::Json::object list_mapped()
|
json11::Json::object list_mapped()
|
||||||
{
|
{
|
||||||
const char *self_filename = exe_name;
|
const char *self_filename = exe_name;
|
||||||
|
@ -798,9 +783,8 @@ help:
|
||||||
if (!strcmp(pid_filename, self_filename))
|
if (!strcmp(pid_filename, self_filename))
|
||||||
{
|
{
|
||||||
json11::Json::object cfg = nbd_proxy::parse_args(argv.size(), argv.data());
|
json11::Json::object cfg = nbd_proxy::parse_args(argv.size(), argv.data());
|
||||||
if (cfg["command"] == "map" || cfg["command"] == "netlink-map")
|
if (cfg["command"] == "map")
|
||||||
{
|
{
|
||||||
cfg["interface"] = (cfg["command"] == "netlink-map") ? "netlink" : "nbd";
|
|
||||||
cfg.erase("command");
|
cfg.erase("command");
|
||||||
cfg["pid"] = pid;
|
cfg["pid"] = pid;
|
||||||
mapped["/dev/nbd"+std::to_string(dev_num)] = cfg;
|
mapped["/dev/nbd"+std::to_string(dev_num)] = cfg;
|
||||||
|
|
|
@ -261,7 +261,6 @@ struct dd_out_info_t
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
// ok
|
// ok
|
||||||
out_size = owatch->cfg.size;
|
|
||||||
return true;
|
return true;
|
||||||
}
|
}
|
||||||
// Wait for sub-command
|
// Wait for sub-command
|
||||||
|
@ -883,8 +882,6 @@ resume_2:
|
||||||
oinfo.end_fsync = oinfo.end_fsync && oinfo.out_seekable;
|
oinfo.end_fsync = oinfo.end_fsync && oinfo.out_seekable;
|
||||||
read_offset = 0;
|
read_offset = 0;
|
||||||
read_end = iinfo.in_seekable ? iinfo.in_size-iseek : 0;
|
read_end = iinfo.in_seekable ? iinfo.in_size-iseek : 0;
|
||||||
if (oinfo.out_size && (!read_end || read_end > oinfo.out_size-oseek))
|
|
||||||
read_end = oinfo.out_size-oseek;
|
|
||||||
if (bytelimit && (!read_end || read_end > bytelimit))
|
if (bytelimit && (!read_end || read_end > bytelimit))
|
||||||
read_end = bytelimit;
|
read_end = bytelimit;
|
||||||
clock_gettime(CLOCK_REALTIME, &tv_begin);
|
clock_gettime(CLOCK_REALTIME, &tv_begin);
|
||||||
|
|
|
@ -35,7 +35,6 @@ struct pool_creator_t
|
||||||
uint64_t new_pools_mod_rev;
|
uint64_t new_pools_mod_rev;
|
||||||
json11::Json state_node_tree;
|
json11::Json state_node_tree;
|
||||||
json11::Json new_pools;
|
json11::Json new_pools;
|
||||||
std::map<osd_num_t, json11::Json> osd_stats;
|
|
||||||
|
|
||||||
bool is_done() { return state == 100; }
|
bool is_done() { return state == 100; }
|
||||||
|
|
||||||
|
@ -47,6 +46,8 @@ struct pool_creator_t
|
||||||
goto resume_2;
|
goto resume_2;
|
||||||
else if (state == 3)
|
else if (state == 3)
|
||||||
goto resume_3;
|
goto resume_3;
|
||||||
|
else if (state == 4)
|
||||||
|
goto resume_4;
|
||||||
else if (state == 5)
|
else if (state == 5)
|
||||||
goto resume_5;
|
goto resume_5;
|
||||||
else if (state == 6)
|
else if (state == 6)
|
||||||
|
@ -89,19 +90,13 @@ resume_1:
|
||||||
// If not forced, check that we have enough osds for pg_size
|
// If not forced, check that we have enough osds for pg_size
|
||||||
if (!force)
|
if (!force)
|
||||||
{
|
{
|
||||||
// Get node_placement configuration from etcd and OSD stats
|
// Get node_placement configuration from etcd
|
||||||
parent->etcd_txn(json11::Json::object {
|
parent->etcd_txn(json11::Json::object {
|
||||||
{ "success", json11::Json::array {
|
{ "success", json11::Json::array {
|
||||||
json11::Json::object {
|
json11::Json::object {
|
||||||
{ "request_range", json11::Json::object {
|
{ "request_range", json11::Json::object {
|
||||||
{ "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/node_placement") },
|
{ "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/config/node_placement") },
|
||||||
} },
|
} }
|
||||||
},
|
|
||||||
json11::Json::object {
|
|
||||||
{ "request_range", json11::Json::object {
|
|
||||||
{ "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/osd/stats/") },
|
|
||||||
{ "range_end", base64_encode(parent->cli->st_cli.etcd_prefix+"/osd/stats0") },
|
|
||||||
} },
|
|
||||||
},
|
},
|
||||||
} },
|
} },
|
||||||
});
|
});
|
||||||
|
@ -117,21 +112,10 @@ resume_2:
|
||||||
return;
|
return;
|
||||||
}
|
}
|
||||||
|
|
||||||
// Get state_node_tree based on node_placement and osd stats
|
// Get state_node_tree based on node_placement and osd peer states
|
||||||
{
|
{
|
||||||
auto node_placement_kv = parent->cli->st_cli.parse_etcd_kv(parent->etcd_result["responses"][0]["response_range"]["kvs"][0]);
|
auto kv = parent->cli->st_cli.parse_etcd_kv(parent->etcd_result["responses"][0]["response_range"]["kvs"][0]);
|
||||||
timespec tv_now;
|
state_node_tree = get_state_node_tree(kv.value.object_items());
|
||||||
clock_gettime(CLOCK_REALTIME, &tv_now);
|
|
||||||
uint64_t osd_out_time = parent->cli->config["osd_out_time"].uint64_value();
|
|
||||||
if (!osd_out_time)
|
|
||||||
osd_out_time = 600;
|
|
||||||
osd_stats.clear();
|
|
||||||
parent->iterate_kvs_1(parent->etcd_result["responses"][1]["response_range"]["kvs"], "/osd/stats/", [&](uint64_t cur_osd, json11::Json value)
|
|
||||||
{
|
|
||||||
if ((uint64_t)value["time"].number_value()+osd_out_time >= tv_now.tv_sec)
|
|
||||||
osd_stats[cur_osd] = value;
|
|
||||||
});
|
|
||||||
state_node_tree = get_state_node_tree(node_placement_kv.value.object_items(), osd_stats);
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// Skip tag checks, if pool has none
|
// Skip tag checks, if pool has none
|
||||||
|
@ -174,18 +158,42 @@ resume_3:
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Get stats (for block_size, bitmap_granularity, ...) of osds in state_node_tree
|
||||||
|
{
|
||||||
|
json11::Json::array osd_stats;
|
||||||
|
|
||||||
|
for (auto osd_num: state_node_tree["osds"].array_items())
|
||||||
|
{
|
||||||
|
osd_stats.push_back(json11::Json::object {
|
||||||
|
{ "request_range", json11::Json::object {
|
||||||
|
{ "key", base64_encode(parent->cli->st_cli.etcd_prefix+"/osd/stats/"+osd_num.as_string()) },
|
||||||
|
} }
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
parent->etcd_txn(json11::Json::object{ { "success", osd_stats } });
|
||||||
|
}
|
||||||
|
|
||||||
|
state = 4;
|
||||||
|
resume_4:
|
||||||
|
if (parent->waiting > 0)
|
||||||
|
return;
|
||||||
|
if (parent->etcd_err.err)
|
||||||
|
{
|
||||||
|
result = parent->etcd_err;
|
||||||
|
state = 100;
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
// Filter osds from state_node_tree based on pool parameters and osd stats
|
// Filter osds from state_node_tree based on pool parameters and osd stats
|
||||||
{
|
{
|
||||||
std::vector<json11::Json> filtered_osd_stats;
|
std::vector<json11::Json> osd_stats;
|
||||||
for (auto & osd_num: state_node_tree["osds"].array_items())
|
for (auto & ocr: parent->etcd_result["responses"].array_items())
|
||||||
{
|
{
|
||||||
auto st_it = osd_stats.find(osd_num.uint64_value());
|
auto kv = parent->cli->st_cli.parse_etcd_kv(ocr["response_range"]["kvs"][0]);
|
||||||
if (st_it != osd_stats.end())
|
osd_stats.push_back(kv.value);
|
||||||
{
|
|
||||||
filtered_osd_stats.push_back(st_it->second);
|
|
||||||
}
|
}
|
||||||
}
|
guess_block_size(osd_stats);
|
||||||
guess_block_size(filtered_osd_stats);
|
|
||||||
state_node_tree = filter_state_node_tree_by_stats(state_node_tree, osd_stats);
|
state_node_tree = filter_state_node_tree_by_stats(state_node_tree, osd_stats);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -193,7 +201,8 @@ resume_3:
|
||||||
{
|
{
|
||||||
auto failure_domain = cfg["failure_domain"].string_value() == ""
|
auto failure_domain = cfg["failure_domain"].string_value() == ""
|
||||||
? "host" : cfg["failure_domain"].string_value();
|
? "host" : cfg["failure_domain"].string_value();
|
||||||
uint64_t max_pg_size = get_max_pg_size(state_node_tree, failure_domain, cfg["root_node"].string_value());
|
uint64_t max_pg_size = get_max_pg_size(state_node_tree["nodes"].object_items(),
|
||||||
|
failure_domain, cfg["root_node"].string_value());
|
||||||
|
|
||||||
if (cfg["pg_size"].uint64_value() > max_pg_size)
|
if (cfg["pg_size"].uint64_value() > max_pg_size)
|
||||||
{
|
{
|
||||||
|
@ -349,35 +358,42 @@ resume_8:
|
||||||
|
|
||||||
// Returns a JSON object of form {"nodes": {...}, "osds": [...]} that
|
// Returns a JSON object of form {"nodes": {...}, "osds": [...]} that
|
||||||
// contains: all nodes (osds, hosts, ...) based on node_placement config
|
// contains: all nodes (osds, hosts, ...) based on node_placement config
|
||||||
// and current osd stats.
|
// and current peer state, and a list of active peer osds.
|
||||||
json11::Json get_state_node_tree(json11::Json::object node_placement, std::map<osd_num_t, json11::Json> & osd_stats)
|
json11::Json get_state_node_tree(json11::Json::object node_placement)
|
||||||
{
|
{
|
||||||
// Erase non-existing osd nodes from node_placement
|
// Erase non-peer osd nodes from node_placement
|
||||||
for (auto np_it = node_placement.begin(); np_it != node_placement.end();)
|
for (auto np_it = node_placement.begin(); np_it != node_placement.end();)
|
||||||
{
|
{
|
||||||
// Numeric nodes are osds
|
// Numeric nodes are osds
|
||||||
osd_num_t osd_num = stoull_full(np_it->first);
|
osd_num_t osd_num = stoull_full(np_it->first);
|
||||||
|
|
||||||
// If node is osd and its stats do not exist, erase it
|
// If node is osd and it is not in peer states, erase it
|
||||||
if (osd_num > 0 && osd_stats.find(osd_num) == osd_stats.end())
|
if (osd_num > 0 &&
|
||||||
|
parent->cli->st_cli.peer_states.find(osd_num) == parent->cli->st_cli.peer_states.end())
|
||||||
|
{
|
||||||
node_placement.erase(np_it++);
|
node_placement.erase(np_it++);
|
||||||
|
}
|
||||||
else
|
else
|
||||||
np_it++;
|
np_it++;
|
||||||
}
|
}
|
||||||
|
|
||||||
// List of osds
|
// List of peer osds
|
||||||
std::vector<std::string> existing_osds;
|
std::vector<std::string> peer_osds;
|
||||||
|
|
||||||
// Record osds and add missing osds/hosts to np
|
// Record peer osds and add missing osds/hosts to np
|
||||||
for (auto & ps: osd_stats)
|
for (auto & ps: parent->cli->st_cli.peer_states)
|
||||||
{
|
{
|
||||||
std::string osd_num = std::to_string(ps.first);
|
std::string osd_num = std::to_string(ps.first);
|
||||||
|
|
||||||
// Record osd
|
// Record peer osd
|
||||||
existing_osds.push_back(osd_num);
|
peer_osds.push_back(osd_num);
|
||||||
|
|
||||||
// Add host if necessary
|
// Add osd, if necessary
|
||||||
|
if (node_placement.find(osd_num) == node_placement.end())
|
||||||
|
{
|
||||||
std::string osd_host = ps.second["host"].as_string();
|
std::string osd_host = ps.second["host"].as_string();
|
||||||
|
|
||||||
|
// Add host, if necessary
|
||||||
if (node_placement.find(osd_host) == node_placement.end())
|
if (node_placement.find(osd_host) == node_placement.end())
|
||||||
{
|
{
|
||||||
node_placement[osd_host] = json11::Json::object {
|
node_placement[osd_host] = json11::Json::object {
|
||||||
|
@ -385,14 +401,13 @@ resume_8:
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
|
||||||
// Add osd
|
|
||||||
node_placement[osd_num] = json11::Json::object {
|
node_placement[osd_num] = json11::Json::object {
|
||||||
{ "parent", node_placement[osd_num]["parent"].is_null() ? osd_host : node_placement[osd_num]["parent"] },
|
{ "parent", osd_host }
|
||||||
{ "level", "osd" },
|
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
return json11::Json::object { { "osds", existing_osds }, { "nodes", node_placement } };
|
return json11::Json::object { { "osds", peer_osds }, { "nodes", node_placement } };
|
||||||
}
|
}
|
||||||
|
|
||||||
// Returns new state_node_tree based on given state_node_tree with osds
|
// Returns new state_node_tree based on given state_node_tree with osds
|
||||||
|
@ -519,13 +534,15 @@ resume_8:
|
||||||
// filtered out by stats parameters (block_size, bitmap_granularity) in
|
// filtered out by stats parameters (block_size, bitmap_granularity) in
|
||||||
// given osd_stats and current pool config.
|
// given osd_stats and current pool config.
|
||||||
// Requires: state_node_tree["osds"] must match osd_stats 1-1
|
// Requires: state_node_tree["osds"] must match osd_stats 1-1
|
||||||
json11::Json filter_state_node_tree_by_stats(const json11::Json & state_node_tree, std::map<osd_num_t, json11::Json> & osd_stats)
|
json11::Json filter_state_node_tree_by_stats(const json11::Json & state_node_tree, std::vector<json11::Json> & osd_stats)
|
||||||
{
|
{
|
||||||
|
auto & osds = state_node_tree["osds"].array_items();
|
||||||
|
|
||||||
// Accepted state_node_tree nodes
|
// Accepted state_node_tree nodes
|
||||||
auto accepted_nodes = state_node_tree["nodes"].object_items();
|
auto accepted_nodes = state_node_tree["nodes"].object_items();
|
||||||
|
|
||||||
// List of accepted osds
|
// List of accepted osds
|
||||||
json11::Json::array accepted_osds;
|
std::vector<std::string> accepted_osds;
|
||||||
|
|
||||||
block_size = cfg["block_size"].uint64_value()
|
block_size = cfg["block_size"].uint64_value()
|
||||||
? cfg["block_size"].uint64_value()
|
? cfg["block_size"].uint64_value()
|
||||||
|
@ -537,25 +554,21 @@ resume_8:
|
||||||
? etcd_state_client_t::parse_immediate_commit(cfg["immediate_commit"].string_value(), IMMEDIATE_ALL)
|
? etcd_state_client_t::parse_immediate_commit(cfg["immediate_commit"].string_value(), IMMEDIATE_ALL)
|
||||||
: parent->cli->st_cli.global_immediate_commit;
|
: parent->cli->st_cli.global_immediate_commit;
|
||||||
|
|
||||||
for (auto osd_num_json: state_node_tree["osds"].array_items())
|
for (size_t i = 0; i < osd_stats.size(); i++)
|
||||||
{
|
{
|
||||||
auto osd_num = osd_num_json.uint64_value();
|
auto & os = osd_stats[i];
|
||||||
auto os_it = osd_stats.find(osd_num);
|
// Get osd number
|
||||||
if (os_it == osd_stats.end())
|
auto osd_num = osds[i].as_string();
|
||||||
{
|
|
||||||
continue;
|
|
||||||
}
|
|
||||||
auto & os = os_it->second;
|
|
||||||
if (!os["data_block_size"].is_null() && os["data_block_size"] != block_size ||
|
if (!os["data_block_size"].is_null() && os["data_block_size"] != block_size ||
|
||||||
!os["bitmap_granularity"].is_null() && os["bitmap_granularity"] != bitmap_granularity ||
|
!os["bitmap_granularity"].is_null() && os["bitmap_granularity"] != bitmap_granularity ||
|
||||||
!os["immediate_commit"].is_null() &&
|
!os["immediate_commit"].is_null() &&
|
||||||
etcd_state_client_t::parse_immediate_commit(os["immediate_commit"].string_value(), IMMEDIATE_NONE) < immediate_commit)
|
etcd_state_client_t::parse_immediate_commit(os["immediate_commit"].string_value(), IMMEDIATE_NONE) < immediate_commit)
|
||||||
{
|
{
|
||||||
accepted_nodes.erase(osd_num_json.as_string());
|
accepted_nodes.erase(osd_num);
|
||||||
}
|
}
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
accepted_osds.push_back(osd_num_json);
|
accepted_osds.push_back(osd_num);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -563,28 +576,87 @@ resume_8:
|
||||||
}
|
}
|
||||||
|
|
||||||
// Returns maximum pg_size possible for given node_tree and failure_domain, starting at parent_node
|
// Returns maximum pg_size possible for given node_tree and failure_domain, starting at parent_node
|
||||||
uint64_t get_max_pg_size(json11::Json state_node_tree, const std::string & level, const std::string & root_node)
|
uint64_t get_max_pg_size(json11::Json::object node_tree, const std::string & level, const std::string & parent_node)
|
||||||
{
|
{
|
||||||
std::set<std::string> level_seen;
|
uint64_t max_pg_sz = 0;
|
||||||
for (auto & osd: state_node_tree["osds"].array_items())
|
|
||||||
|
std::vector<std::string> nodes;
|
||||||
|
|
||||||
|
// Check if parent node is an osd (numeric)
|
||||||
|
if (parent_node != "" && stoull_full(parent_node))
|
||||||
{
|
{
|
||||||
// find OSD parent at <level>, but stop at <root_node>
|
// Add it to node list if osd is in node tree
|
||||||
auto cur_id = osd.string_value();
|
if (node_tree.find(parent_node) != node_tree.end())
|
||||||
auto cur = state_node_tree["nodes"][cur_id];
|
nodes.push_back(parent_node);
|
||||||
while (!cur.is_null())
|
}
|
||||||
|
// If parent node given, ...
|
||||||
|
else if (parent_node != "")
|
||||||
{
|
{
|
||||||
if (cur["level"] == level)
|
// ... look for children nodes of this parent
|
||||||
|
for (auto & sn: node_tree)
|
||||||
{
|
{
|
||||||
level_seen.insert(cur_id);
|
auto & props = sn.second.object_items();
|
||||||
|
|
||||||
|
auto parent_prop = props.find("parent");
|
||||||
|
if (parent_prop != props.end() && (parent_prop->second.as_string() == parent_node))
|
||||||
|
{
|
||||||
|
nodes.push_back(sn.first);
|
||||||
|
|
||||||
|
// If we're not looking for all osds, we only need a single
|
||||||
|
// child osd node
|
||||||
|
if (level != "osd" && stoull_full(sn.first))
|
||||||
break;
|
break;
|
||||||
}
|
}
|
||||||
if (cur_id == root_node)
|
|
||||||
break;
|
|
||||||
cur_id = cur["parent"].string_value();
|
|
||||||
cur = state_node_tree["nodes"][cur_id];
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
return level_seen.size();
|
// No parent node given, and we're not looking for all osds
|
||||||
|
else if (level != "osd")
|
||||||
|
{
|
||||||
|
// ... look for all level nodes
|
||||||
|
for (auto & sn: node_tree)
|
||||||
|
{
|
||||||
|
auto & props = sn.second.object_items();
|
||||||
|
|
||||||
|
auto level_prop = props.find("level");
|
||||||
|
if (level_prop != props.end() && (level_prop->second.as_string() == level))
|
||||||
|
{
|
||||||
|
nodes.push_back(sn.first);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
// Otherwise, ...
|
||||||
|
else
|
||||||
|
{
|
||||||
|
// ... we're looking for osd nodes only
|
||||||
|
for (auto & sn: node_tree)
|
||||||
|
{
|
||||||
|
if (stoull_full(sn.first))
|
||||||
|
{
|
||||||
|
nodes.push_back(sn.first);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Process gathered nodes
|
||||||
|
for (auto & node: nodes)
|
||||||
|
{
|
||||||
|
// Check for osd node, return constant max size
|
||||||
|
if (stoull_full(node))
|
||||||
|
{
|
||||||
|
max_pg_sz += 1;
|
||||||
|
}
|
||||||
|
// Otherwise, ...
|
||||||
|
else
|
||||||
|
{
|
||||||
|
// ... exclude parent node from tree, and ...
|
||||||
|
node_tree.erase(parent_node);
|
||||||
|
|
||||||
|
// ... descend onto the resulting tree
|
||||||
|
max_pg_sz += get_max_pg_size(node_tree, level, node);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return max_pg_sz;
|
||||||
}
|
}
|
||||||
|
|
||||||
json11::Json create_pool(const etcd_kv_t & kv)
|
json11::Json create_pool(const etcd_kv_t & kv)
|
||||||
|
|
|
@ -499,19 +499,6 @@ void nfs_proxy_t::check_default_pool()
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
void nfs_proxy_t::create_client()
|
|
||||||
{
|
|
||||||
auto cli = new nfs_client_t();
|
|
||||||
cli->parent = this->proxy;
|
|
||||||
if (kvfs)
|
|
||||||
nfs_kv_procs(cli);
|
|
||||||
else
|
|
||||||
nfs_block_procs(cli);
|
|
||||||
for (auto & fn: pmap.proc_table)
|
|
||||||
cli->proc_table.insert(fn);
|
|
||||||
rpc_clients.insert(cli);
|
|
||||||
}
|
|
||||||
|
|
||||||
void nfs_proxy_t::do_accept(int listen_fd)
|
void nfs_proxy_t::do_accept(int listen_fd)
|
||||||
{
|
{
|
||||||
struct sockaddr_storage addr;
|
struct sockaddr_storage addr;
|
||||||
|
@ -525,8 +512,18 @@ void nfs_proxy_t::do_accept(int listen_fd)
|
||||||
fcntl(nfs_fd, F_SETFL, fcntl(nfs_fd, F_GETFL, 0) | O_NONBLOCK);
|
fcntl(nfs_fd, F_SETFL, fcntl(nfs_fd, F_GETFL, 0) | O_NONBLOCK);
|
||||||
int one = 1;
|
int one = 1;
|
||||||
setsockopt(nfs_fd, SOL_TCP, TCP_NODELAY, &one, sizeof(one));
|
setsockopt(nfs_fd, SOL_TCP, TCP_NODELAY, &one, sizeof(one));
|
||||||
auto cli = this->create_client();
|
auto cli = new nfs_client_t();
|
||||||
|
if (kvfs)
|
||||||
|
nfs_kv_procs(cli);
|
||||||
|
else
|
||||||
|
nfs_block_procs(cli);
|
||||||
|
cli->parent = this;
|
||||||
cli->nfs_fd = nfs_fd;
|
cli->nfs_fd = nfs_fd;
|
||||||
|
for (auto & fn: pmap.proc_table)
|
||||||
|
{
|
||||||
|
cli->proc_table.insert(fn);
|
||||||
|
}
|
||||||
|
rpc_clients[nfs_fd] = cli;
|
||||||
epmgr->tfd->set_fd_handler(nfs_fd, true, [cli](int nfs_fd, int epoll_events)
|
epmgr->tfd->set_fd_handler(nfs_fd, true, [cli](int nfs_fd, int epoll_events)
|
||||||
{
|
{
|
||||||
// Handle incoming event
|
// Handle incoming event
|
||||||
|
@ -784,7 +781,7 @@ void nfs_client_t::stop()
|
||||||
if (refs <= 0)
|
if (refs <= 0)
|
||||||
{
|
{
|
||||||
auto parent = this->parent;
|
auto parent = this->parent;
|
||||||
parent->rpc_clients.erase(this);
|
parent->rpc_clients.erase(nfs_fd);
|
||||||
parent->active_connections--;
|
parent->active_connections--;
|
||||||
parent->epmgr->tfd->set_fd_handler(nfs_fd, true, NULL);
|
parent->epmgr->tfd->set_fd_handler(nfs_fd, true, NULL);
|
||||||
close(nfs_fd);
|
close(nfs_fd);
|
||||||
|
@ -1088,8 +1085,8 @@ void nfs_proxy_t::daemonize()
|
||||||
// Stop all clients because client I/O sometimes breaks during daemonize
|
// Stop all clients because client I/O sometimes breaks during daemonize
|
||||||
// I.e. the new process stops receiving events on the old FD
|
// I.e. the new process stops receiving events on the old FD
|
||||||
// It doesn't happen if we call sleep(1) here, but we don't want to call sleep(1)...
|
// It doesn't happen if we call sleep(1) here, but we don't want to call sleep(1)...
|
||||||
for (auto & cli: rpc_clients)
|
for (auto & clp: rpc_clients)
|
||||||
cli->stop();
|
clp.second->stop();
|
||||||
if (fork())
|
if (fork())
|
||||||
exit(0);
|
exit(0);
|
||||||
setsid();
|
setsid();
|
||||||
|
|
|
@ -55,7 +55,7 @@ public:
|
||||||
vitastorkv_dbw_t *db = NULL;
|
vitastorkv_dbw_t *db = NULL;
|
||||||
kv_fs_state_t *kvfs = NULL;
|
kv_fs_state_t *kvfs = NULL;
|
||||||
block_fs_state_t *blockfs = NULL;
|
block_fs_state_t *blockfs = NULL;
|
||||||
std::set<nfs_client_t*> rpc_clients;
|
std::map<int, nfs_client_t*> rpc_clients;
|
||||||
|
|
||||||
std::vector<XDR*> xdr_pool;
|
std::vector<XDR*> xdr_pool;
|
||||||
|
|
||||||
|
@ -72,7 +72,6 @@ public:
|
||||||
void watch_stats();
|
void watch_stats();
|
||||||
void parse_stats(etcd_kv_t & kv);
|
void parse_stats(etcd_kv_t & kv);
|
||||||
void check_default_pool();
|
void check_default_pool();
|
||||||
nfs_client_t* create_client();
|
|
||||||
void do_accept(int listen_fd);
|
void do_accept(int listen_fd);
|
||||||
void daemonize();
|
void daemonize();
|
||||||
void write_pid();
|
void write_pid();
|
||||||
|
@ -102,8 +101,6 @@ struct rpc_free_buffer_t
|
||||||
unsigned size;
|
unsigned size;
|
||||||
};
|
};
|
||||||
|
|
||||||
struct nfs_rdma_conn_t;
|
|
||||||
|
|
||||||
class nfs_client_t
|
class nfs_client_t
|
||||||
{
|
{
|
||||||
public:
|
public:
|
||||||
|
@ -111,7 +108,6 @@ public:
|
||||||
int refs = 0;
|
int refs = 0;
|
||||||
bool stopped = false;
|
bool stopped = false;
|
||||||
std::set<rpc_service_proc_t> proc_table;
|
std::set<rpc_service_proc_t> proc_table;
|
||||||
nfs_rdma_conn_t *rdma_conn = NULL;
|
|
||||||
|
|
||||||
// <TCP>
|
// <TCP>
|
||||||
int nfs_fd;
|
int nfs_fd;
|
||||||
|
|
|
@ -45,7 +45,6 @@ struct nfs_rdma_context_t
|
||||||
int max_send = 8, max_recv = 8; --- FIXME max_send and max_recv should probably be equal
|
int max_send = 8, max_recv = 8; --- FIXME max_send and max_recv should probably be equal
|
||||||
uint64_t max_send_size = 256*1024, max_recv_size = 256*1024;
|
uint64_t max_send_size = 256*1024, max_recv_size = 256*1024;
|
||||||
|
|
||||||
nfs_proxy_t *proxy = NULL;
|
|
||||||
epoll_manager_t *epmgr = NULL;
|
epoll_manager_t *epmgr = NULL;
|
||||||
|
|
||||||
int max_cqe = 0, used_max_cqe = 0;
|
int max_cqe = 0, used_max_cqe = 0;
|
||||||
|
@ -77,7 +76,6 @@ struct nfs_rdma_conn_t
|
||||||
nfs_rdma_context_t* nfs_proxy_t::create_rdma(const std::string & bind_address, int rdmacm_port)
|
nfs_rdma_context_t* nfs_proxy_t::create_rdma(const std::string & bind_address, int rdmacm_port)
|
||||||
{
|
{
|
||||||
nfs_rdma_context_t* self = new nfs_rdma_context_t;
|
nfs_rdma_context_t* self = new nfs_rdma_context_t;
|
||||||
self->proxy = this;
|
|
||||||
self->epmgr = epmgr;
|
self->epmgr = epmgr;
|
||||||
self->bind_address = bind_address;
|
self->bind_address = bind_address;
|
||||||
self->rdmacm_port = rdmacm_port;
|
self->rdmacm_port = rdmacm_port;
|
||||||
|
@ -303,8 +301,6 @@ void nfs_rdma_context_t::rdmacm_accept(rdma_cm_event *ev)
|
||||||
conn->id = ctx->id;
|
conn->id = ctx->id;
|
||||||
rdma_connections[ctx->id] = conn;
|
rdma_connections[ctx->id] = conn;
|
||||||
rdma_connections_by_qp[conn->id->qp->qp_num];
|
rdma_connections_by_qp[conn->id->qp->qp_num];
|
||||||
auto cli = this->proxy->create_client();
|
|
||||||
cli->rdma_conn = conn;
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -226,7 +226,6 @@ class osd_t
|
||||||
void parse_config(bool init);
|
void parse_config(bool init);
|
||||||
void init_cluster();
|
void init_cluster();
|
||||||
void on_change_osd_state_hook(osd_num_t peer_osd);
|
void on_change_osd_state_hook(osd_num_t peer_osd);
|
||||||
void on_change_backfillfull_hook(pool_id_t pool_id);
|
|
||||||
void on_change_pg_history_hook(pool_id_t pool_id, pg_num_t pg_num);
|
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(std::map<std::string, etcd_kv_t> & changes);
|
||||||
void on_load_config_hook(json11::Json::object & changes);
|
void on_load_config_hook(json11::Json::object & changes);
|
||||||
|
|
|
@ -65,7 +65,6 @@ void osd_t::init_cluster()
|
||||||
st_cli.tfd = tfd;
|
st_cli.tfd = tfd;
|
||||||
st_cli.log_level = log_level;
|
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_osd_state_hook = [this](osd_num_t peer_osd) { on_change_osd_state_hook(peer_osd); };
|
||||||
st_cli.on_change_backfillfull_hook = [this](pool_id_t pool_id) { on_change_backfillfull_hook(pool_id); };
|
|
||||||
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_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](std::map<std::string, etcd_kv_t> & 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.on_load_config_hook = [this](json11::Json::object & cfg) { on_load_config_hook(cfg); };
|
||||||
|
@ -415,14 +414,6 @@ void osd_t::on_change_osd_state_hook(osd_num_t peer_osd)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
void osd_t::on_change_backfillfull_hook(pool_id_t pool_id)
|
|
||||||
{
|
|
||||||
if (!(peering_state & (OSD_RECOVERING | OSD_FLUSHING_PGS)))
|
|
||||||
{
|
|
||||||
peering_state = peering_state | OSD_RECOVERING;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
void osd_t::on_change_etcd_state_hook(std::map<std::string, etcd_kv_t> & changes)
|
void osd_t::on_change_etcd_state_hook(std::map<std::string, etcd_kv_t> & changes)
|
||||||
{
|
{
|
||||||
if (changes.find(st_cli.etcd_prefix+"/config/global") != changes.end())
|
if (changes.find(st_cli.etcd_prefix+"/config/global") != changes.end())
|
||||||
|
|
|
@ -252,18 +252,10 @@ bool osd_t::pick_next_recovery(osd_recovery_op_t &op)
|
||||||
auto mask = recovery_last_degraded ? (PG_ACTIVE | PG_HAS_DEGRADED) : (PG_ACTIVE | PG_DEGRADED | PG_HAS_MISPLACED);
|
auto mask = recovery_last_degraded ? (PG_ACTIVE | PG_HAS_DEGRADED) : (PG_ACTIVE | PG_DEGRADED | PG_HAS_MISPLACED);
|
||||||
auto check = recovery_last_degraded ? (PG_ACTIVE | PG_HAS_DEGRADED) : (PG_ACTIVE | PG_HAS_MISPLACED);
|
auto check = recovery_last_degraded ? (PG_ACTIVE | PG_HAS_DEGRADED) : (PG_ACTIVE | PG_HAS_MISPLACED);
|
||||||
// Restart scanning from the same PG as the last time
|
// Restart scanning from the same PG as the last time
|
||||||
restart:
|
|
||||||
for (auto pg_it = pgs.lower_bound(recovery_last_pg); pg_it != pgs.end(); pg_it++)
|
for (auto pg_it = pgs.lower_bound(recovery_last_pg); pg_it != pgs.end(); pg_it++)
|
||||||
{
|
{
|
||||||
if ((pg_it->second.state & mask) == check)
|
if ((pg_it->second.state & mask) == check)
|
||||||
{
|
{
|
||||||
auto pool_it = st_cli.pool_config.find(pg_it->first.pool_id);
|
|
||||||
if (pool_it != st_cli.pool_config.end() && pool_it->second.backfillfull)
|
|
||||||
{
|
|
||||||
// Skip the pool
|
|
||||||
recovery_last_pg.pool_id++;
|
|
||||||
goto restart;
|
|
||||||
}
|
|
||||||
auto & src = recovery_last_degraded ? pg_it->second.degraded_objects : pg_it->second.misplaced_objects;
|
auto & src = recovery_last_degraded ? pg_it->second.degraded_objects : pg_it->second.misplaced_objects;
|
||||||
assert(src.size() > 0);
|
assert(src.size() > 0);
|
||||||
// Restart scanning from the next object
|
// Restart scanning from the next object
|
||||||
|
|
|
@ -19,12 +19,9 @@ ANTIETCD=1 ./test_etcd_fail.sh
|
||||||
|
|
||||||
./test_interrupted_rebalance.sh
|
./test_interrupted_rebalance.sh
|
||||||
IMMEDIATE_COMMIT=1 ./test_interrupted_rebalance.sh
|
IMMEDIATE_COMMIT=1 ./test_interrupted_rebalance.sh
|
||||||
|
|
||||||
SCHEME=ec ./test_interrupted_rebalance.sh
|
SCHEME=ec ./test_interrupted_rebalance.sh
|
||||||
SCHEME=ec IMMEDIATE_COMMIT=1 ./test_interrupted_rebalance.sh
|
SCHEME=ec IMMEDIATE_COMMIT=1 ./test_interrupted_rebalance.sh
|
||||||
|
|
||||||
./test_create_halfhost.sh
|
|
||||||
|
|
||||||
./test_failure_domain.sh
|
./test_failure_domain.sh
|
||||||
|
|
||||||
./test_snapshot.sh
|
./test_snapshot.sh
|
||||||
|
|
|
@ -1,35 +0,0 @@
|
||||||
#!/bin/bash -ex
|
|
||||||
|
|
||||||
. `dirname $0`/common.sh
|
|
||||||
|
|
||||||
node mon/mon-main.js $MON_PARAMS --etcd_address $ETCD_URL --etcd_prefix "/vitastor" >>./testdata/mon.log 2>&1 &
|
|
||||||
MON_PID=$!
|
|
||||||
wait_etcd
|
|
||||||
|
|
||||||
TIME=$(date '+%s')
|
|
||||||
$ETCDCTL put /vitastor/config/global '{"placement_levels":{"dc":10,"host":100,"half":105,"osd":110}}'
|
|
||||||
$ETCDCTL put /vitastor/config/node_placement '{
|
|
||||||
"h11":{"level":"half","parent":"host1"},
|
|
||||||
"h12":{"level":"half","parent":"host1"},
|
|
||||||
"h21":{"level":"half","parent":"host2"},
|
|
||||||
"h22":{"level":"half","parent":"host2"},
|
|
||||||
"h31":{"level":"half","parent":"host3"},
|
|
||||||
"h32":{"level":"half","parent":"host3"},
|
|
||||||
"1":{"parent":"h11"},
|
|
||||||
"2":{"parent":"h12"},
|
|
||||||
"3":{"parent":"h21"},
|
|
||||||
"4":{"parent":"h22"},
|
|
||||||
"5":{"parent":"h31"},
|
|
||||||
"6":{"parent":"h32"}
|
|
||||||
}'
|
|
||||||
$ETCDCTL put /vitastor/osd/stats/1 '{"host":"host1","size":1073741824,"time":"'$TIME'"}'
|
|
||||||
$ETCDCTL put /vitastor/osd/stats/2 '{"host":"host1","size":1073741824,"time":"'$TIME'"}'
|
|
||||||
$ETCDCTL put /vitastor/osd/stats/3 '{"host":"host2","size":1073741824,"time":"'$TIME'"}'
|
|
||||||
$ETCDCTL put /vitastor/osd/stats/4 '{"host":"host2","size":1073741824,"time":"'$TIME'"}'
|
|
||||||
$ETCDCTL put /vitastor/osd/stats/5 '{"host":"host3","size":1073741824,"time":"'$TIME'"}'
|
|
||||||
$ETCDCTL put /vitastor/osd/stats/6 '{"host":"host3","size":1073741824,"time":"'$TIME'"}'
|
|
||||||
build/src/cmd/vitastor-cli --etcd_address $ETCD_URL osd-tree
|
|
||||||
# check that it doesn't fail
|
|
||||||
build/src/cmd/vitastor-cli --etcd_address $ETCD_URL create-pool testpool --ec 2+1 -n 32
|
|
||||||
|
|
||||||
format_green OK
|
|
Loading…
Reference in New Issue