Commit graph

779 commits

Author SHA1 Message Date
826294209b [] services/object: Remove nmSrc wrapper
It calls a single method from source without any processing.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-03-01 15:29:54 +03:00
eb48a5bb33 [] services/object: Remove useless helpers
We have lots of small _private_ methods on `execCtx` whose sole purpose
is to just return a struct field.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-03-01 15:29:54 +03:00
6925fb4c59 [] node: Use typed HRW methods
Update HRW lib and use typed HRW methods to sort shards and nodes

Signed-off-by: Dmitrii Stepanov <d.stepanov@yadro.com>
2023-02-28 13:36:25 +03:00
73bb590cb1 [] node: Use pool_size_local and separate pool for local puts
Signed-off-by: Alejandro Lopez <a.lopez@yadro.com>
2023-02-22 13:43:19 +03:00
cb5468abb8 [] node: Replace interface{} with any
Signed-off-by: Alejandro Lopez <a.lopez@yadro.com>
2023-02-21 16:47:07 +03:00
22f3c7d080 [] Reload config for pprof and metrics on SIGHUP
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2023-02-20 13:53:27 +03:00
2567f8020e [] services/object: Do not assemble object with TTL=1
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-02-20 13:53:27 +03:00
Pavel Karpy
901d62567d [] node: Broadcast link objects
It boosts object assembling by an _average_ container node.

Signed-off-by: Pavel Karpy <p.karpy@yadro.com>
2023-02-17 11:58:27 +03:00
cb016d53a6 [] Fix comments and error messages
Signed-off-by: Stanislav Bogatyrev <s.bogatyrev@yadro.com>
2023-02-06 17:41:14 +03:00
c761a95eef [] Fix project name in control service
Signed-off-by: Stanislav Bogatyrev <s.bogatyrev@yadro.com>
2023-02-06 17:41:14 +03:00
d65a95a2c6 [] pilorama: Remove LogMove struct
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-01-25 15:31:47 +03:00
46c62be7e8 [] Fix linter issues
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-01-25 15:31:47 +03:00
67c97c6804 [] services/tree: Drop messages not in queue
Currently, under high load clients are blocked on channel send
and the number of goroutines can increase indefinitely.
In this commit we drop replication messages if send/recv queue is full
and rely on a background synchronization.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-01-25 15:31:47 +03:00
0d8366f475 [] object/acl: Return status error for expired session token
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-01-25 15:31:47 +03:00
Evgenii Stratonikov
6efa93be0a [] services/tree: Return Apply result asyncronously
Signed-off-by: Evgenii Stratonikov <evgeniy@morphbits.ru>
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-01-25 15:31:47 +03:00
554b85411f [] services/object: Log service error with INFO level
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-01-25 15:31:47 +03:00
3d1d2ee7b1 [] Regenerate proto files
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2023-01-12 08:55:47 +03:00
f0be0befc5 [] services/object_manager: Use generic LRU cache
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-31 23:04:06 +03:00
1b3374ac7f [] services/tree: User generic LRU cache
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-31 23:04:06 +03:00
8f61cc1dcc [] policer: Use generic LRU client
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-31 23:04:06 +03:00
6f5edac730 [] network/cache: Do not reconnect to failed clients immediately
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
b4e90cdf51 [] pilorama: Optimize TreeApply when used for synchronization
Because synchronization _most likely_ will have apply already existing
operations, it is much faster to check their presence in a read
transaction. However, always doing this will degrade the perfomance
for normal `Apply`. And, let's be honest, it is already not good.
Thus we add a separate parameter which specifies whether this logic is
enabled.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
f9fcd85363 [] services/tree: Remember starting height for the synchronization
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
06137dbf8e [] services/tree: Do not export synchronizeAllTrees
It is used only privately.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
c299b98afe [] services/tree: Parallelize synchronization
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
de9957e076 [] services/tree: Always synchronize all containers
In case of split-brain we must synchronize everything.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
Pavel Karpy
6a4e5e6f0a [] node: Try node's private key if dynamic token fetching failed
`GETRANGEHASH` request spawns `GETRANGE` requests if an object could not be
found locally. If the original request contains session, it can be static
and, therefore, fetching session key can not be performed successfully.
As the best effort a node could request object's range with its own key.

Signed-off-by: Pavel Karpy <p.karpy@yadro.com>
2022-12-30 11:07:35 +03:00
Pavel Karpy
86a4fba571 [] node: Clarify KeyStorage.GetKey method
Actualize the doc, fix API status error return.

Signed-off-by: Pavel Karpy <p.karpy@yadro.com>
2022-12-30 11:07:35 +03:00
Evgenii Stratonikov
04b5ec759b [] object/put: Use sync.Pool for temporary payloads
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
9e0decd12d [] services/tree: Close connection after the syncronization
There was a goroutine leak here.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
Pavel Karpy
306609030a [] node: Add tree replication timeout configuration
Signed-off-by: Pavel Karpy <p.karpy@yadro.com>
2022-12-30 11:07:35 +03:00
3bb5a320d7 [] services/tree: Do not log an error when synchronizing container of 1 node
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
387d1e2977 [] services/tree: Randomize node order for synchronization
Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
b207dc424f [] policer: Reduce default cache size
We use cache to avoid policing the same object multiple times in a short
time span (< 30 seconds). If we have 200_000 objects in a blobstor, it is a bit useless
-- if it takes 1 second to process an object and we have `replicator.pool_size: 20`
in config, the next iteration will happen in 10_000 second which is much
larger than 30 second. However we still consume a lot of memory, so it
makes sense to use saner default.

Signed-off-by: Evgenii Stratonikov <e.stratonikov@yadro.com>
2022-12-30 11:07:35 +03:00
Pavel Karpy
b413094704 [] node: Fix collecting child objects
Stop child objects collection if the last returned object (the most "left"
object in the collected chain) starts exactly from the `GETRANGE`'s `from`
value.

Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
2022-12-30 11:07:35 +03:00
Pavel Karpy
350eecfa13 [] node: Do not allow GETRANGE requests with zero length
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
2022-12-30 11:07:35 +03:00
Pavel Karpy
923f84722a Move to frostfs-node
Signed-off-by: Pavel Karpy <p.karpy@yadro.com>
2022-12-28 15:04:29 +03:00
Pavel Karpy
d54022eacc [] node: Do not send chunk twice on request forwarding
That could happen if a node forwards request to a node that closed the
connection during the original object stream.

Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
2022-12-02 11:27:48 +03:00
Evgenii Stratonikov
bd25db5d4a [] metrics: Use separate metrics for success/failed requests
Signed-off-by: Evgenii Stratonikov <evgeniy@morphbits.ru>
2022-12-01 14:18:10 +03:00
Evgenii Stratonikov
e21c472dc7 [] services/object: Increase put_req_count after the request is processed
As it is specified in metrics description.

Signed-off-by: Evgenii Stratonikov <evgeniy@morphbits.ru>
2022-12-01 14:18:10 +03:00
Pavel Karpy
51963abce7 [] node: Fix errors comments in the Put service
Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
2022-11-30 16:58:52 +03:00
Evgenii Stratonikov
660c38d07e [] services/policer: Use a proper key for object cache
Signed-off-by: Evgenii Stratonikov <evgeniy@morphbits.ru>
2022-11-19 11:01:04 +03:00
Evgenii Stratonikov
1779664644 [] services/policer: Fix panic in shardPolicyWorker
```
2022/11/15 08:40:56 worker exits from a panic: runtime error: index out of range [0] with length 0
2022/11/15 08:40:56 worker exits from panic: goroutine 1188 [running]:
github.com/panjf2000/ants/v2.(*goWorker).run.func1.1()
	github.com/panjf2000/ants/v2@v2.4.0/worker.go:58 +0x10c
panic({0x1042b60, 0xc0015ae018})
	runtime/panic.go:1038 +0x215
github.com/nspcc-dev/neofs-node/pkg/services/policer.(*Policer).shardPolicyWorker.func1()
	github.com/nspcc-dev/neofs-node/pkg/services/policer/process.go:65 +0x366
github.com/panjf2000/ants/v2.(*goWorker).run.func1()
	github.com/panjf2000/ants/v2@v2.4.0/worker.go:68 +0x97
created by github.com/panjf2000/ants/v2.(*goWorker).run
	github.com/panjf2000/ants/v2@v2.4.0/worker.go:48 +0x68
```

Signed-off-by: Evgenii Stratonikov <evgeniy@morphbits.ru>
2022-11-19 11:01:04 +03:00
9a20498f34 [] Removing all trees by container ID if tree ID is empty in pilorama.Forest.TreeDrop
Signed-off-by: Anton Nikiforov <an.nikiforov@yadro.com>
2022-11-19 11:01:04 +03:00
Pavel Karpy
634792077e [] node: Store lock object on every container node
Includes extending listing methods in the Storage Engine with object types.
It allows tuning replication/policer algorithms: container nodes do
not remove `LOCK` objects as redundant and try to fulfill `LOCK` placement
on the ohter container nodes.

Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
2022-11-19 11:01:04 +03:00
Pavel Karpy
d5a14041e0 [] node: Do not attach tokens in the assembly process
A container node is expected to have full "get" access to assemble the
object.
A non-container node is expected to forward any request to a container node.
Any token is expected to be issued for an original request sender not for a
node so any new request is invalid by design with that token.

Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
2022-11-19 11:01:04 +03:00
Pavel Karpy
fd61bdadcb [] node: Attach original meta to the spawned requests
Do not lose meta information of the original requests: cache session and
bearer tokens of the original request b/w a new generated ones. Middle
request wrappers should not contain any meta information, since it is
useless (e.g. ACL service checks only the original tokens).

Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
2022-11-19 11:01:04 +03:00
Pavel Karpy
481b48b942 [] node: Check session token's NBF and IAT
ACL service did not check "Not Valid Before" and "Issued At" claims.

Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
2022-11-19 11:01:04 +03:00
Pavel Karpy
aadd2ad050 [] node: Do not wrap malformed request errors
After presenting request statuses on the API level, all the errors are
unwrapped before sending to the caller side. It led to a losing invalid
request's context.

Signed-off-by: Pavel Karpy <carpawell@nspcc.ru>
2022-11-19 11:01:04 +03:00
Evgenii Stratonikov
2522d924b9 [] services/object: Fix concurrent map writes in traverser
```
fatal error: concurrent map writes

goroutine 4337 [running]:
github.com/nspcc-dev/neofs-node/pkg/services/object/put.(*traversal).submitProcessed(...)
        github.com/nspcc-dev/neofs-node/pkg/services/object/put/distributed.go:78
github.com/nspcc-dev/neofs-node/pkg/services/object/put.(*distributedTarget).iteratePlacement.func1()
        github.com/nspcc-dev/neofs-node/pkg/services/object/put/distributed.go:198 +0x265
github.com/panjf2000/ants/v2.(*goWorker).run.func1()
        github.com/panjf2000/ants/v2@v2.4.0/worker.go:68 +0x97
created by github.com/panjf2000/ants/v2.(*goWorker).run
        github.com/panjf2000/ants/v2@v2.4.0/worker.go:48 +0x65
```

Signed-off-by: Evgenii Stratonikov <evgeniy@morphbits.ru>
2022-11-19 11:01:04 +03:00