#ceph IRC Log

Index

IRC Log for 2010-11-11

Timestamps are in GMT/BST.

[0:39] * allsystemsarego (~allsystem@188.27.167.113) Quit (Quit: Leaving)
[0:55] * terang (~me@ip-66-33-206-8.dreamhost.com) has joined #ceph
[1:38] * terang (~me@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[1:55] * terang (~me@ip-66-33-206-8.dreamhost.com) has joined #ceph
[2:17] * cmccabe (~cmccabe@dsl081-243-128.sfo1.dsl.speakeasy.net) has left #ceph
[3:24] * greglap1 (~Adium@ip-66-33-206-8.dreamhost.com) Quit (Quit: Leaving.)
[3:49] * greglap (~Adium@166.205.139.73) has joined #ceph
[4:00] * terang (~me@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[4:14] * sjust (~sam@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[4:17] * terang (~me@ip-66-33-206-8.dreamhost.com) has joined #ceph
[4:18] * Jiaju (~jjzhang@222.126.194.154) has joined #ceph
[4:27] * root (~root@c66.203.209-92.clta.globetrotter.net) has joined #ceph
[4:27] * root is now known as TiCPU
[4:29] <TiCPU> eI'm planning to replicate 2 sites in which there will be big files created (PC images) once in a while but lots of read, the link between the 2 sites is 100kilobytes/s coax cable Internet link, I read in the FAQ
[4:29] <TiCPU> ethat ceph isnt suggested for this situation, is that right, no option tweakable for slow link? Data does not need to be always in sync.
[4:31] <greglap> TiCPU: we've seen interest in this situation before but it's not something that fits very well with the Ceph architecture
[4:31] <greglap> it's just not designed for delayed synchronization
[4:33] * TiCPU_ (gaston@c66.203.209-92.clta.globetrotter.net) has joined #ceph
[4:34] <TiCPU_> sorry, iPhone crashed, greglap, last line was that ceph wasn't designed for delayed sync, right?
[4:34] <greglap> yeah
[4:34] <TiCPU_> alright, I was trying to see if ceph evolved that way, I'm pretty new to this :)
[4:34] <greglap> unfortunately not
[4:34] <TiCPU_> for such a slow link, do you happend to know any alternative?
[4:35] <TiCPU_> I read about unison
[4:35] <greglap> I haven't done any research into it but XtreemFS is the closest possible match I know about
[4:35] <TiCPU_> drdb would be read-write one way, read-only the other
[4:36] <TiCPU_> nice, I havn't even seen that name today (looking at this for now 3-4 hours)
[4:36] <TiCPU_> BTW, I tried ceph with QoS limiting to 100 kbit, really painful for big files :)
[4:37] <greglap> yeah, it was architected for running in one data-center with immediate replication for safety :)
[4:39] <TiCPU_> makes more sense now, reading the description was leading me to think that "multi petabyte file system" sounds to me it wasn't designed from the ground to work on slow links anyway, currently looking at XtreemFS, sounds good, first look at the page was looking like a commercial product, but surprissingly, it is GPL2!
[4:44] * TiCPU (~root@c66.203.209-92.clta.globetrotter.net) Quit (Ping timeout: 480 seconds)
[4:55] * joshd (~joshd@ip-66-33-206-8.dreamhost.com) Quit (Quit: Leaving.)
[4:55] * TiCPU (~root@c66.203.209-92.clta.globetrotter.net) has joined #ceph
[5:00] * TiCPU (~root@c66.203.209-92.clta.globetrotter.net) Quit (Quit: Lost terminal)
[5:00] * greglap (~Adium@166.205.139.73) Quit (Read error: Connection reset by peer)
[5:14] * greglap (~Adium@cpe-76-90-74-194.socal.res.rr.com) has joined #ceph
[6:20] * terang (~me@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[6:21] <sage> greglap: still around?
[6:22] <greglap> sage: for some definition :)
[6:22] <sage> :)
[6:23] <sage> is #561 in a state I can look at tomorrow? would like to include the fix in 0.23 if possible
[6:23] <greglap> *checking log*
[6:25] <greglap> well it's still a little wonky, but it's a lot better than it was
[6:25] <greglap> have a few errors like this:
[6:25] <greglap> Delete all the files and directories ...
[6:25] <greglap> rm: cannot remove `./100/_test3_1/10': Read-only file system
[6:25] <greglap> (test_3 is a snapshot in an ancestor directory that already got deleted, supposedly)
[6:25] <greglap> but it does let you remove the dirs now
[6:26] <sage> hmm interseting
[6:26] <sage> if you have a full log for that just put the path in teh bug and i'll take a look tomrrow?
[6:26] <greglap> can do
[6:27] <sage> cool thanks. i'll stop harassing you now.. as you were! :)
[6:27] <greglap> heh, np
[6:27] <greglap> now that's just weird
[6:28] <greglap> I started it back up and looked at what was left and dir 100 remained with a few files, but rm -r worked fine
[6:28] * terang (~me@ip-66-33-206-8.dreamhost.com) has joined #ceph
[6:43] * greglap1 (~Adium@cpe-76-90-74-194.socal.res.rr.com) has joined #ceph
[6:43] * greglap (~Adium@cpe-76-90-74-194.socal.res.rr.com) Quit (Read error: Connection reset by peer)
[6:52] * terang (~me@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[7:12] * f4m8_ is now known as f4m8
[7:15] * terang (~me@ip-66-33-206-8.dreamhost.com) has joined #ceph
[8:04] * terang (~me@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[8:08] * cmccabe (~cmccabe@adsl-75-37-26-87.dsl.pltn13.sbcglobal.net) has joined #ceph
[8:30] * allsystemsarego (~allsystem@188.27.167.113) has joined #ceph
[9:04] * cmccabe (~cmccabe@adsl-75-37-26-87.dsl.pltn13.sbcglobal.net) Quit (Ping timeout: 480 seconds)
[9:37] * henrychang (~henry_c_c@59-124-35-221.HINET-IP.hinet.net) has joined #ceph
[9:57] * terang (~me@ip-66-33-206-8.dreamhost.com) has joined #ceph
[11:23] * terang (~me@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[11:55] * terang (~me@pool-173-55-24-140.lsanca.fios.verizon.net) has joined #ceph
[12:04] * hijacker (~hijacker@213.91.163.5) Quit (Read error: Connection reset by peer)
[12:05] <vuvuzela> mds/AnchorServer.cc: In function 'virtual void AnchorServer::handle_query(MMDSTableRequest*)':
[12:05] <vuvuzela> mds/AnchorServer.cc:242: FAILED assert(anchor_map.count(curino) == 1)
[12:05] <vuvuzela> ceph version 0.23~rc (commit:be9328ac7de09285b444a73ba8fee78e0fe384e3)
[12:05] <vuvuzela> 1: (MDS::_dispatch(Message*)+0x1947) [0x4bda77]
[12:05] <vuvuzela> 2: (MDS::ms_dispatch(Message*)+0x5b) [0x4be74b]
[12:05] <vuvuzela> 3: (SimpleMessenger::dispatch_entry()+0x6c9) [0x49e619]
[12:05] <vuvuzela> 4: (SimpleMessenger::DispatchThread::entry()+0x1c) [0x49359c]
[12:40] * hijacker (~hijacker@213.91.163.5) has joined #ceph
[12:51] * hijacker (~hijacker@213.91.163.5) Quit (Remote host closed the connection)
[12:56] * hijacker (~hijacker@213.91.163.5) has joined #ceph
[14:30] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) has joined #ceph
[15:02] * darkfader (~floh@host-82-135-62-109.customer.m-online.net) Quit (Remote host closed the connection)
[15:02] * darkfader (~floh@host-82-135-62-109.customer.m-online.net) has joined #ceph
[15:03] * jantje_ (~jan@paranoid.nl) Quit (Remote host closed the connection)
[15:03] * jantje (~jan@paranoid.nl) has joined #ceph
[15:41] * jantje (~jan@paranoid.nl) Quit (Remote host closed the connection)
[15:41] * jantje (~jan@paranoid.nl) has joined #ceph
[15:46] * f4m8 is now known as f4m8_
[16:29] * terang (~me@pool-173-55-24-140.lsanca.fios.verizon.net) Quit (Ping timeout: 480 seconds)
[17:02] * NoahWatkins (~jayhawk@kyoto.soe.ucsc.edu) has joined #ceph
[19:11] <wido> Hi
[19:12] <wido> I saw this abort today: http://pastebin.com/gTWLdWag
[19:12] <wido> 'ceph -w' aborted with the above output, couldn't reproduce it
[20:39] * rharper (~rharper@32.97.110.59) has joined #ceph
[21:24] * rharper (~rharper@32.97.110.59) Quit (Ping timeout: 480 seconds)
[21:35] * rharper (~rharper@32.97.110.64) has joined #ceph
[22:11] <vuvuzela> VUVUUUUUUUUUUUUUU~~~~~~~~~~~~~~~~~~
[22:14] * cmccabe (~cmccabe@adsl-76-202-118-226.dsl.pltn13.sbcglobal.net) has joined #ceph
[22:14] * cmccabe (~cmccabe@adsl-76-202-118-226.dsl.pltn13.sbcglobal.net) Quit ()
[22:31] * rharper (~rharper@32.97.110.64) Quit (Ping timeout: 480 seconds)
[22:54] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) Quit (Quit: Yoric)
[23:47] <sagewk> wido: added to #540

These logs were automatically created by CephLogBot on irc.oftc.net using the Java IRC LogBot.