On Tue, 26 Feb 2002, Tom Lane wrote:
> AFAICS the only real win that can be gotten with a change like
> Janardhana's would be to avoid writing multiple blocks in the case
> where the filesystem block size is smaller than the xlog's BLCKSZ.
> Tuning this correctly would require knowing the kernel's block size.
> Anyone have ideas about a portable way to find that out?
I have been thinking for quite some time now that it would be a cool
project to turn Postgres into using aio_(read|write) + O_DIRECT instead of
read|write + fsync; in that case the caller gets to control the blocksize
within the limits permitted by the hardware, and Janardhana's optimization
could safely be applied.
Regards
--
Helge Bahmann <bahmann@math.tu-freiberg.de> /| \__
Network admin, systems programmer /_|____\
_/\ | __)
$ ./configure \\ \|__/__|
checking whether build environment is sane... yes \\/___/ |
checking for AIX... no (we already did this) |