Re: elevator-starvation-4 (2.2.14 && 2.3.42)

From: Rik van Riel (riel@nl.linux.org)
Date: Sat Feb 12 2000 - 08:49:06 EST


On Fri, 11 Feb 2000, Andrea Arcangeli wrote:
> On Fri, 11 Feb 2000, Peter Rival wrote:
> >Andrea Arcangeli wrote:
> >> You never generate I/O from tasks. It's when the buffer is too old that
> >> kupdate flushes writes to disk. At that time the process is just exited
> >> and the user just run another program that gets stalled due the write
> >> flood.
> >
> >I believe this is technically incorrect - what about fsync() calls and files
>
> Yes, I was generalizing in speach-mode to bias my words (it's been
> a fast reply), and my only object was to comment on the per-task
> information that become meaningless with async write I/O (that's
> the common case).

And don't forget about read requests either :)
(which are, IIRC, the reason this thread started in the first place)

regards,

Rik

--
The Internet is not a network of computers. It is a network
of people. That is its real strength.

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Tue Feb 15 2000 - 21:00:22 EST