Re: Small fix in buffer cache

Stephen C. Tweedie (sct@redhat.com)
Mon, 6 Dec 1999 10:51:52 +0000 (GMT)


Hi,

On Sun, 5 Dec 1999 17:06:18 +0100, Jan Kara <jack@suse.cz> said:

>> >I think it's cleaner to have those buffers attached...
>> The only advantage is for SYSRQ+M. I don't think it worth to make things
>> slower for it.

> I don't think those slowing will be noticable but I agree that
> current state doesn't require it.

You need the lru_list_lock spinlock, and you can be sure that any
unnecessary locking on SMP will slow things measurably.

--Stephen

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/