tag:blogger.com,1999:blog-6977755959349847093.post161232759069924901..comments2024-03-01T21:53:15.921-08:00Comments on The Pith of Performance: Hadoop, MAA, ML, MR and Performance DataNeil Guntherhttp://www.blogger.com/profile/11441377418482735926noreply@blogger.comBlogger2125tag:blogger.com,1999:blog-6977755959349847093.post-20598770663145489872009-10-18T13:40:07.251-07:002009-10-18T13:40:07.251-07:00Some good pointers here. Thanks.
I see some inter...Some good pointers here. Thanks.<br /><br />I see some interesting performance data in the google-sawzall paper that jives with the discussion in Chap. 7 (section 7.4.2) of my <a href="http://www.perfdynamics.com/iBook/ppa_new.html" rel="nofollow">Perl::PDQ</a> book. Might do a blog post about it.Neil Guntherhttps://www.blogger.com/profile/11441377418482735926noreply@blogger.comtag:blogger.com,1999:blog-6977755959349847093.post-7954441962471473452009-10-15T20:18:40.379-07:002009-10-15T20:18:40.379-07:00You should also check out Pig (see http://wiki.apa...You should also check out Pig (see http://wiki.apache.org/pig/ & http://hadoop.apache.org/pig/about.html). It's intended to be used like google's sawzall(http://labs.google.com/papers/sawzall.html). I have several friends (who all work for companies who have been recipients of our government's largesse <br />) that using Pig to mine application logs as part of an effort to track usage. An I'm also know that it'sbeing used as a critical component of a system that gathers resource demand data off of a very large server cluster of VMware hosts as part of a system to track and rebalance guest vm workload.Unknownhttps://www.blogger.com/profile/00789011619037210527noreply@blogger.com