Wednesday, 2021-01-06

*** jmasud has joined #openstack-meeting00:06
*** rubasov has quit IRC00:12
*** jmasud has quit IRC00:16
*** jmasud has joined #openstack-meeting00:16
*** jmasud has quit IRC00:20
*** tosky has quit IRC00:23
*** martial has quit IRC00:25
*** jmasud has joined #openstack-meeting00:48
*** lifeless has quit IRC00:53
*** lifeless has joined #openstack-meeting00:54
*** jmasud has quit IRC01:21
*** jmasud has joined #openstack-meeting01:21
*** gyee has quit IRC01:25
*** jmasud has quit IRC01:29
*** jmasud has joined #openstack-meeting01:30
*** jmasud has quit IRC01:30
*** jmasud has joined #openstack-meeting01:53
*** rubasov has joined #openstack-meeting01:59
*** jmasud has quit IRC02:05
*** jmasud has joined #openstack-meeting02:10
*** macz_ has joined #openstack-meeting02:12
*** rh-jelabarre has quit IRC02:29
*** jmasud has quit IRC02:36
*** armax has quit IRC03:12
*** psachin has joined #openstack-meeting03:30
*** manpreet has joined #openstack-meeting03:33
*** armax has joined #openstack-meeting04:11
*** armax has quit IRC04:15
*** ociuhandu has joined #openstack-meeting05:08
*** ociuhandu has quit IRC05:13
*** jmasud has joined #openstack-meeting05:31
*** evrardjp has quit IRC05:33
*** evrardjp has joined #openstack-meeting05:33
*** macz_ has quit IRC05:45
*** mvalsecc has joined #openstack-meeting06:57
*** jmasud has quit IRC07:02
*** dklyle has quit IRC07:46
*** macz_ has joined #openstack-meeting07:46
*** macz_ has quit IRC07:50
*** rpittau|afk is now known as rpittau08:01
*** mvalsecc has quit IRC08:06
*** ociuhandu has joined #openstack-meeting09:34
*** ricolin has joined #openstack-meeting09:41
*** macz_ has joined #openstack-meeting09:47
*** macz_ has quit IRC09:52
*** slaweq has joined #openstack-meeting09:55
*** ociuhandu has quit IRC09:57
*** e0ne has joined #openstack-meeting09:58
*** ociuhandu has joined #openstack-meeting10:02
*** slaweq has quit IRC10:38
*** rfolco has joined #openstack-meeting10:43
*** jmasud has joined #openstack-meeting10:46
*** e0ne has quit IRC11:16
*** ricolin has quit IRC11:17
*** cmart has quit IRC11:20
*** cmart has joined #openstack-meeting11:27
*** zaneb has quit IRC11:44
*** zaneb has joined #openstack-meeting11:48
*** ociuhandu has quit IRC11:59
*** ociuhandu has joined #openstack-meeting12:00
*** ociuhandu has quit IRC12:05
*** tosky has joined #openstack-meeting12:15
*** jmasud has quit IRC12:17
*** lpetrut has joined #openstack-meeting12:17
*** slaweq has joined #openstack-meeting12:17
*** ociuhandu has joined #openstack-meeting12:26
*** ociuhandu has joined #openstack-meeting12:27
*** ociuhandu has quit IRC12:28
*** ociuhandu has joined #openstack-meeting12:29
*** ociuhandu has quit IRC12:35
*** e0ne has joined #openstack-meeting12:38
*** ociuhandu has joined #openstack-meeting12:51
*** ociuhandu has quit IRC13:02
*** ociuhandu has joined #openstack-meeting13:07
*** falencastro has quit IRC13:10
*** ociuhandu has quit IRC13:12
*** slaweq has quit IRC13:15
*** ociuhandu has joined #openstack-meeting13:33
*** rosmaita has left #openstack-meeting13:34
*** ociuhandu has quit IRC13:37
*** ricolin has joined #openstack-meeting13:41
*** ociuhandu has joined #openstack-meeting13:55
*** e0ne has quit IRC13:56
*** rh-jelabarre has joined #openstack-meeting14:00
*** jeremyfreudberg has left #openstack-meeting14:08
*** TrevorV has joined #openstack-meeting14:37
*** dklyle has joined #openstack-meeting15:26
*** armax has joined #openstack-meeting15:27
*** lpetrut has quit IRC15:27
*** ociuhandu has quit IRC15:34
*** spotz has quit IRC15:44
*** ociuhandu has joined #openstack-meeting15:46
*** ociuhandu has quit IRC15:56
*** mlavalle has joined #openstack-meeting16:01
*** macz_ has joined #openstack-meeting16:10
*** macz_ has quit IRC16:10
*** macz_ has joined #openstack-meeting16:11
*** jamesden_ is now known as jamesdenton16:46
*** gyee has joined #openstack-meeting16:50
*** ociuhandu has joined #openstack-meeting16:51
*** ociuhandu has quit IRC16:52
*** ociuhandu has joined #openstack-meeting16:52
*** ircuser-1 has joined #openstack-meeting17:20
*** psachin has quit IRC17:23
*** jmasud has joined #openstack-meeting17:26
*** ociuhandu has joined #openstack-meeting17:27
*** ociuhandu has quit IRC17:33
*** rpittau is now known as rpittau|afk17:43
*** ociuhandu has joined #openstack-meeting19:13
*** bnemec has quit IRC19:18
*** bnemec has joined #openstack-meeting19:24
*** ociuhandu has quit IRC19:26
*** bnemec has quit IRC19:30
*** bnemec has joined #openstack-meeting19:32
*** bnemec has quit IRC19:37
*** bnemec has joined #openstack-meeting19:39
*** jamesmcarthur has joined #openstack-meeting19:41
*** jamesmcarthur has quit IRC19:57
*** dsariel has joined #openstack-meeting20:04
*** jamesmcarthur has joined #openstack-meeting20:04
*** jamesmcarthur has quit IRC20:09
*** ociuhandu has joined #openstack-meeting20:17
*** ociuhandu has quit IRC20:18
*** ociuhandu has joined #openstack-meeting20:19
*** ociuhandu has joined #openstack-meeting20:20
*** ociuhandu has quit IRC20:29
*** jamesmcarthur has joined #openstack-meeting20:31
*** ociuhandu has joined #openstack-meeting20:34
*** jamesmcarthur has quit IRC20:40
*** jamesmcarthur has joined #openstack-meeting20:41
*** jamesmcarthur has quit IRC20:42
*** ociuhandu has quit IRC20:43
*** jmasud has quit IRC20:45
*** jamesmcarthur has joined #openstack-meeting20:48
*** ociuhandu has joined #openstack-meeting20:56
*** alecuyer has joined #openstack-meeting20:58
*** jmasud has joined #openstack-meeting20:58
*** zaitcev has joined #openstack-meeting20:59
*** acoles has joined #openstack-meeting21:00
timburke#startmeeting swift21:00
openstackMeeting started Wed Jan  6 21:00:21 2021 UTC and is due to finish in 60 minutes.  The chair is timburke. Information about MeetBot at http://wiki.debian.org/MeetBot.21:00
openstackUseful Commands: #action #agreed #help #info #idea #link #topic #startvote.21:00
*** openstack changes topic to " (Meeting topic: swift)"21:00
openstackThe meeting name has been set to 'swift'21:00
timburkewho's here for the swift meeting?21:00
kota_o/21:00
acoleso/21:00
seongsoochoo/21:00
rledisezhi! o/21:01
alecuyero/21:01
zaitcevo/21:01
mattoliverauo/21:01
timburkeas usual, the agenda's at https://wiki.openstack.org/wiki/Meetings/Swift21:01
clayg0/21:02
timburkefirst up21:02
timburke#topic happy new year21:02
*** openstack changes topic to "happy new year (Meeting topic: swift)"21:02
timburkehope everyone had a good break for the end of the year21:02
timburkewe've done a lot of great stuff this last year, and i'm sure this coming year will be great, too :-)21:03
*** ociuhandu has quit IRC21:03
timburkebut... there's also some stuff that's not so great21:03
mattoliverau2020 is finally over, may 2021 be less 2020y :P21:03
timburke#topic stable gates21:04
*** openstack changes topic to "stable gates (Meeting topic: swift)"21:04
timburkemattoliverau, so far... that's not looking great. but we should always be hopeful!21:04
timburkeso for about the past month we've had broken stable gates21:05
timburkea lot of fixes have landed to resolve the bandit troubles (on pike, queens, and rocky, and a slightly different tack tacken for victoria)21:07
timburkeand is seems like we've got fixes for stein and train, though they're currently held up on some devstack patches21:07
timburke#link https://review.opendev.org/c/openstack/swift/+/76621421:07
timburke#link https://review.opendev.org/c/openstack/swift/+/76648921:08
timburkewhich depend on21:08
timburke#link https://review.opendev.org/c/openstack/devstack/+/76825621:08
timburke#link https://review.opendev.org/c/openstack/devstack/+/76825721:08
claygAmazing work Tim!  🙏. Do you need any reviews or anything we can do to help?21:10
timburkei tried applying a similar fix for ussuri as was used for r-t21:10
timburke#link https://review.opendev.org/c/openstack/swift/+/76943921:10
timburkebut there seems to be some trouble with grenade21:11
timburkei'll keep working at it, will keep folks updated21:11
timburkeclayg, thanks -- i'm not sure there *is* much to be done at this point, unless someone else would like to become the stable-branch champion. i'll keep trying to make it work, but there's other stuff i want to get done, too ;-)21:13
timburke#topic OpenStack Xena21:13
*** openstack changes topic to "OpenStack Xena (Meeting topic: swift)"21:13
timburkewe have a new release name!21:13
timburke#link http://lists.openstack.org/pipermail/openstack-discuss/2020-December/019537.html21:13
mattoliverauI wonder if we can add the swift core group to swift stable, is there still a stable team?21:14
mattoliverauNice I used to work on an opensource project called Xena, so this take me back.. let all the warrior princess memes begin :P21:14
timburkethere is a separate swift-stable-maint group; if anyone else would like to join it, review some backports and i'd be happy to propose you be added to it21:15
timburkein general, i feel like the problem isn't review bandwidth, though; mostly a matter of putting in time to make sure things still work *shrug*21:16
timburkebut speaking of new releases...21:17
timburke#topic swift 2.27.021:17
*** openstack changes topic to "swift 2.27.0 (Meeting topic: swift)"21:17
claygwe're only at 2.26.0.6 - it hasn't been *that* long since a release 🤷‍♂️21:18
timburkei feel like we've landed a good bit of stuff lately, and we should probably do a fresh release soon21:18
*** jmasud has quit IRC21:19
timburkewe've added audit watchers, improved waterfall ec, improved logging, fixed some py3 issues, added a new option to deal with libec upgrades, ...21:20
clayg💪 :shipit:21:21
timburkeso i'm going to work on getting some release notes up in the next week or two; if you know of anything else that really should land for the next release, let me know and i'll try to get it reviewed!21:21
claygshard range caching (spoiler!!!)21:21
timburke(or add it to https://wiki.openstack.org/wiki/Swift/PriorityReviews -- or do both!)21:21
*** jmasud has joined #openstack-meeting21:21
acoleshttps://review.opendev.org/c/openstack/swift/+/76165921:21
timburkespeaking of...21:21
timburke#topic shard range caching for listings21:22
*** openstack changes topic to "shard range caching for listings (Meeting topic: swift)"21:22
timburkeacoles, clayg take it away;-)21:22
acoleshttps://review.opendev.org/c/openstack/swift/+/761659 adds caching shard ranges in memcache for container listings21:22
acoleswe've had it in production for a month or so and it works21:23
claygwhen we shipped it to prod our baseline 5XX dropped to almost nothing and everyone was singing @acoles praises21:23
acolesit's had a few rounds of review so I hope it is close to merging21:24
claygwell, but it's blocked on you BUGFIX!!! (don don DUUUUUUN)21:24
acolesclayg: yeah, I was going to mention the bug too21:24
acolesso while working on this I discovered a nasty bug, but one I doubt any is at risk of yet21:25
acolesthe bug fix is here https://review.opendev.org/c/openstack/swift/+/767410/521:25
mattoliverauI plan to review your bug + cache chain today.21:26
mattoliverauAnd is something that we shold land before the next release ;)21:26
*** jamesmcarthur has quit IRC21:26
acolesthere's a corner case risk of loops in proxy, but only when shrinking shards, and then only in very particular conditions, but I really want to get that fixed, cos loops aren't good21:26
* mattoliverau is never biased toward sharding patches :P21:27
*** jamesmcarthur has joined #openstack-meeting21:27
acoleshappily, the fix is relatively simple. so that is https://review.opendev.org/c/openstack/swift/+/76741021:27
acolesback to the caching patch, I wanted to mention that by default the shard caching is enabled21:28
acoles(BTW, this is similar to the existing object PUT shard caching that timburke added a while back)21:28
claygtrue true, which also was on by default - and helps with object PUT throughput quite a big on sharded containers21:29
acolesthe complete set of shard ranges are cached on memcache, so if you have big containers with lots of shard ranges, the memcache values can be large. we have found it necessary to increase the default memcache config to allow for these increased sizes21:29
zaitcevso, how do I know what sizes to use?21:30
clayghence: https://bugs.launchpad.net/swift/+bug/189064321:30
openstackLaunchpad bug 1890643 in OpenStack Object Storage (swift) "shard range cache can get too big for memcache" [Undecided,New]21:30
acoleswhich is why I flag up the 'on by default' property21:30
mattoliverauMaybe we need to make sure that is mentioned something in doc? deployment or admin guide?21:30
acolesmattoliverau: yes! and we knew you would volunteer :D21:30
acoles;)21:30
claygmattoliverau: I think a doc change would be a GREAT fix for lp bug #189064321:30
mattoliveraulol, ok.. so long as someone gives me a hint on the right asswer I'll add it somewhere :P21:31
acoleszaitcev: yes, so we propose to add doc about memcache sizing21:31
claygzaitcev: IIRC we bumped up from 1MB to 5MB?  although 10MB would have probably been more reasonable 🤔21:31
claygby the time we caught it our largest container's shard ranges were something like 1400 KiB (but I think it was also full of overlaps) - point is we're close enough to the default swift deployments should be aware of it21:32
timburkethe default for memcache is something like 1MB, right? ballpark an upper bound for a serialized shard range at something like 2-4kb, so you ought to be good until you've got >250 or so shard ranges for a container21:32
claygmaybe worse is that caching 5MB of json in memcache might not be like... "perfectly optimized" 😬21:32
*** jmlowe has quit IRC21:33
timburkewe should probably also flag up what happens when we exceed the max memcache value size (both here and in the deployment guide somewhere ;-)21:34
timburkein short, the `set` then works like a `delete`, and you start hammering the container DB again, similar to if caching were disabled21:35
*** ociuhandu has joined #openstack-meeting21:36
claygyeah, caching disable sucks - which is why it's on by default21:36
claygbut if you're sharding (which is still notoriously difficult/manual) - but if you're sharding, luckily you'll also be caching (unless you didn't know the sekret memcache tweak - then you won't be caching... which sucks)21:37
mattoliverauhmm, maybe can recommend pulling the size stats from memcache peridically in one's monitoring scripts. Then you can know when your going to hit a ceiling.21:37
claygbut after we merge p 761659 and mattoliverau fixes lp bug #1890643 everything will be great!21:37
openstackLaunchpad bug 1890643 in OpenStack Object Storage (swift) "shard range cache can get too big for memcache" [Undecided,New] https://launchpad.net/bugs/189064321:37
claygmattoliverau: uhh... WE should probably do that 🤔21:38
claygwe have some other memcache stats - like hit/miss - it's possible "min/max/avg key size" comes out too?21:39
acoleswe should also figure out shrinking so that our shard lists do not grow infinitely long...I'm working on that21:39
mattoliverauaccording to google you can 'states sizes'21:39
mattoliverauaccording to google you can *'stats sizes'21:39
*** ociuhandu has quit IRC21:40
mattoliveraubut the call may lock up for a while, so only something you'd want to do occasitionally21:40
mattoliverauacoles: YES!21:41
claygSTAT sizes_status disabled 🤔21:41
timburkeit may also come back with `STAT sizes_status disabled` (apparently; that's what my vsaio says, anyway)21:41
mattoliveraubugger21:41
claygNEWAY - point is mattoliverau is going to merge this AWESOME FEATURE this afternoon - and do some docs soon - because matt is 'mazing21:42
mattoliveraulol, or rather acoles rocks :)21:42
claygthere's not a finate amount of awesomeness in the universe - you AND acoles can both rock 💪21:42
acolesyou rock I'll roll21:43
timburkeis anyone opposed to the caching being on by default? iirc there was some concern about it before, but it sounds like most of the people involved with the patch now feel like on-by-default is the right way to go21:43
acoles(repeating) the object PUT shard caching is already on by default21:44
mattoliverauI figure 1. it's proven itself in prod and 2. sharding isn't something that is suppose to happen all the time so caching for some time is fine :)21:44
*** ociuhandu has joined #openstack-meeting21:44
claygyeah the "amount of time" is configurable - but the "pounding the root to get ranges every object PUT and every container listing" was NOT working21:45
claygi guess in theory you could turn the value to 0 if you hate your container servers 🤔21:45
claygor your clients21:45
timburkeall right, sounds like we've got a plan then21:46
timburkethat's all we had on the agenda21:46
timburke#topic open discussion21:46
acolesclayg: yep, setting the expiry time to 0 disables the caching21:46
*** openstack changes topic to "open discussion (Meeting topic: swift)"21:46
timburkewhat else should we bring up this week?21:46
claygidk, we have some crazy clients - they be listing like massive concurrency for like parallel search or something21:47
acolesdid I see audit watchers merged?21:47
zaitcevYes21:47
acolesthen we should congratulate zaitcev  and all others involved - congrats!21:48
timburkeit's so great. i need to write a few more watchers :-)21:48
claygzaitcev: congrats!!!21:48
zaitcevacoles: dsariel did a lot of work21:48
acolesI mean, I had an entire career diversion while you kept plugging away on that21:48
mattoliverauYeah! great work21:48
timburkeslo validation's gonna be a good one...21:48
zaitcevUnfortunately, torgomatic is no longer around.21:49
mattoliverauacoles: lol21:49
acolesdsariel: congrats and thanks too21:49
*** TrevorV has quit IRC21:50
zaitcevWe had some good changes done in the very final round of reviews. I just wish this good feedback could be gotten a year ago. I remember what I rolled out 2 PTGs ago, oh boy. And I thought it was ready to merge, too.21:50
acoleszaitcev: :'( yes, but maybe torgomatic is .... 'watching'21:50
timburkeif anyone wants to look at some other watcher code, i've got https://review.opendev.org/c/openstack/swift/+/744078/ (EC stats, looking at libec versions and crcs) and https://review.opendev.org/c/openstack/swift/+/766640 (per-policy stats) proposed21:51
*** ociuhandu has quit IRC21:51
zaitcevI don't quite understand what the EC watcher does, but the CRC one clearly is useful.21:51
zaitcevI already went and abandoned Sam's original review 212824.21:53
timburkeyeah, the CRC guy seems real useful for figuring out whether it's safe to upgrade libec21:53
timburkethe per-policy stats are mainly just me wanting a way to get a size distribution of objects, and a split on how much data's in each policy21:54
*** ociuhandu has joined #openstack-meeting21:54
timburkeall right, i'm calling it21:55
timburkethank you all for coming, and thank you for working on swift!21:55
timburke#endmeeting21:56
*** openstack changes topic to "OpenStack Meetings || https://wiki.openstack.org/wiki/Meetings/"21:56
openstackMeeting ended Wed Jan  6 21:56:00 2021 UTC.  Information about MeetBot at http://wiki.debian.org/MeetBot . (v 0.1.4)21:56
openstackMinutes:        http://eavesdrop.openstack.org/meetings/swift/2021/swift.2021-01-06-21.00.html21:56
openstackMinutes (text): http://eavesdrop.openstack.org/meetings/swift/2021/swift.2021-01-06-21.00.txt21:56
openstackLog:            http://eavesdrop.openstack.org/meetings/swift/2021/swift.2021-01-06-21.00.log.html21:56
*** acoles has left #openstack-meeting21:56
*** zaitcev has left #openstack-meeting21:56
*** dsariel has left #openstack-meeting21:56
*** ociuhandu has quit IRC21:58
*** jamesmcarthur has quit IRC22:10
*** ociuhandu has joined #openstack-meeting22:10
*** jamesmcarthur has joined #openstack-meeting22:13
*** ociuhandu has quit IRC22:19
*** rcernin has joined #openstack-meeting22:27
*** jamesmcarthur has quit IRC22:28
*** jamesmcarthur has joined #openstack-meeting22:28
*** jmasud has quit IRC22:41
*** bnemec has quit IRC22:45
*** jamesmcarthur has quit IRC22:46
*** jamesmcarthur has joined #openstack-meeting22:47
*** rfolco has quit IRC22:50
*** jmasud has joined #openstack-meeting22:57
*** bnemec has joined #openstack-meeting23:01
*** eharney has quit IRC23:09
*** rh-jelabarre has quit IRC23:21
*** ociuhandu has joined #openstack-meeting23:25
*** ociuhandu has quit IRC23:30
*** jamesmcarthur has quit IRC23:39
*** jmasud has quit IRC23:49
*** jmasud has joined #openstack-meeting23:51
*** tosky has quit IRC23:51
*** jamesmcarthur has joined #openstack-meeting23:58

Generated by irclog2html.py 2.17.2 by Marius Gedminas - find it at https://mg.pov.lt/irclog2html/!