* Using random in interrupts for RT
@ 2012-08-14 14:30 Steven Rostedt
2012-08-14 15:17 ` Thomas Gleixner
2012-08-21 18:12 ` Steven Rostedt
0 siblings, 2 replies; 4+ messages in thread
From: Steven Rostedt @ 2012-08-14 14:30 UTC (permalink / raw)
To: Thomas Gleixner; +Cc: LKML, Ben Hutchings, RT
Thomas,
Ben Hutchings asked me if we still need "genirq: Disable random call on
preempt-rt" for -rt? With commit 902c098a366 "random: use lockless
techniques in the interrupt path" there is no more locks used. But does
it still produce high latencies?
-- Steve
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Using random in interrupts for RT
2012-08-14 14:30 Using random in interrupts for RT Steven Rostedt
@ 2012-08-14 15:17 ` Thomas Gleixner
2012-08-21 18:12 ` Steven Rostedt
1 sibling, 0 replies; 4+ messages in thread
From: Thomas Gleixner @ 2012-08-14 15:17 UTC (permalink / raw)
To: Steven Rostedt; +Cc: LKML, Ben Hutchings, RT
On Tue, 14 Aug 2012, Steven Rostedt wrote:
> Ben Hutchings asked me if we still need "genirq: Disable random call on
> preempt-rt" for -rt? With commit 902c098a366 "random: use lockless
> techniques in the interrupt path" there is no more locks used. But does
> it still produce high latencies?
Haven't tested it. Will put it on my ever growing todo list....
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Using random in interrupts for RT
2012-08-14 14:30 Using random in interrupts for RT Steven Rostedt
2012-08-14 15:17 ` Thomas Gleixner
@ 2012-08-21 18:12 ` Steven Rostedt
2012-08-21 19:12 ` Ben Hutchings
1 sibling, 1 reply; 4+ messages in thread
From: Steven Rostedt @ 2012-08-21 18:12 UTC (permalink / raw)
To: Thomas Gleixner; +Cc: LKML, Ben Hutchings, RT, Theodore Tso
On Tue, 2012-08-14 at 10:30 -0400, Steven Rostedt wrote:
> Thomas,
>
> Ben Hutchings asked me if we still need "genirq: Disable random call on
> preempt-rt" for -rt? With commit 902c098a366 "random: use lockless
> techniques in the interrupt path" there is no more locks used. But does
> it still produce high latencies?
Ben,
Looks that the #ifndef can't be removed just yet. The code is not
totally lockless...
add_interrupt_randomness ->
credit_entropy_bits ->
kill_fasync ->
kill_fasync_rcu ->
spin_lock_irqsave(&fa->fa_lock, flags)
to make things worse, that spinlock turns into a mutex on -rt, so it may
crash the box if triggered.
-- Steve
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: Using random in interrupts for RT
2012-08-21 18:12 ` Steven Rostedt
@ 2012-08-21 19:12 ` Ben Hutchings
0 siblings, 0 replies; 4+ messages in thread
From: Ben Hutchings @ 2012-08-21 19:12 UTC (permalink / raw)
To: Steven Rostedt; +Cc: Thomas Gleixner, LKML, RT, Theodore Tso
On Tue, Aug 21, 2012 at 02:12:13PM -0400, Steven Rostedt wrote:
> On Tue, 2012-08-14 at 10:30 -0400, Steven Rostedt wrote:
> > Thomas,
> >
> > Ben Hutchings asked me if we still need "genirq: Disable random call on
> > preempt-rt" for -rt? With commit 902c098a366 "random: use lockless
> > techniques in the interrupt path" there is no more locks used. But does
> > it still produce high latencies?
>
> Ben,
>
> Looks that the #ifndef can't be removed just yet. The code is not
> totally lockless...
>
>
> add_interrupt_randomness ->
> credit_entropy_bits ->
> kill_fasync ->
> kill_fasync_rcu ->
> spin_lock_irqsave(&fa->fa_lock, flags)
>
> to make things worse, that spinlock turns into a mutex on -rt, so it may
> crash the box if triggered.
Thanks for checking this.
Ben.
--
Ben Hutchings
We get into the habit of living before acquiring the habit of thinking.
- Albert Camus
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2012-08-21 19:12 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-08-14 14:30 Using random in interrupts for RT Steven Rostedt
2012-08-14 15:17 ` Thomas Gleixner
2012-08-21 18:12 ` Steven Rostedt
2012-08-21 19:12 ` Ben Hutchings
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).