aarifullin/frostfs-node
1
0
Fork 0
forked from TrueCloudLab/frostfs-node
Code Issues Pull requests Projects Releases Packages Wiki Activity
2695 commits 130 branches 26 tags 52 MiB
Commit graph

472 commits

Author SHA1 Message Date
Evgenii Stratonikov
06f2681178 [#1442] pilorama: Generate timestamp based on node position in the container 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:19:50 +03:00
Evgenii Stratonikov
fa57a8be44 [#1431] pilorama: Use Batch for write transactions 
Helps a lot in case of concurrent request flow.

```
name                      old time/op    new time/op    delta
ApplySequential/bbolt-8     78.0µs ± 9%    59.8µs ± 4%  -23.39%  (p=0.000 n=10+9)
ApplyReorderLast/bbolt-8     143µs ± 5%     113µs ±15%  -21.06%  (p=0.000 n=10+10)

name                      old alloc/op   new alloc/op   delta
ApplySequential/bbolt-8     56.9kB ± 8%    28.9kB ± 3%  -49.22%  (p=0.000 n=10+10)
ApplyReorderLast/bbolt-8    87.3kB ± 3%    40.9kB ±10%  -53.16%  (p=0.000 n=10+10)

name                      old allocs/op  new allocs/op  delta
ApplySequential/bbolt-8        224 ±11%       262 ± 5%  +16.93%  (p=0.000 n=9+10)
ApplyReorderLast/bbolt-8       518 ± 4%       674 ±11%  +30.09%  (p=0.000 n=10+10)
```

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:18:55 +03:00
Evgenii Stratonikov
d6d7e35454 [#1431] pilorama: Cache attributes in the index 
Currently to find a node by path we iterate over all the children on
each level. This is far from optimal and scales badly with the number of
nodes on a single level. Thus we introduce "indexed attributes" for
which an additional information is stored and which can be use in
`*ByPath` operations. Currently this set only includes `FileName`
attribute but this may change in future.

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:18:23 +03:00
Evgenii Stratonikov
241d4d6810 [#1431] engine: Add benchmark for Select vs TreeGetByPath 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:18:15 +03:00
Evgenii Stratonikov
35fa445195 [#1329] pilorama: Allow to benchmark all tree backends 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:18:01 +03:00
Evgenii Stratonikov
9cbd4271f1 [#1329] services/tree: Implement GetOpLog RPC 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:17:22 +03:00
Evgenii Stratonikov
3cc67db083 [#1419] pilorama: Create new nodes in path if needed 
Consider a node `{FileName: "dir", Attribute: "xxx"}`. In case we add
a new node by path `["dir", "file.txt"]`, create a new intermediate node
with a single attribute.

`GetByPath` now also considers only nodes with a single attribute while building a path.

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:16:16 +03:00
Evgenii Stratonikov
730f14e4eb [#1406] pilorama: Return parent from TreeGetMeta 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:15:52 +03:00
Evgenii Stratonikov
34cab7be82 [#1344] pilorama: Document errors for Get* methods 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:13:39 +03:00
Evgenii Stratonikov
59bd5ac973 [#1344] engine: Log errors in Tree* operations 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:13:32 +03:00
Evgenii Stratonikov
e2c88a9983 [#1344] pilorama: Use require.ErrorIs in tests 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 13:13:27 +03:00
Evgenii Stratonikov
dd7c4385c6 [#1326] services/tree: Implement GetSubTree RPC 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 12:50:13 +03:00
Evgenii Stratonikov
4a65eb7e5f [#1324] engine: Implement Forest interface for storage engine 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 12:47:40 +03:00
Evgenii Stratonikov
cf73feb3f8 [#1324] local_object_storage: Implement tree service backend 
In this commit we implement algorithm for CRDT trees from
https://martin.klepmann.com/papers/move-op.pdf

Each tree is identified by the ID of a container it belongs to
and the tree name itself. Essentially, it is a sequence of operations
which should be applied in chronological order to get a usual tree
representation.

There are 2 backends for now: bbolt database and in-memory.
In-memory backend is here for debugging and will eventually act
as a memory-cache for the on-disk database.

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-07-08 12:47:40 +03:00
Evgenii Stratonikov
633b4e7d2d [#1483] metabase: Add VERSION.md 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-21 17:48:28 +03:00
Evgenii Stratonikov
6f243a2a76 [#1483] metabase: Store version 
The main problem is to distinguish the case of initial initialization
and update from version 0. We can't do this at `Open`, because of
`resync_metabase` flag. Thus, the following approach was taken:
1. During `Open` check whether the metabase was initialized.
2. Check for the version in `Init` or write the new one if the metabase
   is new.
3. Update version in `Reset`.

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-21 17:48:28 +03:00
Evgenii Stratonikov
7df50297cd [#1520] shard: Ignore errors on metabase refill 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-21 17:25:28 +03:00
Evgenii Stratonikov
78ea450c25 [#1502] shard: Process locks on metabase refill 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-21 11:07:26 +03:00
Evgenii Stratonikov
972ca83e23 [#1524] writecache: Add some bolt parameters to the configuration 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-20 17:04:35 +03:00
Evgenii Stratonikov
07e06249d5 [#1524] metabase: Add some bolt parameters to the configuration 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-20 17:04:35 +03:00
Evgenii Stratonikov
81f925d5a0 [#1516] metabase: Optimize ListWithCursor for long listings 
Cache buckets outside of the main loop and allocate memory for the
resulting offset only once.

```
name                        old time/op    new time/op    delta
ListWithCursor/1_item-8       6.45µs ±14%    5.79µs ±11%  -10.24%  (p=0.002 n=10+10)
ListWithCursor/10_items-8     20.9µs ±17%    17.3µs ± 9%  -17.27%  (p=0.000 n=10+10)
ListWithCursor/100_items-8     153µs ±12%     131µs ± 9%  -14.63%  (p=0.000 n=10+10)

name                        old alloc/op   new alloc/op   delta
ListWithCursor/1_item-8       2.31kB ± 0%    1.91kB ± 0%  -17.46%  (p=0.000 n=10+10)
ListWithCursor/10_items-8     6.94kB ± 0%    5.50kB ± 0%  -20.78%  (p=0.000 n=8+8)
ListWithCursor/100_items-8    53.3kB ± 0%    41.5kB ± 0%  -22.18%  (p=0.000 n=10+10)

name                        old allocs/op  new allocs/op  delta
ListWithCursor/1_item-8         40.0 ± 0%      34.0 ± 0%  -15.00%  (p=0.000 n=10+10)
ListWithCursor/10_items-8        121 ± 0%       100 ± 0%  -17.36%  (p=0.000 n=10+10)
ListWithCursor/100_items-8       930 ± 0%       758 ± 0%  -18.49%  (p=0.000 n=10+10)
```

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-15 20:49:41 +03:00
Evgenii Stratonikov
a93373fe71 [#1516] metabase: Cache graveyard buckets in ListWithCursor 
```
name                        old time/op    new time/op    delta
ListWithCursor/1_item-8       6.40µs ±13%    6.45µs ±14%     ~     (p=0.739 n=10+10)
ListWithCursor/10_items-8     30.9µs ±21%    20.9µs ±17%  -32.49%  (p=0.000 n=10+10)
ListWithCursor/100_items-8     274µs ±27%     153µs ±12%  -44.09%  (p=0.000 n=10+10)

name                        old alloc/op   new alloc/op   delta
ListWithCursor/1_item-8       2.26kB ± 0%    2.31kB ± 0%   +2.46%  (p=0.000 n=10+10)
ListWithCursor/10_items-8     10.8kB ± 0%     6.9kB ± 0%  -36.07%  (p=0.000 n=8+8)
ListWithCursor/100_items-8    96.8kB ± 0%    53.3kB ± 0%  -44.98%  (p=0.000 n=10+10)

name                        old allocs/op  new allocs/op  delta
ListWithCursor/1_item-8         39.0 ± 0%      40.0 ± 0%   +2.56%  (p=0.000 n=10+10)
ListWithCursor/10_items-8        192 ± 0%       121 ± 0%  -36.98%  (p=0.000 n=10+10)
ListWithCursor/100_items-8     1.72k ± 0%     0.93k ± 0%  -45.93%  (p=0.000 n=10+10)
```

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>

name                        old time/op    new time/op    delta
ListWithCursor/1_item-8       5.23µs ±19%    5.26µs ±15%     ~     (p=0.853 n=10+10)
ListWithCursor/10_items-8     27.2µs ±15%    18.0µs ±19%  -33.80%  (p=0.000 n=10+10)
ListWithCursor/100_items-8     250µs ±13%     139µs ±15%  -44.27%  (p=0.000 n=10+10)

name                        old alloc/op   new alloc/op   delta
ListWithCursor/1_item-8       1.99kB ± 0%    2.04kB ± 0%   +2.82%  (p=0.000 n=8+8)
ListWithCursor/10_items-8     10.3kB ± 0%     6.4kB ± 0%  -37.83%  (p=0.000 n=8+10)
ListWithCursor/100_items-8    93.9kB ± 0%    50.4kB ± 0%  -46.37%  (p=0.000 n=10+10)

name                        old allocs/op  new allocs/op  delta
ListWithCursor/1_item-8         35.0 ± 0%      36.0 ± 0%   +2.86%  (p=0.000 n=10+10)
ListWithCursor/10_items-8        184 ± 0%       113 ± 0%  -38.59%  (p=0.000 n=10+10)
ListWithCursor/100_items-8     1.67k ± 0%     0.88k ± 0%  -47.29%  (p=0.000 n=10+10)
```

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-15 20:49:41 +03:00
Evgenii Stratonikov
af4db8a73b [#1516] metabase: Cache address key and do not decode address twice 
```
name                        old time/op    new time/op    delta
ListWithCursor/1_item-8       10.6µs ± 1%     6.4µs ±13%  -39.62%  (p=0.000 n=7+10)
ListWithCursor/10_items-8     75.3µs ± 2%    30.9µs ±21%  -58.97%  (p=0.000 n=10+10)
ListWithCursor/100_items-8     726µs ± 2%     274µs ±27%  -62.28%  (p=0.000 n=10+10)

name                        old alloc/op   new alloc/op   delta
ListWithCursor/1_item-8       3.19kB ± 0%    2.26kB ± 0%  -29.21%  (p=0.000 n=10+10)
ListWithCursor/10_items-8     20.7kB ± 0%    10.8kB ± 0%  -47.68%  (p=0.000 n=10+8)
ListWithCursor/100_items-8     196kB ± 0%      97kB ± 0%  -50.65%  (p=0.000 n=7+10)

name                        old allocs/op  new allocs/op  delta
ListWithCursor/1_item-8         55.0 ± 0%      39.0 ± 0%  -29.09%  (p=0.000 n=10+10)
ListWithCursor/10_items-8        346 ± 0%       192 ± 0%  -44.51%  (p=0.000 n=10+10)
ListWithCursor/100_items-8     3.25k ± 0%     1.72k ± 0%  -47.13%  (p=0.000 n=9+10)
```

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-15 20:49:41 +03:00
Evgenii Stratonikov
504f45e9ee [#1516] metabase: Add benchmark for ListWithCursor 
```
name                        time/op
ListWithCursor/1_item-8     10.6µs ± 1%
ListWithCursor/10_items-8   75.3µs ± 2%
ListWithCursor/100_items-8   726µs ± 2%

name                        alloc/op
ListWithCursor/1_item-8     3.19kB ± 0%
ListWithCursor/10_items-8   20.7kB ± 0%
ListWithCursor/100_items-8   196kB ± 0%

name                        allocs/op
ListWithCursor/1_item-8       55.0 ± 0%
ListWithCursor/10_items-8      346 ± 0%
ListWithCursor/100_items-8   3.25k ± 0%
```

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-15 20:49:41 +03:00
Evgenii Stratonikov
f602d05b0a [#1494] *: Fix linter warnings 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-15 12:26:10 +03:00
Evgenii Stratonikov
38772e1a2e writecache: provide timeout to bbolt.Open 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-09 14:19:47 +03:00
Pavel Karpy
010253a97a [#1460] blobovnicza: Do not use pointers as the results 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Pavel Karpy
0e4a1beecf [#1460] blobstor: Do not use pointers as the results 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Pavel Karpy
08bf8a68f1 [#1460] engine: Do not use pointers as the results 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Pavel Karpy
7b6363f4c6 [#1460] shard: Do not use pointers as the results 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Pavel Karpy
9b2932609b [#1460] meta: Do not use pointers as the results 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Pavel Karpy
a580429996 [#1460] meta: Add a benchmark on Get operation 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Pavel Karpy
b0c7b7851a [#1418] blobstor: Do not use pointers as parameters 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Pavel Karpy
14366bbd89 [#1418] engine: Do not use pointers as parameters 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Pavel Karpy
5f57db6bf8 [#1418] shard: Do not use pointers as parameters 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Pavel Karpy
6d4d920bad [#1418] meta: Do not use pointers as parameters 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-06 18:03:12 +03:00
Evgenii Stratonikov
feef9a98f7 [#1462] writecache: remove useless logs 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:30:00 +03:00
Evgenii Stratonikov
2ae7c94cd6 [#1462] *: Remove log.With invocations 
`log.With` is suitable during initialization, but in other places it induces
some overhead, even when branches with logging are not taken.

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:30:00 +03:00
Evgenii Stratonikov
43e776dfb1 [#1462] writecache: Persist objects in batches 
`Update` becomes a botleneck under a heavy load.

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:30:00 +03:00
Evgenii Stratonikov
6ad87e7959 [#1462] writecache: Fill flush marks during startup 
Some of the objects are already flushed, don't do it twice.

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:30:00 +03:00
Evgenii Stratonikov
f2a7503964 [#1462] fstree: Allow to fetch file content lazily 
If we should process address based on some condition, there is no need
to read file content in memory.

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:30:00 +03:00
Evgenii Stratonikov
54d4503701 [#1462] writecache: Rename flushWorkersCount 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:30:00 +03:00
Evgenii Stratonikov
0148209168 [#1462] writecache: Use Timer instead of Ticker in flush 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:30:00 +03:00
Evgenii Stratonikov
5073a37930 [#1433] metabase: Optimize Select 
For some filters we can scan only a subset of keys instead of checking
each key.

```
name                       old time/op  new time/op  delta
Select/string_equal-8      49.3µs ± 4%  11.0µs ± 4%  -77.68%  (p=0.000 n=10+10)
Select/string_not_equal-8  7.01ms ± 5%  7.06ms ±10%     ~     (p=0.971 n=10+10)
Select/common_prefix-8      118µs ± 6%    79µs ± 5%  -33.04%  (p=0.000 n=10+9)
Select/unknown-8           21.3µs ± 4%   3.2µs ± 4%  -84.88%  (p=0.000 n=10+9)
```

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:25:07 +03:00
Evgenii Stratonikov
5c48588c64 [#1433] metabase: Add more tests for Select 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:25:07 +03:00
Evgenii Stratonikov
ea76c989ca [#1433] metabase: Add a benchmark for Select 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 14:25:07 +03:00
Evgenii Stratonikov
b602fff01f [#1463] blobovnicza: Remove pointers from struct members 
Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 13:42:54 +03:00
Evgenii Stratonikov
d9f0ac8909 [#1463] blobovnicza: Determine db size via os.Stat 
Currently we use `(*bbolt.Bucket).Stats().KeyN` for estimating database
size. However, it iterates over all pages in bucket and thus heavily
depends on the bucket size. This commit replaces initial size estimation
with a single `os.Stat` call.

Signed-off-by: Evgenii Stratonikov <evgeniy@nspcc.ru>
 2022-06-03 13:42:54 +03:00
Pavel Karpy
021aa97965 [#1418] blobovnicza: Do not use pointers as parameters 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-03 07:35:17 +03:00
Pavel Karpy
281befec67 [#1418] blobstor: Do not use pointers as parameters 
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
 2022-06-03 07:35:17 +03:00