Re: [HACKERS] Performance while loading data and indexing
Justin Clift <justin@postgresql.org>
From: Justin Clift <justin@postgresql.org>
To: shridhar_daithankar@persistent.co.in
Cc: pgsql-hackers@postgresql.org, pgsql-general@postgresql.org
Date: 2002-09-26T09:49:53Z
Lists: pgsql-hackers, pgsql-performance, pgsql-general
Shridhar Daithankar wrote: <snip> > > > fsync=true (Sad but true. Left untouched.. Will that make a difference on > > > SCSI?) > > > > Definitely. Have directly measured a ~ 2x tps throughput increase on > > FreeBSD when leaving fsync off whilst performance measuring stuff > > recently (PG 7.2.2). Like anything it'll depend on workload, phase of > > moon, etc, but it's a decent indicator. > > I didn't know even that matters with SCSI..Will check out.. Cool. When testing it had FreeBSD 4.6.2 installed on one drive along with the PostgreSQL 7.2.2 binaries, it had the data on a second drive (mounted as /pgdata), and it had the pg_xlog directory mounted on a third drive. Swap had it's own drive as well. Everything is UltraSCSI, etc. Haven't yet tested for a performance difference through moving the indexes to another drive after creation though. That apparently has the potential to help as well. :-) Regards and best wishes, Justin Clift -- "My grandfather once told me that there are two kinds of people: those who work and those who take the credit. He told me to try to be in the first group; there was less competition there." - Indira Gandhi