Re: MemoryContext reset/delete callbacks - Mailing list pgsql-hackers

From Robert Haas
Subject Re: MemoryContext reset/delete callbacks
Date
Msg-id CA+TgmoZgdwa5jwmt+PnDKbRCVNDMQabFAsrfW7h3pOh5b79Jrg@mail.gmail.com
Whole thread Raw
In response to Re: MemoryContext reset/delete callbacks  (Tom Lane <tgl@sss.pgh.pa.us>)
List pgsql-hackers
On Thu, Feb 26, 2015 at 9:34 PM, Tom Lane <tgl@sss.pgh.pa.us> wrote:
> Andres Freund <andres@2ndquadrant.com> writes:
>> It's a bit sad to push AllocSetContextData onto four cachelines from the
>> current three... That stuff is hot. But I don't really see a way around
>> it right now. And it seems like it'd give us more amunition to improve
>> things than the small loss of speed it implies.
>
> Meh.  I doubt it would make any difference, especially seeing that the
> struct isn't going to be aligned on any special boundary.

It might not make much difference, but I think avoiding unnecessary
padding space inside frequently-used data structures is probably a
smart idea.

-- 
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company



pgsql-hackers by date:

Previous
From: Pavel Stehule
Date:
Subject: Re: Providing catalog view to pg_hba.conf file - Patch submission
Next
From: Tom Lane
Date:
Subject: Re: Renaming MemoryContextResetAndDeleteChildren to MemoryContextReset