Comment 251 for bug 131094

Revision history for this message
Tobias Oetiker (tobi-oetiker) wrote : Re: [Bug 131094] Re: Heavy Disk I/O harms desktop responsiveness

Hi Yan,

Yesterday Yan Li wrote:

> Tobi, your testing and results are great and very useful. It would be
> better if you can run those tests on ext4. Thank you.

I have now also put ext4 through the paces ... its overall
behaviour seems to be that same than with ext3, the same settings
render the best performance. Overall, the single reader scenario
seems to suffer a performance drop of 20% to 30% while the three
reader scenario gains about 30%. Large maximum latencies have
become bigger if anything.

I have updated the report on

http://insights.oetiker.ch/linux/fsopbench/

including the detailed results ...

The cfq scheduler seems todo a pretty good job at being fair. The
main problem (no one seems to be talking about) in my eyes, is the
hangups, where suddently an mkdir call takes up 19 seconds to
complete. This makes all the rest seem like minor issues.

cheers
tobi

--
Tobi Oetiker, OETIKER+PARTNER AG, Aarweg 15 CH-4600 Olten, Switzerland
http://it.oetiker.ch <email address hidden> ++41 62 775 9902 / sb: -9900