This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
Re: Unified tracing buffer
- From: "Frank Ch. Eigler" <fche at redhat dot com>
- To: KOSAKI Motohiro <kosaki dot motohiro at jp dot fujitsu dot com>
- Cc: Masami Hiramatsu <mhiramat at redhat dot com>, Martin Bligh <mbligh at google dot com>, Linux Kernel Mailing List <linux-kernel at vger dot kernel dot org>, Linus Torvalds <torvalds at linux-foundation dot org>, Thomas Gleixner <tglx at linutronix dot de>, Mathieu Desnoyers <compudj at krystal dot dyndns dot org>, Steven Rostedt <rostedt at goodmis dot org>, od at novell dot com, systemtap-ml <systemtap at sources dot redhat dot com>
- Date: Tue, 23 Sep 2008 11:02:09 -0400
- Subject: Re: Unified tracing buffer
- References: <33307c790809221313s3532d851g7239c212bc72fe71@mail.gmail.com> <48D81B5F.2030702@redhat.com> <20080923232239.DC1E.KOSAKI.MOTOHIRO@jp.fujitsu.com>
Hi -
On Tue, Sep 23, 2008 at 11:36:26PM +0900, KOSAKI Motohiro wrote:
> > By the way, systemtap uses two modes;
> >
> > - single-channel mode
> > In this mode, all cpus share one buffer channel to write and read.
> > each writer locks spinlock and write a probe-local data to buffer.
> > - per-cpu buffer mode [...]
>
> I can't imazine a merit of the single-channel mode.
> Could you please explain it?
It could be a way of saving some memory and merging hassle for
low-throughput data. (Remember that systemtap enables in-situ
analysis of events so that often only brief final results need be sent
along need be sent out.) If timestampwise cross-cpu merging can be
done on demand by the hypothetical future buffer widget, then little
reason remains not to use it.
- FChE