Hi,
As you pointed out, cgroup iocontext stuff isn't well designed yet
since the current implementation of dm-iband doesn't need it.
I'd like to leave the iocontext stuff to you I/O scheduler guys
if you want to implement the bio-cgroup infrastructure to handle iocotexts
as the I/O schedulers
Anthony Liguori wrote:
I don't think it's established that PV/VF will have less latency than
using virtio-net. virtio-net requires a world switch to send a group
of packets. The cost of this (if it stays in kernel) is only a few
thousand cycles on the most modern processors.
Using VT-d
Avi Kivity wrote:
Anthony Liguori wrote:
I don't think it's established that PV/VF will have less latency than
using virtio-net. virtio-net requires a world switch to send a group
of packets. The cost of this (if it stays in kernel) is only a few
thousand cycles on the most modern
On Friday 14 November 2008 20:00:23 Jens Axboe wrote:
Queue clustering is on by default though when you allocate your queue,
so I'm surprised you see a difference by doing:
+ /* Gather adjacent buffers to minimize sg length. */
+ queue_flag_set(QUEUE_FLAG_CLUSTER, vblk-disk-queue);
Setting max_segment_size allows more than 64k per sg element, unless
the host specified a limit. Setting max_sectors indicates that our
max_hw_segments is the only limit.
Signed-off-by: Rusty Russell [EMAIL PROTECTED]
diff -r 446171198334 drivers/block/virtio_blk.c
---