On 5/8/2019 4:14 PM, Christoph Hellwig wrote:
On Tue, May 07, 2019 at 04:38:37PM +0300, Max Gurtovoy wrote:
Performance results running fio (24 jobs, 128 iodepth) using
write_generate=1 and read_verify=1 (w/w.o patch):
bs IOPS(read) IOPS(write)
---- ---------- ----------
512 1262.4K/1243.3K 1732.1K/1725.1K
4k 570902/571233 773982/743293
32k 72086/72388 96164/71789
Using write_generate=0 and read_verify=0 (w/w.o patch):
bs IOPS(read) IOPS(write)
---- ---------- ----------
512 1600.1K/1572.1K 1830.3K/1823.5K
4k 937272/921992 815304/753772
32k 77369/75052 97435/73180
This seems to roughtly get us back to the previous performance levels.
Maybe it would be better to compare against the baseline without the
whole series?
Yes, we'll add another column to the table (w/w.o/baseline) that will
show the whole comparison.
Thanks.
