"Tom Lane" <tgl@sss.pgh.pa.us> writes:
> I don't see any good reason why overwriting a whole cache line oughtn't be
> the same speed either way.
I can think of a couple theories, but I don't know if they're reasonable. The
one the comes to mind is the inter-processor cache coherency protocol. When
writing to a cache line the processor already owns maybe it can skip having to
check for other processors owning that cache line?
What happens if VACUUM comes across buffers that *are* already in the buffer
cache. Does it throw those on the freelist too? That seems like it would be
dangerous if they were in the buffer cache for a reason.
-- Gregory Stark EnterpriseDB http://www.enterprisedb.com