Commit message (Collapse) | Author | Age | Files | Lines | ||
---|---|---|---|---|---|---|
... | ||||||
* | Improvements to block resync queue & worker | Alex Auvolat | 2020-04-22 | 1 | -21/+47 | |
| | ||||||
* | I'm stupid though | Alex Auvolat | 2020-04-22 | 1 | -2/+4 | |
| | ||||||
* | Do not delete block if just a single replication error. Write TODO stuff. | Alex Auvolat | 2020-04-22 | 2 | -18/+36 | |
| | ||||||
* | Well they still have to exit when we're exiting though | Alex Auvolat | 2020-04-22 | 3 | -12/+12 | |
| | ||||||
* | Better concurrency: | Alex Auvolat | 2020-04-22 | 10 | -120/+153 | |
| | | | | | | Use Notify instead of stupid sleep in background worker Use Semaphore to limit concurrent requests in rpc_client Make more background tasks cancellable | |||||
* | Remove a few features in dependencies | Alex Auvolat | 2020-04-21 | 2 | -39/+2 | |
| | ||||||
* | Make UUID & Hash Copy and remove some .clone() noise | Alex Auvolat | 2020-04-21 | 12 | -80/+64 | |
| | ||||||
* | Return BadRequest codes for some admin_rpc failure cases | Alex Auvolat | 2020-04-21 | 1 | -7/+10 | |
| | ||||||
* | Make the repair command accept subcommands to not do everything all the time | Alex Auvolat | 2020-04-21 | 3 | -48/+112 | |
| | ||||||
* | Do full sync on node (re)start | Alex Auvolat | 2020-04-21 | 1 | -1/+8 | |
| | ||||||
* | Improve table sync | Alex Auvolat | 2020-04-21 | 2 | -87/+173 | |
| | ||||||
* | Do not insert deletion marker if there is no object to delete | Alex Auvolat | 2020-04-21 | 2 | -8/+29 | |
| | ||||||
* | Add node tags in configuration | Alex Auvolat | 2020-04-21 | 4 | -15/+44 | |
| | ||||||
* | Pretty logging | Alex Auvolat | 2020-04-21 | 14 | -103/+223 | |
| | ||||||
* | Log which workers are doing what | Alex Auvolat | 2020-04-19 | 5 | -16/+25 | |
| | ||||||
* | Implement repair object->version and version->block ref | Alex Auvolat | 2020-04-19 | 3 | -17/+111 | |
| | ||||||
* | Don't do version & block_ref updates in background on deletion | Alex Auvolat | 2020-04-19 | 7 | -46/+56 | |
| | ||||||
* | Implement repair command | Alex Auvolat | 2020-04-19 | 4 | -11/+152 | |
| | ||||||
* | Less output | Alex Auvolat | 2020-04-19 | 1 | -14/+18 | |
| | ||||||
* | More aggressive sync timings & improve other stuff | Alex Auvolat | 2020-04-19 | 13 | -44/+113 | |
| | ||||||
* | Add hostname to node info | Alex Auvolat | 2020-04-19 | 5 | -11/+52 | |
| | ||||||
* | Begin implement bucket management & admin commands | Alex Auvolat | 2020-04-19 | 13 | -55/+433 | |
| | ||||||
* | Add support for fully replicated tables with epidemic dissemination of updates | Alex Auvolat | 2020-04-19 | 5 | -7/+122 | |
| | ||||||
* | Refactor sharding logic; coming next: full replication with epidemic ↵ | Alex Auvolat | 2020-04-19 | 8 | -165/+221 | |
| | | | | dissemination | |||||
* | Reorder imports. | Alex Auvolat | 2020-04-18 | 7 | -11/+18 | |
| | | | | | | | Trying to separate: 1. Stuff for handling the swarm of nodes and generic table data replication 2. Stuff for the object store core application: metadata tables and block management 3. Stuff for the S3 API | |||||
* | Remove proto.rs & move some definitions out of data.rs | Alex Auvolat | 2020-04-18 | 9 | -62/+52 | |
| | ||||||
* | Massive RPC refactoring | Alex Auvolat | 2020-04-18 | 10 | -444/+570 | |
| | ||||||
* | Fix sync: use max root checksum level | Alex Auvolat | 2020-04-17 | 4 | -79/+112 | |
| | ||||||
* | Fix add to resync on incref | Alex Auvolat | 2020-04-17 | 1 | -5/+6 | |
| | ||||||
* | Fix walk_ring_from | Alex Auvolat | 2020-04-17 | 2 | -9/+11 | |
| | ||||||
* | Several resync workers; add delay on retry resync | Alex Auvolat | 2020-04-17 | 2 | -21/+20 | |
| | ||||||
* | Implement missing handler for read_range | Alex Auvolat | 2020-04-17 | 1 | -0/+36 | |
| | ||||||
* | Fix paths :o | Alex Auvolat | 2020-04-17 | 1 | -6/+8 | |
| | ||||||
* | Implement sending blocks to nodes that need them | Alex Auvolat | 2020-04-17 | 5 | -6/+69 | |
| | ||||||
* | Don't send items... | Alex Auvolat | 2020-04-17 | 4 | -40/+89 | |
| | | | | | ...if syncer doesn't need them because he's going to delete the partition anyway. Also, fix block resync queue | |||||
* | Resync block on read error | Alex Auvolat | 2020-04-17 | 1 | -1/+8 | |
| | ||||||
* | Make sync send data both ways | Alex Auvolat | 2020-04-17 | 3 | -25/+59 | |
| | ||||||
* | WIP | Alex Auvolat | 2020-04-17 | 9 | -112/+236 | |
| | | | | | | TODOs: - ensure sync goes both way - finish sending blocks to other nodes when they need them before deleting | |||||
* | Implement getting missing blocks when RC increases | Alex Auvolat | 2020-04-17 | 9 | -140/+326 | |
| | | | | | | | Issue: RC increases also when the block ref entry is first put by the actual client. At that point the client is probably already sending us the block content, so we don't need to do a get... We should add a delay before the task is added or find something to do. | |||||
* | Table range deletion | Alex Auvolat | 2020-04-17 | 5 | -25/+39 | |
| | ||||||
* | Make all requests continue in the background even after we got enough responses. | Alex Auvolat | 2020-04-16 | 5 | -19/+31 | |
| | ||||||
* | Enable debug info in release profile | Alex Auvolat | 2020-04-16 | 1 | -0/+3 | |
| | ||||||
* | Better prints again, and a great question | Alex Auvolat | 2020-04-16 | 2 | -4/+11 | |
| | ||||||
* | Change debug prints a bit | Alex Auvolat | 2020-04-16 | 1 | -10/+10 | |
| | ||||||
* | WIP | Alex Auvolat | 2020-04-16 | 6 | -37/+129 | |
| | ||||||
* | WIP | Alex Auvolat | 2020-04-16 | 3 | -28/+205 | |
| | ||||||
* | Implement ring comparison algorithm | Alex Auvolat | 2020-04-16 | 3 | -13/+142 | |
| | ||||||
* | Begin work on sync... | Alex Auvolat | 2020-04-16 | 9 | -94/+297 | |
| | ||||||
* | Fix table RPC to not be interruptible | Alex Auvolat | 2020-04-12 | 2 | -34/+25 | |
| | ||||||
* | Small refactorings | Alex Auvolat | 2020-04-12 | 7 | -21/+22 | |
| |