[DRBD-user] Primary 0.6.13 box crashing under load

Todd Denniston Todd.Denniston at ssa.crane.navy.mil
Thu Sep 22 20:56:53 CEST 2005

Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.


Matt Smith wrote:
> 
> Thanks for the reply!
> 
<SNIP>
> 4.  Not since this started, but given it's happening on two separate
> boxes, I kind of discounted stuff like that - it's worth a try.

As long as you are ESD protected it should not do harm.

> 
> Raid 0 in hardware.  7 pairs of disks, two disks per RAID 0 volume.
> That's it.
> 
<SNIP>

it is possible (probable?) that in 2+ years of heavy operation you have had
one of 7 drives start faulting.

With this configuration I would (on the secondary node):
service heartbeat stop
service drbd stop

# at a minimum
badblocks -vs -b 128 -r \
-o /root/RaidbadblocksPartion /dev/underlyingRaidpartiton
# if you have the time though...
badblocks -vs -b 128 -n \
-o /root/RaidbadblocksPartion /dev/underlyingRaidpartiton

#repeat the above for each partion. (note you want to change the output name
each time)

service drbd start
service heartbeat start
#make this node primary
#if been here already, stop
#else repeat procedure on new secondary.

-- 
Todd Denniston
Crane Division, Naval Surface Warfare Center (NSWC Crane) 
Harnessing the Power of Technology for the Warfighter



More information about the drbd-user mailing list