Re: patch for Linux NFS client

From: Brad Knowles <brad.knowles_at_skynet.be>
Date: Mon, 8 Mar 2004 12:37:39 +0100
At 12:25 AM -0800 2004/03/08, Matthew Dillon wrote:

>      Even so, it might be a good idea for us to use a significantly larger
>      soreserve value, or to increase the buffer limit when a large data
>      block size is negotiated.  Instead of adding a slop of 2048
>      (aka 32768 + 404 + 2048 = 35220 bytes) it might be better to set
>      the soreserve value to 65535 by default.

	Out of curiosity, is it possible to set this value to be twice 
the negotiated block size?

>      Generally speaking the TCP buffer ought to be large enough to buffer
>      at least two full-sized NFS data packets to reduce NFSD interlock
>      stalls when combined with read-ahead.

	That's exactly what I was thinking.  Hence my question.

-- 
Brad Knowles, <brad.knowles_at_skynet.be>

"They that can give up essential liberty to obtain a little temporary
safety deserve neither liberty nor safety."
     -Benjamin Franklin, Historical Review of Pennsylvania.

GCS/IT d+(-) s:+(++)>: a C++(+++)$ UMBSHI++++$ P+>++ L+ !E-(---) W+++(--) N+
!w--- O- M++ V PS++(+++) PE- Y+(++) PGP>+++ t+(+++) 5++(+++) X++(+++) R+(+++)
tv+(+++) b+(++++) DI+(++++) D+(++) G+(++++) e++>++++ h--- r---(+++)* z(+++)
Received on Mon Mar 08 2004 - 02:40:55 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:37:46 UTC