Manfred Spraul <[EMAIL PROTECTED]> writes:
> MAX_ALIGNOF affects the on-disk format, correct?
Right, it could affect placement of fields on-disk. I was thinking we
could change it as an easy test, but maybe not ...
If you set up the shared buffers at an appropriate offset, that should
get most o
Tom Lane wrote:
Manfred Spraul <[EMAIL PROTECTED]> writes:
... Initially I tried to increase MAX_ALIGNOF to 16, but
the result didn't work:
You would need to do a full recompile and initdb to alter MAX_ALIGNOF.
I think I did that, but it still failed. 7.4cvs works, I'll ignore it.
MAX_AL
Manfred Spraul <[EMAIL PROTECTED]> writes:
> ... Initially I tried to increase MAX_ALIGNOF to 16, but
> the result didn't work:
You would need to do a full recompile and initdb to alter MAX_ALIGNOF.
However, if you are wanting to raise it past about 8, that's probably
not the way to go anyway; it
Tom Lane wrote:
Oh, pgbench ;-). Are you aware that you need a "scale factor" (-s)
larger than the number of clients to avoid unreasonable levels of
contention in pgbench?
No. What about adding a few reasonable examples to README? I've switched
to "pgbench -c 10 -s 11 -t 1000 test". Is that ok?
Manfred Spraul <[EMAIL PROTECTED]> writes:
> Tom Lane wrote:
>> I'd be more interested in asking why you're seeing long series
>> of semops in the first place.
> I couldn't figure out what exactly causes the long series of semops. I
> tried to track it down (enable LOCK_DEBUG):
> - postgres 7.3.3
Tom Lane wrote:
AFAIK, semops are not done unless we actually have to yield the
processor, so saving a syscall or two in that path doesn't sound like a
big win. I'd be more interested in asking why you're seeing long series
of semops in the first place.
Virtually all semops yield the processor
Manfred Spraul <[EMAIL PROTECTED]> writes:
> I've noticed that postgres strace output contains long groups of
> setitimer/semop/setitimer.
> Just FYI: semtimedop is a special syscalls that implements a semop with
> a timeout. It was added just for the purpose of avoiding the setitimer
> calls.
>
I've noticed that postgres strace output contains long groups of
setitimer/semop/setitimer.
Just FYI: semtimedop is a special syscalls that implements a semop with
a timeout. It was added just for the purpose of avoiding the setitimer
calls.
I know that it's supported by Solaris and recent Linux
