Commit graph

1165 commits

Author SHA1 Message Date
167c52a1a9 [#1103] node: Reduce amount of lines for method StorageEngine.head
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-04-24 16:31:04 +03:00
e5e0542482 [#1085] log: Move storage log message to constants package
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-04-15 07:57:00 +00:00
5be36924e3 [#41] log: Log storage operations in only in Debug
They are mostly useless unless we need to _debug_ a specific issue.
The amount of logs we produce is too big.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-04-15 07:57:00 +00:00
40781b3a20 [#1086] engine: Change mode in case of errors async
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-04-10 12:29:43 +00:00
5ef5734c4e Reapply "[#972] Drop x/exp/slices dependency"
This reverts commit 946f2ec2bf.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-04-10 12:09:34 +00:00
2c4b50a71e Reapply "[#972] Use require.ElementsMatch() where possible"
This reverts commit 7627d08914.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-04-10 12:09:34 +00:00
3dc81cb4fc Reapply "[#972] Use min/max builtins"
This reverts commit dad56d2e98.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-04-10 12:09:34 +00:00
d864945961 Reapply "[#972] pilorama: Remove removeDuplicatesInPlace()"
This reverts commit 9f68305c2e.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-04-10 12:09:34 +00:00
1b17258c04 [#1029] metabase: Add refill metrics
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-04-10 13:05:44 +03:00
e3d9dd6ee8 [#1024] blobovnicza: Copy data on iterate
DB value is only valid while the tx is alive.
But handler may to run something in other goroutine.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-04-10 10:21:11 +03:00
57466594fb [#1024] shard: Resync metabase concurrently
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-04-10 10:21:10 +03:00
1005bf4f56 [#1024] shard: Add refill metabase benchmark
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-04-10 10:21:10 +03:00
76398c06b0 [#1080] metabase: Add StorageID metric
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-04-10 10:00:08 +03:00
7b1adfed3e [#1080] metabase: Open bucket for container counter once
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-04-10 10:00:08 +03:00
5b8200de88 [#984] blobovnicza: Do not fail rebuild on big objects
If blobovnicza contains objects larger than object size parameter
value, then rebuild fails with an error, because there is no such
bucket in database. This commit forces to create bucket on rebuild.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-04-09 11:51:18 +00:00
d614f04a0a [#1072] Fix gofumpt issues
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-04-03 22:21:14 +03:00
17af91619a [#1070] pilorama: Fix cycling behaviour for sorted listing
In case there are no items left, return empty slice.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-04-02 14:41:31 +00:00
d5194ab2a6 [#949] metabase: fix shard.UpdateID()
metabase.Open() now reports metabase mode metric. shard.UpdateID()
needs to read shard ID from metabase => needs to open metabase.
It caused reporting 'shard undefined' metrics. To avoid reporting
wrong metrics metabase.GetShardID() was added which also opens
metabase and does not report metrics.

Signed-off-by: Ekaterina Lebedeva <ekaterina.lebedeva@yadro.com>
2024-04-01 17:27:34 +03:00
81a0346a96 [#949] metabase: fix metabase mode metric
It used to always show CLOSED regardless of actual mode.
Now metric represents actual metabase mode of operations.

Signed-off-by: Ekaterina Lebedeva <ekaterina.lebedeva@yadro.com>
2024-04-01 17:27:34 +03:00
e12fcc041d [#1059] services/tree: Fast sorted listing
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-04-01 12:37:34 +00:00
f23e38c285 Revert "[#446] engine: Move to read-only on blobstor errors"
This reverts commit 69df0d21c2.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-04-01 12:48:30 +03:00
942d83611b [#874] engine: Revert Check object existance concurrently
This reverts commit f526f49995.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-04-01 08:42:34 +00:00
0990a9b0bd [#1055] blobstor: fix mode metric
It used to always show CLOSED after setting shard mode
to read-only regardless of actual mode.
Now metric represents actual blobstor mode of operations.

Signed-off-by: Ekaterina Lebedeva <ekaterina.lebedeva@yadro.com>
2024-03-29 20:44:47 +00:00
c09c701613 [#1048] metabase: Fix drop buckets during resync
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-03-19 14:28:31 +03:00
31e2396a5f [#1043] control: Add ResetEvacuationStatus implementation
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-03-13 10:29:45 +00:00
3195142d67 [#959] writecache: Avoid manipulation with cache in DEGRADED mode
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-03-11 18:35:41 +00:00
d433b49265 [#973] node: Resolve perfsprint linter
`fmt.Errorf can be replaced with errors.New` and `fmt.Sprintf can be replaced with string addition`

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-03-11 17:55:50 +03:00
66a26b7775 [#973] node: Resolve revive: unused-parameter linter
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-03-11 17:11:49 +03:00
0882840bf5 [#634] shard: Add writecache inhume tests
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-03-06 13:12:34 +03:00
ae5bb87e70 Revert "[#866] Use TTL for blobovnicza tree cache"
This reverts commit d9cbb16bd3.

Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-03-01 19:29:33 +03:00
d6534fd755 [#1016] frostfs-node: Fix gopls issues
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-03-01 12:13:43 +03:00
918613546f [#1008] metabase: Do not update storageID on put
There may be a race condition between put an object and
flushing the writecache:
1. Put object to the writecache
2. Writecache flushes object to the blobstore and sets blobstore's
storageID
3. Put object to the metabase, set writecache's storageID

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-28 11:01:50 +03:00
2ad433dbcb [#1005] engine: Drop shards weights
Unused.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-26 17:25:05 +03:00
7470c383dd [#997] metabase: Drop toMoveIt bucket
It is not used.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-21 10:06:05 +03:00
adf7ebab5b [#996] metabase: Speed up bucket creation
Most of the time it exits, e.g. when it is per-container and use on each
object PUT. Bbolt implementation first tries to create bucket and then
returns it if it exists. Create operation uses cursor and thus is not
very lightweight, we can avoid it.

```
goos: linux
goarch: amd64
pkg: git.frostfs.info/TrueCloudLab/frostfs-node/pkg/local_object_storage/metabase
cpu: 11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz
                 │     old     │                new                 │
                 │   sec/op    │   sec/op     vs base               │
Put/parallel-8     174.4µ ± 3%   163.3µ ± 3%  -6.39% (p=0.000 n=10)
Put/sequential-8   263.3µ ± 2%   259.0µ ± 1%  -1.64% (p=0.000 n=10)
geomean            214.3µ        205.6µ       -4.05%

                 │     old      │                 new                 │
                 │     B/op     │     B/op      vs base               │
Put/parallel-8     275.3Ki ± 3%   281.1Ki ± 4%       ~ (p=0.063 n=10)
Put/sequential-8   413.0Ki ± 2%   426.6Ki ± 2%  +3.29% (p=0.003 n=10)
geomean            337.2Ki        346.3Ki       +2.70%

                 │     old     │                 new                 │
                 │  allocs/op  │  allocs/op   vs base                │
Put/parallel-8      678.0 ± 1%    524.5 ± 2%  -22.64% (p=0.000 n=10)
Put/sequential-8   1.329k ± 0%   1.183k ± 0%  -10.91% (p=0.000 n=10)
geomean             949.1         787.9       -16.98%
```

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-20 15:42:58 +00:00
9f68305c2e Revert "[#972] pilorama: Remove removeDuplicatesInPlace()"
This reverts commit 45fd4e4ff1.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-19 15:36:01 +00:00
dad56d2e98 Revert "[#972] Use min/max builtins"
This reverts commit 89784b2e0a.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-19 15:36:01 +00:00
7627d08914 Revert "[#972] Use require.ElementsMatch() where possible"
This reverts commit 6d9707ff1f.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-19 15:36:01 +00:00
946f2ec2bf Revert "[#972] Drop x/exp/slices dependency"
This reverts commit f3e50772fd.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-19 15:36:01 +00:00
f3e50772fd [#972] Drop x/exp/slices dependency
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-19 13:13:09 +00:00
6d9707ff1f [#972] Use require.ElementsMatch() where possible
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-19 13:13:09 +00:00
89784b2e0a [#972] Use min/max builtins
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-19 13:13:09 +00:00
45fd4e4ff1 [#972] pilorama: Remove removeDuplicatesInPlace()
Also, check that slices.CompareFunc() indeed passes all the tests before
removal.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-19 13:13:09 +00:00
05b5f5ca85 [#959] writecache: Fix panic on Get when it is not initialized
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-02-14 16:10:33 +03:00
2429508ac5 [#959] shard: Skip rebuild in DEGRADED mode
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-02-14 15:39:28 +03:00
0bd030507e [#948] metrics: Set actual value for shard_id after restart
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-02-13 09:43:21 +03:00
6a5769d1da [#948] Fix gofumpt issue
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-02-13 09:40:46 +03:00
b36a453238 [#970] fstree: Add build tag to enable generic version on linux
Unless tested, generic version can start gaining bugs. With a separate
build tag we can have the best of both worlds:
1. Use optimized implementation for linux by default.
2. Run tests or benchmarks for both. Note that they are not actually
   run automatically now, but this is at leas possible.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-09 16:12:11 +00:00
abd502215f [#970] fstree: Move file locking to the generic writer
It is not a part of FSTree itself, but rather a way to solve concurrent
counter update on non-linux implementations. New linux implementations
is pretty simple: link fails when the file exists, unlink fails when the
file doesn't exist.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-09 16:12:11 +00:00
fb74524ac7 [#970] fstree: Move delete implementation to a separate file
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-09 16:12:11 +00:00
7f692409cf [#970] fstree: Handle unsupported O_TMPFILE
Metabase test relied on this behaviour, so fix the test too.

Cherry-picking was hard and did too many conflicts,
here is an original PR:
https://github.com/nspcc-dev/neofs-node/pull/2624

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-09 16:12:11 +00:00
Roman Khimov
fc31b9c947 [#970] fstree: Add linux-specific file writer using O_TMPFILE
O_TMPFILE is implemented for all modern FSes and it's much easier and safer to
use. If application crashes in the middle of writing this file would be gone
and won't leave any garbage.

Notice that this implementation makes a different choice wrt EEXIST handling,
generic one always overwrites, while this one keeps the old data.

There is no real performance difference.

SSD (slow&old), XFS, Core i7-8565U:

Sync
```
name                                  old time/op    new time/op    delta
Put/size=1024,thread=1/fstree-8         1.74ms ± 3%    0.06ms ± 7%  -96.31%  (p=0.000 n=10+10)
Put/size=1024,thread=20/fstree-8        10.0ms ±41%     1.1ms ±18%  -88.95%  (p=0.000 n=9+10)
Put/size=1024,thread=100/fstree-8       32.3ms ±60%     6.5ms ±14%  -79.97%  (p=0.000 n=10+10)
Put/size=1048576,thread=1/fstree-8      17.8ms ±90%     3.4ms ±70%  -81.08%  (p=0.000 n=10+10)
Put/size=1048576,thread=20/fstree-8     103ms ±174%    112ms ±158%     ~     (p=0.971 n=10+10)
Put/size=1048576,thread=100/fstree-8     949ms ±78%    583ms ±132%     ~     (p=0.089 n=10+10)

name                                  old alloc/op   new alloc/op   delta
Put/size=1024,thread=1/fstree-8         3.17kB ± 1%    1.96kB ± 0%  -38.09%  (p=0.000 n=10+10)
Put/size=1024,thread=20/fstree-8        59.6kB ± 1%    39.2kB ± 1%  -34.30%  (p=0.000 n=8+10)
Put/size=1024,thread=100/fstree-8        299kB ± 0%     198kB ± 0%  -33.90%  (p=0.000 n=7+9)
Put/size=1048576,thread=1/fstree-8      3.38kB ± 1%    2.36kB ± 1%  -30.22%  (p=0.000 n=10+10)
Put/size=1048576,thread=20/fstree-8     65.7kB ± 4%    47.7kB ± 6%  -27.27%  (p=0.000 n=10+10)
Put/size=1048576,thread=100/fstree-8     351kB ± 8%     245kB ± 8%  -30.22%  (p=0.000 n=10+10)

name                                  old allocs/op  new allocs/op  delta
Put/size=1024,thread=1/fstree-8           30.3 ± 2%      21.0 ± 0%  -30.69%  (p=0.000 n=10+10)
Put/size=1024,thread=20/fstree-8           554 ± 1%       413 ± 0%  -25.35%  (p=0.000 n=8+10)
Put/size=1024,thread=100/fstree-8        2.77k ± 0%     2.07k ± 0%  -25.27%  (p=0.000 n=7+10)
Put/size=1048576,thread=1/fstree-8        32.0 ± 0%      25.0 ± 0%  -21.88%  (p=0.000 n=9+8)
Put/size=1048576,thread=20/fstree-8        609 ± 5%       494 ± 6%  -18.93%  (p=0.000 n=10+10)
Put/size=1048576,thread=100/fstree-8     3.25k ± 9%     2.50k ± 8%  -23.21%  (p=0.000 n=10+10)
```

No sync
```
name                                  old time/op    new time/op    delta
Put/size=1024,thread=1/fstree-8         71.3µs ±10%    59.8µs ±10%  -16.21%  (p=0.000 n=10+10)
Put/size=1024,thread=20/fstree-8        1.43ms ± 6%    1.22ms ±13%  -14.53%  (p=0.000 n=10+10)
Put/size=1024,thread=100/fstree-8       8.12ms ± 3%    6.36ms ± 2%  -21.67%  (p=0.000 n=8+9)
Put/size=1048576,thread=1/fstree-8      1.88ms ±70%    1.61ms ±78%     ~     (p=0.393 n=10+10)
Put/size=1048576,thread=20/fstree-8     32.7ms ±28%   34.2ms ±112%     ~     (p=0.968 n=9+10)
Put/size=1048576,thread=100/fstree-8     262ms ±56%     226ms ±34%     ~     (p=0.447 n=10+9)

name                                  old alloc/op   new alloc/op   delta
Put/size=1024,thread=1/fstree-8         2.89kB ± 0%    1.96kB ± 0%  -32.28%  (p=0.000 n=10+10)
Put/size=1024,thread=20/fstree-8        58.2kB ± 0%    39.5kB ± 0%  -32.09%  (p=0.000 n=8+8)
Put/size=1024,thread=100/fstree-8        291kB ± 0%     198kB ± 0%  -32.19%  (p=0.000 n=9+9)
Put/size=1048576,thread=1/fstree-8      3.05kB ± 1%    2.13kB ± 1%  -30.16%  (p=0.000 n=10+9)
Put/size=1048576,thread=20/fstree-8     62.6kB ± 0%    44.3kB ± 0%  -29.23%  (p=0.000 n=9+9)
Put/size=1048576,thread=100/fstree-8     302kB ± 0%     210kB ± 1%  -30.39%  (p=0.000 n=9+9)

name                                  old allocs/op  new allocs/op  delta
Put/size=1024,thread=1/fstree-8           27.0 ± 0%      21.0 ± 0%  -22.22%  (p=0.000 n=10+10)
Put/size=1024,thread=20/fstree-8           539 ± 0%       415 ± 0%  -22.98%  (p=0.000 n=10+10)
Put/size=1024,thread=100/fstree-8        2.69k ± 0%     2.07k ± 0%  -23.09%  (p=0.000 n=9+9)
Put/size=1048576,thread=1/fstree-8        28.0 ± 0%      22.3 ± 3%  -20.36%  (p=0.000 n=8+10)
Put/size=1048576,thread=20/fstree-8        577 ± 0%       458 ± 0%  -20.72%  (p=0.000 n=9+9)
Put/size=1048576,thread=100/fstree-8     2.76k ± 0%     2.15k ± 0%  -22.05%  (p=0.000 n=9+8)
```

HDD (LVM), ext4, Ryzen 5 1600:

Sync
```
                                      │ fs.sync-generic │            fs.sync-linux            │
                                      │     sec/op      │    sec/op     vs base               │
Put/size=1024,thread=1/fstree-12           34.70m ± 19%   33.59m ± 16%       ~ (p=0.529 n=10)
Put/size=1024,thread=20/fstree-12          188.8m ±  8%   189.2m ± 16%       ~ (p=0.739 n=10)
Put/size=1024,thread=100/fstree-12         264.8m ± 22%   273.6m ± 28%       ~ (p=0.353 n=10)
Put/size=1048576,thread=1/fstree-12        54.90m ± 14%   47.08m ± 18%       ~ (p=0.063 n=10)
Put/size=1048576,thread=20/fstree-12       244.1m ± 14%   220.4m ± 22%       ~ (p=0.579 n=10)
Put/size=1048576,thread=100/fstree-12      847.2m ±  5%   893.6m ±  3%  +5.48% (p=0.000 n=10)
geomean                                    164.3m         158.9m        -3.29%

                                      │ fs.sync-generic │            fs.sync-linux             │
                                      │      B/op       │     B/op      vs base                │
Put/size=1024,thread=1/fstree-12           3.375Ki ± 1%   2.471Ki ± 1%  -26.80% (p=0.000 n=10)
Put/size=1024,thread=20/fstree-12          66.62Ki ± 6%   49.21Ki ± 6%  -26.15% (p=0.000 n=10)
Put/size=1024,thread=100/fstree-12         319.2Ki ± 1%   230.9Ki ± 2%  -27.64% (p=0.000 n=10)
Put/size=1048576,thread=1/fstree-12        3.457Ki ± 1%   2.559Ki ± 1%  -25.97% (p=0.000 n=10)
Put/size=1048576,thread=20/fstree-12       66.91Ki ± 1%   49.16Ki ± 1%  -26.52% (p=0.000 n=10)
Put/size=1048576,thread=100/fstree-12      338.8Ki ± 2%   252.3Ki ± 3%  -25.54% (p=0.000 n=10)
geomean                                    42.17Ki        31.02Ki       -26.44%

                                      │ fs.sync-generic │            fs.sync-linux            │
                                      │    allocs/op    │  allocs/op   vs base                │
Put/size=1024,thread=1/fstree-12             33.00 ± 0%    27.00 ± 0%  -18.18% (p=0.000 n=10)
Put/size=1024,thread=20/fstree-12            639.5 ± 1%    519.0 ± 2%  -18.84% (p=0.000 n=10)
Put/size=1024,thread=100/fstree-12          3.059k ± 1%   2.478k ± 2%  -18.99% (p=0.000 n=10)
Put/size=1048576,thread=1/fstree-12          33.50 ± 1%    28.00 ± 4%  -16.42% (p=0.000 n=10)
Put/size=1048576,thread=20/fstree-12         638.5 ± 1%    520.0 ± 1%  -18.56% (p=0.000 n=10)
Put/size=1048576,thread=100/fstree-12       3.209k ± 2%   2.655k ± 2%  -17.28% (p=0.000 n=10)
geomean                                      405.3         332.1       -18.05%
```

No sync
```
                                      │ fs.nosync-generic │             fs.nosync-linux              │
                                      │      sec/op       │    sec/op     vs base                    │
Put/size=1024,thread=1/fstree-12           148.2µ ± 20%     136.6µ ± 19%   -7.89% (p=0.029 n=10)
Put/size=1024,thread=20/fstree-12          1.140m ± 26%     1.364m ± 16%        ~ (p=0.143 n=10)
Put/size=1024,thread=100/fstree-12         11.93m ± 68%     26.89m ± 62%        ~ (p=0.123 n=10)
Put/size=1048576,thread=1/fstree-12        1.302m ±  3%     1.287m ±  5%        ~ (p=0.481 n=10)
Put/size=1048576,thread=20/fstree-12       77.52m ±  8%     74.07m ±  7%        ~ (p=0.278 n=10+9)
Put/size=1048576,thread=100/fstree-12      226.1m ±   ∞ ¹
geomean                                    5.986m           3.434m        +18.60%                  ²
¹ need >= 6 samples for confidence interval at level 0.95
² benchmark set differs from baseline; geomeans may not be comparable

                                      │ fs.nosync-generic │             fs.nosync-linux              │
                                      │       B/op        │     B/op      vs base                    │
Put/size=1024,thread=1/fstree-12           2.879Ki ± 0%     1.972Ki ± 0%  -31.51% (p=0.000 n=10)
Put/size=1024,thread=20/fstree-12          55.94Ki ± 1%     37.90Ki ± 1%  -32.25% (p=0.000 n=10)
Put/size=1024,thread=100/fstree-12         272.6Ki ± 0%     182.1Ki ± 9%  -33.21% (p=0.000 n=10)
Put/size=1048576,thread=1/fstree-12        3.158Ki ± 0%     2.259Ki ± 0%  -28.46% (p=0.000 n=10)
Put/size=1048576,thread=20/fstree-12       58.87Ki ± 0%     41.03Ki ± 0%  -30.30% (p=0.000 n=10+9)
Put/size=1048576,thread=100/fstree-12      299.8Ki ±  ∞ ¹
geomean                                    36.71Ki          16.60Ki       -31.17%                  ²
¹ need >= 6 samples for confidence interval at level 0.95
² benchmark set differs from baseline; geomeans may not be comparable

                                      │ fs.nosync-generic │            fs.nosync-linux            │
                                      │     allocs/op     │  allocs/op   vs base                  │
Put/size=1024,thread=1/fstree-12             28.00 ± 0%      22.00 ± 0%  -21.43% (p=0.000 n=10)
Put/size=1024,thread=20/fstree-12            530.0 ± 0%      407.5 ± 1%  -23.11% (p=0.000 n=10)
Put/size=1024,thread=100/fstree-12          2.567k ± 0%     1.956k ± 9%  -23.77% (p=0.000 n=10)
Put/size=1048576,thread=1/fstree-12          30.00 ± 0%      24.00 ± 0%  -20.00% (p=0.000 n=10)
Put/size=1048576,thread=20/fstree-12         553.5 ± 0%      434.0 ± 0%  -21.59% (n=10+9)
Put/size=1048576,thread=100/fstree-12       2.803k ±  ∞ ¹
geomean                                      347.9           178.8       -21.99%                ²
¹ need >= 6 samples for confidence interval at level 0.95
² benchmark set differs from baseline; geomeans may not be comparable
```

Signed-off-by: Roman Khimov <roman@nspcc.ru>
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-09 16:12:11 +00:00
ff488b53a1 [#970] fstree: Move write functions to a separate file
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-09 16:12:11 +00:00
9a622a750d [#970] fstree: Move temporary path handling in a separate function
Allow to easier test different implementations.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2024-02-09 16:12:11 +00:00
d19ade23c8 [#959] node: Set mode to shard's components when open it
Avoid opening database for `metabase` and `cache` in `Degraded` mode.

Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-02-09 14:04:01 +00:00
db67c21d55 [#947] engine: Evacuate trees to remote nodes
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-09 11:33:15 +03:00
728150d1d2 [#947] engine: Evacuate trees to local shards
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-09 11:33:15 +03:00
15d853ea22 [#947] controlSvc: Return tree evacuation stat
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-09 11:20:39 +03:00
b3f3505ada [#947] cli: Allow to specify evacuation scope
It may be required to evacuate only objects or only tree or all, so
now it spossible to specify.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-09 11:20:38 +03:00
a6eb66bf9c [#947] evacuate: Refactor evacuate parameters
Drop methods to make it easier to extend.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-09 11:20:38 +03:00
8e2a0611f4 [#947] tree: Add method to list all trees
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-09 11:20:38 +03:00
cfc5ce7853 [#964] metabase: Drop GC marks if object not found
GC inhumes expired locks and tombstones on all the shards.
So it could be GC mark without object.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-08 07:54:39 +00:00
9ba48c582d [#917] engine: Allow to detach shards
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-02-06 14:49:47 +03:00
d0eadf7ea2 [#799] engine: Skip put when object removed from shard
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-02-01 17:49:22 +00:00
e3573de6db [#930] gc: Stop internal activity by context
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2024-01-31 08:30:34 +00:00
675eec91f3 [#938] shard: Update only changed counters
If metric value hasn't changed, but we update metric, then
non existed metric will apear with zero value.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-30 12:37:48 +03:00
c681354afd [#938] engine: Fix container count removal
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-30 12:37:48 +03:00
5ed330e436 [#927] metabase: Delete GC marks
`key` is changed inside `db.get`, so encode address again after get.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-24 18:51:16 +03:00
931a5e9aaf [#918] engine: Move shard to degraded mode if metabase open failed
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-23 11:16:40 +03:00
f526f49995 [#874] engine: Check object existance concurrently
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-23 09:28:29 +03:00
f5160b27fc [#920] tests: Fix data races
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-19 14:06:05 +03:00
63d3ed1ad8 [#904] tests: Close test engine after test
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-17 19:04:39 +03:00
57171907e3 [#904] metabase: Return if object was actuall inserted
This requires to count metrics properly.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-17 19:04:39 +03:00
c1a80235db [#904] metabase: Log Inhume operation
It will be very useful for troubleshooting.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-17 18:42:52 +03:00
a2ab373a0a [#895] metabase: Do not delete GC mark for virtual objects
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-11 12:32:09 +00:00
7166e77c2b [#895] test: Add logger to test shard
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-11 12:32:09 +00:00
47dcfa20f3 [#895] test: Use t.Cleanup only for external resources
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-11 12:32:09 +00:00
f1b2b8bffa [#895] test: Fix NewLogger arguments list
`debug` is always true.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-11 12:32:09 +00:00
4b8b4da681 [#864] engine: Drop container count metric if container removed
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-10 10:45:32 +03:00
d75e7e9a21 [#864] engine: Drop container size metric if container deleted
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-10 10:44:54 +03:00
dfd62ca6b1 [#864] metabase: Refactor delete/inhume
Available -> Logic, Raw -> Phy for delete/inhume results.
Use single counter instead of vectors.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2024-01-09 09:59:42 +03:00
225fe2d4d5 [#894] blobovniczatree: Speedup rebuild test
Down from 3s to 300ms.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-12-29 16:28:54 +00:00
581887148a [#569] cli: Add control shards writecache seal command
It does the same as `control shards flush-writecache --seal`, but
has better name.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-29 16:05:37 +03:00
7a9db5bcdd [#569] writecache: Do not wait modeMtx if mode changes
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-29 16:05:37 +03:00
32c282ca10 [#569] writecache: Refactor flush
Make single RUnlock call instead of two.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-29 16:05:37 +03:00
0cb0fc1735 [#569] writecache: Allow to seal writecache after flush
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-29 16:05:37 +03:00
8180a0664f [#887] node: Drop badger writecache implementation
Badger implementation isn't tested and works not well,
but requires human resources to maintain.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-22 13:00:54 +03:00
d9cbb16bd3 [#866] Use TTL for blobovnicza tree cache
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2023-12-19 16:36:28 +00:00
7eb46404a1 [#863] blobovnicza: Fix counters
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-13 13:34:29 +03:00
94ffe8bb45 [#857] golangci: Add testifylint linter
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-12 16:27:02 +03:00
3b7c0362a8 [#861] shard: Fix Delete object
It is possible that object doesn't exist in metabase.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-12 14:25:40 +03:00
681b2c5fd4 [#825] policer: Do not drop required linking objects
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-12 11:04:03 +00:00
db49ad16cc [#826] blobovniczatree: Do not create DB's on init
Blobovniczas will be created on write requests.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
ad0697adc4 [#661] blobovnicza: Compute size with record size
To get more accurate size of blobovnicza use record
size (lenght of key + lenght of data).

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
e54dc3dc7c [#698] blobovnicza: Store counter values
Blobovnicza initialization take a long time because of bucket
Stat() call. So now blobovnicza stores counters in META bucket.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
5e8c08da3e [#661] blobstore: Add address to error logs
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
8911656b1a [#661] metrcis: Add rebuild percent metric
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
2407e5f5ff [#661] blobovniczatree: Do not sort DB's and indicies
Put stores object to next active DB, so there is no need to sort DBs.
In addition, it adds unnecessary DB openings.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
c6a739e746 [#661] blobovniczatree: Make Rebuild concurrent for objects
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
f1c7905263 [#661] blobovniczatree: Make Rebuild concurrent
Different DBs can be rebuild concurrently.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
d4d905ecc6 [#661] metrics: Add blobovniczatree rebuild metrics
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
b2769ca3de [#661] blobovniczatree: Make Rebuild failover safe
Now move info stores in blobovnicza, so in case of failover
rebuild completes previous operation first.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
da4fee2d0b [#698] blobovniczatree: Init blobovniczas concurrently
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:33 +03:00
422226da18 [#661] blobovniczatree: Add Rebuild implementation
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:32 +03:00
a531eaf8bc [#661] blobstor: Add Rebuild implementation
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:32 +03:00
c1667a11d2 [#661] blobovniczatree: Allow to change depth or width
Now it is possible to change depth or with of blobovniczatree.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:32 +03:00
484eb59893 [#661] blobovniczatree: Use .db extension for db files
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:32 +03:00
44552a849b [#661] shard: Add blobstor rebuilder
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-07 15:37:32 +03:00
a478050639 [#838] metabase: Resolve funlen linter
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-06 15:44:21 +03:00
d30ab5f29e [#838] metabase: Count user objects
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-06 15:44:21 +03:00
f314da4af3 [#838] metabase: Add user object type counter
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-06 15:44:21 +03:00
29550fe600 [#838] shard: Refactor updateMetrics method
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-12-06 15:44:21 +03:00
b2c63e57ba [#651] engine/test: Speedup StorageEngine_Inhume
Signed-off-by: Alexander Chuprov <a.chuprov@yadro.com>
2023-11-30 13:19:43 +00:00
445ebcc0e7 [#651] shard/test: Speedup Shard_Delete
Signed-off-by: Alexander Chuprov <a.chuprov@yadro.com>
2023-11-30 13:19:43 +00:00
2302e5d342 [#651] shard/test: Refactor Shard_Delete
Signed-off-by: Alexander Chuprov <a.chuprov@yadro.com>
2023-11-30 13:19:43 +00:00
07390ad4e3 [#715] node: Unify config parameter names
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-22 17:13:50 +03:00
8d18fa159e [#667] writecache: Fix flush test
Allow to disable background flusher for testing purposes.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-17 17:45:43 +03:00
76ff26039c [#96] node: Drop neo-go's slices package
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-17 13:24:04 +03:00
47286ebf32 [#805] pilorama: Fix TreeDrop
* If treeID is empty then deleting buckets for cursor may get
  invalidated. So, buckets should be gathered before deleting.

Signed-off-by: Airat Arifullin <a.arifullin@yadro.com>
2023-11-17 10:21:35 +00:00
29fe8c41f3 [#655] storage: Drop ErrorHandler
The only one usage was for logging.
Now logging performed by storage anyway.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-16 17:27:38 +03:00
137e987a4e [#655] storage: Drop LazyHandler
LazyHandler is implemented and used incorrectly.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-16 17:27:38 +03:00
1b22801eed [#788] engine: Fix flaky tests
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-09 10:25:46 +03:00
70ab1ebd54 [#763] metrics: Add container_objects_total metric
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-08 12:30:57 +03:00
9c98fa6152 [#763] metabase: Add container objects counter
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-08 12:30:57 +03:00
226e84d782 [#684] node: Add skipped objects count to evacuation result
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-07 12:17:11 +00:00
c80b46fad3 [#754] blobstor: Estimate compressability
Now it is possible to enable compressability estimation.
If data is likely uncompressable, it should reduce CPU time and memory.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-11-01 11:24:32 +03:00
79088baa06 [#772] node: Apply gofumpt
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-10-31 17:03:03 +03:00
00aa6d9749 [#633] shard/test: Fix TestCounters()
Introduced in 362f24953a, forgotten to be changed because test
generator didn't provide payload size.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-10-31 12:53:28 +00:00
b8f79f4227 [#633] shard/test: Fix race conditions in TestCounters()
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-10-31 12:53:28 +00:00
869518be0a [#728] writecache: Fix Badger writecache race.
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-10-30 18:36:41 +03:00
d4b6ebe7e7 [#725] writecache: Fix metric values
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-10-27 12:22:29 +03:00
559ad58ab1 [#642] writecache: Remove usage of close channel in bbolt
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2023-10-24 15:57:50 +00:00
c0b86f2d93 [#642] writecache: Remove usage of close channel in badger
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2023-10-24 15:57:50 +00:00
f2437f7ae9 [#734] shard: Fix Delete method
Due to the flushing data from the writecache to the storage
and simultaneous deletion, a partial deletion situation is possible.
So as a solution, deletion is allowed only when the object is in storage,
because object will be deleted from writecache by flush goroutine.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-10-16 17:00:18 +03:00
f26233b47a [#734] metabase: Include UpdateStorageID in metrics and traces
Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-10-16 17:00:18 +03:00
7e0c5a55de [#734] writecache: Fix flush
Now UpdateStorageID doesn't return error in case of logical error.
If object is in graveyard or GC market, it is still required to
update storage ID.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-10-16 17:00:17 +03:00
d07afd803c [#726] writecache: Fix small object flush for Badger
Do not marshal object twice.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-10-06 11:32:50 +03:00
997ac7cd8d [#726] writecache: Fix small object flush for BBolt
Do not marshal object twice.

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-10-06 11:32:44 +03:00
c1e4130020 [#146] node: Add trace_id to logs
Signed-off-by: Alexander Chuprov <a.chuprov@yadro.com>
2023-09-27 11:05:27 +03:00
3889e829e6 [#667] writecache: Add logs for report error func in tests
Signed-off-by: Airat Arifullin a.arifullin@yadro.com
2023-09-14 17:02:54 +00:00
c6af4a3ec8 [#679] engine: Do not increase error counter on meta mismatch
It was introduced in 69e1e6ca to help node determine faulty shards.
However, the situation is possible in a real-life scenario:
1. Object O is evacuated from shard A to B.
2. Shard A is unmounted because of lower-level errors.
3. We now have object in meta on A and in blobstor on B. Technically we
   have it in meta on shard B too, but we still got the error if B goes
   to a degraded mode.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-09-14 10:39:18 +03:00
8a81af5a3b [#653] Add context parameter to Open functions
Signed-off-by: Ekaterina Lebedeva <ekaterina.lebedeva@yadro.com>
2023-09-07 18:03:29 +03:00
a716db99db [#668] shard/test: Do not alter rootPath option
Supposedly, this was added to allow creating 2 different shards without
subtest. Now we use t.TempDir() everywhere, so this should not be a
problem.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-09-07 07:39:39 +00:00
36759f8434 [#668] shard/test: Properly check event processing
See https://git.frostfs.info/TrueCloudLab/frostfs-node/actions/runs/1594/jobs/2

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-09-07 07:39:39 +00:00
39879fa868 [#668] shard/test: Add dontRelease options
Most of the time we would like to close shard with minor exceptions.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-09-07 07:39:39 +00:00
c661ba1312 [#668] shard/test: Use sane defaults in the test constructor
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-09-07 07:39:39 +00:00
268adb79cb [#668] shard/test: Simplify shard construction
newCustomShard() has many parameters but only the first is obligatory.
`enableWriteCache` is left as-is, because it directly affects the
functionality.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-09-07 07:39:39 +00:00
429f941cda [#668] shard/test: Release shard in t.Cleanup()
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-09-07 07:39:39 +00:00
382eb8a485 [#668] shard/test: Disable GC where it is not needed
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-09-07 07:39:39 +00:00
42696016de [#668] shard: Close stopChannel in GC
It is done once, but now we could read it from multiple places.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-09-07 07:39:39 +00:00