Date: Sat, 24 Aug 2002 08:41:59 +0200 From: Poul-Henning Kamp <phk@critter.freebsd.dk> To: Luigi Rizzo <rizzo@icir.org> Cc: current@FreeBSD.ORG Subject: Re: how to compute the skew between TSC in SMP systems ? Message-ID: <37274.1030171319@critter.freebsd.dk> In-Reply-To: Your message of "Fri, 23 Aug 2002 15:11:27 PDT." <20020823151127.A82640@iguana.icir.org>
next in thread | previous in thread | raw e-mail | index | archive | help
In message <20020823151127.A82640@iguana.icir.org>, Luigi Rizzo writes: >ok, i'll look into the ACPI counter. >But you still did not tell me why trying to determine the TSC >skew cannot be done reliably ... > >On Fri, Aug 23, 2002 at 11:44:08PM +0200, Poul-Henning Kamp wrote: >> In message <20020823144256.A82380@iguana.icir.org>, Luigi Rizzo writes: >> >> >I want to find performance problems in the kernel, and to this purpose, >> >sometimes i need to timestamp events in the kernel using the >> >least-intrusive technique i can use, and hopefully get reasonably >... >> Alternatively, consider using "basic-block profiling" (see kernbb(8) and >> gcc docs), that will tell you not only how many instructions but also >> _which_ instructions are executed. > >this one does not give timing info at all, and it is probably >also on the "terribly intrusive" side of the spectrum... Neither does TSC, it tells you how many cpu clock cycles were consumed, but now how (ie: instruction executions, pipeline stalls, cache stalls etc etc). -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 phk@FreeBSD.ORG | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?37274.1030171319>