twittering on 2008-09-15

  • working on legion of tech IT stuff. #
  • @marsee thanks for sharing. good quote for a monday! #
  • my coffee is cold already. #
  • @kmazz NOOOOOO. but that would be pretty great tv. #
  • @verso feel better soon! #
  • @petdance harsh! #
  • wishing all technical documentation could be in the form of comic books. #

twittering on 2008-09-12

  • @brianaker that’s not nearly enough. #
  • i think ‘minder’ is a nicer word than ‘wrangler’ or ‘tamer’. how about you? #
  • RT: @spinnerin WhereCamp PDX is looking for sponsors: http://www.wherecamppdx.org #
  • Will I see you at Side Project to Startup tonight? Lots of people coming!! http://upcoming.yahoo.com/event/898641 #
  • @brianaker HSR would be sweet! i love taking the train to seattle, but don’t do it enough. #
  • thanks for the minder comments, btw. i think “herding recalcitrant children” sets the right tone in this instance 🙂 #
  • @joshwhite probably a little late, but I’ve been listening to batanga reggaeton. repetitive, but looks like they switched it up today. #
  • oh, sweet! WhereCampPDX mentioned on o’reilly radar: http://tinyurl.com/49nhnl thanks, @brady! #
  • @sourceforge ugh! when will you be back up? Also pls put status page on non-sourceforge hosted site! kthx. #

Filesystem I/O at the Linux Plumbers Conference

http://osdldbt.sourceforge.net/dl380/4disk/sraid10/ext3/read-write/
graph from software raid, RAID10, no partition table, ext3, read-write load

If you haven’t heard, the Linux Plumbers Conference is happening September 17-19, 2008 in Portland, OR. It’s a gathering designed to attract Linux developers – kernel hackers, tool developers and problem solvers.

A few of us that met through the Portland PostgreSQL User Group (PDXPUG) pitched an idea for a talk on filesystem performance. We wanted to examine performance conventional wisdom and put it to the test on some sweet new hardware, recently donated for performance testing Postgres. We’re asking questions like: Is RAID5 really the worst performing configuration for a database? How much does partition alignment really matter? Is there one Linux filesystem that a DBA should always choose for best performance under any load? Is adaptive readahead all that?

Our talk was accepted, so we’ve been furiously gathering data, and drawing interesting conclusions, ever since. Gabrielle Roth and I are presenting, using the results of extensive testing conducted by Mark Wong, a database benchmarking expert and author of pg_top. We’ll be sharing 6 different assumptions about filesystem performance, tested on five different filesystems, under five types of loads generated by fio, a benchmarking tool designed by kernel hacker Jens Axboe to test I/O.