[DRBD-user] recovery from "page allocation failure"

Christian Balzer chibi at gol.com
Wed Jul 17 10:25:13 CEST 2013

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


On Mon, 3 Jun 2013 21:55:01 +0900 Junko IKEDA wrote:

Better late than never...

> Hi,
> I got the following error while running drbd-8.3.15,
> kernel: drbd1_receiver: page allocation failure. order:4, mode:0x20
> and I also found some kernel tuning tips in this list.
> http://lists.linbit.com/pipermail/drbd-user/2012-March/018036.html
In the replies to this thread and the one before it was suggested that
these events are "harmless".

BTW, you're not mentioning what transport you're using, but I only ever
saw these problems with IPoIB, so is that what you're using?

On a very busy cluster with kernel 3.4.48 and DRBD 8.4.3 I was able to
reduce these kernel messages from dozens a day to nearly none by setting

vm/min_free_kbytes = 524288

Lars, as this keeps popping up and always suggests DRBD to be guilty party
even if it's not, I wonder if you guys should have some back channel talk
with the relevant people on the kernel ML...

Dewa dewa,

Christian Balzer        Network/Systems Engineer                
chibi at gol.com   	Global OnLine Japan/Fusion Communications

More information about the drbd-user mailing list