On 9/19/18 1:46 AM, lampahome wrote:
All images are on the RAID0(3 SSD).
Below is the performance:
image number seq. read(MB/s) seq. write(MB/s)
1 1480 60
16 1453 36
32 1450 36
64 1430 36
128 1400 36
It shows reading better than writing.
I confused about why, does qemu did something to delay the write?
Not intentionally. But you'd have to profile things to learn where the
hotspots are, in order to figure out how to reduce the overhead.
--
Eric Blake, Principal Software Engineer
Red Hat, Inc. +1-919-301-3266
Virtualization: qemu.org | libvirt.org