| opendevreview | Merged openstack/swift master: Change getting major:minor of blkdev https://review.opendev.org/c/openstack/swift/+/887021 | 01:25 |
|---|---|---|
| opendevreview | Merged openstack/swift master: Imported Translations from Zanata https://review.opendev.org/c/openstack/swift/+/886694 | 01:27 |
| *** enick_178 is now known as diablo_rojo | 04:03 | |
| opendevreview | Alistair Coles proposed openstack/swift master: s3api: emit metrics for error responses https://review.opendev.org/c/openstack/swift/+/887267 | 11:28 |
| reid_g | Hello, I have another cluster where a disk went bad, we replaced it, and the handoff partitions are not going back to where they belong. Is there a way we can see if there is a specific file that is causing the reconstructor to fail? | 14:22 |
| reid_g | The server with the handoffs is throwing "Unexpected response: ":ERROR: 0 '15 seconds: /srv/node/d1/.lock'" followed by "60 seconds: missing_check start wait" | 14:23 |
| reid_g | Currently running Ussuri | 14:24 |
| DHE | I have an old Train (2.23.1) system where proxies, at least on EC segments, have a somewhat high probability of jamming up. object servers are returning data to it according to `netstat` but the client never gets anything. not even HTTP headers | 16:15 |
| reid_g | Do the reconstructors go through the proxies to do the ssync? | 17:33 |
| reid_g | timburke I manually tried these modifications https://review.opendev.org/c/openstack/swift/+/886868 and that did not stop the object-replicators/object-reconstructors from blocking the object-server if only the server was restarted. | 17:35 |
| opendevreview | Tim Burke proposed openstack/swift master: versioning: Only list versions container if it seems to exist https://review.opendev.org/c/openstack/swift/+/887345 | 22:58 |
Generated by irclog2html.py 2.17.3 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!