| *** pberis has quit IRC | 00:02 | |
| *** pberis has joined #openstack-swift | 00:04 | |
| *** kevinc_ has quit IRC | 00:06 | |
| *** pberis has quit IRC | 00:13 | |
| *** pberis has joined #openstack-swift | 00:16 | |
| *** bszabo has joined #openstack-swift | 00:25 | |
| *** bszabo has quit IRC | 00:30 | |
| *** shri has left #openstack-swift | 00:38 | |
| *** pberis has quit IRC | 00:40 | |
| *** pberis has joined #openstack-swift | 00:42 | |
| *** pberis has quit IRC | 00:51 | |
| *** mwstorer has quit IRC | 00:52 | |
| *** pberis has joined #openstack-swift | 00:53 | |
| *** jthorne has joined #openstack-swift | 00:57 | |
| openstackgerrit | A change was merged to openstack/swift: Disable case-changing behavior in Eventlet https://review.openstack.org/93780 | 01:02 |
|---|---|---|
| *** foexle_ has joined #openstack-swift | 01:06 | |
| *** foexle has quit IRC | 01:10 | |
| *** pberis has quit IRC | 01:43 | |
| *** pberis has joined #openstack-swift | 01:44 | |
| *** nosnos has joined #openstack-swift | 01:49 | |
| *** haomaiw__ has joined #openstack-swift | 02:04 | |
| *** haomaiwang has quit IRC | 02:07 | |
| *** pberis has quit IRC | 02:21 | |
| *** pberis has joined #openstack-swift | 02:23 | |
| *** bkopilov has quit IRC | 02:37 | |
| *** pberis has quit IRC | 02:43 | |
| *** pberis has joined #openstack-swift | 02:45 | |
| *** tongli has joined #openstack-swift | 02:49 | |
| *** chandankumar has joined #openstack-swift | 02:51 | |
| *** chandankumar has quit IRC | 02:52 | |
| *** chandankumar has joined #openstack-swift | 02:55 | |
| *** nosnos has quit IRC | 03:06 | |
| *** tong_ has joined #openstack-swift | 03:24 | |
| *** tong_ has quit IRC | 03:24 | |
| *** tongli has quit IRC | 03:24 | |
| *** tongli has joined #openstack-swift | 03:25 | |
| *** nosnos has joined #openstack-swift | 03:33 | |
| *** pberis has quit IRC | 03:34 | |
| *** chandankumar has quit IRC | 03:34 | |
| *** pberis has joined #openstack-swift | 03:36 | |
| *** tongli has quit IRC | 03:38 | |
| *** tongli has joined #openstack-swift | 03:39 | |
| openstackgerrit | Yuan Zhou proposed a change to openstack/python-swiftclient: Allow to specify storage policy when uploading objects https://review.openstack.org/73920 | 03:45 |
| *** chandankumar has joined #openstack-swift | 03:48 | |
| *** tongli has quit IRC | 03:59 | |
| *** bkopilov has joined #openstack-swift | 04:00 | |
| *** bszabo has joined #openstack-swift | 04:02 | |
| *** bszabo has quit IRC | 04:06 | |
| *** zaitcev has quit IRC | 04:19 | |
| *** judd7 has quit IRC | 04:44 | |
| *** chandankumar has quit IRC | 04:48 | |
| *** ppai has joined #openstack-swift | 04:53 | |
| *** chandankumar has joined #openstack-swift | 04:56 | |
| *** chandankumar has quit IRC | 04:57 | |
| *** anand_ts has joined #openstack-swift | 04:58 | |
| *** chandankumar has joined #openstack-swift | 04:59 | |
| *** psharma has joined #openstack-swift | 05:12 | |
| *** kota_ has joined #openstack-swift | 05:19 | |
| *** kota_ has quit IRC | 06:00 | |
| *** mmcardle has joined #openstack-swift | 06:08 | |
| *** k4n0 has joined #openstack-swift | 06:22 | |
| *** foexle_ has quit IRC | 06:29 | |
| *** patchbot` has joined #openstack-swift | 06:30 | |
| *** patchbot has quit IRC | 06:30 | |
| *** patchbot` is now known as patchbot | 06:32 | |
| *** dosaboy has joined #openstack-swift | 06:33 | |
| *** ahale_ has joined #openstack-swift | 06:33 | |
| *** pberis has quit IRC | 06:34 | |
| *** amandap has quit IRC | 06:34 | |
| *** fleducquede_ has quit IRC | 06:34 | |
| *** psharma has quit IRC | 06:34 | |
| *** rando has quit IRC | 06:34 | |
| *** d0ugal has quit IRC | 06:34 | |
| *** zackmdavis has quit IRC | 06:34 | |
| *** Tyger has quit IRC | 06:34 | |
| *** clayg_ has joined #openstack-swift | 06:34 | |
| *** mdonohoe has joined #openstack-swift | 06:34 | |
| *** JelleB has quit IRC | 06:34 | |
| *** omame has quit IRC | 06:34 | |
| *** dosaboy_ has quit IRC | 06:34 | |
| *** IRTermite has quit IRC | 06:34 | |
| *** k4n0 has quit IRC | 06:34 | |
| *** ahale has quit IRC | 06:34 | |
| *** pconstantine has quit IRC | 06:34 | |
| *** clayg has quit IRC | 06:34 | |
| *** pberis has joined #openstack-swift | 06:34 | |
| *** amandap has joined #openstack-swift | 06:34 | |
| *** fleducquede_ has joined #openstack-swift | 06:34 | |
| *** pconstantine has joined #openstack-swift | 06:35 | |
| *** zackmdavis has joined #openstack-swift | 06:35 | |
| *** psharma has joined #openstack-swift | 06:35 | |
| *** omame has joined #openstack-swift | 06:35 | |
| *** JelleB has joined #openstack-swift | 06:35 | |
| *** d0ugal has joined #openstack-swift | 06:36 | |
| *** k4n0 has joined #openstack-swift | 06:36 | |
| *** IRTermite has joined #openstack-swift | 06:36 | |
| *** Tyger has joined #openstack-swift | 06:36 | |
| *** foexle has joined #openstack-swift | 06:44 | |
| *** madhuri has joined #openstack-swift | 06:54 | |
| madhuri | Hi, is there any documentation available for all the request headers used in swift? | 06:55 |
| *** msahin_ has quit IRC | 07:00 | |
| *** gvernik has joined #openstack-swift | 07:18 | |
| *** bszabo has joined #openstack-swift | 07:38 | |
| *** bszabo has quit IRC | 07:43 | |
| *** gvernik has quit IRC | 07:47 | |
| *** nacim has joined #openstack-swift | 07:56 | |
| *** zslot has joined #openstack-swift | 07:58 | |
| *** zslot1 has joined #openstack-swift | 08:01 | |
| *** zslot has quit IRC | 08:03 | |
| *** haomaiw__ has quit IRC | 08:05 | |
| *** haomaiwang has joined #openstack-swift | 08:06 | |
| *** mmcardle has quit IRC | 08:09 | |
| *** mmcardle has joined #openstack-swift | 08:14 | |
| *** acoles_away is now known as acoles | 08:17 | |
| *** haomai___ has joined #openstack-swift | 08:19 | |
| *** haomaiwang has quit IRC | 08:22 | |
| *** jthorne has quit IRC | 08:23 | |
| *** ppai has quit IRC | 08:29 | |
| *** mrmoje has joined #openstack-swift | 08:34 | |
| *** ppai has joined #openstack-swift | 08:35 | |
| *** bvandenh has joined #openstack-swift | 08:35 | |
| *** haomai___ has quit IRC | 08:45 | |
| *** haomaiwang has joined #openstack-swift | 08:45 | |
| *** Dev_Jin has joined #openstack-swift | 08:48 | |
| Dev_Jin | I am trying to figure out if swift storage can be used as local package repository (like say local repository for apt) .. but no luck till now.. any help would be appreciated | 08:49 |
| *** mkerrin has quit IRC | 09:16 | |
| *** mkerrin has joined #openstack-swift | 09:23 | |
| *** kopparam has joined #openstack-swift | 09:33 | |
| *** bvandenh has quit IRC | 09:35 | |
| *** bszabo_ has joined #openstack-swift | 09:36 | |
| *** kopparam has quit IRC | 09:40 | |
| *** kopparam has joined #openstack-swift | 09:40 | |
| *** Dafna has quit IRC | 09:43 | |
| *** kopparam has quit IRC | 09:45 | |
| *** bvandenh has joined #openstack-swift | 09:47 | |
| *** nosnos has quit IRC | 09:54 | |
| pconstantine | Dev_Jin: it's simple | 09:55 |
| pconstantine | Dev_Jin: just use reprepro to build local apt repo | 09:55 |
| pconstantine | Dev_Jin: then upload it as-is to some Swift container | 09:56 |
| pconstantine | Dev_Jin: make that container public-readable | 09:56 |
| pconstantine | Dev_Jin: that's it | 09:56 |
| pconstantine | Dev_Jin: ah, one more thing: do not use https, apt-get is very bad with https | 09:57 |
| *** ppai has quit IRC | 09:59 | |
| *** Shivani has joined #openstack-swift | 10:00 | |
| *** nosnos has joined #openstack-swift | 10:01 | |
| *** haomaiwang has quit IRC | 10:08 | |
| *** haomaiwang has joined #openstack-swift | 10:09 | |
| *** nosnos has quit IRC | 10:10 | |
| *** haomaiw__ has joined #openstack-swift | 10:11 | |
| *** nosnos has joined #openstack-swift | 10:12 | |
| *** haomaiwang has quit IRC | 10:14 | |
| *** ppai has joined #openstack-swift | 10:15 | |
| Dev_Jin | thanks pconstantine.. let me try that out | 10:23 |
| *** chandankumar has quit IRC | 10:25 | |
| *** chandankumar has joined #openstack-swift | 10:33 | |
| *** nosnos has quit IRC | 10:38 | |
| *** bszabo_ has quit IRC | 10:47 | |
| *** bszabo has joined #openstack-swift | 10:47 | |
| openstackgerrit | Alistair Coles proposed a change to openstack/swift: Add v2 API to list endpoints middleware https://review.openstack.org/101665 | 10:50 |
| *** bszabo has quit IRC | 10:52 | |
| openstackgerrit | Alistair Coles proposed a change to openstack/swift: Update doc for list_endpoints v2 API https://review.openstack.org/107648 | 10:57 |
| *** bszabo_ has joined #openstack-swift | 10:57 | |
| acoles | clayg: ^^ added this as follow-on patch in case you don't like it | 10:58 |
| *** ppai has quit IRC | 10:58 | |
| *** ppai has joined #openstack-swift | 11:01 | |
| *** Dafna has joined #openstack-swift | 11:01 | |
| *** pconstantine has quit IRC | 11:19 | |
| *** bszabo_ has quit IRC | 11:22 | |
| *** Dafna has quit IRC | 11:29 | |
| *** mmcardle has quit IRC | 11:43 | |
| *** Dafna has joined #openstack-swift | 11:43 | |
| *** andyandy has joined #openstack-swift | 11:46 | |
| *** mahati has quit IRC | 11:52 | |
| *** bkopilov has quit IRC | 12:05 | |
| *** mmcardle has joined #openstack-swift | 12:15 | |
| *** bkopilov has joined #openstack-swift | 12:18 | |
| *** tongli has joined #openstack-swift | 12:19 | |
| acoles | clayg: re replicate & .meta cleanup - yes there is an opportunity to merge .meta's during replication. at the cost of reading the files. maybe it's only done *then* when >N meta's have accumulated (normally merge would be done during a POST). | 12:33 |
| *** bkopilov has quit IRC | 12:39 | |
| *** miqui has joined #openstack-swift | 12:41 | |
| *** chandankumar has quit IRC | 12:50 | |
| *** pconstantine has joined #openstack-swift | 12:52 | |
| mattoliverau | Hey all | 12:57 |
| mattoliverau | clayg_, acoles, notmyname, torgomatic: and anyone I missed, could someone take a look at my formpost change (https://review.openstack.org/#/c/104101/). The infra guys here are looking at uploading test results to swift, and this is a feature they'd love to use. | 12:59 |
| *** bvandenh has quit IRC | 12:59 | |
| *** k4n0 has quit IRC | 13:01 | |
| *** chandankumar has joined #openstack-swift | 13:07 | |
| *** psharma has quit IRC | 13:09 | |
| *** ppai has quit IRC | 13:17 | |
| *** nacim has quit IRC | 13:26 | |
| *** anand_ts has quit IRC | 13:28 | |
| *** ppai has joined #openstack-swift | 13:31 | |
| *** andyandy has quit IRC | 13:35 | |
| *** kenhui has joined #openstack-swift | 13:42 | |
| *** mahati_ has joined #openstack-swift | 13:47 | |
| *** Manish has joined #openstack-swift | 13:55 | |
| Manish | Hi All | 13:55 |
| Manish | I have one query.... can any one please let me know that why in SWIFT API documentation, "Create Account" feature is not mentioned, although in SWIFT code we have PUT Account support? | 13:56 |
| Manish | is it because, so that user can only create account in SWIFT (after creating in Keystone) , while creating the first container in that account? | 13:57 |
| Manish | it will be great help, if some one can explain this | 13:58 |
| pconstantine | Manish: I suppose it's because creating the account was an "admin only" feature, so it's technically not a part of public API but a part of admin API | 14:03 |
| *** mrmoje has quit IRC | 14:04 | |
| *** mrmoje has joined #openstack-swift | 14:04 | |
| *** ppai has quit IRC | 14:11 | |
| *** dmsimard_away is now known as dmsimard | 14:12 | |
| *** judd7 has joined #openstack-swift | 14:15 | |
| *** mmcardle has quit IRC | 14:22 | |
| *** Dev_Jin has quit IRC | 14:22 | |
| Manish | pconstantine: probably you are right..Thanks :) | 14:29 |
| *** CybergeekDK has quit IRC | 14:31 | |
| *** mrmoje has quit IRC | 14:36 | |
| *** nacim has joined #openstack-swift | 14:36 | |
| *** mrmoje has joined #openstack-swift | 14:37 | |
| *** CybergeekDK has joined #openstack-swift | 14:42 | |
| *** rando has joined #openstack-swift | 14:44 | |
| *** mmcardle has joined #openstack-swift | 14:44 | |
| *** mdonohoe has quit IRC | 14:47 | |
| *** kevinc_ has joined #openstack-swift | 14:49 | |
| *** haomaiwa_ has joined #openstack-swift | 14:55 | |
| *** pberis1 has joined #openstack-swift | 14:58 | |
| *** clayg has joined #openstack-swift | 14:58 | |
| *** foexle has quit IRC | 15:01 | |
| *** haomaiw__ has quit IRC | 15:02 | |
| *** pberis has quit IRC | 15:02 | |
| *** clayg_ has quit IRC | 15:02 | |
| *** mrmoje has quit IRC | 15:02 | |
| *** Dafna has quit IRC | 15:02 | |
| *** JelleB has quit IRC | 15:02 | |
| *** omame has quit IRC | 15:02 | |
| *** fleducquede_ has quit IRC | 15:02 | |
| *** bkopilov has joined #openstack-swift | 15:02 | |
| *** mrmoje has joined #openstack-swift | 15:04 | |
| *** JelleB has joined #openstack-swift | 15:06 | |
| *** fleducquede_ has joined #openstack-swift | 15:06 | |
| *** Dafna has joined #openstack-swift | 15:07 | |
| *** omame has joined #openstack-swift | 15:07 | |
| acoles | clayg: torgomatic: i _almost_ have something (very crude) working, merging .meta's during POST and replication. | 15:13 |
| *** acoles is now known as acoles_away | 15:14 | |
| torgomatic | I wonder why the infra folks are looking at formpost instead of using plain tempurls | 15:17 |
| *** tdasilva has joined #openstack-swift | 15:29 | |
| peluse_ | torgomatic: I've been brainstorming the EC object name collision question for a bit and am coming up with a light drizzle at best... can you restate for me the specific steps/scenario that lead us into the problem situation just to make sure I'm understanding the problem correctly? | 15:32 |
| *** ujjain has quit IRC | 15:53 | |
| *** kevinc_ has quit IRC | 15:59 | |
| *** chandankumar has quit IRC | 16:06 | |
| *** dencaval has quit IRC | 16:08 | |
| *** tongli has quit IRC | 16:08 | |
| *** tongli has joined #openstack-swift | 16:09 | |
| *** kevinc_ has joined #openstack-swift | 16:09 | |
| *** pberis1 has quit IRC | 16:11 | |
| *** Manish has quit IRC | 16:12 | |
| *** dmsimard_away has joined #openstack-swift | 16:17 | |
| *** mkerrin has quit IRC | 16:24 | |
| *** dmsimard_away has quit IRC | 16:24 | |
| *** mwstorer has joined #openstack-swift | 16:26 | |
| *** pberis has joined #openstack-swift | 16:32 | |
| openstackgerrit | paul luse proposed a change to openstack/swift: Initial Erasure Code Docs https://review.openstack.org/104713 | 16:32 |
| *** pberis has quit IRC | 16:36 | |
| *** pberis has joined #openstack-swift | 16:37 | |
| *** pberis has quit IRC | 16:42 | |
| *** zslot1 has quit IRC | 17:04 | |
| notmyname | good morning | 17:07 |
| *** zaitcev has joined #openstack-swift | 17:14 | |
| *** ChanServ sets mode: +v zaitcev | 17:14 | |
| peluse_ | good morning! | 17:15 |
| *** Dafna has quit IRC | 17:16 | |
| *** kevinc_ has quit IRC | 17:17 | |
| notmyname | peluse_: I'm looking over the EC docs right now | 17:25 |
| notmyname | peluse_: I completely assume it's not a "done" document, but if it's all ok, I'll merge it | 17:26 |
| notmyname | "ok" meaning "what's talked about is reasonable and correct" | 17:26 |
| *** mmcardle has quit IRC | 17:27 | |
| *** kenhui has quit IRC | 17:28 | |
| *** bvandenh has joined #openstack-swift | 17:28 | |
| *** erlon has quit IRC | 17:39 | |
| notmyname | peluse_: a couple of things on the docs to fix. if you don't get to it soon, I'll try to later today or tomorrow | 17:43 |
| *** kevinc_ has joined #openstack-swift | 17:52 | |
| *** jthorne has joined #openstack-swift | 18:24 | |
| mattoliverau | torgomatic: the infra guys are using form post because they want the test nodes to upload the logs.. And because they could be running arbitory code, and so considered untrusted. So formpost. Thanks for the suggestions I'll implement them when I get in front of a computer :) | 18:34 |
| torgomatic | mattoliverau: yeah, I was thinking why not use tempurl for exactly the same thing, but I think I figured it out | 18:35 |
| torgomatic | with formpost, you can have the testrunner inject a single thing(swift-url + form params) and upload any arbitrary set of logs you want, so that decouples things better | 18:37 |
| JoshNang | hey guys, can i get reviews on adding tempurls? we've got two drivers in ironic target for juno blocked on it. thanks!! https://review.openstack.org/#/c/102632/ | 18:38 |
| mattoliverau | Yeah that's infras point of view too, so soon all the logs being shared through zuul will be in swift ;) | 18:40 |
| *** bvandenh has quit IRC | 18:46 | |
| *** fifieldt has joined #openstack-swift | 19:00 | |
| *** mmcardle has joined #openstack-swift | 19:02 | |
| notmyname | JoshNang: done | 19:10 |
| notmyname | JoshNang: also, nice feature :-) | 19:10 |
| notmyname | thanks | 19:10 |
| JoshNang | notmyname: thanks! woo!! | 19:11 |
| *** kevinc_ has quit IRC | 19:11 | |
| JoshNang | notmyname: any idea when it would get packaged and put in a new release? this is my first swift patch | 19:12 |
| JoshNang | this patch will use the tempurls in ironic: https://review.openstack.org/#/c/81391/ but from what i understand, i'll have to get global-requirements bumped up after tempurls are packaged | 19:14 |
| peluse_ | notmyname: feel free to take a shot at rewording what I was trying to explain in that paragraph in the EC docs... appreciate it | 19:15 |
| peluse_ | torgomatic: did you see my question earlier? | 19:17 |
| *** pberis has joined #openstack-swift | 19:22 | |
| *** fifieldt has quit IRC | 19:31 | |
| *** mmcardle has quit IRC | 19:33 | |
| torgomatic | peluse_: no | 19:42 |
| notmyname | JoshNang: well, soon, actually. I want to see https://review.openstack.org/#/c/73920/ land and then cut a release of the client | 19:42 |
| peluse_ | torgomatic: I've been brainstorming the EC object name collision question for a bit and am coming up with a light drizzle at best... can you restate for me the specific steps/scenario that lead us into the problem situation just to make sure I'm understanding the problem correctly? | 19:43 |
| JoshNang | notmyname: awesome. thanks for your help! | 19:43 |
| torgomatic | peluse_: so with replication, the replicators will move data closer to home, even if only partway | 19:43 |
| torgomatic | so it might go from 3rd handoff -> 1st handoff, then the 3rd will clean up | 19:44 |
| torgomatic | if you do this with EC stuff, it's harder to tell if the closer handoff really has a copy of *your* fragment archive or if it's got a different one for the same object | 19:44 |
| *** nacim has quit IRC | 19:45 | |
| peluse_ | torgomatic: OK, thanks. Will explore a few ideas a bit deeper and get back to ya | 19:46 |
| notmyname | peluse_: for the docs, we'll get it all good before final release. all I'm "worried" about now is making sure we have the right placeholders and the build warning | 19:47 |
| peluse_ | ditto | 19:50 |
| peluse_ | good call on the handoffs too, forgot a todo section for htat... | 19:50 |
| peluse_ | that | 19:50 |
| peluse_ | notmyname / torgomatic: did you peruse the EC spec yet? | 19:50 |
| notmyname | no | 19:51 |
| *** mahati_ has quit IRC | 19:52 | |
| *** foexle has joined #openstack-swift | 19:53 | |
| peluse_ | check it out :) | 19:55 |
| *** mmcardle has joined #openstack-swift | 20:00 | |
| *** mmcardle has quit IRC | 20:12 | |
| *** kevinc___ has joined #openstack-swift | 20:13 | |
| notmyname | peluse_: still around? | 20:35 |
| peluse_ | yup | 20:43 |
| notmyname | peluse_: I want to chat about something that I thought of while reading the EC doc. | 20:46 |
| notmyname | peluse_: I think there may be a way to improve master today that will also be necessary for EC | 20:47 |
| notmyname | peluse_: so with EC, the proxy will need to open up concurrent connections to many storage nodes to read an object (object GET) | 20:48 |
| notmyname | peluse_: today with replication, we try one object server, then another, then another, etc until the data is read | 20:48 |
| notmyname | but there's been the idea floating around for a while of opening up connections to all the primary nodes and then using the first that responds and dropping the others on the floor | 20:49 |
| *** fifieldt has joined #openstack-swift | 20:49 | |
| notmyname | peluse_: so an interesting proposal to master would be to add this ability to the object read path, and then reuse it for the EC read path | 20:50 |
| peluse_ | notmyname: I like it | 20:52 |
| peluse_ | notmyname: I'll throw a card up on Trello | 20:52 |
| notmyname | peluse_: I think it starts with rewriting the _get_source_and_node() method in proxy/controllers/base.py (line 746) | 20:52 |
| notmyname | peluse_: IIRC, the arguments against doing this is that it means there will be a lot more sockets (connections) opened in the cluster as a whole | 20:53 |
| notmyname | but the upside for today's replicated clusters is that we could probably lower time-to-first-byte latency | 20:53 |
| peluse_ | notmyname: yeah, but maybe that socket buffer pool idea can help mitigate the overhead a bit there | 20:53 |
| notmyname | right | 20:54 |
| notmyname | exactly | 20:54 |
| peluse_ | was reading about another obj storage system that used that scheme for PUT also and then used background tasks to rebalance the uneven distrubtion that resulted... | 20:54 |
| peluse_ | can't remember where though... | 20:54 |
| notmyname | so anyway, as I was reading through the EC doc, it sounded like that's going to be a crucial part of the EC read path anyway, so I thought it might be nice to solve the general case and get it to master before feature/ec merges | 20:54 |
| peluse_ | agree | 20:55 |
| peluse_ | I put a card on Trello and if nobody else nabs it I'll jump on it after I get some more progress on the obj name collision thing as its blocking me on the reconstructor framework | 20:55 |
| notmyname | awesome. thanks | 20:55 |
| peluse_ | no prob, cool idea! | 20:56 |
| peluse_ | I pasted our dicsussion in the Trello card :) | 20:56 |
| *** occupant has quit IRC | 20:57 | |
| *** occupant has joined #openstack-swift | 20:57 | |
| notmyname | peluse_: I think torgomatic has some good ideas on this too (we chatted a little on it in the office). so definitely get his input as you tackle it :-) | 20:57 |
| peluse_ | awesome, will do. need to learn a little more on my own, maybe tomorrow I'll ping | 20:59 |
| notmyname | heh, he's deep in django-landia for now. at some point, he'll emerge with strange and terrible stories of wonder and adventure | 21:00 |
| peluse_ | that sounds like loads of fun! | 21:01 |
| *** mrmoje has quit IRC | 21:12 | |
| *** jthorne has quit IRC | 21:16 | |
| *** tongli has quit IRC | 21:19 | |
| *** occup4nt has joined #openstack-swift | 21:21 | |
| *** occupant has quit IRC | 21:24 | |
| *** occup4nt is now known as occupant | 21:27 | |
| *** occupant has quit IRC | 21:42 | |
| torgomatic | what are all these new dsvm-blah-havana and -icehouse jobs? | 21:42 |
| notmyname | torgomatic: hmm...look at that. new tests | 21:43 |
| notmyname | no idea | 21:43 |
| torgomatic | well, it's a good thing that all the tests are 100% reliable and this will in no way make it harder to land changes in Swift | 21:44 |
| notmyname | gate tests. the electric third rail of openstack politics | 21:44 |
| notmyname | torgomatic: like the one that just failed for swiftclient? ;-) | 21:45 |
| torgomatic | notmyname: something like that, yes :) | 21:45 |
| *** occupant has joined #openstack-swift | 21:45 | |
| notmyname | oh. the test "test_cinder_extra_specs_list" failed. good thing we check that | 21:47 |
| *** ChanServ sets mode: +v clayg | 21:56 | |
| *** foexle has quit IRC | 22:15 | |
| *** judd7 has quit IRC | 22:23 | |
| MooingLemur | is there a way to specify write_affinity to a zone/region which entirely consists of weight-0 devices and have it only use those for incoming writes? The use case is being able to place ingest nodes at remote locations that can take PUTs at high speed, and have replication push everything into place, but without caring about immediate availability of objects. | 22:38 |
| *** dmsimard is now known as dmsimard_away | 22:45 | |
| *** kevinc___ has quit IRC | 22:45 | |
| torgomatic | MooingLemur: nope; a 0-weight device will have no partitions assigned, so it'll never get any data on it | 22:46 |
| MooingLemur | torgomatic: Can you think of a way of doing what I want to achieve? I want storage devices with no partitions actually assigned, but I want them to be used for PUTs, and have replication take over. I suppose a separate ring known to the proxy server with only the devices I want to write to, but that will break GETs if they happen to come through that proxy. | 22:48 |
| torgomatic | MooingLemur: I think you're out of luck; "no partitions actually assigned" and "used for PUTs" are mutually incompatible the way Swift stands today | 22:49 |
| *** kevinc_ has joined #openstack-swift | 22:49 | |
| *** elambert has quit IRC | 22:50 | |
| *** Shivani has quit IRC | 22:50 | |
| *** madhuri has quit IRC | 22:50 | |
| *** Shivani has joined #openstack-swift | 22:51 | |
| *** madhuri has joined #openstack-swift | 22:51 | |
| *** kevinc_ has quit IRC | 22:51 | |
| *** clayg has quit IRC | 22:51 | |
| *** ekarlso has quit IRC | 22:51 | |
| *** dfg has quit IRC | 22:51 | |
| *** jokke_ has quit IRC | 22:51 | |
| *** redbo has quit IRC | 22:51 | |
| *** thurloat has quit IRC | 22:51 | |
| *** zaitcev has quit IRC | 22:52 | |
| *** fleducquede_ has quit IRC | 22:52 | |
| *** haomaiwa_ has quit IRC | 22:52 | |
| *** pconstantine has quit IRC | 22:52 | |
| *** otoolee has quit IRC | 22:52 | |
| *** rpedde has quit IRC | 22:52 | |
| *** cschwede has quit IRC | 22:52 | |
| *** swat30 has quit IRC | 22:52 | |
| *** acoles_away has quit IRC | 22:52 | |
| *** sandywalsh has quit IRC | 22:52 | |
| *** zaitcev has joined #openstack-swift | 22:53 | |
| *** fleducquede_ has joined #openstack-swift | 22:53 | |
| *** haomaiwa_ has joined #openstack-swift | 22:53 | |
| *** pconstantine has joined #openstack-swift | 22:53 | |
| *** otoolee has joined #openstack-swift | 22:53 | |
| *** rpedde has joined #openstack-swift | 22:53 | |
| *** cschwede has joined #openstack-swift | 22:53 | |
| *** swat30 has joined #openstack-swift | 22:53 | |
| *** acoles_away has joined #openstack-swift | 22:53 | |
| *** sandywalsh has joined #openstack-swift | 22:53 | |
| *** dickson.freenode.net sets mode: +vv zaitcev acoles_away | 22:53 | |
| *** kevinc_ has joined #openstack-swift | 22:53 | |
| *** clayg has joined #openstack-swift | 22:53 | |
| *** ekarlso has joined #openstack-swift | 22:53 | |
| *** dfg has joined #openstack-swift | 22:53 | |
| *** jokke_ has joined #openstack-swift | 22:53 | |
| *** redbo has joined #openstack-swift | 22:53 | |
| *** thurloat has joined #openstack-swift | 22:53 | |
| *** dickson.freenode.net sets mode: +vvv clayg dfg redbo | 22:53 | |
| *** Mikalv has quit IRC | 22:54 | |
| *** Mikalv has joined #openstack-swift | 22:54 | |
| *** patchbot has quit IRC | 22:54 | |
| *** zacksh has quit IRC | 22:54 | |
| *** ryao has quit IRC | 22:54 | |
| *** mtreinish has quit IRC | 22:54 | |
| *** zigo has quit IRC | 22:54 | |
| *** MooingLemur has quit IRC | 22:54 | |
| *** openfly has quit IRC | 22:54 | |
| *** bobby_ has quit IRC | 22:54 | |
| *** bgmccollum has quit IRC | 22:54 | |
| *** pandemicsyn has quit IRC | 22:54 | |
| *** nottrobin has quit IRC | 22:54 | |
| *** StevenK has quit IRC | 22:54 | |
| *** dmorita has quit IRC | 22:55 | |
| *** sudorandom has quit IRC | 22:55 | |
| *** AbyssOne has quit IRC | 22:55 | |
| *** tanee2 has quit IRC | 22:55 | |
| *** ondergetekende_ has quit IRC | 22:55 | |
| *** infotection has quit IRC | 22:55 | |
| *** joearnold has quit IRC | 22:55 | |
| *** ciypro|afk has quit IRC | 22:55 | |
| *** patchbot has joined #openstack-swift | 22:55 | |
| *** zacksh has joined #openstack-swift | 22:55 | |
| *** ryao has joined #openstack-swift | 22:55 | |
| *** mtreinish has joined #openstack-swift | 22:55 | |
| *** zigo has joined #openstack-swift | 22:55 | |
| *** MooingLemur has joined #openstack-swift | 22:55 | |
| *** bobby_ has joined #openstack-swift | 22:55 | |
| *** openfly has joined #openstack-swift | 22:55 | |
| *** bgmccollum has joined #openstack-swift | 22:55 | |
| *** pandemicsyn has joined #openstack-swift | 22:55 | |
| *** nottrobin has joined #openstack-swift | 22:55 | |
| *** StevenK has joined #openstack-swift | 22:55 | |
| *** ryao has quit IRC | 22:55 | |
| *** ryao has joined #openstack-swift | 22:55 | |
| MooingLemur | torgomatic: thanks for the answer, I guess I wanted to bend write_affinity beyond its intended purpose. Looks problematic. :) | 22:56 |
| *** dmorita has joined #openstack-swift | 22:56 | |
| *** sudorandom has joined #openstack-swift | 22:56 | |
| *** AbyssOne has joined #openstack-swift | 22:56 | |
| *** tanee2 has joined #openstack-swift | 22:56 | |
| *** ondergetekende_ has joined #openstack-swift | 22:56 | |
| *** infotection has joined #openstack-swift | 22:56 | |
| *** joearnold has joined #openstack-swift | 22:56 | |
| *** ciypro|afk has joined #openstack-swift | 22:56 | |
| torgomatic | MooingLemur: Yep :) I think you really want an HTTP write-back caching proxy that handles PUTs; combine that with tempurls for the PUT requests, and it might stand a chance of workign | 22:57 |
| torgomatic | of course, I don't know if anyone's written such a thing; all the HTTP caches I know are focused on GET | 22:57 |
| *** Tyger_ has joined #openstack-swift | 22:58 | |
| *** Tyger has quit IRC | 23:00 | |
| * MooingLemur ponders | 23:05 | |
| *** elambert has joined #openstack-swift | 23:05 | |
| MooingLemur | yeah, if I could have a generic writeback HTTP cache, that speaks swift auth. :) | 23:06 |
| MooingLemur | (so that it can give the client a reasonable return code based on whether it'd be likely to succeed on swift itself) | 23:08 |
| *** zul has quit IRC | 23:17 | |
| torgomatic | MooingLemur: well, that's why you'd use tempurl for the PUTs; it's a different auth mechanism that's more likely to work :) | 23:23 |
| MooingLemur | torgomatic: Well, this idea came up to placate users complaining about ingest speeds. The easiest remedy is to have them parallelize uploads more, because they are geographically kinda far from the proxy, and also because the object sizes are small. I was just trying to come up with a solution that would improve the case where the user made no changes to their process. | 23:29 |
| torgomatic | MooingLemur: ah... yeah, either move the cluster closer to the users, or have them do more stuff in parallel | 23:30 |
| torgomatic | there's also the bulk uploads; I think those can take .tar.gz so you get some compression going, if the users are bandwidth-constrained | 23:31 |
| *** zul has joined #openstack-swift | 23:31 | |
| *** kevinc_ has quit IRC | 23:35 | |
| *** occupant has quit IRC | 23:48 | |
| *** occupant has joined #openstack-swift | 23:49 | |
Generated by irclog2html.py 2.14.0 by Marius Gedminas - find it at mg.pov.lt!