Before commit 580b6b2aa2(dataplane: use the QEMU block
layer for I/O), dataplane for virtio-blk submits block
I/O as a batch.
This commit 580b6b2aa2 replaces the custom linux AIO
implementation(including submit I/O as a batch) with QEMU
block layer, but this commit causes ~40% throughput regression
on virtio-blk performance, and removing submitting I/O
as a batch is one of the causes.
This patch applies the newly introduced bdrv_io_plug() and
bdrv_io_unplug() interfaces to support submitting I/O
at batch for Qemu block layer, and in my test, the change
can improve throughput by ~30% with 'aio=native'.
Following my fio test script:
[global]
direct=1
size=4G
bsrange=4k-4k
timeout=40
numjobs=4
ioengine=libaio
iodepth=64
filename=/dev/vdc
group_reporting=1
[f]
rw=randread
Result on one of my small machine(host: x86_64, 2cores, 4thread, guest: 4cores):
- qemu master: 65K IOPS
- qemu master with these patches: 92K IOPS
- 2.0.0 release(dataplane using custom linux aio): 104K IOPS
Reviewed-by: Paolo Bonzini <pbonz...@redhat.com>
Signed-off-by: Ming Lei <ming....@canonical.com>
---
hw/block/dataplane/virtio-blk.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index 20f12c7..227bb15 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -77,6 +77,7 @@ static void handle_notify(EventNotifier *e)
VirtIOBlock *vblk = VIRTIO_BLK(s->vdev);
event_notifier_test_and_clear(&s->host_notifier);
+ bdrv_io_plug(s->blk->conf.bs);
for (;;) {
MultiReqBuffer mrb = {
.num_writes = 0,
@@ -115,6 +116,7 @@ static void handle_notify(EventNotifier *e)
break;
}
}
+ bdrv_io_unplug(s->blk->conf.bs);
}
/* Context: QEMU global mutex held */
--
1.7.9.5
