Austen
Austen
This patch adds a roachtest to validate the accuracy of the allocation simulator. It collects results of running identical configurations in simulated and real cluster. The collected results are then...
This is a tracking issue for the allocation simulator. ## Why do we need a simulator? > There is an agreement that unit tests and roachtests are useful but not...
`splits/load/sequential/nodes=3` would occasionally flake due to variable request timing between worker threads executing concurrent operations. For example, a later sequence 5 could be evaluated and recorded for load based splitting...
A race could occur when a replica queue and post lease application both attempted to switch the lease type. This race would cause the queue to not process the replica...
When a range with exactly 1 replica is scattered it could only add an additional replica to a valid store, without also removing the existing replica. This left ranges post-scatter...
Previously, scatter processing would only be retried when encountering a snapshot error. Other errors commonly occur, which we expect to be transient and retryable, such as the range descriptor changing...
Backport 1/2 commits from #124284 on behalf of @kvoli. The first commit 1fe25bc3296a1a814e90ec45930acf9ee1fad786 is omitted, as the simulator did not reproduce thrashing on this release. /cc @cockroachdb/release ---- The allocator...
This commit introduces metrics related to stream eval tokens and stream send tokens. Hooking up these metrics to the registry will be in a subsequent commit. There are two separate...
This commit implements `HandleRaftEvent` on the `RangeController`. When `HandleRaftEvent` is called by the `Processor` on the leader, the `RangeController` will perform local replica state management for the range and potentially...
Previously, `server.time_after_store_suspect` was set to 10s, down from the default of 30s in `perturbation` roachtests. It is uncommon for users to alter this cluster setting, let alone decrease it. Restore...