Re: [PATCH] convert hh_lock to seqlock

From: Stephen Hemminger <[EMAIL PROTECTED]> Date: Thu, 7 Dec 2006 11:33:09 -0800 > The hard header cache is in the main output path, so using > seqlock instead of reader/writer lock should reduce overhead. > > Signed-off-by: Stephen Hemminger <[EMAIL PROTECTED]> I've applied this, thanks Stephen

Re: [PATCH] convert hh_lock to seqlock

Stephen Hemminger a écrit : On Thu, 07 Dec 2006 23:27:00 +0100 Eric Dumazet <[EMAIL PROTECTED]> wrote: Stephen Hemminger a écrit : On Thu, 07 Dec 2006 21:23:07 +0100 Eric Dumazet <[EMAIL PROTECTED]> wrote: Stephen Hemminger a écrit : The hard header cache is in the main output path, so usin

Re: [PATCH] convert hh_lock to seqlock

From: Eric Dumazet <[EMAIL PROTECTED]> Date: Fri, 08 Dec 2006 00:02:44 +0100 > What's the problem with my suggestion of keeping hh_refcnt on > another cache line ? It is basically free (once your change from > rwlock to seqlock put in), and no change of algorithm. I think this change is worthwhi

Re: [PATCH] convert hh_lock to seqlock

On Thu, 07 Dec 2006 23:27:00 +0100 Eric Dumazet <[EMAIL PROTECTED]> wrote: > Stephen Hemminger a écrit : > > On Thu, 07 Dec 2006 21:23:07 +0100 > > Eric Dumazet <[EMAIL PROTECTED]> wrote: > > > >> Stephen Hemminger a écrit : > >>> The hard header cache is in the main output path, so using > >>> s

Re: [PATCH] convert hh_lock to seqlock

Stephen Hemminger a écrit : On Thu, 07 Dec 2006 21:23:07 +0100 Eric Dumazet <[EMAIL PROTECTED]> wrote: Stephen Hemminger a écrit : The hard header cache is in the main output path, so using seqlock instead of reader/writer lock should reduce overhead. Nice work Stephen, I am very interested.

Re: [PATCH] convert hh_lock to seqlock

On Thu, 07 Dec 2006 21:23:07 +0100 Eric Dumazet <[EMAIL PROTECTED]> wrote: > Stephen Hemminger a écrit : > > The hard header cache is in the main output path, so using > > seqlock instead of reader/writer lock should reduce overhead. > > > > Nice work Stephen, I am very interested. > > Did you

Re: [PATCH] convert hh_lock to seqlock

Stephen Hemminger a écrit : The hard header cache is in the main output path, so using seqlock instead of reader/writer lock should reduce overhead. Nice work Stephen, I am very interested. Did you benchmarked it ? I ask because I think hh_refcnt frequent changes may defeat the gain you want

[PATCH] convert hh_lock to seqlock

The hard header cache is in the main output path, so using seqlock instead of reader/writer lock should reduce overhead. Signed-off-by: Stephen Hemminger <[EMAIL PROTECTED]> --- include/linux/netdevice.h |2 +- include/net/neighbour.h | 18 ++ net/core/neighbour.c |