From: Bharata B Rao <bharata@xxxxxxx> 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/20210830121603.1081-1-bharata@xxxxxxx Link: https://lkml.kernel.org/r/20210830121603.1081-2-bharata@xxxxxxx Signed-off-by: Bharata B Rao <bharata@xxxxxxx> Acked-by: Mel Gorman <mgorman@xxxxxxx> Reviewed-by: Anshuman Khandual <anshuman.khandual@xxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: Lee Schermerhorn <lee.schermerhorn@xxxxxx> Cc: Krupa Ramakrishnan <krupa.ramakrishnan@xxxxxxx> Cc: Sadagopan Srinivasan <Sadagopan.Srinivasan@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/page_alloc.c | 4 ++++ 1 file changed, 4 insertions(+) --- 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 _
