Hi
with this change in top of my previous patch (shrink_mmap take2)
I get the same performance on IO that the removing the page->zone test
from shrink_mmap. Could people seing improvements in ac21 (or later)
test this patch.
Comments and positive/negative reports are welcome.
Later, Juan.
This patch does:
- We allocate for a zone with more than pages_high free pages if
possible.
diff -urN --exclude-from=/home/lfcia/quintela/work/kernel/exclude base/mm/page_alloc.c working/mm/page_alloc.c
--- base/mm/page_alloc.c Mon Jun 19 23:35:41 2000
+++ working/mm/page_alloc.c Tue Jun 20 03:03:51 2000
@@ -233,6 +233,23 @@
* We are falling back to lower-level zones if allocation
* in a higher zone fails.
*/
+
+ for (;;) {
+ zone_t *z = *(zone++);
+ if (!z)
+ break;
+ if (!z->size)
+ BUG();
+
+ /* If there are zones with a lot of free memory
allocate from them */
+ if (z->free_pages > z->pages_high) {
+ struct page *page = rmqueue(z, order);
+ if (page)
+ return page;
+ }
+ }
+
+ zone = zonelist->zones;
for (;;) {
zone_t *z = *(zone++);
if (!z)
-- In theory, practice and theory are the same, but in practice they are different -- Larry McVoy- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Fri Jun 23 2000 - 21:00:18 EST