block: Add rdma affinity based queue mapping helper
Like pci and virtio, we add a rdma helper for affinity spreading. This achieves optimal mq affinity assignments according to the underlying rdma device affinity maps. Reviewed-by: Jens Axboe <axboe@fb.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Max Gurtovoy <maxg@mellanox.com> Signed-off-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Doug Ledford <dledford@redhat.com>
This commit is contained in:
parent
40b24403f3
commit
24c5dc6610
|
@ -206,4 +206,9 @@ config BLK_MQ_VIRTIO
|
|||
depends on BLOCK && VIRTIO
|
||||
default y
|
||||
|
||||
config BLK_MQ_RDMA
|
||||
bool
|
||||
depends on BLOCK && INFINIBAND
|
||||
default y
|
||||
|
||||
source block/Kconfig.iosched
|
||||
|
|
|
@ -29,6 +29,7 @@ obj-$(CONFIG_BLK_CMDLINE_PARSER) += cmdline-parser.o
|
|||
obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
|
||||
obj-$(CONFIG_BLK_MQ_PCI) += blk-mq-pci.o
|
||||
obj-$(CONFIG_BLK_MQ_VIRTIO) += blk-mq-virtio.o
|
||||
obj-$(CONFIG_BLK_MQ_RDMA) += blk-mq-rdma.o
|
||||
obj-$(CONFIG_BLK_DEV_ZONED) += blk-zoned.o
|
||||
obj-$(CONFIG_BLK_WBT) += blk-wbt.o
|
||||
obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o
|
||||
|
|
|
@ -0,0 +1,52 @@
|
|||
/*
|
||||
* Copyright (c) 2017 Sagi Grimberg.
|
||||
*
|
||||
* This program is free software; you can redistribute it and/or modify it
|
||||
* under the terms and conditions of the GNU General Public License,
|
||||
* version 2, as published by the Free Software Foundation.
|
||||
*
|
||||
* This program is distributed in the hope it will be useful, but WITHOUT
|
||||
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
||||
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
||||
* more details.
|
||||
*/
|
||||
#include <linux/blk-mq.h>
|
||||
#include <linux/blk-mq-rdma.h>
|
||||
#include <rdma/ib_verbs.h>
|
||||
|
||||
/**
|
||||
* blk_mq_rdma_map_queues - provide a default queue mapping for rdma device
|
||||
* @set: tagset to provide the mapping for
|
||||
* @dev: rdma device associated with @set.
|
||||
* @first_vec: first interrupt vectors to use for queues (usually 0)
|
||||
*
|
||||
* This function assumes the rdma device @dev has at least as many available
|
||||
* interrupt vetors as @set has queues. It will then query it's affinity mask
|
||||
* and built queue mapping that maps a queue to the CPUs that have irq affinity
|
||||
* for the corresponding vector.
|
||||
*
|
||||
* In case either the driver passed a @dev with less vectors than
|
||||
* @set->nr_hw_queues, or @dev does not provide an affinity mask for a
|
||||
* vector, we fallback to the naive mapping.
|
||||
*/
|
||||
int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
|
||||
struct ib_device *dev, int first_vec)
|
||||
{
|
||||
const struct cpumask *mask;
|
||||
unsigned int queue, cpu;
|
||||
|
||||
for (queue = 0; queue < set->nr_hw_queues; queue++) {
|
||||
mask = ib_get_vector_affinity(dev, first_vec + queue);
|
||||
if (!mask)
|
||||
goto fallback;
|
||||
|
||||
for_each_cpu(cpu, mask)
|
||||
set->mq_map[cpu] = queue;
|
||||
}
|
||||
|
||||
return 0;
|
||||
|
||||
fallback:
|
||||
return blk_mq_map_queues(set);
|
||||
}
|
||||
EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues);
|
|
@ -0,0 +1,10 @@
|
|||
#ifndef _LINUX_BLK_MQ_RDMA_H
|
||||
#define _LINUX_BLK_MQ_RDMA_H
|
||||
|
||||
struct blk_mq_tag_set;
|
||||
struct ib_device;
|
||||
|
||||
int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
|
||||
struct ib_device *dev, int first_vec);
|
||||
|
||||
#endif /* _LINUX_BLK_MQ_RDMA_H */
|
Loading…
Reference in New Issue