[lkml]   [2011]   [Feb]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH 3/3] perf events: add timehist option to record and report
Em Fri, Feb 18, 2011 at 11:53:16AM -0700, David Ahern escreveu:
> On 02/18/11 11:41, Arnaldo Carvalho de Melo wrote:
> > Think about tcpdump + networking tracepoints or 'perf probe' dynamic
> > events in the network stack, he wants to merge those logs and correlate
> > the tcpdump packet exchange with the tracepoints events in the network
> > stack, etc.

> I'm zoned in on ap logs, but tcpdump and network analysis is another
> very good example. packets are tagged with realtime:

> static inline void __net_timestamp(struct sk_buff *skb)
> {
> skb->tstamp = ktime_get_real();
> }

I'd bet the original intent was to merge that with app specific logs :-)

Anyway, I think the way out of this is to have a clock_gettime like
interface, let the users decide what they need (or think they do),
sample it together with the other events and be done with it.

- Arnaldo

 \ /
  Last update: 2011-02-18 20:09    [W:0.067 / U:3.012 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site