Horton

Re: Reduce timing overhead of EXPLAIN ANALYZE using rdtsc?

Andres Freund <andres@anarazel.de>

View thread
From: Andres Freund <andres@anarazel.de>
To: Tom Lane <tgl@sss.pgh.pa.us>
Cc: David Geier <geidav.pg@gmail.com>, vignesh C <vignesh21@gmail.com>, Lukas Fittl <lukas@fittl.com>, Michael Paquier <michael@paquier.xyz>, Ibrar Ahmed <ibrar.ahmad@gmail.com>, Maciek Sakrejda <m.sakrejda@gmail.com>, pgsql-hackers <pgsql-hackers@postgresql.org>
Date: 2023-01-13T20:59:33Z
Lists: pgsql-hackers

Commits

Same data as JSON: GET /api/v1/messages/:b64id/commits the thread's linked commits as JSON, with link sources. API reference →

  1. pg_test_timing: Also test RDTSC[P] timing, report time source, TSC frequency

  2. Allow retrieving x86 TSC frequency/flags from CPUID

  3. instrumentation: Standardize ticks to nanosecond conversion method

  4. instrumentation: Use Time-Stamp Counter on x86-64 to lower overhead

  5. Zero initialize uses of instr_time about to trigger compiler warnings

  6. instr_time: Represent time as an int64 on all platforms

  7. Add 250c8ee07ed to git-blame-ignore-revs

Hi,

On 2023-01-13 15:25:16 -0500, Tom Lane wrote:
> Andres Freund <andres@anarazel.de> writes:
> > Does anybody see a reason to not move forward with this aspect? We do a fair
> > amount of INSTR_TIME_ACCUM_DIFF() etc, and that gets a good bit cheaper by
> > just using nanoseconds.
>
> Cheaper, and perhaps more accurate too?  Don't recall if we have any code
> paths where the input timestamps are likely to be better-than-microsecond,
> but surely that's coming someday.

instr_time on !WIN32 use struct timespec, so we already should have nanosecond
precision available. IOW, we could add a INSTR_TIME_GET_NANOSEC today. Or am I
misunderstanding what you mean?


> I'm unsure that we want to deal with rdtsc's vagaries in general, but
> no objection to changing instr_time.

Cool.

Looking at the instr_time.h part of the change, I think it should go further,
and basically do the same thing in the WIN32 path. The only part that needs to
be be win32 specific is INSTR_TIME_SET_CURRENT(). That'd reduce duplication a
good bit.

Greetings,

Andres Freund