Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On Friday 23 January 2009 18:13:55 Florian Haas wrote:
> Mark,
>
> On 01/23/2009 05:01 PM, Mark Watts wrote:
> > The following test was used to obtain a write average:
> > # for loop in `seq 1 10`; do echo "Writing to /empty, loop $loop"; dd
> > if=/dev/zero of=/empty bs=$(( 1024 * 1024 * 1024 )) count=4; done
>
> You're not writing to your disk, but to your page/buffer cache. Add
> "oflag=direct".
Ok. We've realised that we don't have the controller batteries either, so
we're going to get some and re-test.
> Firstly, I repeat, because you hadn't been writing to your disk, but to
> your page cache (i.e. memory). But:
> > syncer {
> > al-extents 257;
> > }
>
> ... is probably way too low for your setup. Try upping that one to 1801,
> maybe as far as 3389.
3389 seems to help a fair bit - its taken the numbers up to ~90MB/sec
> Still, this:
> > syncer {
> > rate 100M;
> > }
>
> ... is likely to kill your foreground I/O performance during any resync,
> even when you've upped your al-extents to the values suggested above.
>
> And of course, you'll never reach your anywhere near your 150 MB/s if
> your replication link is Gigabit Ethernet, as that tops out at 110 MB/s.
Yep, GigE here. Having said that, if everything else is capable/tuned of going
faster then we should be hitting 100M almost all the time, right?
> These resources may provide additional insights:
> http://www.linbit.com/en/education/on-demand-webinars/drbd-performance-tuni
>ng/ http://www.drbd.org/users-guide/s-configure-syncer-rate.html
Looks like I've found my lunch-time reading :)
Cheers,
Mark.
--
Mark Watts BSc RHCE MBCS
Senior Systems Engineer
QinetiQ Applied Technologies
GPG Key: http://www.linux-corner.info/mwatts.gpg
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 197 bytes
Desc: This is a digitally signed message part.
URL: <http://lists.linbit.com/pipermail/drbd-user/attachments/20090126/f430afc9/attachment.pgp>