mirror of
https://github.com/torvalds/linux.git
synced 2024-11-05 03:21:32 +00:00
959f5f5b2f
Suppose that a system has two CPU sockets, three cores per socket, that it does not support hyperthreading and that four hardware queues are provided by a block driver. With the current algorithm this will lead to the following assignment of CPU cores to hardware queues: HWQ 0: 0 1 HWQ 1: 2 3 HWQ 2: 4 5 HWQ 3: (none) This patch changes the queue assignment into: HWQ 0: 0 1 HWQ 1: 2 HWQ 2: 3 4 HWQ 3: 5 In other words, this patch has the following three effects: - All four hardware queues are used instead of only three. - CPU cores are spread more evenly over hardware queues. For the above example the range of the number of CPU cores associated with a single HWQ is reduced from [0..2] to [1..2]. - If the number of HWQ's is a multiple of the number of CPU sockets it is now guaranteed that all CPU cores associated with a single HWQ reside on the same CPU socket. Signed-off-by: Bart Van Assche <bvanassche@acm.org> Reviewed-by: Sagi Grimberg <sagig@mellanox.com> Cc: Jens Axboe <axboe@fb.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@canonical.com> Cc: Alexander Gordeev <agordeev@redhat.com> Signed-off-by: Jens Axboe <axboe@fb.com>
120 lines
2.5 KiB
C
120 lines
2.5 KiB
C
/*
|
|
* CPU <-> hardware queue mapping helpers
|
|
*
|
|
* Copyright (C) 2013-2014 Jens Axboe
|
|
*/
|
|
#include <linux/kernel.h>
|
|
#include <linux/threads.h>
|
|
#include <linux/module.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/cpu.h>
|
|
|
|
#include <linux/blk-mq.h>
|
|
#include "blk.h"
|
|
#include "blk-mq.h"
|
|
|
|
static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
|
|
const int cpu)
|
|
{
|
|
return cpu * nr_queues / nr_cpus;
|
|
}
|
|
|
|
static int get_first_sibling(unsigned int cpu)
|
|
{
|
|
unsigned int ret;
|
|
|
|
ret = cpumask_first(topology_thread_cpumask(cpu));
|
|
if (ret < nr_cpu_ids)
|
|
return ret;
|
|
|
|
return cpu;
|
|
}
|
|
|
|
int blk_mq_update_queue_map(unsigned int *map, unsigned int nr_queues)
|
|
{
|
|
unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
|
|
cpumask_var_t cpus;
|
|
|
|
if (!alloc_cpumask_var(&cpus, GFP_ATOMIC))
|
|
return 1;
|
|
|
|
cpumask_clear(cpus);
|
|
nr_cpus = nr_uniq_cpus = 0;
|
|
for_each_online_cpu(i) {
|
|
nr_cpus++;
|
|
first_sibling = get_first_sibling(i);
|
|
if (!cpumask_test_cpu(first_sibling, cpus))
|
|
nr_uniq_cpus++;
|
|
cpumask_set_cpu(i, cpus);
|
|
}
|
|
|
|
queue = 0;
|
|
for_each_possible_cpu(i) {
|
|
if (!cpu_online(i)) {
|
|
map[i] = 0;
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* Easy case - we have equal or more hardware queues. Or
|
|
* there are no thread siblings to take into account. Do
|
|
* 1:1 if enough, or sequential mapping if less.
|
|
*/
|
|
if (nr_queues >= nr_cpus || nr_cpus == nr_uniq_cpus) {
|
|
map[i] = cpu_to_queue_index(nr_cpus, nr_queues, queue);
|
|
queue++;
|
|
continue;
|
|
}
|
|
|
|
/*
|
|
* Less then nr_cpus queues, and we have some number of
|
|
* threads per cores. Map sibling threads to the same
|
|
* queue.
|
|
*/
|
|
first_sibling = get_first_sibling(i);
|
|
if (first_sibling == i) {
|
|
map[i] = cpu_to_queue_index(nr_uniq_cpus, nr_queues,
|
|
queue);
|
|
queue++;
|
|
} else
|
|
map[i] = map[first_sibling];
|
|
}
|
|
|
|
free_cpumask_var(cpus);
|
|
return 0;
|
|
}
|
|
|
|
unsigned int *blk_mq_make_queue_map(struct blk_mq_tag_set *set)
|
|
{
|
|
unsigned int *map;
|
|
|
|
/* If cpus are offline, map them to first hctx */
|
|
map = kzalloc_node(sizeof(*map) * nr_cpu_ids, GFP_KERNEL,
|
|
set->numa_node);
|
|
if (!map)
|
|
return NULL;
|
|
|
|
if (!blk_mq_update_queue_map(map, set->nr_hw_queues))
|
|
return map;
|
|
|
|
kfree(map);
|
|
return NULL;
|
|
}
|
|
|
|
/*
|
|
* We have no quick way of doing reverse lookups. This is only used at
|
|
* queue init time, so runtime isn't important.
|
|
*/
|
|
int blk_mq_hw_queue_to_node(unsigned int *mq_map, unsigned int index)
|
|
{
|
|
int i;
|
|
|
|
for_each_possible_cpu(i) {
|
|
if (index == mq_map[i])
|
|
return cpu_to_node(i);
|
|
}
|
|
|
|
return NUMA_NO_NODE;
|
|
}
|