| opendevreview | Tim Burke proposed openstack/swift-bench master: Use py3 as the default runtime for tox https://review.opendev.org/c/openstack/swift-bench/+/787082 | 01:20 |
|---|---|---|
| opendevreview | Merged openstack/swift-bench master: Switch to xena jobs https://review.opendev.org/c/openstack/swift-bench/+/741554 | 01:25 |
| opendevreview | Merged openstack/swift-bench master: Use py3 as the default runtime for tox https://review.opendev.org/c/openstack/swift-bench/+/787082 | 01:30 |
| opendevreview | Merged openstack/swift master: recon: refactor common recon names into a common location https://review.opendev.org/c/openstack/swift/+/783997 | 02:10 |
| opendevreview | Tim Burke proposed openstack/swift-bench master: Migrate from testr to stestr https://review.opendev.org/c/openstack/swift-bench/+/798941 | 02:21 |
| opendevreview | Matthew Oliver proposed openstack/swift master: Sharder: Add root_audit overlap stats https://review.opendev.org/c/openstack/swift/+/798994 | 07:17 |
| opendevreview | Alistair Coles proposed openstack/swift master: relinker: tolerate existing tombstone with same X-Timestamp https://review.opendev.org/c/openstack/swift/+/798849 | 10:57 |
| opendevreview | Alistair Coles proposed openstack/swift master: relinker: tolerate existing tombstone with same timestamp https://review.opendev.org/c/openstack/swift/+/798849 | 11:15 |
| *** dviroel|out is now known as dviroel | 11:32 | |
| godog | hi folks, I think I'm running into https://bugs.launchpad.net/swift/+bug/1636663 on swift 2.19, specifically on large multipart uploads on a multi-region cluster. I'd like to get positive confirmation though, I can't find the connection timeouts in logs yet though, should the timeouts be logged ? thank you | 12:44 |
| opendevreview | Alistair Coles proposed openstack/swift master: relinker: tolerate existing tombstone with same timestamp https://review.opendev.org/c/openstack/swift/+/798849 | 14:19 |
| opendevreview | Clay Gerrard proposed openstack/swift master: Do not use epoll in relinker https://review.opendev.org/c/openstack/swift/+/799093 | 15:18 |
| *** dviroel is now known as dviroel|lunch | 16:00 | |
| *** dviroel|lunch is now known as dviroel | 16:28 | |
| timburke | godog, yeah, i'd expect there to be some timeouts in the object-server logs -- something like "container update failed with ... (saving for async update later): Timeout (Xs)" | 17:18 |
| timburke | if you've got swift-recon-cron set up, you could also check the async_pending count in object.recon | 17:21 |
| opendevreview | Tim Burke proposed openstack/swift master: Add some more arm64 non-voting tests https://review.opendev.org/c/openstack/swift/+/793280 | 17:39 |
| godog | timburke: thank you! nothing of sorts in the logs no, and no async_pending reported by swift-recon. I noticed it only with big multipart uploads from Thanos though, I'm also investigating my options to upgrade to 2.26.0 since we have to do that anyways at some point | 18:53 |
| timburke | as we like to say, new swift is best swift :-) | 18:53 |
| godog | hehehe | 18:55 |
| godog | truly looking forward to the upgrade, we have both 2.10 and 2.19 clusters depending on the Debian distribution | 18:55 |
| *** dviroel is now known as dviroel|sfk | 19:00 | |
| *** dviroel|sfk is now known as dviroel|afk | 19:01 | |
| opendevreview | Merged openstack/swift master: bufferedhttp: Tolerate socket being None https://review.opendev.org/c/openstack/swift/+/796548 | 20:16 |
| *** dviroel|afk is now known as dviroel | 20:21 | |
| timburke | thinking some more about https://bugs.launchpad.net/swift/+bug/1927720 -- i'm not sure how the proxy will handle that situation... | 21:38 |
| *** dviroel is now known as dviroel|out | 21:52 | |
| opendevreview | Tim Burke proposed openstack/swift master: AUTHORS/CHANGELOG for 2.28.0 https://review.opendev.org/c/openstack/swift/+/799121 | 22:29 |
| opendevreview | Tim Burke proposed openstack/swift master: utils: Make PipeMutex marginally more robust to "Too many open files" errors https://review.opendev.org/c/openstack/swift/+/753397 | 22:38 |
| opendevreview | Tim Burke proposed openstack/swift master: More PipeMutex/EMFILE robustness https://review.opendev.org/c/openstack/swift/+/799122 | 22:38 |
| timburke | idk if that second one's really worth the trouble -- mostly just trying to get some scratch ideas i had off my machine | 22:39 |
| opendevreview | Tim Burke proposed openstack/swift master: Add an audit watcher to check partition numbers https://review.opendev.org/c/openstack/swift/+/784471 | 22:53 |
Generated by irclog2html.py 2.17.2 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!