Hi, 2011/11/8 Craig Ringer <ringerc@xxxxxxxxxxxxx>: > "Spreads reads too much" ? > > Are you saying there's too much random I/O? Is it possible it'd benefit from > a column store? > When you're using Greenplum are you using "Polymorphic Data Storage" column > storage "WITH (orientation=column)" ? yes, exactly. Column store and compression speed up queries even more (sometimes beyond 100x times) comparing to postgres. > > Or is the performance different just in better utilisation of the hardware > under Greenplum? >> Yes, looks like that they can better utilise available hardware. >> Is there >> a way to get PG backed IO stats using stock CentOS (5.7) kernel and >> tools? (I can't change my env easily) > > Dunno; check postgresql high performance (book), the manual, etc. Useful > tools are the pg_stat_ tables, "vmstat", "iostat", "iotop", etc. Yeah, I know about those.. I like iotop but enterprise distributions do not ship fresh kernels... I need something which can I "safely" (slightly worse performance is acceptable but machine must survie) run in production for several hours and then cross reference it with postgres and other system logs > That said, Pg's codebase isn't exactly trivial :S and trying to get involved > in major re-engineering like parallelisation isn't going to be practical > when you're just getting started. That's what I meant ;) -- Ondrej Ivanic (ondrej.ivanic@xxxxxxxxx) -- Sent via pgsql-general mailing list (pgsql-general@xxxxxxxxxxxxxx) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-general
