Re: memory mapped store entries

On Tue, Aug 25, 1998 at 02:19:49PM +1000, Stewart Forster wrote:

> We're talking about doing these operations once at startup. After
> that we don't care. The map exists, the lock exists. After
> startup, overhead for mmap and mlock is irrelevant.

OK, fair enough. I misread the original posting. I was under the
impression somebody had made patches for squid to work via
mmap+writev as opposed to read/write to/from userland.

-cw
Received on Tue Jul 29 2003 - 13:15:52 MDT