Am 01.06.2017 um 15:32 schrieb Paolo Bonzini:
On 01/06/2017 15:30, Peter Lieven wrote:
Hi,
i noticed a while ago that if I start a job like this in a vserver:
dd if=/dev/zero of=/x bs=1M count=128 oflag=direct
I see each of the 1M request splitted into 516096 + 516096 + 16384 bytes
with virtio-scsi
If I use virtio-blk the request goes through with 1M size.
Any idea whats the cause of this?
It may depend on memory fragmentation.
This sounds like nothing that can be influenced or changed?
I forgot to mention, if I specify bs=512k the requests go through also with
virtio-scsi
Thanks,
Peter
