linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "linux-mm@kvack.org" <linux-mm@kvack.org>,
	"containers@lists.osdl.org" <containers@lists.osdl.org>,
	"balbir@linux.vnet.ibm.com" <balbir@linux.vnet.ibm.com>,
	"yamamoto@valinux.co.jp" <yamamoto@valinux.co.jp>,
	hugh@veritas.com
Subject: [RFC][ for -mm] memory controller enhancements for NUMA [7/10] calc scan numbers per zone
Date: Wed, 14 Nov 2007 17:51:29 +0900	[thread overview]
Message-ID: <20071114175129.406804d1.kamezawa.hiroyu@jp.fujitsu.com> (raw)
In-Reply-To: <20071114173950.92857eaa.kamezawa.hiroyu@jp.fujitsu.com>

Define function for calculating the number of scan target on each Zone/LRU.

Signed-off-by: KAMEZAWA Hiruyoki <kamezawa.hiroyu@jp.fujitsu.com>

 include/linux/memcontrol.h |   15 +++++++++++++++
 mm/memcontrol.c            |   40 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+)

Index: linux-2.6.24-rc2-mm1/include/linux/memcontrol.h
===================================================================
--- linux-2.6.24-rc2-mm1.orig/include/linux/memcontrol.h
+++ linux-2.6.24-rc2-mm1/include/linux/memcontrol.h
@@ -73,6 +73,10 @@ extern void mem_cgroup_note_reclaim_prio
 extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
 							int priority);
 
+extern long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
+				struct zone *zone, int priority);
+extern long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
+				struct zone *zone, int priority);
 
 #else /* CONFIG_CGROUP_MEM_CONT */
 static inline void mm_init_cgroup(struct mm_struct *mm,
@@ -173,6 +177,17 @@ static inline void mem_cgroup_record_rec
 	return 0;
 }
 
+static inline long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
+					struct zone *zone, int priority)
+{
+	return 0;
+}
+
+static inline long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
+					struct zone *zone, int priority)
+{
+	return 0;
+}
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */
Index: linux-2.6.24-rc2-mm1/mm/memcontrol.c
===================================================================
--- linux-2.6.24-rc2-mm1.orig/mm/memcontrol.c
+++ linux-2.6.24-rc2-mm1/mm/memcontrol.c
@@ -449,6 +449,46 @@ void mem_cgroup_record_reclaim_priority(
 	mem->prev_priority = priority;
 }
 
+/*
+ * Calculate # of pages to be scanned in this proirity/zone.
+ * See also vmscan.c
+ *
+ * priority statrs from "DEF_PRIORITY" and decremented in each loop.
+ * (see include/linux/mmzone.h)
+ */
+
+long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
+				   struct zone *zone, int priority)
+{
+	s64 nr_active, total, inactive;
+	int nid = zone->zone_pgdat->node_id;
+	int zid = zone_idx(zone);
+
+	total = mem_cgroup_get_zonestat(mem, nid, zid, MEM_CGROUP_ZSTAT_TOTAL);
+	inactive = mem_cgroup_get_zonestat(mem, nid, zid,
+						MEM_CGROUP_ZSTAT_INACTIVE);
+	nr_active = total - inactive;
+	/*
+	 * FIXME: on NUMA, returning 0 here is not good ?
+	 */
+	return (long)(nr_active >> priority);
+}
+
+long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
+					struct zone *zone, int priority)
+{
+	s64 nr_inactive;
+	int nid = zone->zone_pgdat->node_id;
+	int zid = zone_idx(zone);
+
+	nr_inactive = mem_cgroup_get_zonestat(mem, nid, zid,
+						MEM_CGROUP_ZSTAT_INACTIVE);
+	/*
+	 * FIXME: on NUMA, returning 0 here is not good ?
+	 */
+	return (long)(nr_inactive >> priority);
+}
+
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					struct list_head *dst,
 					unsigned long *scanned, int order,

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2007-11-14  8:51 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-11-14  8:39 [RFC][ for -mm] memory controller enhancements for NUMA [0/10] introduction KAMEZAWA Hiroyuki
2007-11-14  8:41 ` [RFC][ for -mm] memory controller enhancements for NUMA [1/10] record nid/zid on page_cgroup KAMEZAWA Hiroyuki
2007-11-14  8:59   ` KAMEZAWA Hiroyuki
2007-11-14  9:22   ` YAMAMOTO Takashi
2007-11-14 10:31   ` kamezawa.hiroyu
2007-11-14  8:42 ` [RFC][ for -mm] memory controller enhancements for NUMA [2/10] account active inactive KAMEZAWA Hiroyuki
2007-11-14  8:43 ` [RFC][ for -mm] memory controller enhancements for NUMA [3/10] define macro for global lru scan KAMEZAWA Hiroyuki
2007-11-14  8:45 ` [RFC][ for -mm] memory controller enhancements for NUMA [4/10] calc mapped_ratio in cgroup KAMEZAWA Hiroyuki
2007-11-14  8:48 ` [RFC][ for -mm] memory controller enhancements for NUMA [5/10] calc active/inactive impabance KAMEZAWA Hiroyuki
2007-11-14  8:50 ` [RFC][ for -mm] memory controller enhancements for NUMA [6/10] record reclaim priority KAMEZAWA Hiroyuki
2007-11-14  8:51 ` KAMEZAWA Hiroyuki [this message]
2007-11-14  8:53 ` [RFC][ for -mm] memory controller enhancements for NUMA [8/10] move reclaim_mapped calc routine (cleanup for later patch) KAMEZAWA Hiroyuki
2007-11-14  8:55 ` [RFC][ for -mm] memory controller enhancements for NUMA [9/10] zone reclaim vs. cgroup reclaim isolation KAMEZAWA Hiroyuki
2007-11-14  8:57 ` [RFC][ for -mm] memory controller enhancements for NUMA [10/10] per-zone-lru KAMEZAWA Hiroyuki
2007-11-14  9:11   ` YAMAMOTO Takashi
2007-11-14 10:29   ` kamezawa.hiroyu
2007-11-15 11:36   ` KAMEZAWA Hiroyuki
2007-11-15  6:25 ` [RFC][ for -mm] memory controller enhancements for NUMA [0/10] introduction Balbir Singh
2007-11-15  6:39   ` KAMEZAWA Hiroyuki

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20071114175129.406804d1.kamezawa.hiroyu@jp.fujitsu.com \
    --to=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=containers@lists.osdl.org \
    --cc=hugh@veritas.com \
    --cc=linux-mm@kvack.org \
    --cc=yamamoto@valinux.co.jp \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox