> > In OS kernel design, you try to avoid process herding bottlenecks. > > Here, we want them herded, and giving up the CPU may be the best way to > > do it. > > Yes, but if everyone yeilds you're back where you started, and with > 128 or more backends do you really want to cause possibly that many > context switches per fsync? You are going to kernel call/yield anyway to fsync, so why not try and if someone does the fsync, we don't need to do it. I am suggesting re-checking the need for fsync after the return from sleep(0). -- Bruce Momjian | http://candle.pha.pa.us [EMAIL PROTECTED] | (610) 853-3000 + If your life is a hard drive, | 830 Blythe Avenue + Christ can be your backup. | Drexel Hill, Pennsylvania 19026
- Re: [HACKERS] WAL fsync schedul... Bruce Momjian
- Re: [HACKERS] WAL fsync schedul... Tom Lane
- Re: [HACKERS] WAL fsync schedul... Peter Eisentraut
- Re: [HACKERS] WAL fsync schedul... Vadim Mikheev
- Re: [HACKERS] WAL fsync schedul... Bruce Momjian
- Re: [HACKERS] WAL fsync schedul... Bruce Momjian
- Re: [HACKERS] RE: [COMMITTERS] ... Bruce Momjian
- Re: [HACKERS] RE: [COMMITTERS] ... Peter Eisentraut
- Re: [HACKERS] RE: [COMMITTERS] ... Bruce Momjian
- Re: [HACKERS] RE: [COMMITTERS] ... Alfred Perlstein
- Re: [HACKERS] RE: [COMMITTERS] ... Bruce Momjian
- Re: [HACKERS] RE: [COMMITTERS] ... Alfred Perlstein
- Re: [HACKERS] RE: [COMMITTERS] ... Tom Lane
- Re: [HACKERS] RE: [COMMITTERS] ... Alfred Perlstein
- Re: [HACKERS] RE: [COMMITTERS] ... Tom Lane
- RE: [HACKERS] RE: [COMMITTERS] pgsql/src/backend/access/t... Mikheev, Vadim
- RE: [HACKERS] RE: [COMMITTERS] pgsql/src/backend/access/t... Mikheev, Vadim