* why are we reduce spin-lock and replace it with lock-free?
@ 2007-05-10 14:23 liang yuanen
2007-05-10 14:32 ` Alan Cox
0 siblings, 1 reply; 2+ messages in thread
From: liang yuanen @ 2007-05-10 14:23 UTC (permalink / raw)
To: linux-kernel
Three are many many spin-lock in the kernel code, and in multi-core
conditions, it push down the kernel performance.why are we reduce
spin-lock and replace it with lock-free?
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: why are we reduce spin-lock and replace it with lock-free?
2007-05-10 14:23 why are we reduce spin-lock and replace it with lock-free? liang yuanen
@ 2007-05-10 14:32 ` Alan Cox
0 siblings, 0 replies; 2+ messages in thread
From: Alan Cox @ 2007-05-10 14:32 UTC (permalink / raw)
To: liang yuanen; +Cc: linux-kernel
On Thu, 10 May 2007 22:23:32 +0800
"liang yuanen" <linux.kernel.liang@gmail.com> wrote:
> Three are many many spin-lock in the kernel code, and in multi-core
> conditions, it push down the kernel performance.why are we reduce
> spin-lock and replace it with lock-free?
If you can find algorithms which are lock free, faster than taking the
lock and have bounded resource consumption then you can test them with
the kernel and send patches.
Alan
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2007-05-10 14:28 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2007-05-10 14:23 why are we reduce spin-lock and replace it with lock-free? liang yuanen
2007-05-10 14:32 ` Alan Cox
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®