Commit graph

624 commits

Author SHA1 Message Date
7f54706b95
Merge branch 'lx-perf-improvements' into netapp-stream-body 2022-09-08 15:50:56 +02:00
d9d199a6c9
Merge branch 'main' into lx-perf-improvements 2022-09-08 15:49:17 +02:00
ceb1f0229a
Move version back into util 2022-09-07 18:36:46 +02:00
f310fce34b
Inject GIT_VERSION even later 2022-09-07 18:30:15 +02:00
06df301de5
Fix merge 2022-09-07 18:16:01 +02:00
8adc654713
Merge branch 'main' into improve-deps 2022-09-07 18:13:27 +02:00
107853334b
Fix build error 2022-09-07 18:10:19 +02:00
1449204439
Add warnings when features are not included in build 2022-09-07 18:02:13 +02:00
2e00809af5
Error messages when system-libs XOR bundled-libs != 1 2022-09-07 17:57:12 +02:00
2559f63e9b
Make all HTTP services optionnal 2022-09-07 17:54:16 +02:00
28d86e7602
Report build features in garage --help 2022-09-07 17:05:21 +02:00
db61f41030
Move GIT_VERSION injection later in build chain to reduce build times 2022-09-07 11:59:56 +02:00
907054775d
Faster copy, better get error message 2022-09-06 22:25:23 +02:00
6b958979bd
Merge branch 'lx-perf-improvements' into netapp-stream-body 2022-09-06 22:13:01 +02:00
c2cc08852b
Reenable node ordering 2022-09-06 19:31:42 +02:00
6f02c36a89
cargo fmt 2022-09-06 17:59:41 +02:00
0f5689c169
Include code from v0.5.1 directly to remove dependencies 2022-09-06 17:52:50 +02:00
1e92e9f782
Disable k2v tests when feature is disabled 2022-09-06 17:29:46 +02:00
431dee050f
Remove opentelemetry-otlp dep in api/ 2022-09-06 17:25:44 +02:00
b886c75450
Make all DB engines optional build features 2022-09-06 17:09:43 +02:00
48ffaaadfc
Bump versions to 0.8.0 (compatibility is broken already) 2022-09-06 16:47:56 +02:00
454d8474ef
Fix clippy 2022-09-06 15:43:50 +02:00
ea36b9ff90 Allow building without Prometheus exporter (/metrics endpoint)
prometheus and opentelemetry-prometheus add 7 extra dependencies in
total and increases the size of the garage binary by ~7 % (with
fat LTO).
2022-09-06 01:15:09 +02:00
e7af006c1c Make OTLP exporter optional via feature "telemetry-otlp"
opentelemetry-otlp add 48 (!) extra dependencies and increases the
size of the garage binary by ~11 % (with fat LTO).
2022-09-06 01:14:47 +02:00
729a910e14
Remove Heed default features 2022-09-05 16:40:13 +02:00
07e6bcde85
Merge branch 'main' into lx-perf-improvements 2022-09-05 12:40:17 +02:00
7511ba5530 Allow linking against system-provided libsqlite
Unfortunately, rusqlite uses the opposite logic for enabling/disabling
bundled libraries to others (libsodium-sys, zstd-sys). Cargo features
are very limited and doesn't allow to enable feature A in a dependency
iff feature B is disabled.

Note, lmdb-rkv-sys doesn't need any special treatment because it
automatically links against system liblmdb if found via pkgconf.

Linux distros should build garage with
`--no-default-features --features system-libs` to disable bundled-libs
and enable system-libs.
2022-09-03 19:15:57 +02:00
a6e40b75ea Add feature "system-libs" to enable linking against system libraries
If this feature is enabled, libsodium-sys and zstd-sys will link
dynamically against system-provided libraries instead of building
and linking statically the bundled (possibly outdated and vulnerable)
copies of them. This feature is intended mainly for linux package
maintainers.
2022-09-03 18:44:34 +02:00
e1751c8a9c
fix clippy 2022-09-02 17:24:26 +02:00
5d4b937a00
Ability to have up to 4 concurrently working resync workers 2022-09-02 17:18:13 +02:00
5e8baa433d
Make BlockManagerLocked fully private again 2022-09-02 16:52:22 +02:00
47be652a1f
block manager: refactor: split resync into separate file 2022-09-02 16:47:15 +02:00
943d76c583
Ability to dynamically set resync tranquility 2022-09-02 15:34:21 +02:00
6226f5ceca
Update to netapp 0.4.5 - fixed ping 2022-09-02 14:33:12 +02:00
13b5f28c7e
Make use of BytesBuf from new Netapp 2022-09-02 13:46:42 +02:00
1ef87ac4cb
cargo fmt 2022-09-02 13:38:29 +02:00
99b532b85b
Apply PRIO_SECONDARY to block data transfers 2022-09-01 16:35:43 +02:00
df094bd807
Less strict timeouts 2022-09-01 16:30:44 +02:00
bc977f9a7a
Update to Netapp with OrderTag support and exploit OrderTags 2022-09-01 12:58:20 +02:00
70231d68b2
Fix bytes_read counter 2022-08-31 19:44:27 +02:00
c9bc9d89de
Merge branch 'lx-perf-improvements' into netapp-stream-body 2022-08-31 17:42:31 +02:00
efbca67ce4
Add env filter to tracing subscriber 2022-08-31 14:39:12 +02:00
44cd98d2e4
Tracing-subscriber: write to stderr 2022-08-31 14:28:17 +02:00
dd5304f6fc
Replace logging crate pretty_env_logger by tracing_subscriber::fmt 2022-08-31 14:24:41 +02:00
322dafc761
Try to fix clippy 2022-08-29 17:32:45 +02:00
1921f4f7e6
Merge branch 'lx-perf-improvements' into netapp-stream-body 2022-08-29 16:45:05 +02:00
ebc20a8798
Merge branch 'main' into lx-perf-improvements 2022-08-29 16:44:13 +02:00
2c7bae935a
Configure structopt to report the right version
By default, structopt reports the value provided by
the env var CARGO_PKG_VERSION, feeded by Cargo when reading
Cargo.toml. However for Garage we use a versioning based on git,
so we often report a version that is behind the real version.
In this commit, we create garage_util::version::garage() that
reports the right version and configure all structopt subcommands
to call this function instead of using the env var.
2022-08-11 10:21:45 +02:00
e935861854
Factor out node request order selection logic & use in manager 2022-07-29 12:25:03 +02:00
68087ee13d
Fix clippy 2022-07-29 12:25:03 +02:00
605a630333
Use streaming in block manager 2022-07-29 12:25:02 +02:00
a35d4da721
update netapp to 0.5 2022-07-29 12:25:02 +02:00
8e7e680afe
First adaptation to WIP netapp with streaming body 2022-07-29 12:25:02 +02:00
16f6a1a65d
fix clippy 2022-07-29 12:24:49 +02:00
ad35b18bb1
Faster chunker 2022-07-29 12:24:49 +02:00
ff4771c36a
cargo fmt 2022-07-29 12:24:48 +02:00
381eb9a5a1
Fix tests 2022-07-29 12:24:48 +02:00
2cad656a03
More make clippy happy 2022-07-29 12:24:48 +02:00
0176da3ad2
Make clippy happy 2022-07-29 12:24:48 +02:00
2f111e6b3d
Performance improvements:
- reduce contention on mutation_lock by having 256 of them
- better lmdb defaults
2022-07-29 12:24:48 +02:00
1b2e1296eb
Compute hashes on dedicated threads 2022-07-29 12:24:44 +02:00
ac03fa7937
Uniformize tracing::* imports (hopefully fixes 32-bit build) 2022-07-15 18:31:19 +02:00
4f38cadf6e Background task manager (#332)
- [x] New background worker trait
- [x] Adapt all current workers to use new API
- [x] Command to list currently running workers, and whether they are active, idle, or dead
- [x] Error reporting
- Optimizations
  - [x] Merkle updater: several items per iteration
  - [ ] Use `tokio::task::spawn_blocking` where appropriate so that CPU-intensive tasks don't block other things going on
- scrub:
  - [x] have only one worker with a channel to start/pause/cancel
  - [x] automatic scrub
  - [x] ability to view and change tranquility from CLI
  - [x] persistence of a few info
- [ ] Testing

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: Deuxfleurs/garage#332
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
2022-07-08 13:30:26 +02:00
aab34bfe54
add delays in k2v test_items_and_indices 2022-07-08 10:41:57 +02:00
fe3fa83de7 Publish k2v-client crate to crates.io (#337)
Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: Deuxfleurs/garage#337
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
2022-07-04 18:27:25 +02:00
b6d59ec19a
Fix poll item when item didn't change 2022-07-04 14:00:02 +02:00
0850bac874 Add poll command to k2v-cli (#335)
Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: Deuxfleurs/garage#335
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
2022-07-04 12:45:32 +02:00
77e3fd6db2 improve internal item counter mechanisms and implement bucket quotas (#326)
- [x] Refactoring of internal counting API
- [x] Repair procedure for counters (it's an offline procedure!!!)
- [x] New counter for objects in buckets
- [x] Add quotas to buckets struct
- [x] Add CLI to manage bucket quotas
- [x] Add admin API to manage bucket quotas
- [x] Apply quotas by adding checks on put operations
- [x] Proof-read

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: Deuxfleurs/garage#326
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
2022-06-15 20:20:28 +02:00
d544a0e0e0
Send CORS headers for all requests 2022-06-13 10:19:52 +02:00
138e13071b
Fix garage_db build on 32-bit systems 2022-06-09 14:55:20 +02:00
b44d3fc796 Abstract database behind generic interface and implement alternative drivers (#322)
- [x] Design interface
- [x] Implement Sled backend
  - [x] Re-implement the SledCountedTree hack ~~on Sled backend~~ on all backends (i.e. over the abstraction)
- [x] Convert Garage code to use generic interface
- [x] Proof-read converted Garage code
- [ ] Test everything well
- [x] Implement sqlite backend
- [x] Implement LMDB backend
- [ ] (Implement Persy backend?)
- [ ] (Implement other backends? (like RocksDB, ...))
- [x] Implement backend choice in config file and garage server module
- [x] Add CLI for converting between DB formats
- Exploit the new interface to put more things in transactions
  - [x] `.updated()` trigger on Garage tables

Fix #284

**Bugs**

- [x] When exporting sqlite, trees iterate empty??
- [x] LMDB doesn't work

**Known issues for various back-ends**

- Sled:
  - Eats all my RAM and also all my disk space
  - `.len()` has to traverse the whole table
  - Is actually quite slow on some operations
  - And is actually pretty bad code...
- Sqlite:
  - Requires a lock to be taken on all operations. The lock is also taken when iterating on a table with `.iter()`, and the lock isn't released until the iterator is dropped. This means that we must be VERY carefull to not do anything else inside a `.iter()` loop or else we will have a deadlock! Most such cases have been eliminated from the Garage codebase, but there might still be some that remain. If your Garage-over-Sqlite seems to hang/freeze, this is the reason.
  - (adapter uses a bunch of unsafe code)
- Heed (LMDB):
  - Not suited for 32-bit machines as it has to map the whole DB in memory.
  - (adpater uses a tiny bit of unsafe code)

**My recommendation:** avoid 32-bit machines and use LMDB as much as possible.

**Converting databases** is actually quite easy. For example from Sled to LMDB:

```bash
cd src/db
cargo run --features cli --bin convert -- -i path/to/garage/meta/db -a sled -o path/to/garage/meta/db.lmdb -b lmdb
```

Then, just add this to your `config.toml`:

```toml
db_engine = "lmdb"
```

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: Deuxfleurs/garage#322
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
2022-06-08 10:01:44 +02:00
ff06d3f082
Fix Content-Type headers for {admin,k2v} errors and admin responses
Fix #315
2022-05-25 17:09:33 +02:00
b2a2d3859f K2V client improvements (#307)
- [x] Better distinguish error types
- [x] Parse error messages received from server
- [x] Remove `src/` folder layer, we don't have that for other crates

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: Deuxfleurs/garage#307
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
2022-05-24 12:48:05 +02:00
382e74c798 First version of admin API (#298)
**Spec:**

- [x] Start writing
- [x] Specify all layout endpoints
- [x] Specify all endpoints for operations on keys
- [x] Specify all endpoints for operations on key/bucket permissions
- [x] Specify all endpoints for operations on buckets
- [x] Specify all endpoints for operations on bucket aliases

View rendered spec at <https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/admin-api/doc/drafts/admin-api.md>

**Code:**

- [x] Refactor code for admin api to use common api code that was created for K2V

**General endpoints:**

- [x] Metrics
- [x] GetClusterStatus
- [x] ConnectClusterNodes
- [x] GetClusterLayout
- [x] UpdateClusterLayout
- [x] ApplyClusterLayout
- [x] RevertClusterLayout

**Key-related endpoints:**

- [x] ListKeys
- [x] CreateKey
- [x] ImportKey
- [x] GetKeyInfo
- [x] UpdateKey
- [x] DeleteKey

**Bucket-related endpoints:**

- [x] ListBuckets
- [x] CreateBucket
- [x] GetBucketInfo
- [x] DeleteBucket
- [x] PutBucketWebsite
- [x] DeleteBucketWebsite

**Operations on key/bucket permissions:**

- [x] BucketAllowKey
- [x] BucketDenyKey

**Operations on bucket aliases:**

- [x] GlobalAliasBucket
- [x] GlobalUnaliasBucket
- [x] LocalAliasBucket
- [x] LocalUnaliasBucket

**And also:**

- [x] Separate error type for the admin API (this PR includes a quite big refactoring of error handling)
- [x] Add management of website access
- [ ] Check that nothing is missing wrt what can be done using the CLI
- [ ] Improve formatting of the spec
- [x] Make sure everyone is cool with the API design

Fix #231
Fix #295

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: Deuxfleurs/garage#298
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
2022-05-24 12:16:39 +02:00
64c193e3db Add a K2V client library and CLI (#303)
lib.rs could use getting split in modules, but I'm not sure how exactly

Co-authored-by: trinity-1686a <trinity@deuxfleurs.fr>
Reviewed-on: Deuxfleurs/garage#303
Co-authored-by: trinity-1686a <trinity.pointard@gmail.com>
Co-committed-by: trinity-1686a <trinity.pointard@gmail.com>
2022-05-18 22:24:09 +02:00
c692f55d5c
K2V: Fix end parameter and add tests (fix #305) 2022-05-17 11:50:23 +02:00
7b474855e3
Make background runner terminate correctly 2022-05-17 11:38:31 +02:00
5768bf3622 First implementation of K2V (#293)
**Specification:**

View spec at [this URL](https://git.deuxfleurs.fr/Deuxfleurs/garage/src/branch/k2v/doc/drafts/k2v-spec.md)

- [x] Specify the structure of K2V triples
- [x] Specify the DVVS format used for causality detection
- [x] Specify the K2V index (just a counter of number of values per partition key)
- [x] Specify single-item endpoints: ReadItem, InsertItem, DeleteItem
- [x] Specify index endpoint: ReadIndex
- [x] Specify multi-item endpoints: InsertBatch, ReadBatch, DeleteBatch
- [x] Move to JSON objects instead of tuples
- [x] Specify endpoints for polling for updates on single values (PollItem)

**Implementation:**

- [x] Table for K2V items, causal contexts
- [x] Indexing mechanism and table for K2V index
- [x] Make API handlers a bit more generic
- [x] K2V API endpoint
- [x] K2V API router
- [x] ReadItem
- [x] InsertItem
- [x] DeleteItem
- [x] PollItem
- [x] ReadIndex
- [x] InsertBatch
- [x] ReadBatch
- [x] DeleteBatch

**Testing:**

- [x] Just a simple Python script that does some requests to check visually that things are going right (does not contain parsing of results or assertions on returned values)
- [x] Actual tests:
  - [x] Adapt testing framework
  - [x] Simple test with InsertItem + ReadItem
  - [x] Test with several Insert/Read/DeleteItem + ReadIndex
  - [x] Test all combinations of return formats for ReadItem
  - [x] Test with ReadBatch, InsertBatch, DeleteBatch
  - [x] Test with PollItem
  - [x] Test error codes
- [ ] Fix most broken stuff
  - [x] test PollItem broken randomly
  - [x] when invalid causality tokens are given, errors should be 4xx not 5xx

**Improvements:**

- [x] Descending range queries
  - [x] Specify
  - [x] Implement
  - [x] Add test
- [x] Batch updates to index counter
- [x] Put K2V behind `k2v` feature flag

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: Deuxfleurs/garage#293
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
2022-05-10 13:16:57 +02:00
def78c5e6f
Update netapp to 0.4.4, fix #300 2022-05-09 12:08:47 +02:00
277a20ec44 Fix layout show to not show changes when there are no changes (#297)
fixes #295, partially

Co-authored-by: Alex Auvolat <alex@adnab.me>
Reviewed-on: Deuxfleurs/garage#297
Co-authored-by: Alex <alex@adnab.me>
Co-committed-by: Alex <alex@adnab.me>
2022-05-09 11:14:55 +02:00
617f28bfa4
Correct small formatting issue 2022-05-05 14:21:57 +02:00
948ff93cf1 Corrected the warnings and errors issued by cargo clippy 2022-05-01 16:05:39 +02:00
2aeaddd5e2
Apply cargo fmt 2022-05-01 09:57:05 +02:00
c1d1646c4d
Change the way new layout assignations are computed.
The function now computes an optimal assignation (with respect to partition size) that minimizes the distance to the former assignation, using flow algorithms.

This commit was written by Mendes Oulamara <mendes.oulamara@pm.me>
2022-05-01 09:54:19 +02:00
c9ef3e461b
fix clippy 2022-04-19 12:50:40 +02:00
c93008d333
Prettier code for defragmentation 2022-04-19 12:50:40 +02:00
e5341ca47b
Defragmentation in UploadPartCopy: first pass (not pretty but it compiles) 2022-04-19 12:50:36 +02:00
a4f9f19ac3 remove size limitation in UploadPartCopy (#280)
This removes the >1mb s3_copy restriction.

This restriction doesn't seem to be documented anywhere (I could be wrong). It also causes some software to fail (such as #248).

Co-authored-by: Rob Landers <landers.robert@gmail.com>
Reviewed-on: Deuxfleurs/garage#280
Co-authored-by: withinboredom <landers.robert@gmail.com>
Co-committed-by: withinboredom <landers.robert@gmail.com>
2022-04-19 12:49:43 +02:00
5d404dcd54
Add missing opentelemetry features 2022-04-08 14:21:04 +02:00
94f1e48fff Update to netapp 0.4.2 (a tiny fix) 2022-04-07 11:50:03 +02:00
cb5836d53c Bring maximum exponential backoff time down from 16h to 1h 2022-04-07 11:49:29 +02:00
0091002ef2
New replication modes and their documentation 2022-03-28 16:26:04 +02:00
8f9cf3a5d1
fix a clippy lint 2022-03-28 15:48:55 +02:00
913f7754bb
Add blocks in errored state to garage stats 2022-03-28 15:47:23 +02:00
42dde54126
Log admin GET requests at debug level instead of info
to reduce noise in logs
2022-03-28 15:46:52 +02:00
9d0ed78887 Add feature flag for Kubernetes discovery 2022-03-24 16:57:43 +01:00
509d256c58
Make layout optimization work in relative terms 2022-03-24 15:27:14 +01:00
2814d41842
Allow garage layout assign to assign to several nodes at once 2022-03-24 15:27:13 +01:00
7e0e2ffda2
Slight change and add comment to layout assignation algo 2022-03-24 15:27:13 +01:00
413ab0eaed
Small change to partition assignation algorithm
This change helps ensure that nodes for each partition are spread
over all datacenters, a property that wasn't ensured previously
when going from a 2 DC deployment to a 3 DC deployment
2022-03-24 15:27:10 +01:00