Mirror of the lttng-dev mailing list
 help / color / mirror / Atom feed
From: compudj@krystal.dyndns.org (Mathieu Desnoyers)
Subject: [ltt-dev] LTTng with 2.6.22.18 and lost events
Date: Thu, 22 Jan 2009 15:06:37 -0500	[thread overview]
Message-ID: <20090122200637.GA11038@Krystal> (raw)
In-Reply-To: <1E65288790442545B413D69F2A8D27DE0463798E@ERLD164A.ww004.siemens.net>

* Akyurek, Ali (EXT) (ali.akyurek.ext at siemens.com) wrote:
> Hi all,
>  
> I've solved the problem with the gui.
>  
> Problem is that i'm running the deamon seperate than lttctl, then i
> couldn't see facilites message.
> After adding -d parameter, i got the facility messages, then i'm able to
> see the results with lttv.
>  
> But i'm still thinking how to solve lost events problem.
> 

This ARM implementation uses a special version of the read seqlock in
the ARM tracing time source. You might want to audit
include/asm-arm/ltt.h to see if increasing the max loop value (which was
5 I think) helps. Basically, it fails after 5 loops so we don't create
an infinite loop if we are nested over the write seqlock.

Also, another possibility : I remember that some version had a problem
with this lock because the update_timer event was located within the
write seqlock of the timer irq handler. It's been fixed in the following
versions, so you might want to audit this too, because then all
update_timer events gets lost.

Mathieu


> 
> ________________________________
> 
> Von: Akyurek, Ali (EXT) 
> Gesendet: Donnerstag, 22. Januar 2009 16:40
> An: ltt-dev at lists.casi.polymtl.ca
> Betreff: [ltt-dev] LTTng with 2.6.22.18 and lost events
> 
> 
> Hi all,
>  
> I'm trying LTTng with a 2.6.22.18 kernel on an Arm machine. I've applied
> patch-2.6.22-rc4-mm2-lttng-0.9.10 patched with some corrections.
> Everything went well, until destroying the channels. 
>  
> I get the following message: 
>  
> "LTT : cpu : 6769 events lost in cpu channel (cpu 0)."
>  
> So when i try to open with lttv-gui, it doesn't work.
>  
> I've searched but found nothing except Mathieu, saying that it may be
> related to buffer size or timestamp.
>  
> Is there anyone having an idea?
> Thanks.
>  
> Mit freundlichem Gruss / Best Regards
> Ali
>  

> _______________________________________________
> ltt-dev mailing list
> ltt-dev at lists.casi.polymtl.ca
> http://lists.casi.polymtl.ca/cgi-bin/mailman/listinfo/ltt-dev


-- 
Mathieu Desnoyers
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68



      parent reply	other threads:[~2009-01-22 20:06 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-01-22 15:39 Akyurek, Ali (EXT)
2009-01-22 15:39 ` Akyurek, Ali (EXT)
2009-01-22 15:39 ` Akyurek, Ali (EXT)
2009-01-22 17:19 ` Akyurek, Ali (EXT)
2009-01-22 17:19   ` Akyurek, Ali (EXT)
2009-01-22 17:19   ` Akyurek, Ali (EXT)
2009-01-22 20:06   ` Mathieu Desnoyers [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20090122200637.GA11038@Krystal \
    --to=compudj@krystal.dyndns.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox