diff options
| author | Stefan Hajnoczi <stefanha@redhat.com> | 2015-07-20 16:54:16 +0100 |
|---|---|---|
| committer | Stefan Hajnoczi <stefanha@redhat.com> | 2015-10-12 09:21:10 +0100 |
| commit | fc73548e444ae3239f6cef44a5200b5d2c3e85d1 (patch) | |
| tree | b403ecd4b4a52f4b10999d36fb78cddf5ff91a0a /scripts/qapi-visit.py | |
| parent | 5ec911c30ff4337d4185e29e82a254349f5a22da (diff) | |
| download | focaccia-qemu-fc73548e444ae3239f6cef44a5200b5d2c3e85d1.tar.gz focaccia-qemu-fc73548e444ae3239f6cef44a5200b5d2c3e85d1.zip | |
virtio-blk: use blk_io_plug/unplug for Linux AIO batching
The raw-posix block driver implements Linux AIO batching so multiple requests can be submitted with a single io_submit(2) system call. Batching is currently only used by virtio-scsi and virtio-blk-data-plane. Enable batching for regular virtio-blk so the number of io_submit(2) system calls is reduced for workloads with queue depth > 1. In 4KB random read performance tests with queue depth 32, the CPU utilization on the host is reduced by 9.4%. The fio job is as follows: [global] bs=4k ioengine=libaio iodepth=32 direct=1 sync=0 time_based=1 runtime=30 clocksource=gettimeofday ramp_time=5 [job1] rw=randread filename=/dev/vdb size=4096M write_bw_log=fio write_iops_log=fio write_lat_log=fio log_avg_msec=1000 This benchmark was run on an raw image on LVM. The disk was an SSD drive and -drive cache=none,aio=native was used. Tested-by: Pradeep Surisetty <psuriset@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com>
Diffstat (limited to 'scripts/qapi-visit.py')
0 files changed, 0 insertions, 0 deletions