<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1">
</head>
<body bgcolor="#FFFFFF" text="#000000">
Hi,<br>
<br>
I'm doing tests on a new DRBD setup, so I'm hammering the DRBD
system with reads and writes (3 VMs writing with dd and three VMs
reading with dd). The test max's out my 2x1GigE bonded links (both
data and sync) and max's out my hard drives (5 7200 RPM SATA,
RAID6). I share the drbd disks to Proxmox (KVM based) via NFS v3.<br>
<br>
1. I tested the system all night, and both DRBD servers handled
everything fine. <br>
2. I reboot the primary<br>
3. failover of the IP and NFS worked, and secondary became primary.<br>
4. reboot server came back up, and entered slit-brain.<br>
<br>
I use uCarp for the failover instead of heartbeat/pacemaker.<br>
<br>
I've used iSCSI over DRBD/heartbeat before, but not NFS. Any ideas
why I hit split brain?<br>
<br>
Gerald<br>
<br>
<br>
drbd.conf<br>
<font face="Courier New, Courier, monospace"># cat /etc/drbd.conf<br>
# You can find an example in
/usr/share/doc/drbd.../drbd.conf.example<br>
<br>
include "drbd.d/global_common.conf";<br>
# include "drbd.d/*.res";<br>
<br>
resource target.0 {<br>
protocol C;<br>
<br>
handlers {<br>
pri-on-incon-degr "echo o > /proc/sysrq-trigger ; halt
-f";<br>
pri-lost-after-sb "echo o > /proc/sysrq-trigger ; halt
-f";<br>
local-io-error "echo o > /proc/sysrq-trigger ; halt
-f";<br>
outdate-peer "/usr/lib/heartbeat/drbd-peer-outdater -t
5"; <br>
before-resync-target /usr/local/bin/resync-start-RAID6.sh;<br>
after-resync-target /usr/local/bin/resync-end-RAID6.sh;<br>
}<br>
<br>
startup {<br>
degr-wfc-timeout 120;<br>
}<br>
<br>
disk {<br>
on-io-error detach;<br>
}<br>
<br>
net {<br>
cram-hmac-alg sha1;<br>
shared-secret "password";<br>
after-sb-0pri disconnect;<br>
after-sb-1pri disconnect;<br>
after-sb-2pri disconnect;<br>
rr-conflict disconnect;<br>
sndbuf-size 0;<br>
}<br>
<br>
syncer {<br>
c-plan-ahead 0;<br>
rate 30M;<br>
verify-alg sha1;<br>
# al-extents 257;<br>
al-extents 3389;<br>
}<br>
<br>
on iscsi-filer-1 {<br>
device /dev/drbd0;<br>
disk /dev/md0;<br>
address 192.168.10.1:7789;<br>
flexible-meta-disk /dev/md3;<br>
}<br>
<br>
on iscsi-filer-2 {<br>
device /dev/drbd0;<br>
disk /dev/md0;<br>
address 192.168.10.2:7789;<br>
flexible-meta-disk /dev/md3;<br>
}<br>
}<br>
<br>
resource target.2 {<br>
protocol C;<br>
<br>
handlers {<br>
pri-on-incon-degr "echo o > /proc/sysrq-trigger ; halt
-f";<br>
pri-lost-after-sb "echo o > /proc/sysrq-trigger ; halt
-f";<br>
local-io-error "echo o > /proc/sysrq-trigger ; halt
-f";<br>
outdate-peer "/usr/lib/heartbeat/drbd-peer-outdater -t
5"; <br>
before-resync-target /usr/local/bin/resync-start-RAID5.sh;<br>
after-resync-target /usr/local/bin/resync-end-RAID5.sh;<br>
}<br>
<br>
startup {<br>
degr-wfc-timeout 120;<br>
}<br>
<br>
disk {<br>
on-io-error detach;<br>
}<br>
<br>
net {<br>
cram-hmac-alg sha1;<br>
shared-secret "password";<br>
after-sb-0pri disconnect;<br>
after-sb-1pri disconnect;<br>
after-sb-2pri disconnect;<br>
rr-conflict disconnect;<br>
sndbuf-size 0;<br>
}<br>
<br>
syncer {<br>
c-plan-ahead 0;<br>
rate 30M;<br>
verify-alg sha1;<br>
# al-extents 257;<br>
al-extents 3389;<br>
}<br>
<br>
on iscsi-filer-1 {<br>
device /dev/drbd2;<br>
disk /dev/md2;<br>
address 192.168.10.1:7790;<br>
flexible-meta-disk /dev/md4;<br>
}<br>
<br>
on iscsi-filer-2 {<br>
device /dev/drbd2;<br>
disk /dev/md2;<br>
address 192.168.10.2:7790;<br>
flexible-meta-disk /dev/md4;<br>
}<br>
}</font>
<pre>
</pre>
<br>
ucarp-up<br>
<font face="Courier New, Courier, monospace">#!/bin/sh  
;
<br>
&nb
sp;
<br>
/sbin/drbdadm primary all<br>
/sbin/ifup $1:ucarp<br>
/sbin/drbdadm primary all<br>
/sbin/drbdadm primary all<br>
/sbin/drbdadm primary all<br>
mount -o defaults,noatime,nodiratime /dev/drbd0
/nfs-exported/raid6<br>
mount -o defaults,noatime,nodiratime /dev/drbd2
/nfs-exported/raid5<br>
/etc/init.d/nfs-kernel-server restart<br>
sleep 2<br>
echo 256 > /proc/fs/nfsd/threads </font> <br>
<br>
<br>
ucarp-down<br>
<font face="Courier New, Courier, monospace">#!/bin/sh  
;
<br>
&nb
sp;
<br>
/etc/init.d/nfs-kernel-server stop<br>
umount /nfs-exported/raid6<br>
umount /nfs-exported/raid5<br>
/sbin/drbdadm secondary all<br>
/sbin/ifdown $1:ucarp </font>
<br>
<pre class="moz-signature" cols="72">
--
Gerald Brandt
Majentis Technologies
<a class="moz-txt-link-abbreviated" href="mailto:gbr@majentis.com">gbr@majentis.com</a>
204-229-6595
<a class="moz-txt-link-abbreviated" href="http://www.majentis.com">www.majentis.com</a>
</pre>
</body>
</html>