oxidecomputer / oxidecomputer/crucible

What caused so many failures in the 4k record size test on the London cluster

Open
#1,334 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Rust
Stars
260
Forks
34
Avg merge
2d 1h
Merged PRs (30d)
8

Description

@faithanalog ran a test on the Madrid cluster, the details of which are recorded here:

https://github.com/oxidecomputer/artemiscellaneous/tree/main/cru-perf/2024-05-24-4krecordsize-omicron_c2f51e25-crucible_92fe269-propolis_6d7ed9a

There was some trouble getting all 64 VMs to start, and there could be noise here in the logs from those errors
vs. errors that happened under IO load.

The logs from propolis and crucible downstairs are here: /staff/artemis/cru-perf/2024-05-24-4krecordsize-omicron_c2f51e25-crucible_92fe269-propolis_6d7ed9a/logs.tar.gz

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the linked 2024-05-24 4k record-size results and the referenced logs.tar.gz from the Crucible performance run. Separate failures during 64-VM startup from errors recorded under I/O load, then correlate the Propolis and Crucible logs. Done means identifying the cause of the London-cluster failures and documenting which errors are startup noise versus load-related.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.