| openstackgerrit | Merged openstack/swift master: probe-tests: Avoid a DuplicateSectionError on py3 https://review.opendev.org/701076 | 00:11 |
|---|---|---|
| openstackgerrit | Merged openstack/swift master: py3: Fix non-ascii chars in staticweb listings https://review.opendev.org/750062 | 00:30 |
| openstackgerrit | Tim Burke proposed openstack/swift master: New proxy logging field for wire status https://review.opendev.org/755639 | 01:01 |
| openstackgerrit | jiasirui proposed openstack/swift master: yaml file start with --- https://review.opendev.org/756419 | 02:13 |
| *** rcernin has quit IRC | 02:45 | |
| *** rcernin has joined #openstack-swift | 02:48 | |
| *** gyee has quit IRC | 02:56 | |
| *** rcernin has quit IRC | 03:01 | |
| *** rcernin has joined #openstack-swift | 03:17 | |
| *** rcernin has quit IRC | 03:22 | |
| *** rcernin has joined #openstack-swift | 03:23 | |
| *** psachin has joined #openstack-swift | 03:41 | |
| *** m75abrams has joined #openstack-swift | 04:10 | |
| *** evrardjp has quit IRC | 04:33 | |
| *** evrardjp has joined #openstack-swift | 04:33 | |
| *** coreycb has quit IRC | 07:20 | |
| *** coreycb has joined #openstack-swift | 07:20 | |
| *** rcernin has quit IRC | 07:39 | |
| *** rpittau|afk is now known as rpittau | 07:41 | |
| *** mikecmpbll has joined #openstack-swift | 08:01 | |
| *** dsariel has joined #openstack-swift | 08:15 | |
| *** dsariel has quit IRC | 08:28 | |
| *** dsariel has joined #openstack-swift | 08:31 | |
| *** mikecmpbll has quit IRC | 10:03 | |
| *** mikecmpbll has joined #openstack-swift | 10:06 | |
| *** rcernin has joined #openstack-swift | 10:20 | |
| *** rcernin has quit IRC | 10:37 | |
| *** dsariel has quit IRC | 11:11 | |
| *** dsariel has joined #openstack-swift | 12:39 | |
| *** dsariel has quit IRC | 13:03 | |
| *** evrardjp has quit IRC | 13:04 | |
| *** mattoliverau has quit IRC | 13:04 | |
| *** evrardjp has joined #openstack-swift | 13:04 | |
| *** dsariel has joined #openstack-swift | 13:09 | |
| *** mattoliverau has joined #openstack-swift | 13:09 | |
| *** tepper.freenode.net sets mode: +v mattoliverau | 13:09 | |
| *** dsariel has quit IRC | 13:58 | |
| *** dsariel has joined #openstack-swift | 13:58 | |
| *** m75abrams has quit IRC | 14:00 | |
| *** rpittau is now known as rpittau|afk | 16:06 | |
| *** psachin has quit IRC | 16:19 | |
| *** mikecmpbll has quit IRC | 16:23 | |
| *** mikecmpbll has joined #openstack-swift | 16:27 | |
| *** dsariel has quit IRC | 17:13 | |
| *** dsariel has joined #openstack-swift | 17:14 | |
| *** mahatic has quit IRC | 17:17 | |
| *** gyee has joined #openstack-swift | 19:12 | |
| *** mikecmpbll has quit IRC | 19:35 | |
| *** mikecmpbll has joined #openstack-swift | 19:39 | |
| *** gmann is now known as gmann_lunch | 20:22 | |
| *** TViernion has quit IRC | 20:32 | |
| *** zamba has quit IRC | 20:32 | |
| *** DHE has quit IRC | 20:33 | |
| *** DHE has joined #openstack-swift | 20:33 | |
| *** zamba has joined #openstack-swift | 20:34 | |
| *** TerianceVi has joined #openstack-swift | 20:34 | |
| mattoliverau | Wife is sick this morn so I might be in and out of the meeting today dealing with kids. | 20:45 |
| timburke | no worries, mattoliverau! hope everyone feels better soon | 20:53 |
| kota_ | morning | 20:58 |
| timburke | meeting time! | 21:01 |
| *** gmann_lunch is now known as gmann | 21:04 | |
| *** openstackgerrit has quit IRC | 22:07 | |
| *** rcernin has joined #openstack-swift | 22:20 | |
| *** hoonetorg has quit IRC | 22:44 | |
| DHE | so I had an idea for a crazy-ish performance improvement. when a service starts it loads the ring files and then forks, so the rings should be shared memory. but if a ring file changes all processes load it independently. correct? | 22:53 |
| *** hoonetorg has joined #openstack-swift | 22:57 | |
| timburke | DHE, yup -- leads to some ballooning memory usage some indeterminate time after restart :-( | 23:09 |
| timburke | i should take a look at https://review.opendev.org/#/c/670674/ again... try to make a shim that looks like a normal ring but actually talks to the service... | 23:10 |
| patchbot | patch 670674 - swift - WIP: Allow ring lookups via a service - 2 patch sets | 23:10 |
| DHE | interesting idea... | 23:11 |
| *** dsariel has quit IRC | 23:20 | |
| *** dsariel has joined #openstack-swift | 23:20 | |
| timburke | oh yeah, DHE: on https://bugs.launchpad.net/swift/+bug/1895739, i've now seen deadlocks still with https://review.opendev.org/#/c/752593/ applied, both when replacing threading._active_limbo_lock and eventlet.patcher.original('threading')._active_limbo_lock | 23:50 |
| openstack | Launchpad bug 1895739 in OpenStack Object Storage (swift) "Proxy server sometimes deadlocks while logging client disconnect" [Undecided,In progress] | 23:50 |
| patchbot | patch 752593 - swift - Replace threading._active_limbo_lock with a re-ent... - 3 patch sets | 23:50 |
| timburke | i'm maybe getting hopeful about some of the iterator cleanup that's happening in https://review.opendev.org/#/c/755639/ though -- if you like, i could get a smaller patch together for you to try | 23:51 |
| *** dsariel has quit IRC | 23:51 | |
| *** dsariel has joined #openstack-swift | 23:51 | |
| patchbot | patch 755639 - swift - New proxy logging field for wire status - 5 patch sets | 23:52 |
| DHE | part of me is considering just making the logging driver non-thread aware. I don't need an ID on the specific thread in my logs | 23:52 |
Generated by irclog2html.py 2.17.2 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!