On Thursday 13 December 2007 09:30, Konstantin Serebryany wrote: > Your comment says: > Examine all ShM/ShR states in the system. For each one, look at ... > > This means that if we have lots of shared memory locations and lots of > condvar/semaphore events we are in trouble. > If we store SegmentIDs in shadow, we can do the same thing in a lazy > manner.
No .. the lazy ownership transitions only happen for memory in Excl state. You have memory in shared states which you want to change to exclusive when a CV sig/wait or sem post/wait happen - the lazy mechanism will not deal with those, even if SegmentIDs were always attached. J ------------------------------------------------------------------------- SF.Net email is sponsored by: Check out the new SourceForge.net Marketplace. It's the best place to buy or sell services for just about anything Open Source. http://ad.doubleclick.net/clk;164216239;13503038;w?http://sf.net/marketplace _______________________________________________ Valgrind-developers mailing list Valgrind-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/valgrind-developers
