Spread queues among present CPUs first, then building the mapping
on other non-present CPUs.
So we can minimize count of dead queues which are mapped by un-present
CPUs only. Then bad IO performance can be avoided by this unbalanced
mapping between CPUs and queues.
The similar policy has been applied on Managed IRQ affinity.
Reported-by: Yi Zhang <yi.zhang@xxxxxxxxxx>
Cc: Yi Zhang <yi.zhang@xxxxxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
---
block/blk-mq-cpumap.c | 34 +++++++++++++++++++++++-----------
1 file changed, 23 insertions(+), 11 deletions(-)
diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index f945621a0e8f..e217f3404dc7 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -15,10 +15,9 @@
#include "blk.h"
#include "blk-mq.h"
-static int cpu_to_queue_index(struct blk_mq_queue_map *qmap,
- unsigned int nr_queues, const int cpu)
+static int queue_index(struct blk_mq_queue_map *qmap, const int q)
{
- return qmap->queue_offset + (cpu % nr_queues);
+ return qmap->queue_offset + q;
}
static int get_first_sibling(unsigned int cpu)
@@ -36,23 +35,36 @@ int blk_mq_map_queues(struct blk_mq_queue_map *qmap)
{
unsigned int *map = qmap->mq_map;
unsigned int nr_queues = qmap->nr_queues;
- unsigned int cpu, first_sibling;
+ unsigned int cpu, first_sibling, q = 0;
+
+ for_each_possible_cpu(cpu)
+ map[cpu] = -1;
+
+ /*
+ * Spread queues among present CPUs first for minimizing
+ * count of dead queues which are mapped by all un-present CPUs
+ */
+ for_each_present_cpu(cpu) {
+ if (q >= nr_queues)
+ break;
+ map[cpu] = queue_index(qmap, q++);
+ }
for_each_possible_cpu(cpu) {
+ if (map[cpu] != -1)
+ continue;
/*
* First do sequential mapping between CPUs and queues.
* In case we still have CPUs to map, and we have some number of
* threads per cores then map sibling threads to the same queue
* for performance optimizations.
*/
- if (cpu < nr_queues) {
- map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
+ first_sibling = get_first_sibling(cpu);
+ if (first_sibling == cpu) {
+ map[cpu] = queue_index(qmap, q);
+ q = (q + 1) % nr_queues;
} else {
- first_sibling = get_first_sibling(cpu);
- if (first_sibling == cpu)
- map[cpu] = cpu_to_queue_index(qmap, nr_queues, cpu);
- else
- map[cpu] = map[first_sibling];
+ map[cpu] = map[first_sibling];
}
}
--
2.20.1
