Messages in this thread | | | Date | Sun, 13 Dec 2009 21:30:15 -0800 | From | Arjan van de Ven <> | Subject | Re: [GIT PATCH] TTY patches for 2.6.33-git |
| |
On Sun, 13 Dec 2009 20:16:08 +0100 Frederic Weisbecker <fweisbec@gmail.com> wrote:
> On Sun, Dec 13, 2009 at 09:55:34AM -0800, Arjan van de Ven wrote: > > On Sun, 13 Dec 2009 07:58:44 +0100 > > Ingo Molnar <mingo@elte.hu> wrote: > > > > > > > > * Linus Torvalds <torvalds@linux-foundation.org> wrote: > > > > > > > We've had quite a bit of BKL work this merge-window. Maybe we'll > > > > even get rid of it one of these days. There are "only" about 600 > > > > instances of "lock_kernel()" in the tree right now ;) > > > > > > I tend to use unlock_kernel() as the metric. (as it's more > > > precisely greppable and it is also more indicative of the > > > underlying complexity of locking, as it gets used more in more > > > complex scenarios) > > > > another metric is... how many times do we take the BKL for some > > workload. (For example booting or compiling a kernel). > > A counter like "BKLs-per-second" would be nice to expose > > (and then we can track that number going up as a regression etc) > > > > We have the bkl tracepoints for that, attaching an example below, > blkdev_get/bkldev_put is among the highest consumer for me.
we have a trace, but not a number that anyone can just pull out without having to go through great lengths to set stuff up... (esp to capture a boot)... Adding a counter always to the lock_kernel function should be fine instead...
-- Arjan van de Ven Intel Open Source Technology Centre For development, discussion and tips for power savings, visit http://www.lesswatts.org
| |