#ceph IRC Log

Index

IRC Log for 2012-05-19

Timestamps are in GMT/BST.

[0:08] * adamcrume (~quassel@adsl-99-115-83-144.dsl.pltn13.sbcglobal.net) has joined #ceph
[0:12] <adamcrume> I'm having trouble with OSDMap mapping all objects to the same OSDs. They're in separate PGs, but all the PGs are mapped to the same OSDs. Would someone mind taking a look at my code? I have a small test case here: http://pastebin.com/XKcN4Bmf
[0:14] <joshd> adamcrume: what does the crushmap look like?
[0:15] * lofejndif (~lsqavnbok@82VAADWZE.tor-irc.dnsbl.oftc.net) Quit (Remote host closed the connection)
[0:15] * Ryan_Lane (~Adium@208-117-193-99.static.idsno.net) Quit (Quit: Leaving.)
[0:15] <adamcrume> joshd: Here's the output: http://pastebin.com/kXeC09pU
[0:16] <adamcrume> As I understand it, I have ten OSDs all on equal footing.
[0:19] <joshd> yeah, the osd map looks ok
[0:19] <joshd> what about the crush rules?
[0:19] <adamcrume> I don't know how to view those off the top of my head.
[0:21] <joshd> if you have the osdmap in a file, you can do osdmaptool --export-crush crushmap filename; crushtool -d crushmap
[0:22] <adamcrume> I don't have any files. I'm trying to configure everything in code.
[0:24] <joshd> you can export the crushmap to a file with:
[0:24] <joshd> bufferlist cbl;
[0:24] <joshd> osdmap.crush->encode(cbl);
[0:24] <joshd> r = cbl.write_file(export_crush.c_str());
[0:25] <joshd> where export_crush is the output filename
[0:26] <joshd> my guess is the default crush rules for an osdmap are strange, and causing the mapping you're seeing
[0:26] * andreask (~andreas@chello062178013131.5.11.vie.surfer.at) Quit (Quit: Leaving.)
[0:29] <adamcrume> Okay, here's the crush map: http://pastebin.com/NHmcft7x
[0:29] * lofejndif (~lsqavnbok@28IAAETZ5.tor-irc.dnsbl.oftc.net) has joined #ceph
[0:30] * s[X]_ (~sX]@eth589.qld.adsl.internode.on.net) has joined #ceph
[0:46] <joshd> it looks like there's some bit of initialization missing to make it work, not sure exactly what yet
[0:51] <joshd> adamcrume: which version are you using? currently osdmap->build_simple takes one fewer parameter than you have
[0:53] <joshd> lpgs were removed in 0.46
[0:53] <adamcrume> I'm using commit 0777613654d22cd2da924fe5bb95f65ee3e25a6b.
[0:57] <adamcrume> I'll try switching to 0.46, but it'll take a while to recompile.
[1:06] <joshd> 0.46 doesn't help
[1:08] * adamcrume (~quassel@adsl-99-115-83-144.dsl.pltn13.sbcglobal.net) Quit (Ping timeout: 480 seconds)
[1:12] * aa (~aa@r200-40-114-26.ae-static.anteldata.net.uy) Quit (Remote host closed the connection)
[1:13] * adamcrume (~quassel@adsl-99-115-83-144.dsl.pltn13.sbcglobal.net) has joined #ceph
[1:13] * joao (~JL@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[1:16] * rturk1 (~rturk@aon.hq.newdream.net) has joined #ceph
[1:16] * rturk1 (~rturk@aon.hq.newdream.net) has left #ceph
[1:17] * todon_ (~todon@46.33.129.2) has joined #ceph
[1:20] * todon (~todon@46.33.129.2) Quit (Ping timeout: 480 seconds)
[1:22] * bchrisman (~Adium@108.60.121.114) Quit (Quit: Leaving.)
[1:23] * rturk (~rturk@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[1:24] * joao (~JL@aon.hq.newdream.net) has joined #ceph
[1:38] * nrheckman (4b9538f1@ircip1.mibbit.com) Quit (Quit: http://www.mibbit.com ajax IRC Client)
[2:06] * joao (~JL@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:06] * Tv_ (~tv@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:14] * joao (~JL@aon.hq.newdream.net) has joined #ceph
[2:21] * jluis (~JL@aon.hq.newdream.net) has joined #ceph
[2:21] * yehudasa_ (~yehudasa@aon.hq.newdream.net) has joined #ceph
[2:21] * gregaf1 (~Adium@aon.hq.newdream.net) has joined #ceph
[2:22] * mkampe1 (~markk@aon.hq.newdream.net) has joined #ceph
[2:23] * joshd1 (~joshd@aon.hq.newdream.net) has joined #ceph
[2:23] * dmick1 (~dmick@aon.hq.newdream.net) has joined #ceph
[2:23] * sjust1 (~sam@aon.hq.newdream.net) has joined #ceph
[2:24] * sagewk1 (~sage@aon.hq.newdream.net) has joined #ceph
[2:27] * jluis (~JL@aon.hq.newdream.net) Quit (Quit: Leaving)
[2:28] * mkampe (~markk@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:28] * gregaf (~Adium@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:28] * joshd (~joshd@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:28] * dmick (~dmick@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:28] * sagewk (~sage@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:28] * sjust (~sam@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:28] * joao (~JL@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:29] * yehudasa (~yehudasa@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:30] <adamcrume> joshd1: It's still not working, even with 0.46. And, oddly enough, OSDMap::build_simple still has a parameter called lpg_bits.
[2:39] * yehudasa__ (~yehudasa@aon.hq.newdream.net) has joined #ceph
[2:39] * gregaf (~Adium@aon.hq.newdream.net) has joined #ceph
[2:40] * mkampe (~markk@aon.hq.newdream.net) has joined #ceph
[2:41] * sjust (~sam@aon.hq.newdream.net) has joined #ceph
[2:45] * mkampe1 (~markk@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:46] * gregaf1 (~Adium@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:46] * dmick1 (~dmick@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:46] * sjust1 (~sam@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:46] * sagewk1 (~sage@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:46] * joshd1 (~joshd@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:46] * yehudasa_ (~yehudasa@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[2:47] * joshd (~joshd@aon.hq.newdream.net) has joined #ceph
[2:47] * sagewk (~sage@aon.hq.newdream.net) has joined #ceph
[2:48] * dmick (~dmick@aon.hq.newdream.net) has joined #ceph
[2:58] <joshd> adamcrume: I didn't find the root cause, but encoding and decoding it makes it work: http://tracker.newdream.net/issues/2448
[3:13] * adjohn (~adjohn@69.170.166.146) Quit (Quit: adjohn)
[3:22] <adamcrume> joshd: Thanks.
[3:39] * lofejndif (~lsqavnbok@28IAAETZ5.tor-irc.dnsbl.oftc.net) Quit (Quit: gone)
[3:58] * joshd (~joshd@aon.hq.newdream.net) Quit (Quit: Leaving.)
[4:14] * adamcrume (~quassel@adsl-99-115-83-144.dsl.pltn13.sbcglobal.net) Quit (Remote host closed the connection)
[4:15] <Qu310> gregaf: thanks for the info :)
[4:20] * renzhi (~renzhi@76.164.216.98) has joined #ceph
[4:21] <Qu310> If we are running XFS FS, and we are using a RBD replica level of 2 or more, we pull file1.dat off a RBD vol, does ceph know if the data blocks from the RBD vol I grabbed is ok or corrupted from the point of view of read errors from a physical disk or memory bit flips/errors? or is this something the fs inside the vm has to sort out?
[4:26] <ajm-> fairly sure ceph doesn't double-check on reads, even internally when copying data
[4:30] * dennisj (~chatzilla@p5DCF7625.dip.t-dialin.net) Quit (Quit: ChatZilla 0.9.88.2 [Firefox 12.0/20120424092743])
[4:36] * yehudasa_ (~yehudasa@aon.hq.newdream.net) has joined #ceph
[4:36] * gregaf1 (~Adium@aon.hq.newdream.net) has joined #ceph
[4:37] * mkampe1 (~markk@aon.hq.newdream.net) has joined #ceph
[4:37] * sagewk1 (~sage@aon.hq.newdream.net) has joined #ceph
[4:38] * sjust1 (~sam@aon.hq.newdream.net) has joined #ceph
[4:38] * dmick1 (~dmick@aon.hq.newdream.net) has joined #ceph
[4:40] * s[X]_ (~sX]@eth589.qld.adsl.internode.on.net) Quit (Remote host closed the connection)
[4:41] * s[X] (~sX]@eth589.qld.adsl.internode.on.net) has joined #ceph
[4:42] * sjust (~sam@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[4:42] * mkampe (~markk@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[4:42] * gregaf (~Adium@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[4:42] * dmick (~dmick@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[4:43] * sagewk (~sage@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[4:43] * yehudasa__ (~yehudasa@aon.hq.newdream.net) Quit (Ping timeout: 480 seconds)
[4:49] * s[X] (~sX]@eth589.qld.adsl.internode.on.net) Quit (Ping timeout: 480 seconds)
[5:14] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[5:37] * cattelan is now known as cattelan_away
[5:38] * cattelan_away is now known as cattelan
[6:22] * dmick1 (~dmick@aon.hq.newdream.net) has left #ceph
[7:17] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Ping timeout: 480 seconds)
[7:34] * cattelan is now known as cattelan_away
[7:44] * cattelan_away is now known as cattelan
[7:45] * cattelan is now known as cattelan_away
[7:56] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[8:03] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[8:23] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[8:53] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[8:56] * stxShadow (~Jens@ip-78-94-238-69.unitymediagroup.de) has joined #ceph
[8:56] * stxShadow (~Jens@ip-78-94-238-69.unitymediagroup.de) has left #ceph
[8:56] * hijacker (~hijacker@213.91.163.5) Quit (Read error: Connection reset by peer)
[8:57] * hijacker (~hijacker@213.91.163.5) has joined #ceph
[9:35] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) Quit (Ping timeout: 480 seconds)
[10:29] * s[X]_ (~sX]@60-241-151-10.tpgi.com.au) has joined #ceph
[10:29] <renzhi> is it not possible to chattr +i on a file that is hosted on a ceph filesystem?
[10:33] * BManojlovic (~steki@212.200.243.232) has joined #ceph
[10:33] * Ryan_Lane (~Adium@254.sub-166-249-193.myvzw.com) has joined #ceph
[10:52] * Ryan_Lane (~Adium@254.sub-166-249-193.myvzw.com) Quit (Read error: Connection reset by peer)
[10:55] * Ryan_Lane (~Adium@254.sub-166-249-193.myvzw.com) has joined #ceph
[10:57] * todon_ (~todon@46.33.129.2) Quit (Ping timeout: 480 seconds)
[11:13] * todon (~todon@46.33.129.2) has joined #ceph
[11:16] * Ryan_Lane (~Adium@254.sub-166-249-193.myvzw.com) Quit (Quit: Leaving.)
[11:23] * todon (~todon@46.33.129.2) Quit (Ping timeout: 480 seconds)
[11:33] * todon (~todon@46.33.129.2) has joined #ceph
[11:49] * renzhi (~renzhi@76.164.216.98) Quit (Quit: Leaving)
[11:51] * s[X]_ (~sX]@60-241-151-10.tpgi.com.au) Quit (Remote host closed the connection)
[12:42] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[13:19] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[13:32] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) has joined #ceph
[14:03] * steki-BLAH (~steki@bojanka.net) has joined #ceph
[14:07] * BManojlovic (~steki@212.200.243.232) Quit (Ping timeout: 480 seconds)
[15:41] * s[X]_ (~sX]@ppp59-167-157-96.static.internode.on.net) Quit (Remote host closed the connection)
[16:43] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) has joined #ceph
[17:07] * MarkDude (~MT@c-71-198-138-155.hsd1.ca.comcast.net) Quit (Read error: Connection reset by peer)
[17:16] <RupS> so I have pg's in stuck unclean
[17:16] <RupS> osd's are up and running
[17:16] <RupS> recovery is stuck somehow I guess...
[17:17] <RupS> I tried "lost" on an osd, bu that doesn't help
[17:17] <RupS> any suggestions? :)
[18:41] * Meths (rift@2.25.191.220) Quit (Quit: )
[18:54] * lofejndif (~lsqavnbok@28IAAEUJF.tor-irc.dnsbl.oftc.net) has joined #ceph
[19:53] * Theuni (~Theuni@91-65-217-125-dynip.superkabel.de) has joined #ceph
[20:15] * CristianDM (~CristianD@host217.190-230-240.telecom.net.ar) Quit ()
[20:50] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[20:52] * Theuni (~Theuni@91-65-217-125-dynip.superkabel.de) Quit (Quit: Leaving.)
[21:00] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[21:12] * Ryan_Lane (~Adium@216.sub-166-249-193.myvzw.com) has joined #ceph
[21:30] * Ryan_Lane (~Adium@216.sub-166-249-193.myvzw.com) Quit (Read error: Connection reset by peer)
[21:36] * Ryan_Lane (~Adium@216.sub-166-249-193.myvzw.com) has joined #ceph
[21:39] * Meths (rift@2.25.191.220) has joined #ceph
[22:07] * Ryan_Lane (~Adium@216.sub-166-249-193.myvzw.com) Quit (Quit: Leaving.)
[23:18] * BManojlovic (~steki@212.200.243.232) has joined #ceph
[23:21] * steki-BLAH (~steki@bojanka.net) Quit (Ping timeout: 480 seconds)

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