lkml.org 
[lkml]   [2007]   [Jun]   [4]   [last100]   RSS Feed
Views: [more markup]  [less markup]  [headers]  [forward] 
 
Messages in this thread
/
DateMon, 4 Jun 2007 16:17:18 +0200
FromIngo Molnar <>
SubjectRe: [bug] very high non-preempt latency in context_struct_compute_av()
* James Morris <jmorris@namei.org> wrote:

> > the latency is caused by a _very_ long loop in the SELinux code:
> > 
> >     sshd-4828  0.N.. 465894us : avtab_search_node (context_struct_compute_av)
> 
> What do the 0DNs fields mean and what did you use to create this 
> trace?

i used the latency tracer from -rt. Here's the meaning of the fields:

                  _------=> CPU#
                 / _-----=> irqs-off
                | / _----=> need-resched 
                || / _---=> hardirq/softirq
                ||| / _--=> preempt-depth
                |||| /
                |||||     delay
    cmd     pid ||||| time  |   caller
       \   /    |||||   \   |   /
 trace-it-4751  0D...    0us : __next_cpu (user_trace_start)
it's very easy to interpret: it traces all the function calls the kernel 
executes, and puts the symbolic function name (and its parent function) 
into the trace, time ordered. So it's a proper execution trace. Normally 
you can ignore the 'DN' type of flags - what matters in this case is the 
observed 130 msecs latency and the functions that were called while that 
latency happened.

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

\
 
 \ /
  Last update: 2007-06-04 16:21    [from the cache]
©2003-2008