TODAY! Synchronized Scanning with Jeff Davis

Welcome to our new meeting day TODAY!

Also, I will have very fancy PostgreSQL Elephant pins. For a mere $5
you can have your very own pin. These are a fund-raiser for Software
in the Public Interest, which funds things like the transportation
costs for PostgreSQL speakers (if you're giving a talk, you should
contact them!), and things like booths, rooms, etc. for advocacy
efforts.

See you tonight!

-selena

Topic: Synchronized Scanning
Speaker: Jeff Davis, Laika
When: Thursday, August 16th, 7:00pm
Where: FreeGeek, 1731 SE 10th Ave

(Jeff didn't write this, so blame me for any inaccuracies or
exaggerations)

Jeff will be presenting his synchronized scanning patch. Jeff's road
to having his patch committed to the PostgreSQL core code was a long
one -- see this post from 2005:

http://archives.postgresql.org/pgsql-hackers/2005-02/msg00832.php

> I had an idea that might improve parallel seqscans on the same
> relation.
>

And then in 2006: http://archives.postgresql.org/pgsql-hackers/
2006-12/msg00140.php

> Now that 8.3 is open, I was considering a revival of this old patch:
>

And I'll skip over the patch chatter right to some benchmark results:

http://archives.postgresql.org/pgsql-hackers/2007-04/msg00084.php

> The results are in the form of log files that contain lots of useful
> debugging info:
>
> * log_executor_stats is on (meaning it shows cache hit rate)
> * the pid, timestamp, and pagenumber being retrieved (for every 5k
> pages
> read)
> * the duration of each scan
>
> The results are very positive and quite conclusive.
>

Jeff is a real smarty-pants and I'm sure you'll all enjoy hearing
about what this patch does exactly, and about his experience
contributing to the PostgreSQL code.

Normal after-meeting libations at the Lucky Lab!