[DRBD-user] Performance hit DRBD vs raw block device, even when disconnected

Florian Haas florian at hastexo.com
Fri Jun 1 21:03:42 CEST 2012

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


On Fri, Jun 1, 2012 at 6:14 PM, Wiebe Cazemier <wiebe at halfgaar.net> wrote:
> Hi,
>
> I'm setting up a DRBD system and I don't really understand the performance hits I'm getting.
>
> I have two hosts (with dedicated GB LAN):
>
> Host1: 3Ware 9650 SE SATA2 hardware RAID6, 5x 2TB disks
> Host2: 2x250GB Linux MD RAID1.
>
> Example: a fully synced DRBD device with ext3 on it, writing a file with dd. Writing on host1:
>
> dd if=/dev/zero of=groot1 bs=10M count=50
> 50+0 records in
> 50+0 records out
> 524288000 bytes (524 MB) copied, 8.04722 s, 65.2 MB/s

Sorry if I rant for a bit, but it's been _years_ since I wrote that
part of the User's Guide, and it's been regurgitated a million times
on this list, by myself and many others. Please, say it after me:

I will not use dd without oflag=direct or oflag=dsync.
I will not use dd without oflag=direct or oflag=dsync.
I will not use dd without oflag=direct or oflag=dsync.

You're kidding yourself. You're measuring *something*, a mix of
caching effects and actual I/O, but not the throughput of your block
device.

Please rerun your tests with oflag=direct, and then come back with
updated results.

Florian

-- 
Need help with High Availability?
http://www.hastexo.com/now



More information about the drbd-user mailing list