[108/262] mm/page_alloc: print node fallback order

Commit Message

Andrew Morton Nov. 5, 2021, 8:40 p.m. UTC

From: Bharata B Rao <[e-mail]>
Subject: mm/page_alloc: print node fallback order

Patch series "Fix NUMA nodes fallback list ordering".

For a NUMA system that has multiple nodes at same distance from other
nodes, the fallback list generation prefers same node order for them
instead of round-robin thereby penalizing one node over others.  This
series fixes it.

More description of the problem and the fix is present in the patch
description.


This patch (of 2):

Print information message about the allocation fallback order for each
NUMA node during boot.

No functional changes here.  This makes it easier to illustrate the
problem in the node fallback list generation, which the next patch fixes.

Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Bharata B Rao <[e-mail]>
Acked-by: Mel Gorman <[e-mail]>
Reviewed-by: Anshuman Khandual <[e-mail]>
Cc: KAMEZAWA Hiroyuki <[e-mail]>
Cc: Lee Schermerhorn <[e-mail]>
Cc: Krupa Ramakrishnan <[e-mail]>
Cc: Sadagopan Srinivasan <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 mm/page_alloc.c |    4 ++++
 1 file changed, 4 insertions(+)

Patch

--- a/mm/page_alloc.c~mm-page_alloc-print-node-fallback-order
+++ a/mm/page_alloc.c
@@ -6262,6 +6262,10 @@  static void build_zonelists(pg_data_t *p
 
 	build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
 	build_thisnode_zonelists(pgdat);
+	pr_info("Fallback order for Node %d: ", local_node);
+	for (node = 0; node < nr_nodes; node++)
+		pr_cont("%d ", node_order[node]);
+	pr_cont("\n");
 }
 
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES