From: Dave Hansen <haveblue@us.ibm.com>
To: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org, Dave Hansen <haveblue@us.ibm.com>
Subject: [RFC][PATCH 2/4] build_zonelists(): abstract node_load[] operations
Date: Tue, 20 Sep 2005 10:23:10 -0700 [thread overview]
Message-ID: <20050920172310.6FA82B0C@kernel.beaverton.ibm.com> (raw)
In-Reply-To: <20050920172303.8CD9190C@kernel.beaverton.ibm.com>
We're shortly going to use find_next_best_node() for both
NUMA and non-NUMA configurations. So, take node_load[],
and hide it behind a couple of helper functions that are
noops when NUMA is off.
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
---
memhotplug-dave/mm/page_alloc.c | 22 +++++++++++++++++++---
1 files changed, 19 insertions(+), 3 deletions(-)
diff -puN mm/page_alloc.c~B1.1-build_zonelists_unification mm/page_alloc.c
--- memhotplug/mm/page_alloc.c~B1.1-build_zonelists_unification 2005-09-14 09:32:38.000000000 -0700
+++ memhotplug-dave/mm/page_alloc.c 2005-09-14 09:32:38.000000000 -0700
@@ -1463,9 +1463,25 @@ static inline zone_index_to_type(int ind
}
-#ifdef CONFIG_NUMA
#define MAX_NODE_LOAD (num_online_nodes())
+
+#ifdef CONFIG_NUMA
static int __initdata node_load[MAX_NUMNODES];
+static int __init get_node_load(int node)
+{
+ return node_load[node];
+}
+static void __init increment_node_load(int node, int load)
+{
+ node_load[node] += load;
+}
+#else
+static inline int get_node_load(int node)
+{
+ return 0;
+}
+static inline void increment_node_load(int node, int load) {}
+#endif
/**
* find_next_best_node - find the next node that should appear in a given node's fallback list
* @node: node whose fallback list we're appending
@@ -1512,7 +1528,7 @@ static int __init find_next_best_node(in
/* Slight preference for less loaded node */
val *= (MAX_NODE_LOAD*MAX_NUMNODES);
- val += node_load[n];
+ val += get_node_load(n);
if (val < min_val) {
min_val = val;
@@ -1552,7 +1568,7 @@ static void __init build_zonelists(pg_da
*/
if (node_distance(local_node, node) !=
node_distance(local_node, prev_node))
- node_load[node] += load;
+ increment_node_load(node, load);
prev_node = node;
load--;
for (i = 0; i < GFP_ZONETYPES; i++) {
_
--
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>
next prev parent reply other threads:[~2005-09-20 17:21 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-09-20 17:23 [RFC][PATCH 0/4] unify both copies of build_zonelists() Dave Hansen
2005-09-20 17:23 ` [RFC][PATCH 1/4] build_zonelists(): create zone_index_to_type() helper Dave Hansen
2005-09-20 17:23 ` Dave Hansen [this message]
2005-09-20 17:23 ` [RFC][PATCH 3/4] build_zonelists() unification: don't re-zero zonelist Dave Hansen
2005-09-20 17:23 ` [RFC][PATCH 4/4] unify both copies of build_zonelists() Dave Hansen
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=20050920172310.6FA82B0C@kernel.beaverton.ibm.com \
--to=haveblue@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
/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