#ceph IRC Log

Index

IRC Log for 2010-11-02

Timestamps are in GMT/BST.

[0:01] * allsystemsarego (~allsystem@188.27.167.113) Quit (Quit: Leaving)
[0:02] * fract (~lbz@fw1.aspsys.com) has joined #ceph
[0:02] <fract> hows ceph coming along these days? :)
[0:06] <sagewk> fract: keeping us busy!
[0:07] <fract> ;)
[0:55] <jantje_> to say the least :P
[1:02] * dubst (~me@ip-66-33-206-8.dreamhost.com) has joined #ceph
[1:09] * terang (~me@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[1:16] * joshd (~joshd@ip-66-33-206-8.dreamhost.com) Quit (Quit: Leaving.)
[1:40] * johnl (~johnl@cpc3-brad19-2-0-cust563.barn.cable.virginmedia.com) Quit (Ping timeout: 480 seconds)
[2:03] * sjust (~sam@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[2:05] * greglap (~Adium@cpe-76-90-74-194.socal.res.rr.com) Quit (Remote host closed the connection)
[2:41] * growler (growler@dog.thdo.woaf.net) Quit (Ping timeout: 480 seconds)
[2:43] * growler (growler@dog.thdo.woaf.net) has joined #ceph
[3:28] * leander_yu (dc8729c2@ircip3.mibbit.com) has joined #ceph
[4:38] * leander_yu (dc8729c2@ircip3.mibbit.com) Quit (Quit: http://www.mibbit.com ajax IRC Client)
[6:13] * Meths_ (rift@91.106.215.115) has joined #ceph
[6:20] * Meths (rift@91.106.242.9) Quit (Ping timeout: 480 seconds)
[6:22] * cmccabe (~cmccabe@adsl-76-202-119-74.dsl.pltn13.sbcglobal.net) Quit (Quit: Leaving.)
[6:27] * dubst (~me@ip-66-33-206-8.dreamhost.com) Quit (Ping timeout: 480 seconds)
[7:06] * dubst (~me@pool-173-55-24-140.lsanca.fios.verizon.net) has joined #ceph
[7:56] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) has joined #ceph
[9:22] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) Quit (Quit: Yoric)
[9:34] * johnl (~johnl@cpc3-brad19-2-0-cust563.barn.cable.virginmedia.com) has joined #ceph
[9:46] * allsystemsarego (~allsystem@188.27.167.113) has joined #ceph
[9:56] <wido> hi
[9:56] <wido> anyone here tried to build the latest unstable?
[10:13] * johnl (~johnl@cpc3-brad19-2-0-cust563.barn.cable.virginmedia.com) Quit (Ping timeout: 480 seconds)
[10:33] * Yoric (~David@213.144.210.93) has joined #ceph
[10:44] <wido> Never mind, see: http://tracker.newdream.net/issues/536
[10:54] <jantje_> hi wido
[10:55] <wido> hi
[10:55] <wido> jantje_: are you using Debian/Ubuntu?
[10:56] <wido> I'm seeing a lot of issues with building the .debs today, not sure if it is my system or the repo
[10:57] * f4m8_ is now known as f4m8
[11:12] * johnl (~johnl@host81-142-82-205.in-addr.btopenworld.com) has joined #ceph
[11:41] * johnl (~johnl@host81-142-82-205.in-addr.btopenworld.com) Quit (Ping timeout: 480 seconds)
[11:47] * johnl (~johnl@host81-142-82-205.in-addr.btopenworld.com) has joined #ceph
[11:53] <jantje_> wido: yes, but i'm not using ceph debian packages any more
[11:54] <jantje_> (or building packages for my system)
[11:54] <jantje_> I just run the binaries from src/*
[11:54] <wido> ah, ok
[11:54] <wido> I have to much machines for that
[11:54] <jantje_> (especially init-ceph)
[11:55] <jantje_> lunch time
[12:32] * johnl (~johnl@host81-142-82-205.in-addr.btopenworld.com) Quit (Ping timeout: 480 seconds)
[12:45] * Yoric (~David@213.144.210.93) Quit (Ping timeout: 480 seconds)
[13:08] * jantje_ thinks it would be cool to be able to use CEPH as an nfsroot
[13:09] <jantje_> (well, not exactlu nfsroot, but you'll get the idea)
[13:47] * johnl (~johnl@cpc3-brad19-2-0-cust563.barn.cable.virginmedia.com) has joined #ceph
[14:50] * gregorg (~Greg@78.155.152.6) has joined #ceph
[15:17] * Meths_ is now known as Meths
[15:53] * f4m8 is now known as f4m8_
[16:31] * sjust (~sam@ip-66-33-206-8.dreamhost.com) has joined #ceph
[16:52] * dubst (~me@pool-173-55-24-140.lsanca.fios.verizon.net) Quit (Ping timeout: 480 seconds)
[17:51] * Meths_ (rift@91.106.196.234) has joined #ceph
[17:57] * Meths (rift@91.106.215.115) Quit (Ping timeout: 480 seconds)
[17:59] * joshd (~joshd@ip-66-33-206-8.dreamhost.com) has joined #ceph
[17:59] * yehudasa_hm (~yehuda@ppp-69-228-129-75.dsl.irvnca.pacbell.net) has joined #ceph
[18:01] * Meths_ is now known as Meths
[18:12] <wido> yehudasa: you there?
[18:12] <wido> I have some thougths on the rbd/libvirt integration
[18:13] <wido> I've looked into this a few months ago and found out that libvirt has two functions
[18:14] <wido> first there are "storage pools", you can find those in src/storage, for example storage_backend_logical.c|h
[18:14] <wido> this is only a wrapper around LVM for managing VG's and LV's, but not for connecting LVM to a VM
[18:15] <wido> for now, libvirt assumes that every device is a file/block device, the virtual devices like NBD and RBD are not supported
[18:16] <wido> Implementing RBD support means two things, one would be a XML scheme for RBD disks
[18:16] <wido> and one for a RBD storage pool, this would give you the ability to manage RBD images via libvirt
[18:20] <yehudasa_hm> wido: I'm here now
[18:20] <sagewk> wido: do you want to follow up on that thread with your thoughts?
[18:20] <sagewk> i'm personally not very familiar with libvirt.. i just want to get some idea which direction we should be going, and hopefully find someone interested in working on it
[18:21] <sagewk> if nobody steps up, i can try to find someone around here to tackle it.
[18:22] * sagewk (~sage@ip-66-33-206-8.dreamhost.com) Quit (Remote host closed the connection)
[18:23] <wido> yehudasa_hm: I thought you were the libvirt "guy", but i'll post my thoughts on the ml
[18:23] <yehudasa_hm> yeah, the best place to discuss this would be on that thread.. should be visible to other people around here that know better about libvirt
[18:23] * cmccabe (~cmccabe@dsl081-243-128.sfo1.dsl.speakeasy.net) has joined #ceph
[18:25] * sagewk (~sage@ip-66-33-206-8.dreamhost.com) has joined #ceph
[18:56] * johnl (~johnl@cpc3-brad19-2-0-cust563.barn.cable.virginmedia.com) Quit (Ping timeout: 480 seconds)
[19:07] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) has joined #ceph
[19:24] <yehudasa_hm> sagewk: notify/watch wouldn't really work with renaming/removing of objects
[19:24] <sagewk> hmm
[19:25] <sagewk> yeah. is that problematic?
[19:25] <yehudasa_hm> can cause wierd issues I guess
[19:26] <yehudasa_hm> not the highest priority, but maybe we can add a notify message that will tell about an intention to remove/rename
[19:27] <yehudasa_hm> so watching clients will be able to agree/disagree about the upcoming operation
[19:30] <yehudasa_hm> btw, we can implement locking in a similar way
[19:31] <yehudasa_hm> and even have it so that we can enforce it on the osd
[19:44] <wido> where should "osd pool default size" be declared? In the osd section?
[19:44] <wido> I've set: osd pool default size = 3 in [osd], but new pools still get size = 2
[19:45] <wido> This config option has been there for a few weeks now, so the daemons have started with this config option
[19:47] * johnl (~johnl@cpc3-brad19-2-0-cust563.barn.cable.virginmedia.com) has joined #ceph
[20:02] <wido> Seems "we" are not the only one with this issue: http://www.redhat.com/archives/libvir-list/2010-October/msg01247.html
[20:03] <cmccabe> hmm
[20:25] <gregaf> wido: new pools get defined in the monitor
[20:25] <gregaf> it needs to be visible to the monitors, so define osd pool default size in either the global or mon section
[20:28] <wido> gregaf: tnx!
[20:28] <gregaf> yep :)
[20:31] <wido> "osd pool" confused me a bit
[20:32] <wido> "mon clock ..." is defined in the [mon] section
[20:32] <wido> "osd recovery .." in the [osd] section, so shouldn't "osd pool default size" be renamed to "mon pool default size" ?
[20:32] <gregaf> yeah, most of them go in their section, we may consider renaming
[20:43] <wido> Did my e-mail get through on the ml?
[20:43] <wido> About libvirt/RBD
[20:43] <yehudasa_hm> wido: when did you send it?
[20:44] <yehudasa_hm> note that it needs to be plain text
[20:44] <wido> yehudasa_hm: sent it about an hour ago, and yes, it was plain-text
[20:46] <yehudasa_hm> never got anything
[20:47] <wido> ok, resend it
[20:48] <yehudasa_hm> got it now
[20:50] <wido> great :)
[20:57] * dubst (~me@pool-173-55-24-140.lsanca.fios.verizon.net) has joined #ceph
[21:05] * dubst (~me@pool-173-55-24-140.lsanca.fios.verizon.net) Quit (Ping timeout: 480 seconds)
[21:07] * tjikkun (~tjikkun@2001:7b8:356:0:204:bff:fe80:8080) has joined #ceph
[21:33] * allsystemsarego (~allsystem@188.27.167.113) Quit (Quit: Leaving)
[22:57] * johnl (~johnl@cpc3-brad19-2-0-cust563.barn.cable.virginmedia.com) Quit (Ping timeout: 480 seconds)
[22:58] * Yoric (~David@dau94-10-88-189-211-192.fbx.proxad.net) Quit (Quit: Yoric)

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