Hi Kai,

Can you tell me if pages are swapped out running your tests with CKRM ?
If not, can you apply the following patch ?
I already made a correction in the f0.3 version to fix that problem, but
it is incomplete.If this patch doesn't change anything on your machine,
can you send me all the "stats" files,eg. /rcfs/stats and c1/stats, and
the output of "cat /proc/vmstat".
Thanks,
  Valérie


diff -ruNp -X dontdiff linux-2.6.13+f0.3+mem/mm/vmscan.c 
linux-2.6.13+f0.3+mem1/mm/vmscan.c
--- linux-2.6.13+f0.3+mem/mm/vmscan.c   2005-12-02 11:02:28.000000000 +0100
+++ linux-2.6.13+f0.3+mem1/mm/vmscan.c  2005-12-02 11:10:58.000000000 +0100
@@ -893,6 +893,7 @@ ckrm_shrink_class(struct ckrm_mem_res *c
        sc.nr_reclaimed = 0;
        sc.priority = 0; /* always very high priority */
        sc.may_swap = 1;
+       sc.gfp_mask = GFP_KERNEL;
        sc.swap_cluster_max = SWAP_CLUSTER_MAX;
 
        for_each_zone(zone) {




-------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc. Do you grep through log files
for problems?  Stop!  Download the new AJAX search engine that makes
searching your log files as easy as surfing the  web.  DOWNLOAD SPLUNK!
http://ads.osdn.com/?ad_idv37&alloc_id865&op=click
_______________________________________________
ckrm-tech mailing list
https://lists.sourceforge.net/lists/listinfo/ckrm-tech

Reply via email to