mirror of
https://github.com/torvalds/linux
synced 2024-11-05 18:23:50 +00:00
bffa9909a6
From commit4b855ad371("blk-mq: Create hctx for each present CPU), blk-mq doesn't remap queue after CPU topo is changed, that said when some of these offline CPUs become online, they are still mapped to hctx 0, then hctx 0 may become the bottleneck of IO dispatch and completion. This patch sets up the mapping from the beginning, and aligns to queue mapping for PCI device (blk_mq_pci_map_queues()). Cc: Stefan Haberland <sth@linux.vnet.ibm.com> Cc: Keith Busch <keith.busch@intel.com> Cc: stable@vger.kernel.org Fixes:4b855ad371("blk-mq: Create hctx for each present CPU) Tested-by: Christian Borntraeger <borntraeger@de.ibm.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
75 lines
1.6 KiB
C
75 lines
1.6 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_queues, const int cpu)
|
|
{
|
|
return cpu % nr_queues;
|
|
}
|
|
|
|
static int get_first_sibling(unsigned int cpu)
|
|
{
|
|
unsigned int ret;
|
|
|
|
ret = cpumask_first(topology_sibling_cpumask(cpu));
|
|
if (ret < nr_cpu_ids)
|
|
return ret;
|
|
|
|
return cpu;
|
|
}
|
|
|
|
int blk_mq_map_queues(struct blk_mq_tag_set *set)
|
|
{
|
|
unsigned int *map = set->mq_map;
|
|
unsigned int nr_queues = set->nr_hw_queues;
|
|
unsigned int cpu, first_sibling;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
/*
|
|
* 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
|
|
* performace optimizations.
|
|
*/
|
|
if (cpu < nr_queues) {
|
|
map[cpu] = cpu_to_queue_index(nr_queues, cpu);
|
|
} else {
|
|
first_sibling = get_first_sibling(cpu);
|
|
if (first_sibling == cpu)
|
|
map[cpu] = cpu_to_queue_index(nr_queues, cpu);
|
|
else
|
|
map[cpu] = map[first_sibling];
|
|
}
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(blk_mq_map_queues);
|
|
|
|
/*
|
|
* 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 local_memory_node(cpu_to_node(i));
|
|
}
|
|
|
|
return NUMA_NO_NODE;
|
|
}
|