Postgres Pro
Downloads
Home   >   mailing lists

Re: TODO: Determine optimal fdatasync/fsync, O_SYNC/O_DSYNC options - Mailing list pgsql-hackers

From Josh Berkus
Subject Re: TODO: Determine optimal fdatasync/fsync, O_SYNC/O_DSYNC options
Date
Msg-id 200606081639.51579.josh@agliodbs.com
Whole thread Raw
In response to Re: TODO: Determine optimal fdatasync/fsync, O_SYNC/O_DSYNC options  (Tom Lane <tgl@sss.pgh.pa.us>)
Responses Re: TODO: Determine optimal fdatasync/fsync, O_SYNC/O_DSYNC options  (Tom Lane <tgl@sss.pgh.pa.us>)
List pgsql-hackers
Tree view 
Tom, JD,

> No, that only tells you if the various alternatives *work*.  Not which
> one performs best.

"Performs best" is pretty elusive.   On Solaris 10, for example, fdatasync 
does best on pgbench on x86, but opendatasync does best on DBT2 on Sparc.  
I'm not certain we can really determine this with any accuracy.

-- 
--Josh

Josh Berkus
PostgreSQL @ Sun
San Francisco

pgsql-hackers by date:

Previous
From: Tom Lane
Date:
Subject: Re: TODO: Rename some /contrib modules from pg* to pg_*
Next
From: Tom Lane
Date:
Subject: Re: self-deadlock at FATAL exit of boostrap process on read error