Buffering GiST leaf pages too

From: Heikki Linnakangas <heikki(dot)linnakangas(at)enterprisedb(dot)com>
To: Alexander Korotkov <aekorotkov(at)gmail(dot)com>, PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org>
Subject: Buffering GiST leaf pages too
Date: 2011-08-23 07:03:55
Message-ID: 4E5350DB.3060209@enterprisedb.com
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

While looking at Alexander's GiST fastbuild patch, which adds buffers to
internal nodes to avoid random I/O during index build, it occurred to me
that inserting the tuples to the leaf pages one at a time is quite
inefficient too, even if the leaf pages are in cache. There's still the
overhead of locking and WAL-logging each insertion separately. I think
we could get a nice further speedup if we attach a small buffer (one
block or so) to every leaf page we're currently writing tuples to, and
update the leaf page in bulk. Conveniently, the code to insert multiple
tuples to a page already exists in GiST code (because inserting a tuple
sometimes splits the page into more than two parts, so you need to
insert multiple downlinks to the parent), so this requires no changes to
the low-level routines and WAL-logging.

Let's finish off the main fastbuild patch first, but I wanted to get the
idea out there.

--
Heikki Linnakangas
EnterpriseDB http://www.enterprisedb.com

Responses

Browse pgsql-hackers by date

  From Date Subject
Next Message daveg 2011-08-23 07:24:47 Re: OperationalError: FATAL: lock AccessShareLock on object 0/1260/0 is already
Previous Message Greg Smith 2011-08-23 03:48:20 Re: Displaying accumulated autovacuum cost