Re: 9.5: Better memory accounting, towards memory-bounded HashAgg - Mailing list pgsql-hackers

From Jeff Davis
Subject Re: 9.5: Better memory accounting, towards memory-bounded HashAgg
Date
Msg-id 1409303753.27388.8.camel@jeff-desktop
Whole thread Raw
In response to Re: 9.5: Better memory accounting, towards memory-bounded HashAgg  (Robert Haas <robertmhaas@gmail.com>)
Responses Re: 9.5: Better memory accounting, towards memory-bounded HashAgg
List pgsql-hackers
On Fri, 2014-08-22 at 12:34 -0400, Robert Haas wrote:
> Still doesn't look good here.  On the same PPC64 machine I've been
> using for testing:

I have a new approach to the patch which is to call a callback at each
block allocation and child contexts inherit the callback from their
parents. The callback could be defined to simply dereference and
increment its argument, which would mean block allocations anywhere in
the hierarchy are incrementing the same variable, avoiding the need to
traverse the hierarchy.

I've made some progress I think (thanks to both Robert and Tomas), but I
have a bit more microoptimization and testing to do. I'll mark it
"returned with feedback" for now, though if I find the time I'll do more
testing to see if the performance concerns are fully addressed.

Regards,Jeff Davis





pgsql-hackers by date:

Previous
From: arhipov
Date:
Subject: Re: Why data of timestamptz does not store value of timezone passed to it?
Next
From: Heikki Linnakangas
Date:
Subject: Re: implement subject alternative names support for SSL connections