Re: [PATCH 0/6] IO context sharing

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: David Chinner <dgc@...>
Cc: Jens Axboe <jens.axboe@...>, <linux-kernel@...>, <knikanth@...>
Date: Wednesday, January 23, 2008 - 4:44 am

David Chinner <dgc@sgi.com> writes:


Wouldn't it make more sense to have an own io context for each
NFS client in this case? Ok that does mean some state per remote
client, but nfsd already keeps that anyways so it would be probably
not too much work to tug an io context in there too.

-Andi
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[PATCH 0/6] IO context sharing, Jens Axboe, (Tue Jan 22, 5:49 am)
Re: [PATCH 0/6] IO context sharing, David Chinner, (Tue Jan 22, 11:50 pm)
Re: [PATCH 0/6] IO context sharing, Andi Kleen, (Wed Jan 23, 4:44 am)
Re: [PATCH 0/6] IO context sharing, Peter Zijlstra, (Tue Jan 22, 10:49 am)
Re: [PATCH 0/6] IO context sharing, Jens Axboe, (Tue Jan 22, 2:21 pm)
Re: [PATCH 4/6] block: cfq: make the io contect sharing lock..., Paul E. McKenney, (Thu Jan 24, 12:42 pm)
[PATCH 2/6] io context sharing: preliminary support, Jens Axboe, (Tue Jan 22, 5:49 am)
Re: [PATCH 2/6] io context sharing: preliminary support, Andrew Morton, (Wed Jan 23, 6:08 pm)
[PATCH 3/6] io_context sharing - cfq changes, Jens Axboe, (Tue Jan 22, 5:49 am)