Re: [patch] Latency Tracer, voluntary-preempt-2.6.8-rc4-O6

From: Ingo Molnar
Date: Fri Aug 13 2004 - 05:39:15 EST



* Lee Revell <rlrevell@xxxxxxxxxxx> wrote:

> > > http://redhat.com/~mingo/voluntary-preempt/voluntary-preempt-2.6.8-rc4-O6
>
> Ugh, this is a bad one:
>
> preemption latency trace v1.0
> -----------------------------
> latency: 506 us, entries: 157 (157)
> process: evolution/3461, uid: 1000
> nice: 0, policy: 0, rt_priority: 0
> =======>
> 0.000ms (+0.000ms): get_random_bytes (__check_and_rekey)
[...]
> 0.493ms (+0.001ms): local_bh_enable (__check_and_rekey)

indeed this is a new one. Entropy rekeying every 300 seconds. Most of
the overhead comes from the memcpy's - 10 usecs a pop!

this could possibly explain some earlier reports of RTC problems every
couple of minutes - on slower boxes it could easily be more than the 0.5
msec you got. (and with a 8192 Hz RTC the interrupt period is 122
usecs.)

such bhs-off spinlocked sections exclude all softirq traffic - and in
the redirected hardirqs case the hardirqs are excluded too.

Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/