lkml.org 
[lkml]   [2001]   [May]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[PATCH] inode & dentry cache balancing
Hi,

the following patch simplifies the if-else conditions in
do_try_to_free_pages() to the extent where it actually
balances the normal pages against the inode & dentry caches
again.

Note that the strange if-else around kmem_cache_reap() isn't
needed either, since page_launder() will, in the first loop,
free the buffer heads that are needed for the second loop and
for shrink_{icache,dcache}_memory() ... and if it doesn't we
still have enough IO outstanding to keep the IO subsystem busy
so it shouldn't matter either.

Please apply for the next -pre or -ac kernel...

regards,

Rik
--
Linux MM bugzilla: http://linux-mm.org/bugzilla.shtml

Virtual memory is like a game you can't win;
However, without VM there's truly nothing to lose...

http://www.surriel.com/
http://www.conectiva.com/ http://distro.conectiva.com/



--- linux-2.4.5-pre3/mm/vmscan.c.orig Wed May 23 14:09:23 2001
+++ linux-2.4.5-pre3/mm/vmscan.c Wed May 23 14:19:32 2001
@@ -865,14 +865,18 @@

/*
* If we're low on free pages, move pages from the
- * inactive_dirty list to the inactive_clean list.
+ * inactive_dirty list to the inactive_clean list
+ * and shrink the inode and dentry caches.
*
* Usually bdflush will have pre-cleaned the pages
* before we get around to moving them to the other
* list, so this is a relatively cheap operation.
*/
- if (free_shortage())
+ if (free_shortage()) {
ret += page_launder(gfp_mask, user);
+ shrink_dcache_memory(DEF_PRIORITY, gfp_mask);
+ shrink_icache_memory(DEF_PRIORITY, gfp_mask);
+ }

/*
* If needed, we move pages from the active list
@@ -882,21 +886,10 @@
ret += refill_inactive(gfp_mask, user);

/*
- * Delete pages from the inode and dentry caches and
- * reclaim unused slab cache if memory is low.
+ * If we're still short on free pages, reclaim unused
+ * slab cache memory.
*/
if (free_shortage()) {
- shrink_dcache_memory(DEF_PRIORITY, gfp_mask);
- shrink_icache_memory(DEF_PRIORITY, gfp_mask);
- } else {
- /*
- * Illogical, but true. At least for now.
- *
- * If we're _not_ under shortage any more, we
- * reap the caches. Why? Because a noticeable
- * part of the caches are the buffer-heads,
- * which we'll want to keep if under shortage.
- */
kmem_cache_reap(gfp_mask);
}

-
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: 2005-03-22 12:53    [W:0.052 / U:0.860 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site