Andrew Dunstan <andrew(at)dunslane(dot)net> writes:
>> Actually, once you build it this way, you could make all writes
>> synchronous (open the files O_SYNC) so that there is never any need for
>> explicit fsync at checkpoint time.
>> 
> Or maybe fdatasync() would be slightly more efficient - do we care about 
> flushing metadata that much?

We don't, but it would just obscure the discussion to spell out "fsync,
or fdatasync where available" ...

			regards, tom lane

In response to

• Re: Experimental patch for inter-page delay in VACUUM at 2003-11-04 15:51:02 from Andrew Dunstan

pgsql-hackers by date

Next:	From: Tom Lane	Date: 2003-11-04 17:31:21
	Subject: Re: [PATCHES] equal() perf tweak
Previous:	From: Tom Lane	Date: 2003-11-04 17:07:34
	Subject: Re: bufmgr code question