Re: [PERFORM] wal sync method

2006-03-01 Thread PFC
Hm, i seem to have mixed fwrite() (which buffers data in userspace) and write() (which apparently doesnt !) Sorry ! PFC <[EMAIL PROTECTED]> writes: Just a stupid question about the various fsync settings. There is fsync=off, but is there fsync=fflush ? fflu

Re: [PERFORM] wal sync method

2006-02-28 Thread Tom Lane
PFC <[EMAIL PROTECTED]> writes: > Just a stupid question about the various fsync settings. > There is fsync=off, but is there fsync=fflush ? > fflush would mean only an OS crash could cause data loss, > I think.it could be useful for some applications where you need a speed

Re: [PERFORM] wal sync method

2006-02-28 Thread PFC
Just a stupid question about the various fsync settings. There is fsync=off, but is there fsync=fflush ? fflush would mean only an OS crash could cause data loss, I think.it could be useful for some applications where you need a speed boost (like testing database impor

Re: [PERFORM] wal sync method

2006-02-27 Thread Bruce Momjian
Use whichever sync method is fastest for you. They are all reliable, except turning fsync off. --- Javier Somoza wrote: > > > > Hi Evgeny > > Im also testing what fsync method to use and using this progr

Re: [PERFORM] wal sync method

2006-02-27 Thread Javier Somoza
    Hi Evgeny     Im also testing what fsync method to use and using this program (http://archives.postgresql.org/pgsql-performance/2003-12/msg00191.php)     a bit modified and i get this results:     write  0.36     write & f

[PERFORM] wal sync method

2006-02-27 Thread Evgeny Gridasov
Hi everybody! Which wal sync method is the fastest under linux 2.6.x? I'm using RAID-10 (JFS filesystem), 2xXEON, 4 Gb RAM. I've tried to switch to open_sync which seems to work faster than default fdatasync, but is it crash-safe? -- Evgeny Gridasov Software Engineer I-Free, Russia -