[DRBD-user] Secondary server works harder than primary

free.fr pascal.berton3 at free.fr
Wed Jun 8 13:29:34 CEST 2011

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


Hi, Chris!

If you have a RAID 0 on 3 disks, why does /dev/sdc on Primary server 
stay inactive or so ? Isn't there kind of ugly thing happening on your 
primary infrastructure ?
Then, your iostat results show different units, blocks on primary, 
KBytes on secondary. The fact that you see different TPS values doesn't 
mean much if the size of I/Os differs on both side. I'm no DRBD expert, 
but are we sure that an X-sized IO on primary generates an identical IO 
size on the secondary ? Might be that IOs are split into smaller units 
on secondary... In that case, what we need is to compare apples with 
apples : What are the KB values on primary ? I would suspect that they 
are approximately the same. If not, then yes you might have something 
odd happening. But I would rather expect similar values, in which case 
it woud solely be a matter of differing IO size on both sides of the mirror.

Best regards,

Pascal.

Le 08/06/2011 02:06, Gouveia, Chris a écrit :
> I have a two machine DRBD setup, supposedly with identical hardware in
> both machines. I have 3 drives in each, with software RAID-0, and DRBD
> on the RAID partition. When I write large amounts of data via NFS to the
> DRBD partition, the harddrive LED on the primary machine blinks slowly.
> However, on the secondary machine, the LED is on solidly. I also ran
> iostat on the drives:
>
> Primary machine
> avg-cpu:  %user   %nice %system %iowait  %steal   %idle
>             0.25    0.00    4.93   25.52    0.00   69.30
>
> Device:            tps   Blk_read/s   Blk_wrtn/s   Blk_read   Blk_wrtn
> sda             349.00     34960.00       680.00      34960        680
> sdb             330.00     35112.00       544.00      35112        544
> sdc               6.00         0.00       144.00          0        144
> md0            2517.00    105736.00      1920.00     105736       1920
>
> Secondary machine
> avg-cpu:  %user   %nice %system %iowait  %steal   %idle
>             0.00    0.00    2.51    0.00    0.00   97.49
>
> Device:            tps    kB_read/s    kB_wrtn/s    kB_read    kB_wrtn
> sda             937.00         0.00     16316.00          0      16316
> sdb             986.00         0.00     16248.00          0      16248
> sdc             905.00         0.00     16324.00          0      16324
> md0           12116.00         0.00     48464.00          0      48464
>
> Notice that the secondary machine TPS is much higher than the primary
> machine.
>
> The two machines have identical configurations:
>
> resource hnlcsv {
> 	protocol	B;
>
> 	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";
> 	}
>
> 	net {
> 		max-epoch-size	16000;
> 		max-buffers	16000;
> 		sndbuf-size	0;
> 	}
>
> 	disk {
> 		use-bmbv;
> 	}
>
> 	syncer {
> 		al-extents	3389;
> 		rate 50M;
> 	}
>
>
> 	on hnlcsv4 {
> 		device	/dev/drbd0;
> 		disk	/dev/md0;
> 		address	192.168.1.2:7789;
> 		flexible-meta-disk	internal;
> 	}
>
> 	on hnlcsv3 {
> 		device	/dev/drbd0;
> 		disk	/dev/md0;
> 		address	192.168.1.1:7789;
> 		flexible-meta-disk	internal;
> 	}
> }
>
> Does anyone know what could cause the secondary to work so hard? I think
> if it didn't have to, I could get much higher throughput on my DRBD
> partition because it's being limited by the secondary machine.
>
> Thanks,
> Chris Gouveia
>
> <DIV><FONT size="1">
>
> E-mail confidentiality.
> --------------------------------
> This e-mail contains confidential and / or privileged information belonging to Spirent Communications plc, its affiliates and / or subsidiaries. If you are not the intended recipient, you are hereby notified that any disclosure, copying, distribution and / or the taking of any action based upon reliance on the contents of this transmission is strictly forbidden. If you have received this message in error please notify the sender by return e-mail and delete it from your system.
>
> Spirent Communications plc
> Northwood Park, Gatwick Road, Crawley, West Sussex, RH10 9XN, United Kingdom.
> Tel No. +44 (0) 1293 767676
> Fax No. +44 (0) 1293 767677
>
> Registered in England Number 470893
> Registered at Northwood Park, Gatwick Road, Crawley, West Sussex, RH10 9XN, United Kingdom.
>
> Or if within the US,
>
> Spirent Communications,
> 26750 Agoura Road, Calabasas, CA, 91302, USA.
> Tel No. 1-818-676- 2300
>
> </FONT></DIV>
> _______________________________________________
> drbd-user mailing list
> drbd-user at lists.linbit.com
> http://lists.linbit.com/mailman/listinfo/drbd-user




More information about the drbd-user mailing list