-1F - Enforced bucket-level quotas in RGW » History » Version 1
Jessica Mack, 06/22/2015 05:46 AM
1 | 1 | Jessica Mack | h1. -1F - Enforced bucket-level quotas in RGW |
---|---|---|---|
2 | |||
3 | <pre> |
||
4 | *** mtk has left #ceph-summit1 11:16 |
||
5 | scuttlemonkey wido/gregaf: one of you guys want to take over sage's notetaking duties for this session? 11:16 |
||
6 | wido I have to go afk in a moment 11:16 |
||
7 | scuttlemonkey k 11:17 |
||
8 | liwang hi 11:17 |
||
9 | wido sorry 11:17 |
||
10 | scuttlemonkey li! 11:17 |
||
11 | paravoid wido: don't get me wrong on the varnish-specific stuff 11:17 |
||
12 | scuttlemonkey so great you could make it 11:17 |
||
13 | paravoid wido: I love Varnish and we heavily use it 11:17 |
||
14 | wido paravoid: No problem :) 11:17 |
||
15 | paravoid wido: I just don't think the two layers should be intermixed 11:17 |
||
16 | liwang yes 11:17 |
||
17 | wido No, they shouldn't indeed. I just wanted to point out the caching issues 11:17 |
||
18 | liwang does the invitation sent 11:18 |
||
19 | wido I want to have a "hook" to tell the cache to purge object X 11:18 |
||
20 | scuttlemonkey liwang: in approximately 42 minutes we'll have a break and I'll make sure you get added to the speakers 11:18 |
||
21 | wido And don't do the caching in RGW, since Varnish is much better in HTTP caching 11:18 |
||
22 | paravoid sure, that's not a bad idea 11:18 |
||
23 | paravoid you could invalidate with VCL too 11:18 |
||
24 | paravoid catch PUT/POST and call out to purge (what was previously set obj.ttl=0s) 11:19 |
||
25 | liwang i mean for the bucket-level quota session 11:19 |
||
26 | paravoid thinking Swift here, not sure about S3 11:19 |
||
27 | wido paravoid: True, but if you have multiple Varnish caches, you still get cache inconsistency 11:19 |
||
28 | scuttlemonkey liwang: you want to join as a speaker? Or just as an observer? 11:19 |
||
29 | wido It will only purge locally 11:19 |
||
30 | paravoid indeed 11:20 |
||
31 | scuttlemonkey youtube stream is at: http://youtu.be/rbVFozB9qls 11:20 |
||
32 | wido I'm thinking about having 10 Varnish caches 11:20 |
||
33 | liwang I registered as interested party for this session 11:20 |
||
34 | paravoid we have layered varnishes with consistent hashing among them 11:20 |
||
35 | scuttlemonkey ahhh! 11:20 |
||
36 | paravoid if you don't do that, then you cache the same URLs multiple times 11:20 |
||
37 | wido paravoid: True, you can do very cool stuff with Varnish that way 11:20 |
||
38 | paravoid it's better to shard your cache 11:20 |
||
39 | wido So you have multiple layers of Varnish servers? 11:21 |
||
40 | scuttlemonkey liwang: url sent via private message in irc 11:21 |
||
41 | *** paravoid_ has joined #ceph-summit1 11:26 |
||
42 | *** paravoid is now known as Guest4609 11:27 |
||
43 | *** paravoid_ is now known as paravoid 11:27 |
||
44 | paravoid damn 11:27 |
||
45 | paravoid what did I miss? 11:27 |
||
46 | paravoid 21:21 < wido> So you have multiple layers of Varnish servers? 11:27 |
||
47 | paravoid wido: yes 11:27 |
||
48 | Guest4609 yes 11:27 |
||
49 | *** Guest4609 has quit IRC 11:27 |
||
50 | wido paravoid: Ah, ok. I just tried to avoid that 11:28 |
||
51 | wido So you have them all as each others backend 11:28 |
||
52 | wido Would love to see that VCL :) 11:28 |
||
53 | paravoid not a VCL 11:28 |
||
54 | wido Inline C? 11:28 |
||
55 | paravoid it's a custom director, for consistent hashing 11:28 |
||
56 | wido Ah, that's cool 11:28 |
||
57 | paravoid https://gerrit.wikimedia.org/r/gitweb?p=operations/debs/varnish.git;a=commit;h=885b7d65fb7d93d0b3caa3fbf59a90fc2fffbaff 11:30 |
||
58 | paravoid anyway, this is getting offtopic 11:31 |
||
59 | *** Elbandi_ has joined #ceph-summit1 11:32 |
||
60 | sergey I think Google App Engine can do a "503 Over Quota" 11:36 |
||
61 | *** ksp has left #ceph-summit1 11:36 |
||
62 | wido paravoid: Aha! Indeed offtopic, but I met one of the Wikimedia people at a VUG in Amsterdam. Got inspired :) 11:39 |
||
63 | *** Ryan_Lane has joined #ceph-summit1 11:39 |
||
64 | paravoid that was Mark, the commiter of the above 11:39 |
||
65 | mikedawson sagewk: what is considered a large size Teuthology ceph cluster? What is a long-running test? 11:40 |
||
66 | sagewk mikedawson: other channel :) 11:40 |
||
67 | scuttlemonkey ^^ (#ceph-summit2) 11:41 |
||
68 | mikedawson what is considered a large size Teuthology ceph cluster? What is a long-running test? 11:41 |
||
69 | mikedawson sorry 11:41 |
||
70 | *** ccourtaut has quit IRC 11:49 |
||
71 | scuttlemonkey new Track 1 video is live on the event page and can also be accessed here: http://youtu.be/OUxEk87RcnI 12:03 |
||
72 | </pre> |