On Tue, Apr 23, 2013 at 04:33:05PM +0100, Mel Gorman wrote: > That's a pretty big drop but it gets bad again for the second worst stall -- > wait_on_page_bit as a result of generic_file_buffered_write. > > Vanilla kernel 1336064 ms stalled with 109 events > Patched kernel 2338781 ms stalled with 164 events Do you have the stack trace for this stall? I'm wondering if this is caused by the waiting for stable pages in write_begin() , or something else. If it is blocking caused by stable page writeback that's interesting, since it would imply that something in your workload is trying to write to a page that has already been modified (i.e., appending to a log file, or updating a database file). Does that make sense given what your workload might be running? - Ted -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>