David Schultz <dschultz@uclink.Berkeley.EDU> writes:
> While looking into a block size mismatch problem between
> Postgresql and FreeBSD's FFS, I noticed that postgresql is making
> some rather odd-sized requests to malloc(3): 0x2034, 0x2020,
> 0x4018, 0x8018, etc.
AFAICT the operative word there is "some" --- the heavily used paths
should make power-of-two requests to malloc, because aset block sizes
will normally be powers of two. Can you put your finger on paths that
generate a significant number of non-power-of-two requests?
regards, tom lane
