Re: 2.4.21-pre2 stalls out when running unixbench

Stephen C. Tweedie (sct@redhat.com)
06 Jan 2003 13:23:55 +0000


Hi,

On Mon, 2003-01-06 at 12:16, Andrew Morton wrote:

> Well personally I prefer slow-and-safe. But we could make 2.4
> do what 2.5 is doing - one pass through the superblocks to start
> the syncs and a second pass to wait on them all.

The 2.5 approach has the problem that it can start queuing writeback for
multiple fs'es on the same disk at the same time --- I wouldn't be
surprised if it increases thrashing in that case. But I guess I'm not
too concerned about sync() performance itself, as long as the in-kernel
background writeback is being done sensibly.

> This is fragile stuff though....

Yep.

--Stephen

-
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/