#ceph IRC Log

Index

IRC Log for 2013-04-01

Timestamps are in GMT/BST.

[0:05] * madkiss1 (~madkiss@089144192148.atnat0001.highway.a1.net) Quit (Ping timeout: 480 seconds)
[0:11] * ScOut3R (~ScOut3R@54029465.dsl.pool.telekom.hu) has joined #ceph
[0:26] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) has joined #ceph
[0:35] * KevinPerks1 (~Adium@cpe-066-026-239-136.triad.res.rr.com) has joined #ceph
[0:40] * KevinPerks (~Adium@cpe-066-026-239-136.triad.res.rr.com) Quit (Ping timeout: 480 seconds)
[0:42] * humbolt (~elias@91-113-96-235.adsl.highway.telekom.at) Quit (Ping timeout: 480 seconds)
[0:48] * BillK (~BillK@124-149-75-169.dyn.iinet.net.au) has joined #ceph
[0:55] * tryggvil (~tryggvil@17-80-126-149.ftth.simafelagid.is) has joined #ceph
[0:55] * matt_ (~matt@220-245-1-152.static.tpgi.com.au) Quit (Read error: Connection reset by peer)
[0:56] * matt_ (~matt@220-245-1-152.static.tpgi.com.au) has joined #ceph
[1:03] * madkiss2 (~madkiss@213162068101.public.t-mobile.at) Quit (Quit: Leaving.)
[1:05] * humbolt (~elias@91-113-96-235.adsl.highway.telekom.at) has joined #ceph
[1:06] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit (Quit: No Ping reply in 180 seconds.)
[1:06] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[1:09] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit ()
[1:09] * tnt (~tnt@91.177.233.80) Quit (Ping timeout: 480 seconds)
[1:09] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[1:10] * xmltok (~xmltok@cpe-76-170-26-114.socal.res.rr.com) has joined #ceph
[1:11] * diegows (~diegows@200-081-038-055.wireless.movistar.net.ar) has joined #ceph
[1:13] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit ()
[1:13] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[1:15] * DarkAce-Z (~BillyMays@50.107.53.115) has joined #ceph
[1:19] * DarkAceZ (~BillyMays@50.107.53.115) Quit (Read error: Operation timed out)
[1:24] * DarkAce-Z is now known as DarkAceZ
[1:32] * Tribaal (uid3081@id-3081.hillingdon.irccloud.com) has joined #ceph
[1:41] * lx0 (~aoliva@lxo.user.oftc.net) has joined #ceph
[1:44] * rustam (~rustam@5e0f5b1e.bb.sky.com) Quit (Remote host closed the connection)
[1:45] * rustam (~rustam@5e0f5b1e.bb.sky.com) has joined #ceph
[1:48] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[1:54] <Psi-jack> What is the likelyhood of me being able to change out my underlying Linux OS with another, keeping /etc/ceph, all the OSD's exactly in-tact, and literally just changing OS, and not mucking up Ceph itself, the data, etc, one by one until all three of my Ceph servers are done this way?
[1:55] * KevinPerks1 (~Adium@cpe-066-026-239-136.triad.res.rr.com) Quit (Quit: Leaving.)
[2:00] * leseb1 (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) has joined #ceph
[2:03] * leseb1 (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) Quit ()
[2:05] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) Quit (Ping timeout: 480 seconds)
[2:25] * KevinPerks (~Adium@cpe-066-026-239-136.triad.res.rr.com) has joined #ceph
[2:30] * humbolt (~elias@91-113-96-235.adsl.highway.telekom.at) Quit (Quit: humbolt)
[2:31] * humbolt (~elias@91-113-96-235.adsl.highway.telekom.at) has joined #ceph
[2:34] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) has joined #ceph
[2:37] * KevinPerks (~Adium@cpe-066-026-239-136.triad.res.rr.com) Quit (Ping timeout: 480 seconds)
[2:38] * LeaChim (~LeaChim@b0fae63d.bb.sky.com) Quit (Ping timeout: 480 seconds)
[2:41] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[2:43] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) Quit (Read error: Operation timed out)
[2:47] * LeaChim (~LeaChim@02d9ee2d.bb.sky.com) has joined #ceph
[3:07] * scuttlemonkey (~scuttlemo@fl-184-1-34-163.dhcp.embarqhsd.net) has joined #ceph
[3:07] * ChanServ sets mode +o scuttlemonkey
[3:17] * BManojlovic (~steki@fo-d-130.180.254.37.targo.rs) Quit (Quit: Ja odoh a vi sta 'ocete...)
[3:18] * humbolt (~elias@91-113-96-235.adsl.highway.telekom.at) Quit (Quit: humbolt)
[3:21] * scalability-junk (uid6422@id-6422.tooting.irccloud.com) has joined #ceph
[3:25] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) has joined #ceph
[3:33] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) Quit (Ping timeout: 480 seconds)
[3:42] * ScOut3R (~ScOut3R@54029465.dsl.pool.telekom.hu) Quit (Remote host closed the connection)
[3:55] * matt_ (~matt@220-245-1-152.static.tpgi.com.au) Quit (Ping timeout: 480 seconds)
[3:57] * scuttlemonkey (~scuttlemo@fl-184-1-34-163.dhcp.embarqhsd.net) Quit (Ping timeout: 480 seconds)
[3:58] * scuttlemonkey (~scuttlemo@fl-184-1-34-163.dhcp.embarqhsd.net) has joined #ceph
[3:58] * ChanServ sets mode +o scuttlemonkey
[4:03] * guerby (~guerby@nc10d-ipv6.tetaneutral.net) Quit (Ping timeout: 480 seconds)
[4:04] * guerby (~guerby@nc10d-ipv6.tetaneutral.net) has joined #ceph
[4:05] * xmltok (~xmltok@cpe-76-170-26-114.socal.res.rr.com) Quit (Read error: Connection reset by peer)
[4:05] * xmltok (~xmltok@cpe-76-170-26-114.socal.res.rr.com) has joined #ceph
[4:23] * scuttlemonkey (~scuttlemo@fl-184-1-34-163.dhcp.embarqhsd.net) Quit (Ping timeout: 480 seconds)
[4:30] * rustam (~rustam@5e0f5b1e.bb.sky.com) Quit (Remote host closed the connection)
[4:35] * BillK (~BillK@124-149-75-169.dyn.iinet.net.au) Quit (Ping timeout: 480 seconds)
[4:35] * xmltok (~xmltok@cpe-76-170-26-114.socal.res.rr.com) Quit (Read error: Operation timed out)
[4:48] * ivotron (~ivo@adsl-76-254-17-170.dsl.pltn13.sbcglobal.net) has joined #ceph
[5:12] * diegows (~diegows@200-081-038-055.wireless.movistar.net.ar) Quit (Ping timeout: 480 seconds)
[5:17] * ivotron (~ivo@adsl-76-254-17-170.dsl.pltn13.sbcglobal.net) Quit (Quit: leaving)
[5:17] * ivotron (~ivo@adsl-76-254-17-170.dsl.pltn13.sbcglobal.net) has joined #ceph
[5:24] * ivotron (~ivo@adsl-76-254-17-170.dsl.pltn13.sbcglobal.net) Quit (Quit: leaving)
[5:35] * BillK (~BillK@58-7-222-160.dyn.iinet.net.au) has joined #ceph
[5:46] * ivotron (~ivo@adsl-76-254-17-170.dsl.pltn13.sbcglobal.net) has joined #ceph
[5:50] <mo-> I was wonderin'.. centos 7 could very much become the new best practice linux for OSD boxes once its ready, no?
[6:08] * quanta (~quanta@118.70.67.142) has joined #ceph
[6:09] * matt_ (~matt@220-245-1-152.static.tpgi.com.au) has joined #ceph
[6:10] <quanta> Has anyone succesfully compiled on CentOS 5?
[6:10] <quanta> I'm getting this error: src/Makefile.am:1115: `doc_DATA' is used but `docdir' is undefined
[6:10] <quanta> when running `make install`
[6:14] <quanta> Actually, it also happened when executing `./autogen.sh`:
[6:14] <quanta> ./autogen.sh
[6:14] <quanta> configure.ac: installing `./install-sh'
[6:14] <quanta> configure.ac: installing `./missing'
[6:14] <quanta> src/Makefile.am: installing `./compile'
[6:14] <quanta> src/Makefile.am: installing `./depcomp'
[6:14] <quanta> src/Makefile.am:1187: installing `./py-compile'
[6:14] <quanta> src/Makefile.am:920: `doc_DATA' is used but `docdir' is undefined
[6:16] <quanta> I have tried to change the docdir to absolute path:
[6:16] <quanta> docdir ?= ${datadir}/doc/ceph
[6:16] <quanta> to:
[6:16] <quanta> docdir = /usr/share/doc/ceph
[6:16] <quanta> but nothing change.
[6:16] * favadi (~favadi@118.70.67.142) has joined #ceph
[6:19] <Psi-jack> Hmmm, CentOS 5 is waaaaaaaaayy too old, I'd say.
[6:23] * super_favadi (~favadi@14.160.47.150) has joined #ceph
[6:24] * quanta (~quanta@118.70.67.142) Quit (Read error: Connection reset by peer)
[6:24] * favadi (~favadi@118.70.67.142) Quit (Read error: Connection reset by peer)
[6:24] * quanta (~quanta@118.70.170.126) has joined #ceph
[7:04] * matt_ (~matt@220-245-1-152.static.tpgi.com.au) Quit (Read error: Connection reset by peer)
[7:05] * matt_ (~matt@220-245-1-152.static.tpgi.com.au) has joined #ceph
[7:16] * mikedawson (~chatzilla@c-98-220-189-67.hsd1.in.comcast.net) Quit (Read error: Connection reset by peer)
[7:16] * mikedawson (~chatzilla@c-98-220-189-67.hsd1.in.comcast.net) has joined #ceph
[7:35] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit (Quit: No Ping reply in 180 seconds.)
[7:35] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[7:40] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit ()
[7:41] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[7:44] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit ()
[7:45] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[7:49] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit ()
[7:49] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[7:52] * tnt (~tnt@91.177.233.80) has joined #ceph
[7:55] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit (Quit: No Ping reply in 180 seconds.)
[7:55] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[7:58] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit ()
[7:59] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[8:02] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit ()
[8:02] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[8:06] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) Quit ()
[8:06] * _are_ (~quassel@2a01:238:4325:ca00:f065:c93c:f967:9285) has joined #ceph
[8:15] * tokitoki (~juneym@180.194.150.148) has joined #ceph
[8:17] * tokitoki (~juneym@180.194.150.148) Quit ()
[8:17] * tokitoki (~juneym@180.194.150.148) has joined #ceph
[8:18] * tokitoki (~juneym@180.194.150.148) has left #ceph
[8:18] * tokitoki (~juneym@180.194.150.148) has joined #ceph
[8:18] * tokitoki (~juneym@180.194.150.148) has left #ceph
[8:31] * Cube (~Cube@cpe-76-172-67-97.socal.res.rr.com) has joined #ceph
[8:31] * wschulze (~wschulze@cpe-69-203-80-81.nyc.res.rr.com) Quit (Quit: Leaving.)
[9:07] * matt_ (~matt@220-245-1-152.static.tpgi.com.au) Quit (Ping timeout: 480 seconds)
[9:11] * matt_ (~matt@220-245-1-152.static.tpgi.com.au) has joined #ceph
[9:12] * BManojlovic (~steki@91.195.39.5) has joined #ceph
[9:17] * madkiss (~madkiss@213162068101.public.t-mobile.at) has joined #ceph
[9:44] * nebrera (~pablo@91.102.241.62) has joined #ceph
[9:51] * lx0 (~aoliva@lxo.user.oftc.net) Quit (Quit: later)
[9:51] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[9:56] * fghaas (~florian@91-119-65-118.dynamic.xdsl-line.inode.at) has joined #ceph
[10:00] * nebrera (~pablo@91.102.241.62) Quit (Quit: nebrera)
[10:12] * KindOne (~KindOne@0001a7db.user.oftc.net) Quit (Ping timeout: 480 seconds)
[10:22] * ScOut3R (~ScOut3R@54029465.dsl.pool.telekom.hu) has joined #ceph
[10:30] * KindOne (KindOne@0001a7db.user.oftc.net) has joined #ceph
[10:31] * nebrera (~pablo@91.102.241.62) has joined #ceph
[10:34] * madkiss (~madkiss@213162068101.public.t-mobile.at) Quit (Quit: Leaving.)
[11:02] * mattch (~mattch@pcw3047.see.ed.ac.uk) has joined #ceph
[11:04] * eschnou (~eschnou@207.103-201-80.adsl-dyn.isp.belgacom.be) has joined #ceph
[11:27] * nebrera (~pablo@91.102.241.62) Quit (Quit: nebrera)
[11:34] * rustam (~rustam@5e0f5b1e.bb.sky.com) has joined #ceph
[11:37] * eschnou (~eschnou@207.103-201-80.adsl-dyn.isp.belgacom.be) Quit (Ping timeout: 480 seconds)
[11:51] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) has joined #ceph
[11:54] * Cube (~Cube@cpe-76-172-67-97.socal.res.rr.com) Quit (Quit: Leaving.)
[12:03] * eschnou (~eschnou@207.103-201-80.adsl-dyn.isp.belgacom.be) has joined #ceph
[12:15] * eschnou (~eschnou@207.103-201-80.adsl-dyn.isp.belgacom.be) Quit (Ping timeout: 480 seconds)
[12:18] * humbolt (~elias@91-113-96-235.adsl.highway.telekom.at) has joined #ceph
[12:22] * rustam (~rustam@5e0f5b1e.bb.sky.com) Quit (Remote host closed the connection)
[12:24] * BManojlovic (~steki@91.195.39.5) Quit (Remote host closed the connection)
[12:25] * BManojlovic (~steki@91.195.39.5) has joined #ceph
[12:25] * humbolt (~elias@91-113-96-235.adsl.highway.telekom.at) Quit (Quit: humbolt)
[12:34] * piti (~piti@82.246.190.142) has joined #ceph
[12:41] * rustam (~rustam@5e0f5b1e.bb.sky.com) has joined #ceph
[12:43] * rustam (~rustam@5e0f5b1e.bb.sky.com) Quit (Remote host closed the connection)
[12:46] * Kioob (~kioob@2a01:e35:2432:58a0:21e:8cff:fe07:45b6) has joined #ceph
[12:48] * rustam (~rustam@5e0f5b1e.bb.sky.com) has joined #ceph
[12:56] * lxo (~aoliva@lxo.user.oftc.net) Quit (Ping timeout: 480 seconds)
[12:58] * nebrera (~pablo@91.102.241.62) has joined #ceph
[12:59] * nebrera (~pablo@91.102.241.62) Quit ()
[13:02] * KindOne (KindOne@0001a7db.user.oftc.net) Quit (Ping timeout: 480 seconds)
[13:04] * KindOne (KindOne@0001a7db.user.oftc.net) has joined #ceph
[13:04] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[13:04] <mattch> Does anyone know if there is any difference in performance between mounting a disk as e.g. /dev/sda versus creating a single partition on it that is 100% of disk and mounting as /dev/sda1 ?
[13:05] <mattch> I suspect not, but I can't find any hard facts either way
[13:15] * nhorman (~nhorman@2001:470:8:a08:7aac:c0ff:fec2:933b) has joined #ceph
[13:24] * mdxi (~mdxi@74-95-29-182-Atlanta.hfc.comcastbusiness.net) Quit (Ping timeout: 480 seconds)
[13:41] * sleinen (~Adium@217-162-132-182.dynamic.hispeed.ch) has joined #ceph
[13:43] * sleinen1 (~Adium@2001:620:0:26:54d3:7842:38c:31b5) has joined #ceph
[13:46] * sleinen (~Adium@217-162-132-182.dynamic.hispeed.ch) Quit (Read error: Operation timed out)
[13:46] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) Quit (Quit: Leaving.)
[13:54] * mdxi (~mdxi@74-95-29-182-Atlanta.hfc.comcastbusiness.net) has joined #ceph
[13:59] <fghaas> mattch: the only significant performance difference would result from your partition's alignment being crappy
[14:00] <fghaas> but that should not be an issue with modern {,s,c}fdisk
[14:00] <fghaas> which should use a 1M alignment by default, rather than the 63 sectors of DOS days of yore
[14:01] <mattch> fghaas: Thanks - I'm treating the answer as 'it won't really matter' but it's irked me enough that I've probably spent more time than I should trying to find a 'proper' answer :)
[14:03] <fghaas> mattch: yes, on a reasonably recent system it really shouldn't matter
[14:14] * mikedawson (~chatzilla@c-98-220-189-67.hsd1.in.comcast.net) Quit (Ping timeout: 480 seconds)
[14:16] * quanta (~quanta@118.70.170.126) Quit (Quit: Leaving.)
[14:17] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) has joined #ceph
[14:18] * super_favadi (~favadi@14.160.47.150) Quit (Remote host closed the connection)
[14:18] * KevinPerks (~Adium@cpe-066-026-239-136.triad.res.rr.com) has joined #ceph
[14:29] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) Quit (Ping timeout: 480 seconds)
[14:29] * Vjarjadian (~IceChat77@5ad6d005.bb.sky.com) Quit (Quit: A day without sunshine is like .... night)
[14:38] * portante (~user@c-24-63-226-65.hsd1.ma.comcast.net) Quit (Ping timeout: 480 seconds)
[14:42] * ScOut3R (~ScOut3R@54029465.dsl.pool.telekom.hu) Quit (Remote host closed the connection)
[14:47] * sivanov (~sivanov@gw2.maxtelecom.bg) has joined #ceph
[14:56] * aliguori (~anthony@cpe-70-112-157-87.austin.res.rr.com) has joined #ceph
[14:57] * Kioob (~kioob@2a01:e35:2432:58a0:21e:8cff:fe07:45b6) Quit (Quit: Leaving.)
[15:00] * mikedawson (~chatzilla@23-25-46-97-static.hfc.comcastbusiness.net) has joined #ceph
[15:04] * MervR (~Merv.rent@gw.logics.net.au) has joined #ceph
[15:04] * wschulze (~wschulze@cpe-69-203-80-81.nyc.res.rr.com) has joined #ceph
[15:12] * loicd (~loic@magenta.dachary.org) has joined #ceph
[15:13] * loicd (~loic@magenta.dachary.org) Quit ()
[15:15] * Loffler (~Loffler@115-166-35-130.ip.adam.com.au) has joined #ceph
[15:16] <MervR> Hello, we have had a recurrence of the reboot problem we had about 3 weeks ago.
[15:17] <MervR> It seems some of our hosts got a kernel upgrade and they would not work with the others.
[15:18] <MervR> We have now upgraded them all to the latest fedora Core kernel 3.8.4-202 and the system has stabilised but is not rebuilding.
[15:18] <MervR> What might I need to do?
[15:19] <MervR> It shows 254pgs actuve and clean, 322 active and degraded and won't change.
[15:20] <MervR> anyone there from Ceph?
[15:22] * diegows (~diegows@200-081-038-055.wireless.movistar.net.ar) has joined #ceph
[15:22] <josef> MervR: not sure about the community people but most the people i know who work on it are pst, so they wont be up for a nother couple of hours
[15:27] * Kioob (~kioob@2a01:e35:2432:58a0:21e:8cff:fe07:45b6) has joined #ceph
[15:28] * slang1 (~slang@207-229-177-80.c3-0.drb-ubr1.chi-drb.il.cable.rcn.com) has joined #ceph
[15:36] <BillK> MervR: Whar ceph version?
[15:36] <BillK> MervR: s/What/What/
[15:37] <BillK> MervR: s/Whar/What/
[15:38] * scuttlemonkey (~scuttlemo@fl-184-1-34-163.dhcp.embarqhsd.net) has joined #ceph
[15:38] * ChanServ sets mode +o scuttlemonkey
[15:45] * mikedawson_ (~chatzilla@23-25-46-97-static.hfc.comcastbusiness.net) has joined #ceph
[15:46] * mikedawson (~chatzilla@23-25-46-97-static.hfc.comcastbusiness.net) Quit (Ping timeout: 480 seconds)
[15:46] * mikedawson_ is now known as mikedawson
[15:47] * madkiss (~madkiss@port-213-160-22-242.static.qsc.de) has joined #ceph
[15:50] <MervR> Our tech. got back in touch and seems to have it working now ... Thanks for offer of help.
[15:51] * MervR (~Merv.rent@gw.logics.net.au) Quit (Quit: Leaving)
[16:00] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) has joined #ceph
[16:11] * maria19 (~fl_cgs000@14.Red-81-33-156.dynamicIP.rima-tde.net) has joined #ceph
[16:12] <maria19> hottyyy https://www.youtube.com/watch?v=NvijX055h5M
[16:13] * maria19 (~fl_cgs000@14.Red-81-33-156.dynamicIP.rima-tde.net) Quit (Remote host closed the connection)
[16:14] * PerlStalker (~PerlStalk@72.166.192.70) has joined #ceph
[16:20] * barryo (~borourke@cumberdale.ph.ed.ac.uk) has left #ceph
[16:25] * barryo (~borourke@cumberdale.ph.ed.ac.uk) has joined #ceph
[16:36] * jskinner (~jskinner@69.170.148.179) has joined #ceph
[16:37] * calebamiles (~caleb@pool-70-109-184-32.burl.east.myfairpoint.net) has joined #ceph
[16:46] * scuttlemonkey (~scuttlemo@fl-184-1-34-163.dhcp.embarqhsd.net) Quit (Ping timeout: 480 seconds)
[16:46] * loicd (~loic@magenta.dachary.org) has joined #ceph
[16:57] * ScOut3R (~ScOut3R@54029465.dsl.pool.telekom.hu) has joined #ceph
[17:02] * rustam (~rustam@5e0f5b1e.bb.sky.com) Quit (Remote host closed the connection)
[17:03] * rustam (~rustam@5e0f5b1e.bb.sky.com) has joined #ceph
[17:21] * mib_wnihpo (522f4fbe@ircip1.mibbit.com) has joined #ceph
[17:21] <mib_wnihpo> http://www.fanteamz.com/bloodstock/cc/9/97
[17:24] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[17:24] * ivotron (~ivo@adsl-76-254-17-170.dsl.pltn13.sbcglobal.net) Quit (Read error: Operation timed out)
[17:24] * loicd (~loic@magenta.dachary.org) has joined #ceph
[17:25] * jlogan1 (~Thunderbi@2600:c00:3010:1:fc52:a0e0:824c:3a1d) has joined #ceph
[17:27] * madkiss1 (~madkiss@port-213-160-22-242.static.qsc.de) has joined #ceph
[17:31] * madkiss (~madkiss@port-213-160-22-242.static.qsc.de) Quit (Ping timeout: 480 seconds)
[17:31] * mib_wnihpo (522f4fbe@ircip1.mibbit.com) Quit (Quit: http://www.mibbit.com ajax IRC Client)
[17:32] * madkiss1 (~madkiss@port-213-160-22-242.static.qsc.de) Quit (Quit: Leaving.)
[17:33] * gregaf1 (~Adium@2607:f298:a:607:5821:1d2f:db7f:4ea2) Quit (Quit: Leaving.)
[17:34] * gregaf (~Adium@2607:f298:a:607:5821:1d2f:db7f:4ea2) has joined #ceph
[17:40] * BManojlovic (~steki@91.195.39.5) Quit (Quit: Ja odoh a vi sta 'ocete...)
[17:41] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[17:54] * lxo (~aoliva@lxo.user.oftc.net) Quit (Remote host closed the connection)
[17:55] * lxo (~aoliva@lxo.user.oftc.net) has joined #ceph
[17:59] * dosaboy (~gizmo@host86-161-164-218.range86-161.btcentralplus.com) has joined #ceph
[18:04] * buck (~buck@bender.soe.ucsc.edu) has joined #ceph
[18:08] * BillK (~BillK@58-7-222-160.dyn.iinet.net.au) Quit (Ping timeout: 480 seconds)
[18:11] <jlogan1> dmick: Thanks for the response about Ubuntu 13.04. I am working on a new openstack cluster and wanting to try out Grizzly and the packages I see for that are 12.04 and 13.04, but no 12.10.
[18:13] * rustam (~rustam@5e0f5b1e.bb.sky.com) Quit (Remote host closed the connection)
[18:15] * glowell (~glowell@c-98-210-224-250.hsd1.ca.comcast.net) Quit (Quit: Leaving.)
[18:16] * madkiss (~madkiss@port-213-160-22-242.static.qsc.de) has joined #ceph
[18:16] * loicd (~loic@185.10.252.15) has joined #ceph
[18:17] * fghaas (~florian@91-119-65-118.dynamic.xdsl-line.inode.at) has left #ceph
[18:18] * jskinner (~jskinner@69.170.148.179) Quit (Remote host closed the connection)
[18:19] * glowell (~glowell@c-98-210-224-250.hsd1.ca.comcast.net) has joined #ceph
[18:21] <mikedawson> jlogan1: I've had success pointing to the ceph repo wiith packages for Quantal to install packages for Raring testing
[18:21] * BillK (~BillK@58-7-168-175.dyn.iinet.net.au) has joined #ceph
[18:22] * terje (~Adium@c-67-176-69-220.hsd1.co.comcast.net) has joined #ceph
[18:25] * jamespage (~jamespage@culvain.gromper.net) Quit (Quit: Coyote finally caught me)
[18:25] * diegows (~diegows@200-081-038-055.wireless.movistar.net.ar) Quit (Read error: Operation timed out)
[18:25] * jamespage (~jamespage@culvain.gromper.net) has joined #ceph
[18:26] <jlogan1> I'm trying that now. I had ceph installed so the Ubuntu upgrade renamed it to Raring.
[18:27] <jlogan1> apt-get update does not complain. but there are no updates. I'll find out when I build the next host.
[18:27] <jlogan1> thanks for the idea.
[18:27] <mikedawson> jlogan1: Instead of "echo deb http://ceph.com/debian-testing/ $(lsb_release -sc) main | sudo tee /etc/apt/sources.list.d/ceph.list"
[18:27] <mikedawson> jlogan1: do "echo deb http://ceph.com/debian-testing/ quantal main | sudo tee /etc/apt/sources.list.d/ceph.list"
[18:28] <jlogan1> Thanks.
[18:29] <mikedawson> jlogan1: I've had some success / some issues, but it seems to work for testing purposes
[18:34] * sleinen1 (~Adium@2001:620:0:26:54d3:7842:38c:31b5) Quit (Quit: Leaving.)
[18:34] * sleinen (~Adium@217-162-132-182.dynamic.hispeed.ch) has joined #ceph
[18:41] * jmlowe (~Adium@173-15-112-198-Illinois.hfc.comcastbusiness.net) has joined #ceph
[18:42] * sleinen (~Adium@217-162-132-182.dynamic.hispeed.ch) Quit (Ping timeout: 480 seconds)
[18:43] * fghaas (~florian@91-119-65-118.dynamic.xdsl-line.inode.at) has joined #ceph
[18:45] * Cube (~Cube@cpe-76-172-67-97.socal.res.rr.com) has joined #ceph
[18:46] * scuttlemonkey (~scuttlemo@fl-184-1-34-163.dhcp.embarqhsd.net) has joined #ceph
[18:46] * ChanServ sets mode +o scuttlemonkey
[18:47] * jmlowe (~Adium@173-15-112-198-Illinois.hfc.comcastbusiness.net) Quit (Quit: Leaving.)
[18:48] * alram (~alram@38.122.20.226) has joined #ceph
[18:48] * jskinner (~jskinner@69.170.148.179) has joined #ceph
[18:52] <sjust> good morning #ceph. Anyone want to review the 4510 pull request?
[18:53] * fghaas (~florian@91-119-65-118.dynamic.xdsl-line.inode.at) Quit (Quit: Leaving.)
[18:56] * madkiss1 (~madkiss@port-213-160-22-242.static.qsc.de) has joined #ceph
[18:56] * madkiss (~madkiss@port-213-160-22-242.static.qsc.de) Quit (Read error: Connection reset by peer)
[18:58] * BManojlovic (~steki@fo-d-130.180.254.37.targo.rs) has joined #ceph
[18:59] * jskinner (~jskinner@69.170.148.179) Quit (Ping timeout: 480 seconds)
[19:06] * portante (~user@66.187.233.206) has joined #ceph
[19:06] <gregaf> yehudasa: test_cors introduced a signed/unsigned comparison warning
[19:06] <gregaf> I've got a patch that just passes argc around as an unsigned which fixes it, sound good?
[19:06] <gregaf> (sagewk: I guess you merged it ^)
[19:07] * sivanov (~sivanov@gw2.maxtelecom.bg) Quit (Ping timeout: 480 seconds)
[19:08] * terje (~Adium@c-67-176-69-220.hsd1.co.comcast.net) Quit (Quit: Leaving.)
[19:10] * rustam (~rustam@5e0f5b1e.bb.sky.com) has joined #ceph
[19:10] <sagewk> gregaf: warning where?
[19:11] <sagewk> oh i see
[19:11] <gregaf> the macro in extract_input compares "int argc" and "unsigned loop"
[19:12] <gregaf> here: http://fpaste.org/jLcx/
[19:12] * rturk-away is now known as rturk
[19:12] <sagewk> gregaf: yeah unsigned argc sounds good
[19:12] <gregaf> k
[19:13] * BillK (~BillK@58-7-168-175.dyn.iinet.net.au) Quit (Read error: Operation timed out)
[19:13] <dmick> it's difficult to suck arguments out of a program, for sure. although now that I say that that's sorta what I'm doing. Maybe I should implement that with negative argc.
[19:16] * jskinner (~jskinner@69.170.148.179) has joined #ceph
[19:18] * jskinner (~jskinner@69.170.148.179) Quit (Remote host closed the connection)
[19:25] * ivotron (~ivo@dhcp-59-180.cse.ucsc.edu) has joined #ceph
[19:27] <Psi-jack> What is the likelyhood of me being able to change out my underlying Linux OS with another, keeping /etc/ceph, all the OSD's exactly in-tact, and literally just changing OS, and not mucking up Ceph itself, the data, etc, one by one until all three of my Ceph servers are done this way?
[19:29] * jskinner (~jskinner@69.170.148.179) has joined #ceph
[19:30] * jmlowe (~Adium@c-71-201-31-207.hsd1.in.comcast.net) has joined #ceph
[19:31] <gregaf> well, you'd need to watch out for changes to your init system (which is just touching and removing a couple files in your data directories for newish Ceph) and for something like going backwards with your leveldb version
[19:31] <gregaf> I think everything else would probably work...
[19:33] * diegows (~diegows@190.190.2.126) has joined #ceph
[19:43] * davidz (~Adium@ip68-96-75-123.oc.oc.cox.net) has joined #ceph
[19:45] * rustam (~rustam@5e0f5b1e.bb.sky.com) Quit (Remote host closed the connection)
[19:50] * dpippenger (~riven@216.103.134.250) has joined #ceph
[19:50] * rustam (~rustam@5e0f5b1e.bb.sky.com) has joined #ceph
[20:01] * terje (~Adium@184-96-148-241.hlrn.qwest.net) has joined #ceph
[20:03] * BMDan (~BMDan@static-108-44-155-130.clppva.fios.verizon.net) has joined #ceph
[20:05] <BMDan> I suspect that all I need here is just a kick in the head, but anyone able to explain what I'm doing wrong with http://pastebin.ca/2347110 ?
[20:06] <dmick> rbd.ko isn't loaded, either because it's not there or a bug
[20:06] * andreask (~andreas@h081217068225.dyn.cm.kabsi.at) has joined #ceph
[20:06] <dmick> which kernel?
[20:07] <BMDan> dmick: "ls -1 /sys/bus/rbd/ | wc -l" == 7
[20:07] <BMDan> kernel = 3.2.0-39-generic
[20:07] <dmick> oh duh
[20:07] <BMDan> rbd shows loaded in lsmod
[20:07] <dmick> sorry, yes, that's just so usual, the open is succeeding tho
[20:08] <BMDan> Right, fair question. :)
[20:08] * sleinen (~Adium@user-28-15.vpn.switch.ch) has joined #ceph
[20:08] <dmick> is volume-bca496cf-ce4a-4944-ba92-0733badfcc2b a format=2 image, by chance?
[20:08] <BMDan> I also was worried about the auth part, so I tried feeding it incorrect or insufficient auth; that gives me a different error, so it's definitely getting *somewhere*.
[20:08] <BMDan> Yeah, that's in the "info" output.
[20:09] <BMDan> It's format=2.
[20:09] <dmick> so it is. there's your problem
[20:09] <dmick> the kernel can't handle that yet
[20:09] <BMDan> Hrmm?
[20:09] <BMDan> Oh.
[20:09] <BMDan> Harrumph.
[20:09] <BMDan> Okay, so here's my ultimate goal: I just want to mount this volume somewhere so I can fiddle directly with the bits, ideally without export/import (which would destroy the CoW).
[20:10] <dmick> can you do it from a qemu-kvm machine?
[20:11] <BMDan> Seems like a lot of work to spawn a virt just so I can edit the volume, but—yes, sounds doable if that's the only way. :\
[20:11] <dmick> it's possible libguestfs would work
[20:12] <dmick> I have no experience with it
[20:13] <BMDan> No, fair enough. Sounds like I'm trying to do something a bit too fancy. Do newer kernels support format=2, or is there a FUSE implementation that does?
[20:14] <dmick> the kernel support is nearly there, but not quite done
[20:15] <dmick> rbd-fuse might work; it's in the source tree but not packaged
[20:15] <dmick> as an experimental
[20:15] <dmick> it's worth a try
[20:15] <dmick> (I've definitely mounted ext4-bearing images with it)
[20:15] <Psi-jack> gregaf: Yeah, init I know already would change, because I'd be switching from systemd-based init to openrc, but I'd be managing the ceph services via supervisord, rather than openrc (since openrc doesn't have supervisor functionality yet)
[20:17] <BMDan> rgr dmick, thanks for the pointers. :)
[20:17] <dmick> no worries. let us know how you get on.
[20:17] <Psi-jack> Main thing is, Arch, as it's designed, makes maintaining build compatability with updates more painful than anything.
[20:18] <Psi-jack> So, I'm pondering switching it out to funtoo. :)
[20:22] * loicd (~loic@185.10.252.15) Quit (Ping timeout: 480 seconds)
[20:24] * ninkotech (~duplo@ip-89-102-24-167.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[20:24] * ninkotech_ (~duplo@ip-89-102-24-167.net.upcbroadband.cz) Quit (Read error: Connection reset by peer)
[20:24] * ninkotech (~duplo@ip-89-102-24-167.net.upcbroadband.cz) has joined #ceph
[20:24] * ninkotech_ (~duplo@ip-89-102-24-167.net.upcbroadband.cz) has joined #ceph
[20:32] * terje (~Adium@184-96-148-241.hlrn.qwest.net) has left #ceph
[20:41] * KevinPerks (~Adium@cpe-066-026-239-136.triad.res.rr.com) Quit (Quit: Leaving.)
[20:52] * loicd (~loic@magenta.dachary.org) has joined #ceph
[20:57] * andreask (~andreas@h081217068225.dyn.cm.kabsi.at) Quit (Quit: Leaving.)
[20:57] * andreask (~andreas@h081217068225.dyn.cm.kabsi.at) has joined #ceph
[21:07] * Cube (~Cube@cpe-76-172-67-97.socal.res.rr.com) Quit (Quit: Leaving.)
[21:08] * SvenPHX (~scarter@wsip-174-79-34-244.ph.ph.cox.net) has joined #ceph
[21:29] * Cube (~Cube@12.248.40.138) has joined #ceph
[21:30] <jlogan1> Has anyone setup Grizzly Cinder with RBD? My setup is still missing something.
[21:31] <scuttlemonkey> jlogan1: missing what? Is it erroring or just not working?
[21:31] <jlogan1> VolumeBackendAPIException: Bad or unexpected response from the storage volume backend API: volume group cinder-volumes doesn't exist
[21:32] <jlogan1> it looks like it's skipping the rbd module
[21:32] <jlogan1> I'm using volume_drivers=cinder.volume.drivers.rbd
[21:32] <jlogan1> I used to use volume_driver=cinder.volume.driver.RBDDriver with the previous release.
[21:34] <jlogan1> Looking at the log it's still using LVM.
[21:35] <scuttlemonkey> hmm
[21:35] <scuttlemonkey> that seems vaguely familiar...and not in a ceph way
[21:35] <scuttlemonkey> one sec
[21:36] <scuttlemonkey> https://bugs.launchpad.net/openstack-manuals/+bug/1078353
[21:38] <scuttlemonkey> that aside, lemme look at what changed w/ grizzly
[21:39] <jlogan1> ok. I'll try making the file as well and see what happens.
[21:39] <scuttlemonkey> dunno if that's the answer...I just remembered stumbling across that bug report
[21:39] <scuttlemonkey> I'll poke at it here in a sec
[21:41] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) Quit (Quit: Leaving.)
[21:44] <scuttlemonkey> jlogan1: fwiw, these appear to be up-to-date
[21:44] <scuttlemonkey> http://ceph.com/docs/master/rbd/rbd-openstack/#configuring-cinder-nova-volume
[21:44] <scuttlemonkey> so the .RBDDriver is the new one (although per Joshd it's backward compatible and will just show a warning)
[21:47] <jlogan1> I still get a warning on start if I don't have the LVM volume.
[21:49] <jlogan1> http://pastebin.com/BrCHtxsX
[21:49] <jlogan1> but once I setup a dummy cinder-volumes then I can see the rbd data.
[21:51] <scuttlemonkey> 'dummy cinder-volumes' ?
[21:52] <scuttlemonkey> user?
[21:53] <scuttlemonkey> so in your cinder.conf you have the volume_driver, rbd_pool, rbd_user, and rbd_secret?
[21:53] <scuttlemonkey> and it's still not using rbd?
[21:53] <scuttlemonkey> (assuming you're using cephx auth)
[21:58] * eschnou (~eschnou@207.103-201-80.adsl-dyn.isp.belgacom.be) has joined #ceph
[21:59] <jlogan1> It's using it, but the first check fails.
[22:00] <jlogan1> http://pastebin.com/KpfV6EB4
[22:01] <jlogan1> the images it lists are on Ceph
[22:03] <BMDan> jlogan1: Does your rbd_secret_UUID actually read "CHANGE"?
[22:03] <jlogan1> no
[22:03] * eschnou (~eschnou@207.103-201-80.adsl-dyn.isp.belgacom.be) Quit (Quit: Leaving)
[22:04] <jlogan1> it's working, but I needed a dummy vgvolume.
[22:05] <BMDan> http://pastebin.com/LjQWhr94 <— this is my working cinder.conf
[22:07] <jlogan1> Need to take a call. I'll compare in a few minutes.
[22:14] * james (~james@143.48.7.168) has joined #ceph
[22:14] * james is now known as Guest908
[22:15] <Guest908> Hi, I noticed that the ceph-client on github is the whole linux 3 tree
[22:15] <Guest908> Is it possible to compile just the ceph module against another kernel?
[22:25] * nhorman (~nhorman@2001:470:8:a08:7aac:c0ff:fec2:933b) Quit (Quit: Leaving)
[22:25] <BMDan> git clone kernel, diff -r kernel ceph-client, apply patch to your kernel, profit?
[22:28] <Guest908> profit as in my company?
[22:29] <dmick> Guest908: I don't think we've made significant, if any, changes to the outside kernel.
[22:30] * houkouonchi-work (~linux@12.248.40.138) Quit (Remote host closed the connection)
[22:31] * houkouonchi-work (~linux@12.248.40.138) has joined #ceph
[22:32] * leseb (~Adium@pha75-6-82-226-32-84.fbx.proxad.net) has joined #ceph
[22:32] * themgt (~themgt@24-177-232-181.dhcp.gnvl.sc.charter.com) has joined #ceph
[22:36] <jlogan1> BMDan: That version does not need the dummy "vgcreate cinder-volumes". You have iscsi_helper = tgtadm set in your config. I wonder if that changed the cinder scanning on startup.
[22:37] * wer__ (~wer@206-248-239-142.unassigned.ntelos.net) has joined #ceph
[22:38] * wer__ (~wer@206-248-239-142.unassigned.ntelos.net) Quit (Remote host closed the connection)
[22:38] * wer_ (~wer@206-248-239-142.unassigned.ntelos.net) Quit (Remote host closed the connection)
[22:38] * wer_ (~wer@206-248-239-142.unassigned.ntelos.net) has joined #ceph
[22:45] <BMDan> jlogan1: Certainly possible. Not sure offhand where I found that setting, but I believe it was in the ceph.org OpenStack docs.
[22:45] * BMDan (~BMDan@static-108-44-155-130.clppva.fios.verizon.net) Quit (Quit: Leaving.)
[22:46] * houkouonchi-home (~linux@pool-108-38-63-48.lsanca.fios.verizon.net) Quit (Ping timeout: 480 seconds)
[22:58] <Elbandi_> how can i speedup the mds replay?
[22:59] <gregaf> Elbandi_: how long is it taking you?
[23:02] <Elbandi_> i restarted the mds ~15 min ago
[23:02] <Elbandi_> and still replay
[23:04] * LOIC_MPTXPC (~IRCLOIC@79.141.160.64) has joined #ceph
[23:04] * humbolt (~elias@91-113-41-56.adsl.highway.telekom.at) has joined #ceph
[23:06] * LOIC_MPTXPC (~IRCLOIC@79.141.160.64) Quit (Remote host closed the connection)
[23:17] * jskinner (~jskinner@69.170.148.179) Quit (Remote host closed the connection)
[23:19] * themgt (~themgt@24-177-232-181.dhcp.gnvl.sc.charter.com) Quit (Quit: themgt)
[23:21] <slang1> Elbandi_: you might verify that the mds is actively replaying with ceph mds a injectargs '--debug_mds 20'
[23:21] <slang1> Elbandi_: and then look at the mds.a.log for a bunch of replay messages
[23:22] <slang1> Elbandi_: (disable it with --debug_mds 0 after you're done checking)
[23:22] <slang1> oops
[23:23] <slang1> Elbandi_: http://ceph.com/docs/master/rados/operations/control/#mds-subsystem
[23:23] <slang1> Elbandi_: its: ceph tell mds a injectargs ...
[23:23] <slang1> Elbandi_: assuming its mds.a that you restarted
[23:23] * jskinner (~jskinner@69.170.148.179) has joined #ceph
[23:24] * ScOut3R (~ScOut3R@54029465.dsl.pool.telekom.hu) Quit (Ping timeout: 480 seconds)
[23:27] <gregaf> yeah, if it's taking 15 minutes something is broken
[23:33] <Elbandi_> i made the injectargs
[23:34] * jskinner (~jskinner@69.170.148.179) Quit (Remote host closed the connection)
[23:34] <Elbandi_> last message
[23:34] <Elbandi_> 2013-04-01 23:33:54.241080 7f8ba5990700 0 mds.1.232 ms_handle_reset on 194.x.x.x:6800/880
[23:34] <Elbandi_> 2013-04-01 23:33:54.242846 7f8ba5990700 0 mds.1.232 ms_handle_connect on 194.x.x.x:6800/880
[23:35] <Elbandi_> this is a osd node
[23:36] <Elbandi_> i restarted the mds with debug_mds 20 in config
[23:40] <gregaf> joao: there?
[23:40] <joao> here
[23:40] <gregaf> Jim Schutt just sent a fun little email to the list about paxos commit times with large pg counts
[23:41] <joao> ceph-devel?
[23:41] <gregaf> yeah
[23:41] <gregaf> this actually sounds familiar as something that we did horribly wrong previously too, but I don't think the absolute values were so high with such low pg counts previously
[23:41] <joao> ah, seen it
[23:41] <joao> s/seen/found
[23:43] * dosaboy (~gizmo@host86-161-164-218.range86-161.btcentralplus.com) Quit (Quit: Leaving.)
[23:43] <joao> well, there's the possibility that a proposal takes more time to finish now that we have a single paxos instance
[23:44] <joao> haven't looked into the timestamps though, don't know how long it is taking
[23:45] * buck (~buck@bender.soe.ucsc.edu) has left #ceph
[23:46] * slang1 (~slang@207-229-177-80.c3-0.drb-ubr1.chi-drb.il.cable.rcn.com) Quit (Read error: Operation timed out)
[23:46] <Elbandi_> is it possible to "commit" the mds journal? so mds need to load the last state only
[23:47] <joao> oh wait
[23:47] <joao> gregaf, that is happening with ONE monitor
[23:47] <joao> that is weird
[23:47] <gregaf> joao: well, his last one is a minute
[23:47] <joao> yeah
[23:47] <joao> just saw that and went to look for how many monitors he was running
[23:47] <joao> I wonder if this is a symptom of an overloaded monitor
[23:48] <joao> too many messages being handled might cause this sort of thing
[23:48] <gregaf> well, the conversion included a switch to handling the PGMap in more discrete chunks, right?
[23:49] <joao> oh, no
[23:49] <joao> and worst of all
[23:49] <gregaf> or am I mixing up Sage's wants with what actually happened?
[23:49] <gregaf> (I know we haven't fully chunked it but I thought it was committing more frequently or something)
[23:49] <joao> I have to check
[23:49] * ninkotech_ (~duplo@ip-89-102-24-167.net.upcbroadband.cz) Quit (Remote host closed the connection)
[23:49] <joao> I wonder how frequently we're checkpointing the pgmap
[23:49] <gregaf> joao: oh, that's what it is — we're passing around a full pgmap on every commit, right?
[23:49] <joao> yeah
[23:49] <joao> think so
[23:50] <joao> and I believe there's a fair chance we're writing the whole thing to disk
[23:50] <joao> have to check that
[23:50] <gregaf> yeah, which we weren't previously
[23:50] <gregaf> although this *ought* to still only be a single commit?
[23:51] <joao> yeah
[23:51] <gregaf> but perhaps the full map is large enough that it's just driving leveldb crazy
[23:51] <joao> I'll have to ask Jim for debug ms = 1 logs
[23:51] <joao> yeah, might be
[23:53] <pioto> hi. with cephfs, i'm wondering the cost of keeping the rbytes option on... is it basically a constant-time operation to get it, or will directory trees with many files have issues if you have it on?
[23:54] <gregaf> pioto: it's basically free and I believe the option is just about what gets displayed in the kernel client — they're kept server-side regardless
[23:55] * loicd (~loic@magenta.dachary.org) Quit (Quit: Leaving.)
[23:55] <pioto> ok. so, each write is basically having the MDS update the 'dirent' objects for all the parents too, as i understand it?
[23:55] <pioto> but it's decided that is cheap enough to keep doing all the time?
[23:56] <pioto> or, is it counted just at the rados object layer in a quick way instead?
[23:56] <gregaf> it's not really on each write; the statistics are lazily updated opportunistically as locking allows
[23:56] <pioto> ah, ok
[23:56] <pioto> but it's "good enough for basic reporting"
[23:56] <pioto> and at least as good if not better than 'du' for the same task
[23:56] <gregaf> yeah, "lazily" has a different meaning here than when we're talking about me cleaning my kitchen ;)
[23:57] <pioto> yes, it's asyncronous
[23:57] <gregaf> I'd be surprised if it were ever 5 seconds out of date
[23:57] <pioto> ok
[23:57] <pioto> so, much better than 'du' would take to traverse some trees
[23:57] * rustam (~rustam@5e0f5b1e.bb.sky.com) Quit (Remote host closed the connection)
[23:57] <pioto> great

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