On Mon, Oct 28 2002, Stephen Cameron wrote:
> Jens Axboe wrote:
> [...]
> > It's not a kernel limit. If you queue limits are all beyond 64 entries,
> > what you typically see is that you just hit what mpage will fill in for
> > you. One thing that should give you max number of sg entries is plain
> > and simple:
> >
> > dd if=/dev/zero of=some_file bs=4096k
>
> What about
>
> dd if=/dev/cciss/c0d1p1 of=/dev/null bs=4096k
It's much better to do it with writes, you know the io scheduler will
stack those up in a long line, all max size. Reads are more difficult to
predict.
-- Jens Axboe- 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 : Thu Oct 31 2002 - 22:00:41 EST