Am 25.01.2019 um 15:36 hat Vladimir Sementsov-Ogievskiy geschrieben: > 25.01.2019 17:21, Vladimir Sementsov-Ogievskiy wrote: > > Results on tmpfs: > > cached is lseek cache by Kevin > > detect is this patch > > no lseek is just remove block_status query on bs->file->bs in > > bdrv_co_block_status > > > > +---------------------+--------+--------+--------+----------+ > > | | master | cached | detect | no lseek | > > +---------------------+--------+--------+--------+----------+ > > | test.qcow2 | 80 | 40 | 0.169 | 0.162 | > > +---------------------+--------+--------+--------+----------+ > > | test_forward.qcow2 | 79 | 0.171 | 0.169 | 0.163 | > > +---------------------+--------+--------+--------+----------+ > > | test_prealloc.qcow2 | 0.054 | 0.053 | 0.055 | 0.263 | > > +---------------------+--------+--------+--------+----------+ > > Forgot to say, tests by Kevin from branch > https://lists.gnu.org/archive/html/qemu-devel/2019-01/msg05463.html > > Hmm. Don't we have something like tests/qemu-iotests, but for performance? > So, all these small pretty tests we have in mailing list may go as git > patches?
Sounds like a good idea. Maybe we can just create a new subdirectory qemu-iotests/perf/ and put some benchmark scripts there? Of course, they wouldn't be able to tell PASS/FAIL like normal qemu-iotests and so they wouldn't be integrated into the normal qemu-iotests suite, but just return numbers that can be compared with different setups or revisions on the same machine. Kevin
