* Why not distribute timer handlers on CPUs on SMP
@ 2010-10-06 1:05 bhs
2010-10-06 1:50 ` bhs
0 siblings, 1 reply; 2+ messages in thread
From: bhs @ 2010-10-06 1:05 UTC (permalink / raw)
To: linux-kernel; +Cc: haishan.bai
Hello,
I am just curious about why handle the timer functions on a CPU serially but not distribute them over CPUs
even on a SMP system?
The timer wheel handler function __run_timers() serializes the timer functions on a CPU,
is there any design consideration that handling timers on a CPU is more reasonable than distribute them
over CPUs?
Best regards
Shan Hai
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: Why not distribute timer handlers on CPUs on SMP
2010-10-06 1:05 Why not distribute timer handlers on CPUs on SMP bhs
@ 2010-10-06 1:50 ` bhs
0 siblings, 0 replies; 2+ messages in thread
From: bhs @ 2010-10-06 1:50 UTC (permalink / raw)
To: bhs; +Cc: linux-kernel
On Oct 6, 2010, at 9:05 AM, bhs wrote:
> Hello,
>
> I am just curious about why handle the timer functions on a CPU serially but not distribute them over CPUs
> even on a SMP system?
>
Yea, it already distributed over CPUs at calling add_timer(), timer function was bounded to a cpu on which
it was created.
I am sorry for my noise.
> The timer wheel handler function __run_timers() serializes the timer functions on a CPU,
> is there any design consideration that handling timers on a CPU is more reasonable than distribute them
> over CPUs?
>
>
> Best regards
> Shan Hai
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2010-10-06 1:50 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2010-10-06 1:05 Why not distribute timer handlers on CPUs on SMP bhs
2010-10-06 1:50 ` bhs
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®