Maciej Soltysiak <solt@dns.toxicfilms.tv> wrote:
>
> > First thing we need to work out is whether it is a CPU scheduler thing
> > or if it is a VM/MM/block/fs latency problem.
> OK
It is a VM/MM/block/latency problem.
> > - How much memory do you have?
> 128 MB
Your machine is swapping and paging like crazy. Bits of your X server get
paged out to disk and take ages to come back because the heavy write streams
are starving reads from disk.
> > - Try setting /proc/sys/vm/swappiness to zero
> i will try.
>
> > - Try decreasing /proc/sys/vm/dirty_ratio to 15
> will try that too.
>
These things should help - possibly the defaults are wrong.
Also the anticipatory IO scheduler in -mm kernels might help reduce the disk
read latency.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Mon Mar 31 2003 - 22:00:17 EST