Messages in this thread |  | | Date | Thu, 4 Jan 2001 14:58:19 -0200 (BRDT) | From | Rik van Riel <> | Subject | Re: [PATCH] filemap_fdatasync & related changes |
| |
On Thu, 4 Jan 2001, Marcelo Tosatti wrote: > On 4 Jan 2001, Christoph Rohland wrote: > > Chris Mason <mason@suse.com> writes:
> > > That would loop forever if the writepage func kept returning 1 though [snip]
> > return 1 if the swap space is exhausted. So everybody using shared > > anonymous, SYSV shared or POSIX shared memory can hit this. > > In case of swap exhausted I think we should just fail.
No. In case of swap exhausted the page needs to be moved to the active list so we don't clog up the inactive_dirty list and have the possibility of a deadlock (already done).
In case of "write ordering not yet satisfied", the writepage function should leave the page on the inactive_dirty list and maybe write out something else (reiserfs, ext3, xfs...).
regards,
Rik -- Hollywood goes for world dumbination, Trailer at 11.
http://www.surriel.com/ http://www.conectiva.com/ http://distro.conectiva.com.br/
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/
|  |