Hi, I'm having issues with data corruption on RBD volumes again. I'm using RBD volumes for virtual harddisks for qemu-kvm virtual machines. Inside these virtual machines I have been running a C++ program (attached) that fills a mounted filesystem with 1 Megabyte files of random data, while using the SHA1-checksum of said random data as the names for those files. After this, it reads all those files in again and checks their checksum. Last time I ran this program, it would report 300 wrong digests out of ~50000. I could not observe those corruptions when running the same test on a volume backed by a qcow2 image on an NFS share. This problem is fairly hard to reproduce, but it is reproducable. So far, the combination that seems most likely to trigger this bug seems to be this: - Run the test on a big (50GB) and freshly created volume (i.e. one that is still mostly sparse) - Write the data with a very large number of concurrent threads (1000+) - In the middle of writing, take down one OSD. It seems to matter which OSD that is, so far I could only reproduce the bug taking down the third of three OSDs My setup is Ceph 0.61.2 on three machines, each running one OSD and one MON. The last one is also running an MDS. The ceph.conf file is attached. I have just updated to 0.61.3 and plan on rerunning the test on that. The platform is Fedora 18 in all cases with kernel 3.9.4-200.fc18.x86_64. The client is a Fedora 17 based machine with Qemu 1.2.0-14.fc17 and Ceph 0.61.2. (The yum repository for Fedora 17 does not appear to contain 0.61.3 yet.) Regards, Guido
; global
[global]
max open files = 131072
log file = /var/log/ceph/$name.log
; log_to_syslog = true ; uncomment this line to log to syslog
pid file = /var/run/ceph/$name.pid
auth client required = cephx
auth service required = cephx
auth cluster required = cephx
; monitors
[mon]
mon data = /mondata/$name
[mon.alpha]
host = storage1
mon addr = 10.6.224.129:6789
[mon.beta]
host = storage2
mon addr = 10.6.224.130:6789
[mon.gamma]
host = storage3
mon addr = 10.6.224.131:6789
; mds
[mds]
; where the mds keeps it's secret encryption keys
keyring = /mdsdata/keyring.$name
;[mds.alpha]
; host = storage1
;[mds.beta]
; host = storage2
[mds.gamma]
host = storage3
; osd
[osd]
osd data = /osddata/$name
osd journal = /journaldata/$name/journal
osd journal size = 1000 ; journal size, in megabytes
; If you want to run the journal on a tmpfs, disable DirectIO
journal dio = false
osd recovery max active = 5
keyring = /osddata/$name/keyring
filestore fiemap = false
[osd.0]
host = storage1
cluster addr = 10.6.224.193
public addr = 10.6.224.129
[osd.1]
host = storage2
cluster addr = 10.6.224.194
public addr = 10.6.224.130
[osd.2]
host = storage3
cluster addr = 10.6.224.195
public addr = 10.6.224.131
[client] ; userspace client
; debug ms = 1
; debug client = 10
Attachment:
iotest-threaded.tar.bz2
Description: application/bzip-compressed-tar
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
