Re: testing ProcArrayLock patches - Mailing list pgsql-hackers

From Kevin Grittner
Subject Re: testing ProcArrayLock patches
Date
Msg-id 4EC6934F0200002500043285@gw.wicourts.gov
Whole thread Raw
In response to Re: testing ProcArrayLock patches  (Andres Freund <andres@anarazel.de>)
Responses Re: testing ProcArrayLock patches
List pgsql-hackers
Andres Freund <andres@anarazel.de> wrote:

> I think opannotate -a -s produces output with instructions/code
> intermingled.

Thanks.  I'll check out perf later (thanks for the tips!), but for
now, here's the function which was at the top of my oprofile
results, annotated with those options.  I'm afraid it's a bit
intimidating to me -- the last time I did much with X86 assembly
language was in the mid-80s, on an 80286.  :-/  Hopefully, since
this is at the top of the oprofile results when running with
prepared statements, it will be of use to somebody.

The instructions which are shown as having that 1% still seem odd to
me, but as you say, they were probably actually waiting for some
previous operation to finish:

 43329  0.3211 :  70b56a:    test   %rbp,%rbp

 99903  0.7404 :  70b58a:    mov    %rax,0x18(%rsp)

If anyone wants any other detail from what I captured, let me know.

-Kevin


Attachment

pgsql-hackers by date:

Previous
From: Tom Lane
Date:
Subject: Re: EXPLAIN (plan off, rewrite off) for benchmarking
Next
From: Robert Haas
Date:
Subject: Re: testing ProcArrayLock patches