> On Tue, 13 Oct 2009 04:03:45 +0900 (JST) > KOSAKI Motohiro <[email protected]> wrote: > > > > Start simple. What's wrong with mutex_lock() on the reader and writer > > > sides? rwsems might be OK too. > > > > > > In both cases we should think about whether persistent readers can > > > block the writer excessively though. > > > > I thought your mention seems reasonable. then I mesured various locking > > performance. > > > > no-contention read-read contetion read-write contention > > w/o patch 4627 ms 7575 ms N/A > > mutex 5717 ms 33872 ms (!) 14793 ms > > rw-semaphoe 6846 ms 10734 ms 36156 ms (!) > > seqlock 4754 ms 7558 ms 9373 ms > > > > Umm, seqlock is significantly better than other. > > Sure, but even the worst case there is 1,000,000 operations in 34 > seconds (yes?). 33 microseconds for a /proc read while under a specific > local DoS attack is OK! > > If so then all implementations are acceptable and we should choose the > simplest, most-obviously-correct one.
Hm, ok! I had guessed you don't accept this slowness. but my guess was wrong. I have no objection to use rw-semaphoe if you accept it. -- To unsubscribe from this list: send the line "unsubscribe linux-api" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
