| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 00:03 |
|---|---|---|
| *** threestrands has joined #openstack-swift | 00:04 | |
| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 00:25 |
| openstackgerrit | Merged openstack/swift master: Make rolling-upgrade job non-voting https://review.opendev.org/721519 | 00:49 |
| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 00:57 |
| openstackgerrit | Tim Burke proposed openstack/swift stable/ussuri: Make rolling-upgrade job non-voting https://review.opendev.org/721756 | 00:58 |
| *** gyee has quit IRC | 01:04 | |
| mattoliverau | oh belated morning, forgot to say it this morn. | 01:13 |
| *** viks____ has joined #openstack-swift | 02:17 | |
| *** psachin has joined #openstack-swift | 03:31 | |
| *** pawan-gupta has joined #openstack-swift | 04:22 | |
| *** djhankb has joined #openstack-swift | 04:34 | |
| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 04:35 |
| *** evrardjp has quit IRC | 04:35 | |
| *** evrardjp has joined #openstack-swift | 04:35 | |
| *** rcernin has quit IRC | 05:24 | |
| *** rcernin has joined #openstack-swift | 06:09 | |
| *** rcernin has quit IRC | 06:10 | |
| *** rcernin has joined #openstack-swift | 06:11 | |
| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 06:16 |
| *** rcernin has quit IRC | 06:25 | |
| *** rcernin has joined #openstack-swift | 06:26 | |
| *** psachin has quit IRC | 06:26 | |
| openstackgerrit | Merged openstack/swift master: sharding: Don't inject shard ranges when user says quit https://review.opendev.org/720786 | 06:33 |
| openstackgerrit | Merged openstack/swift stable/ussuri: Make rolling-upgrade job non-voting https://review.opendev.org/721756 | 06:33 |
| *** psachin has joined #openstack-swift | 06:45 | |
| *** threestrands has quit IRC | 06:53 | |
| *** threestrands has joined #openstack-swift | 06:54 | |
| *** threestrands has quit IRC | 06:55 | |
| *** threestrands has joined #openstack-swift | 06:55 | |
| *** threestrands has quit IRC | 06:56 | |
| *** threestrands has joined #openstack-swift | 06:56 | |
| *** threestrands has quit IRC | 06:58 | |
| *** threestrands has joined #openstack-swift | 06:58 | |
| *** threestrands has quit IRC | 06:59 | |
| *** threestrands has joined #openstack-swift | 06:59 | |
| *** threestrands has quit IRC | 07:01 | |
| *** threestrands has joined #openstack-swift | 07:01 | |
| *** threestrands has quit IRC | 07:02 | |
| *** threestrands has joined #openstack-swift | 07:02 | |
| *** threestrands has quit IRC | 07:04 | |
| *** threestrands has joined #openstack-swift | 07:04 | |
| *** threestrands has quit IRC | 07:05 | |
| *** threestrands has joined #openstack-swift | 07:06 | |
| *** threestrands has quit IRC | 07:07 | |
| *** threestrands has joined #openstack-swift | 07:07 | |
| *** threestrands has quit IRC | 07:08 | |
| *** threestrands has joined #openstack-swift | 07:08 | |
| *** threestrands has quit IRC | 07:10 | |
| *** threestrands has joined #openstack-swift | 07:10 | |
| *** threestrands has quit IRC | 07:11 | |
| *** threestrands has joined #openstack-swift | 07:12 | |
| *** threestrands has quit IRC | 07:13 | |
| *** threestrands has joined #openstack-swift | 07:13 | |
| *** rcernin has quit IRC | 07:13 | |
| *** threestrands has quit IRC | 07:14 | |
| *** threestrands has joined #openstack-swift | 07:14 | |
| *** threestrands has quit IRC | 07:16 | |
| *** threestrands has joined #openstack-swift | 07:16 | |
| *** threestrands has quit IRC | 07:17 | |
| *** threestrands has joined #openstack-swift | 07:18 | |
| *** threestrands has quit IRC | 07:19 | |
| *** threestrands has joined #openstack-swift | 07:19 | |
| *** threestrands has quit IRC | 07:20 | |
| *** threestrands has joined #openstack-swift | 07:21 | |
| *** threestrands has quit IRC | 07:22 | |
| *** threestrands has joined #openstack-swift | 07:22 | |
| *** threestrands has quit IRC | 07:23 | |
| *** threestrands has joined #openstack-swift | 07:24 | |
| *** rpittau|afk is now known as rpittau | 07:24 | |
| *** threestrands has quit IRC | 07:25 | |
| *** threestrands has joined #openstack-swift | 07:25 | |
| *** threestrands has quit IRC | 07:26 | |
| *** threestrands has joined #openstack-swift | 07:27 | |
| *** threestrands has quit IRC | 07:28 | |
| *** threestrands has joined #openstack-swift | 07:28 | |
| *** threestrands has quit IRC | 07:29 | |
| *** threestrands has joined #openstack-swift | 07:30 | |
| *** threestrands has quit IRC | 07:31 | |
| *** threestrands has joined #openstack-swift | 07:31 | |
| *** threestrands has quit IRC | 07:32 | |
| *** threestrands has joined #openstack-swift | 07:33 | |
| *** threestrands has quit IRC | 07:34 | |
| *** threestrands has joined #openstack-swift | 07:34 | |
| *** threestrands has quit IRC | 07:35 | |
| *** threestrands has joined #openstack-swift | 07:36 | |
| *** threestrands has quit IRC | 07:37 | |
| *** threestrands has joined #openstack-swift | 07:37 | |
| *** threestrands has quit IRC | 07:38 | |
| *** threestrands has joined #openstack-swift | 07:39 | |
| *** threestrands has quit IRC | 07:40 | |
| *** threestrands has joined #openstack-swift | 07:40 | |
| *** threestrands has quit IRC | 07:41 | |
| *** threestrands has joined #openstack-swift | 07:41 | |
| *** threestrands has quit IRC | 07:43 | |
| *** threestrands has joined #openstack-swift | 07:43 | |
| *** threestrands has quit IRC | 07:44 | |
| *** threestrands has joined #openstack-swift | 07:45 | |
| *** threestrands has quit IRC | 07:46 | |
| *** threestrands has joined #openstack-swift | 07:46 | |
| *** threestrands has quit IRC | 07:47 | |
| *** threestrands has joined #openstack-swift | 07:47 | |
| *** threestrands has quit IRC | 07:49 | |
| *** threestrands has joined #openstack-swift | 07:49 | |
| *** threestrands has quit IRC | 07:50 | |
| *** threestrands has joined #openstack-swift | 07:51 | |
| *** threestrands has quit IRC | 07:52 | |
| *** threestrands has joined #openstack-swift | 07:52 | |
| *** threestrands has quit IRC | 07:53 | |
| *** threestrands has joined #openstack-swift | 07:54 | |
| *** threestrands has quit IRC | 07:55 | |
| *** threestrands has joined #openstack-swift | 07:55 | |
| *** threestrands has quit IRC | 07:56 | |
| *** threestrands has joined #openstack-swift | 07:57 | |
| *** ccamacho has joined #openstack-swift | 07:57 | |
| *** threestrands has quit IRC | 07:58 | |
| *** threestrands has joined #openstack-swift | 07:58 | |
| *** threestrands has quit IRC | 07:59 | |
| *** threestrands has joined #openstack-swift | 08:00 | |
| *** threestrands has quit IRC | 08:01 | |
| *** threestrands has joined #openstack-swift | 08:01 | |
| *** threestrands has quit IRC | 08:02 | |
| *** threestrands has joined #openstack-swift | 08:02 | |
| *** threestrands has quit IRC | 08:04 | |
| *** threestrands has joined #openstack-swift | 08:04 | |
| *** threestrands has quit IRC | 08:05 | |
| *** threestrands has joined #openstack-swift | 08:06 | |
| *** threestrands has quit IRC | 08:07 | |
| *** threestrands has joined #openstack-swift | 08:07 | |
| *** threestrands has quit IRC | 08:08 | |
| *** tkajinam has quit IRC | 08:15 | |
| *** manuvakery has quit IRC | 09:32 | |
| *** rdejoux has quit IRC | 09:39 | |
| *** rdejoux has joined #openstack-swift | 09:40 | |
| *** dtantsur|afk is now known as dtantsur | 09:42 | |
| *** evrardjp has quit IRC | 09:51 | |
| *** evrardjp has joined #openstack-swift | 09:51 | |
| *** takamatsu has joined #openstack-swift | 10:28 | |
| *** rpittau is now known as rpittau|bbl | 10:42 | |
| *** jv has quit IRC | 11:32 | |
| *** jv has joined #openstack-swift | 11:37 | |
| *** rpittau|bbl is now known as rpittau | 11:50 | |
| *** manuvakery has joined #openstack-swift | 12:04 | |
| *** psachin has quit IRC | 13:14 | |
| *** manuvakery has quit IRC | 14:14 | |
| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 15:00 |
| *** manuvakery has joined #openstack-swift | 15:10 | |
| *** gyee has joined #openstack-swift | 15:11 | |
| timburke | good morning | 15:47 |
| *** rpittau is now known as rpittau|afk | 16:29 | |
| *** evrardjp has quit IRC | 16:35 | |
| *** evrardjp has joined #openstack-swift | 16:35 | |
| *** dtantsur is now known as dtantsur|afk | 16:55 | |
| openstackgerrit | Tim Burke proposed openstack/swift master: dsvm: Enable more middlewares https://review.opendev.org/722120 | 18:56 |
| *** manuvakery has quit IRC | 19:19 | |
| timburke | rledisez, do you guys see https://bugs.launchpad.net/swift/+bug/1719860 sometimes? i'm a little surprised at how often i'm seeing it in this one cluster :-/ | 19:41 |
| openstack | Launchpad bug 1719860 in OpenStack Object Storage (swift) "traceback and client error when concurrent PUTs result in data file removed before being commited" [Medium,Confirmed] | 19:41 |
| openstackgerrit | Tim Burke proposed openstack/swift master: obj: _finalize_durable may succeed even when data file is missing https://review.opendev.org/722128 | 19:44 |
| rledisez | timburke: yes, it took me a longtime to (try to) understand what is going on. I'm still not convinced it's only related to concurrency, but clearly it's one if the issue, and it's frequent | 19:47 |
| rledisez | I think at some point I wrote a workaround for that, like check mtime before cleaning a data file | 19:47 |
| timburke | mmm -- yeah, that'd work too. i was pleasantly surprised at how straightforward what i just wrote was, but maybe given the frequency we don't want the extra listdir()... otoh, stat() isn't free, either, so... *shrug* | 19:50 |
| *** ccamacho has quit IRC | 19:54 | |
| rledisez | at this place, the directory inode should be in cache so we can hope the extra listdir does not do any IO | 20:05 |
| rledisez | as long as it is not a long time after the initial listdir (define long…) | 20:06 |
| timburke | almost meeting time! | 20:49 |
| kota_ | morning | 20:57 |
| seongsoocho | morning | 20:58 |
| alecuyer | hello | 20:58 |
| mattoliverau | Morning | 20:59 |
| mattoliverau | thanks for all the great auto-sharding ideas, I'll dump them in the doc so we can discuss them and not miss them in the solution :) | 21:47 |
| mattoliverau | As for sharding space, we shard in batches. In an ideal world, for a large container we'd shard a few ranges at a time, then replicated them off so we can delete them locally. So extra space is used during sharding, but not double the container size. Unless of course it isn't a large container and can be complely sharded into < shard_batch_size shards. In which case we will get to 2*container. | 21:51 |
| mattoliverau | So ideally it should cost roughly container space + shard_batch_size shard space, so long as replication happens successfully when we're finished with thos batching shards, otherwise they may stick around longer. | 21:52 |
| mattoliverau | ^ thats from memory. | 21:53 |
| mattoliverau | anyway, breakfast time :) | 21:54 |
| timburke | well, we don't double the space *locally* -- looking at the cluster as a *whole*, though... | 21:55 |
| timburke | but that's the whole reason for sharding -- your container layer's lumpy, so some disks are probably pretty full while others are mostly empty | 21:56 |
| timburke | i need to find a way to reload the proxy after making my edits in https://review.opendev.org/#/c/722120/ :-/ | 21:57 |
| patchbot | patch 722120 - swift - dsvm: Enable more middlewares - 1 patch set | 21:57 |
| timburke | oh! i think that also explains my trouble with the service user in https://review.opendev.org/#/c/620189/ ! | 21:58 |
| patchbot | patch 620189 - swift - WIP: swift-dsvm: Create more Keystone users so we ... - 11 patch sets | 21:58 |
| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 22:09 |
| openstackgerrit | Tim Burke proposed openstack/swift master: Add experimental job to upgrade from master https://review.opendev.org/722160 | 22:24 |
| *** rcernin has joined #openstack-swift | 22:31 | |
| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 22:32 |
| *** tkajinam has joined #openstack-swift | 22:54 | |
| openstackgerrit | Merged openstack/swift stable/ussuri: Update TOX_CONSTRAINTS_FILE for stable/ussuri https://review.opendev.org/721215 | 23:14 |
| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 23:18 |
| openstackgerrit | Tim Burke proposed openstack/swift master: WIP: swift-dsvm: Create more Keystone users so we skip fewer tests https://review.opendev.org/620189 | 23:21 |
| openstackgerrit | Tim Burke proposed openstack/swift master: obj: _finalize_durable may succeed even when data file is missing https://review.opendev.org/722128 | 23:59 |
Generated by irclog2html.py 2.15.3 by Marius Gedminas - find it at mg.pov.lt!