Bruce Momjian <[EMAIL PROTECTED]> writes: > It could be tough. Imagine the delay increasing to 3 seconds? Seems > there has to be an upper bound on the sleep. The more you delay, the > more likely you will be to find someone to fsync you. Good point, and an excellent illustration of the fact that self-adjusting algorithms aren't that easy to get right the first time ;-) > Are we waking processes up after we have fsync()'ed them? Not at the moment. That would be another good mechanism to investigate for 7.2; but right now there's no infrastructure that would allow a backend to discover which other ones were sleeping for fsync. regards, tom lane
- Re: [HACKERS] CommitDelay performance improvemen... Tom Lane
- Re: [HACKERS] CommitDelay performance improv... Bruce Momjian
- Re: [HACKERS] CommitDelay performance im... Tom Lane
- Re: [HACKERS] CommitDelay performanc... Bruce Momjian
- Re: [HACKERS] CommitDelay performance improvement Nathan Myers
- Re: [HACKERS] CommitDelay performance improvemen... Bruce Momjian
- Re: [HACKERS] CommitDelay performance improvemen... Tom Lane
- Re: [HACKERS] CommitDelay performance improv... Bruce Momjian
- Re: [HACKERS] CommitDelay performance im... Tom Lane
- Re: [HACKERS] CommitDelay performanc... Bruce Momjian
- Re: [HACKERS] CommitDelay perfo... Tom Lane
- Re: [HACKERS] CommitDelay p... Bruce Momjian
- Re: [HACKERS] CommitDelay p... Tom Lane
- Re: [HACKERS] CommitDelay p... Bruce Momjian
- Re: [HACKERS] CommitDelay p... Philip Warner
- Re: [HACKERS] CommitDelay p... Bruce Momjian
- Re: [HACKERS] CommitDelay p... Bruce Momjian
- Re: [HACKERS] CommitDelay p... Philip Warner
- Re: [HACKERS] CommitDelay p... Bruce Momjian
- Re: [HACKERS] CommitDelay p... Dominique Quatravaux
- Re: [HACKERS] CommitDelay p... Tom Lane