On Thu, Apr 3, 2008 at 4:14 PM, Johannes Berg <johannes@xxxxxxxxxxxxxxxx> wrote: > > On Tue, 2008-04-01 at 18:23 +0200, Johannes Berg wrote: > > As discussed earlier, we can unify locking in struct sta_info > > and use just a single spinlock protecting all members of the > > structure that need protection. Many don't, but one of the > > especially bad ones is the 'flags' member that can currently > > be clobbered when RX and TX is being processed on different > > CPUs at the same time. > > No objections? I remember Tomas wasn't entirely happy with the > suggestion that RX/TX aggregation don't need separate spinlocks. Yes starting TX and RX aggregation happens usually proximately at the same time, i.e. both sides of the link decide at the same time that it's worth to start the hight throughput traffic. We didn't get to investigating if the single lock will be a problem. Unfortunately there are too many open issues currently so we need to prioritize. I think it's time we push multqueue in, otherwise we will have to push some ugly patches to solve some problems with aggregation we found lately. Thanks Tomas > johannes > -- To unsubscribe from this list: send the line "unsubscribe linux-wireless" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
