Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:

• Next message: Martin Dalecki: "Re: PATCH: killing read_ahead[]"
• Previous message: Mark Cooke: "Re: Possible critical VIA vt82c686a chip bug"
• In reply to: Andi Kleen: "Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:"
• Next in thread: Rik van Riel: "Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:"
• Reply: Rik van Riel: "Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On Mon, Oct 30, 2000 at 07:29:51AM +0100, Andi Kleen wrote:
> It should not be needed anymore for 2.4, because the accept() wakeup has been
> fixed.

Certainly sleeping in accept will be just way better than file any locking.

OTOH accept() is still _wrong_ as it wake-one FIFO while it should wake-one
LIFO (so that we optimize the cache usage skip TLB flushes and allow the
redundand tasks to be paged out). I can only see cons in doing FIFO wake-one.

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

• Next message: Martin Dalecki: "Re: PATCH: killing read_ahead[]"
• Previous message: Mark Cooke: "Re: Possible critical VIA vt82c686a chip bug"
• In reply to: Andi Kleen: "Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:"
• Next in thread: Rik van Riel: "Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:"
• Reply: Rik van Riel: "Re: [PATCH] Re: Negative scalability by removal of lock_kernel()?(Was:"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This archive was generated by hypermail 2b29 : Tue Oct 31 2000 - 21:00:26 EST