On Mon, May 31, 2010 at 06:07:57PM +1000, Nick Piggin wrote: > Hi Andrew, > > Could you put this in your tree? It could do with a bit more testing. I > will update you with updates or results from Steven. > > Thanks, > Nick > -- > > Provide a free area cache for the vmalloc virtual address allocator, based > on the approach taken in the user virtual memory allocator. > > This reduces the number of rbtree operations and linear traversals over > the vmap extents to find a free area. The lazy vmap flushing makes this problem > worse because because freed but not yet flushed vmaps tend to build up in > the address space between flushes. > > Steven noticed a performance problem with GFS2. Results are as follows... > Reviewed-by: Minchan Kim <minchan.kim@xxxxxxxxx> -- Kind regards, Minchan Kim -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>