Subject: HEADS UP: UBC code integrated
To: None <email@example.com>
From: Chuck Silvers <firstname.lastname@example.org>
Date: 11/27/2000 01:18:34
the Unified Buffer Cache project that I've been working on pretty much forever
has finally been integrated into -current. so what does this mean for you?
you'll need to rerun config again, but before you do, you'll want to
remove any settings for "BUFCACHE", "NBUF" or "BUFPAGES", and let the size
of the buffer cache go back to the default. under UBC, the traditional
buffer cache is no longer used for storing regular file data, only metadata,
so you want to allow the VM system to manage most of your physical memory.
the default buffer cache size will be fine for most people, regardless of
the amount of memory in the machine. the amount of memory in the boot
messages about "using X buffers containing Y memory" no longer indicates
the amount of memory available for caching file data, so don't worry if
those numbers don't change.
so what's different now? for most people, more memory will be available
for caching regular file data, so filesystem i/o will be faster since
there will be more times when the data you're accessing is already in
memory. how much faster depends on what you're doing, but you'll probably
notice the difference.
applications that depend on read() and mmap() giving coherent access to
cached file data will now work correctly. for an example of this, try
running ftp://ftp.netbsd.org/pub/NetBSD/misc/chs/vmtest.c on an older
kernel and again on a kernel from today's sources or later.
as usual, if you find any problems please send a report with send-pr.