![]() | ||||||||||
Messages in this thread |
> > On 26 Oct 2005, Andi Kleen wrote: > > > If you add locks to the reader make sure it is only taken > > if the list is non empty. Otherwise you will add unacceptable > > overhead to some fast paths. > > I don't understand this comment. What point is there in avoiding a > lock > when the list is empty? It doesn't add locking overhead for a common case. > Did you mean that a lock should be taken only if > the list _is_ empty? No. > > Better would be likely to use RCU. > > Note that the RCU documentation says RCU critical sections are not > allowed > to sleep. In this case it would be ok. -Andi - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ | |||||||||
| Last update: 2005-10-26 19:08 [from the cache] ©2003-2008 | ||||||||||