Hello all. I fight with strange problem for more than a 3 week.
What we have:2xDell 2950 with Debian 5.0 2.6.32-bpo.5-amd64 from backports with DRBD inside + OCFS2
I make a heavy load by iozone on OCFS2 partition: iozone -RK -t 4 -s 10g -i 0 -i 1 -i 2 -b /tmp/`hostname`.xls on both nodes.And after a 1-3 hour servers(both) reboots. It is DRBD or OCFS2 related just because it is not happend on normal partition. OCFS2 developers look at stack trace what I catch(in attachment) and say what it is not a OCFS2 problem.
I start to think what it is hardware or system. I try 2.6.26 kernel and updating to testing - not helps at all.
So - it is hardware or DRBD. Could you please help me to find out there problem is?
Configs below:
mail01:~# cat /etc/drbd.d/drbd0.res
resource drbd0 {
on mail01.fxclub.org {
device /dev/drbd0;
disk /dev/sda9;
address 192.168.1.1:7789;
meta-disk internal;
}
on mail02.fxclub.org {
device /dev/drbd0;
disk /dev/sda9;
address 192.168.1.2:7789;
meta-disk internal;
}
}
mail01:~# cat /etc/drbd.d/global_common.conf
global {
usage-count yes;
# minor-count dialog-refresh disable-ip-verification
}
common {
protocol C;
handlers {
pri-on-incon-degr "/usr/lib/drbd/notify-pri-on-incon-degr.sh;
/usr/lib/drbd/notify-emergency-reboot.sh; echo b > /proc/sysrq-trigger ;
reboot -f";
pri-lost-after-sb "/usr/lib/drbd/notify-pri-lost-after-sb.sh;
/usr/lib/drbd/notify-emergency-reboot.sh; echo b > /proc/sysrq-trigger ;
reboot -f";
local-io-error "/usr/lib/drbd/notify-io-error.sh;
/usr/lib/drbd/notify-emergency-shutdown.sh; echo o > /proc/sysrq-trigger
; halt -f";
outdate-peer "/usr/lib/heartbeat/drbd-peer-outdater -t 5";
# fence-peer "/usr/lib/drbd/crm-fence-peer.sh";
split-brain "/usr/lib/drbd/notify-split-brain.sh root";
# out-of-sync "/usr/lib/drbd/notify-out-of-sync.sh root";
# before-resync-target "/usr/lib/drbd/snapshot-resync-target-lvm.sh -p
15 -- -c 16k";
# after-resync-target
/usr/lib/drbd/unsnapshot-resync-target-lvm.sh;
}
startup {
wfc-timeout 60;
degr-wfc-timeout 30;
outdated-wfc-timeout 15;
become-primary-on both;
# wait-after-sb;
}
disk {
fencing resource-and-stonith;
no-disk-flushes;
no-md-flushes;
no-disk-barrier;
# on-io-error fencing use-bmbv no-disk-barrier no-disk-flushes
# no-disk-drain no-md-flushes max-bio-bvecs
}
net {
cram-hmac-alg sha1;
shared-secret "password";
allow-two-primaries;
ping-timeout 20;
after-sb-0pri discard-zero-changes;
after-sb-1pri discard-secondary;
after-sb-2pri disconnect;
data-integrity-alg sha1;
# Tuning
max-buffers 8000;
max-epoch-size 8000;
sndbuf-size 0;
# snd.buf-size rcvbuf-size timeout connect-int ping-int ping-timeout
max-buffers
# max-epoch-size ko-count allow-two-primaries cram-hmac-alg
shared-secret
# after-sb-0pri after-sb-1pri after-sb-2pri data-integrity-alg
no-tcp-cork
}
syncer {
rate 60M;
al-extents 3389;
# rate after al-extents use-rle cpu-mask verify-alg csums-alg
}
}
P.S. I start to think what it can be a handlers and comented them - not
help.
-- Best regards, Proskurin Kirill
<<attachment: debian-bug.jpg>>
_______________________________________________ drbd-user mailing list [email protected] http://lists.linbit.com/mailman/listinfo/drbd-user
