> Tobias Oetiker:
>
> Thank you very much for the update. I'm a bit surprised to see the
> single-reader on ext4 is worse than that on ext3. I'm to postpone the
> upgrade of my systems to ext4. I dare not using data=writeback yet.
>
> I'm a bit confused about why you ran this on a RAID6 system. The RAID
> card/driver might affected the performance in a way yet to be
> understood. IMHO the less layers between Linux kernel and hard drive,
> the better we can understand the kernel I/O scheduler/fs etc.
>
> Again, thank you for the great data.
As you can see from the results, running the test on a RAID6 gives
vastly different results. Fact is that for reliability we are
running all our servers on RAID6, so this is the configuration I am
most interested to see working well ... good performance on a
single disk does not help me much ... (I am glad to see that it is
even worse to some extent, than my RAID6 performance).
I think at the heart of the problem lies the fact benchmarks focus
on single aspects of subsystems which then get optimized without
looking at the overall impact.
Today Yan Li wrote:
> Tobias Oetiker:
>
> Thank you very much for the update. I'm a bit surprised to see the
> single-reader on ext4 is worse than that on ext3. I'm to postpone the
> upgrade of my systems to ext4. I dare not using data=writeback yet.
>
> I'm a bit confused about why you ran this on a RAID6 system. The RAID
> card/driver might affected the performance in a way yet to be
> understood. IMHO the less layers between Linux kernel and hard drive,
> the better we can understand the kernel I/O scheduler/fs etc.
>
> Again, thank you for the great data.
As you can see from the results, running the test on a RAID6 gives
vastly different results. Fact is that for reliability we are
running all our servers on RAID6, so this is the configuration I am
most interested to see working well ... good performance on a
single disk does not help me much ... (I am glad to see that it is
even worse to some extent, than my RAID6 performance).
I think at the heart of the problem lies the fact benchmarks focus
on single aspects of subsystems which then get optimized without
looking at the overall impact.
cheers
tobi
>
>
-- it.oetiker. ch <email address hidden> ++41 62 775 9902 / sb: -9900
Tobi Oetiker, OETIKER+PARTNER AG, Aarweg 15 CH-4600 Olten, Switzerland
http://