[DRBD-user] tuning DRBD

Lars Ellenberg lars.ellenberg at linbit.com
Wed Jun 13 13:48:20 CEST 2007

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

On Tue, Jun 12, 2007 at 12:17:52PM -0700, Ben wrote:
> On Jun 12, 2007, at 11:34 AM, Lars Ellenberg wrote:
> >whether or not the tcp buffer fills up or not does not change things.
> >in this case the tcp buffer does only what it was supposed to do,
> >smooth the tcp stuff. having a larger buffer (which, depending on your
> >actual network performance may never fill up) cannot possibly increase
> >latency?
> Doh. Of course. Thanks for point out the obvious to me. :)
> >>>>3. What's a reasonable formula for determining max-buffers? Does
> >>>>increasing them imply I should increase something else too?
> >
> >if you tune it too small, io will throttle on it.
> >to not thottle here, it should be larger than the maximum expected
> >amount of in-flight io (io requests submitted but not yet completed).
> I see. I don't suppose there happens to be a way to see what my in- 
> flight io high/average watermark currently is?

to get a rough estimate, use
 (disk throughput) * (average-to-max latency)
the default of 2048 @ 4k -> 8M is sufficient to saturate
a of-the-shelf single disk, even when assuming some
worst case latency of ~100ms
 70 MByte/sec * 100 ms -> 7MB
most of the time only a fraction of that should be used.
btw, this is only interessting for the secondary side, mostly.

you also can monitor the "lo:" values in /proc/drbd on both nodes, or
the "ap:" value on the Primary, an see whether you can find a maximum...

: Lars Ellenberg                            Tel +43-1-8178292-0  :
: LINBIT Information Technologies GmbH      Fax +43-1-8178292-82 :
: Vivenotgasse 48, A-1120 Vienna/Europe    http://www.linbit.com :
please use the "List-Reply" function of your email client.

More information about the drbd-user mailing list