On Thu, Jan 23, 2014 at 01:47:53PM +0100, Peter Zijlstra wrote: > On Tue, Jan 21, 2014 at 02:18:52PM -0800, Kent Overstreet wrote: > > > I do not get the comment near prepare to wait -- why does it matter if > > > percpu_ida_free() flips a cpus_have_tags bit? > > > > Did I write that comment? It is a crappy comment... > > > > Ok, in userspace we'd be using condition variables here, but this is the kernel > > so we need to carefully order putting ourselves on a waitlist, and checking the > > condition that determines whether we wait, and on the wakeup end changing things > > that affect that condition and doing the wakeup. steal_tags() is checking the > > condition that goes with the prepare_to_wait(), that's all. > > How about something like so? I like it - my only concern is that your patch has the effect of calling __alloc_global_tag() twice before sleeping on alloc failure - given that we're also doing a prepare_to_wait() I'm not concerned about touching the global freelist twice, but we're also calling steal_tags() twice and that's potentially more expensive. It should be ok, because I expect when steal_tags() is going to fail most of the time it'll check the bitmap and not run the loop, but I think there's enough room for pathological behaviour here to sleep on it. pool->lock is also going to be fairly badly contended in the worst case, and that can get real bad real fast... now that I think about it we probably want to avoid the __alloc_global_tag() double call just because of that, pool->lock is going to be quite a bit more contended than the waitlist lock just because fo the amount of work done under it. though my old code was also calling prepare_to_wait() with pool->lock held, which was dumb. -- To unsubscribe from this list: send the line "unsubscribe target-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
