Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.
On 2004-07-22T22:15:34,
Lars Ellenberg <Lars.Ellenberg at linbit.com> said:
> or: xfs for some reason kmem_zone_free's (kmem_cache_free) the
> submitted pages _before_ they are sent (so before io on that page has
> completed. no bio_endio called yet!). which means that xfs "frees" a
> page of which the tcp stack still holds a reference.
> this seem to be the likely code path.
> now. either no one except xfs may hold a reference to their pages.
> then xfs should prominently state this somewhere.
> or xfs just does something it must not do: freeing pages that have
> reference counts.
>
> someone wants to ask the xfs guys about this?
Just drop them an e-mail ;-)
> solution approaches:
> a. we could disable zero copy networking completely (tcp_sendpage).
> b. we could make it configurable.
> c. we could simply fall back to tcp_sendmsg for slab pages.
>
> patch for c. is attached. if it works for Florin (please confirm),
> then it will go into svn soonish.
Sounds OK, what's the performance impact here? Does this affect anything
but !&@#&#(! XFS?
Sincerely,
Lars Marowsky-Brée <lmb at suse.de>
--
High Availability & Clustering \ ever tried. ever failed. no matter.
SUSE Labs, Research and Development | try again. fail again. fail better.
SUSE LINUX AG - A Novell company \ -- Samuel Beckett