Commit graph

678 commits

Author SHA1 Message Date
84bbbfaa7b Add multiple headers to object model 2020-07-08 17:33:14 +02:00
a5fa2a136b (WIP) New object table model, TODO: update API calls to use it 2020-07-08 16:46:47 +02:00
86bf4dedac Add support for model migrations 2020-07-08 16:10:53 +02:00
86fb7bbba5 Apply cargo fmt; add trace output when request signature is bad 2020-07-08 13:33:02 +02:00
f22ecb60a8 Update to Hyper 0.13.6 that accepts non-Sync streams in wrap_stream.
Simplifies code and makes it possible to publish on crates.io
2020-07-07 17:15:53 +02:00
3b0b11085e Add versions to dependencies 2020-07-07 14:18:47 +02:00
cc65cdc0fe Add license, description and repository to .toml files 2020-07-07 14:14:58 +02:00
bec26a1312 Rename garage_core to garage_model 2020-07-07 13:59:22 +02:00
f0918b377e Talk about consul discovery in readme 2020-06-30 18:37:37 +02:00
fbe8fe81f2 Add automatic peer discovery from Consul 2020-06-30 18:33:14 +02:00
ade29cf63a Build Docker image 2020-06-30 17:18:42 +02:00
db6f1f35a8 Rename epidemic_factor to epidemic_fanout (that's what it is); complete conf example in readme 2020-06-30 15:03:34 +02:00
c56de7fdd1 Write some README 2020-06-30 14:59:55 +02:00
fa13cf6996 Repair: do not mark deleted when upstream object is not found
With the previous behaviour, repairing could see some data as absent
and decide that the object or version was deleted,
thus going on to delete the version and blocks.
In the case where read_quorum + write_quorum <= replication_factor
however, entries may not yet be returned by the get, thus data would
have been deleted that should hot have been. The new behavior is more
cautious and just skips the entry when the warning is emitted.
2020-05-04 13:30:42 +00:00
b46a7788d1 Implement HTTP ranges in get 2020-05-04 13:09:23 +00:00
16fbb32fd3 Rate limit requests a bit more seriously
droping the slot later (after reading the request response)
means that we aren't freeing our quota slot,
so the maximum number of simultaneous requests now also counts the
response reading phase

TODO next: quotas per rpc destination node, or maybe per datacenter (?)
2020-05-01 19:18:54 +00:00
d867bbcfb5 Implement DeleteObjects 2020-05-01 15:52:35 +00:00
3324971701 Slightly improved S3 compatibility
- ListBucket does not require any of the parameters (delimiter,
    prefix, max-keys, etc)
- URLs are properly percent_decoded
- PutObject and DeleteObject calls now answer correctly
    (empty body, version id in the x-amz-version-id: header)
2020-05-01 14:30:50 +00:00
3686f100b7 Compatibility fixes 2020-04-28 10:35:04 +00:00
0957d0fdfa Work on API 2020-04-28 10:18:14 +00:00
be35cbdce2 update todo 2020-04-26 20:50:23 +00:00
0877a5500c Abort multipart upload 2020-04-26 20:46:33 +00:00
81ecc4999e Implement multipart uploads 2020-04-26 20:39:32 +00:00
1999c0ae51 Update delete code 2020-04-26 19:11:19 +00:00
0a283e4e70 Fix deletion propagation 2020-04-26 18:59:17 +00:00
9cb870f950 Prepare for multipart uploads 2020-04-26 18:55:13 +00:00
ea7e4748ed S3 compatibility: fix bucket listing and HEAD and PUT on bucket 2020-04-26 16:22:33 +00:00
0e49e0c8b5 Add key table to repair procedure 2020-04-26 16:22:22 +00:00
e3203f998b Remove leading / in keys; better delimiter handling 2020-04-24 22:28:15 +02:00
be4831d768 Less verbosity 2020-04-24 19:27:27 +00:00
200f2254a3 TODO update 2020-04-24 19:01:10 +00:00
a52db67954 xml escape 2020-04-24 18:56:00 +00:00
91b2d1fcc1 Some basic S3 functionnality 2020-04-24 18:47:11 +00:00
f2e05986c4 Starting to be S3 compatible 2020-04-24 17:46:52 +00:00
d8f5e643bc Split code for modular compilation 2020-04-24 10:10:01 +00:00
51fb3799a1 Key management admin commands 2020-04-23 20:25:45 +00:00
4ef84a0558 Move repair to separate file 2020-04-23 18:36:12 +00:00
44a1089d95 Make table objects slightly more fool-proof; add key table 2020-04-23 18:16:52 +00:00
c9c6b0dbd4 Reorganize code 2020-04-23 17:05:46 +00:00
01a8acdeec Better error reporting 2020-04-23 16:23:06 +00:00
82f4cd8719 Continue pinging nodes when they are down ; overall better handling of down nodes 2020-04-23 16:06:11 +00:00
2fe82be3bc RPC to ourself do not pass through serialization + HTTPS 2020-04-23 14:40:59 +00:00
37f880bc09 RequestStrategy with possible interruption or not 2020-04-23 13:37:10 +00:00
73574ab43e Fix in rpc_client (see comment in code) 2020-04-22 20:42:23 +00:00
897fafa8db Improvements to block resync queue & worker 2020-04-22 20:32:58 +00:00
2556a1e383 I'm stupid though 2020-04-22 20:06:12 +00:00
231cb32955 Do not delete block if just a single replication error. Write TODO stuff. 2020-04-22 19:25:15 +00:00
8971f34c81 Well they still have to exit when we're exiting though 2020-04-22 17:04:33 +00:00
e8214cb180 Better concurrency:
Use Notify instead of stupid sleep in background worker
Use Semaphore to limit concurrent requests in rpc_client
Make more background tasks cancellable
2020-04-22 16:51:52 +00:00
c0335ac690 Remove a few features in dependencies 2020-04-21 20:37:02 +00:00