blk-mq: respect rq_affinity
The blk-mq code is using it's own version of the I/O completion affinity tunables, which causes a few issues: - the rq_affinity sysfs file doesn't work for blk-mq devices, even if it still is present, thus breaking existing tuning setups. - the rq_affinity = 1 mode, which is the defauly for legacy request based drivers isn't implemented at all. - blk-mq drivers don't implement any completion affinity with the default flag settings. This patches removes the blk-mq ipi_redirect flag and sysfs file, as well as the internal BLK_MQ_F_SHOULD_IPI flag and replaces it with code that respects the queue-wide rq_affinity flags and also implements the rq_affinity = 1 mode. This means I/O completion affinity can now only be tuned block-queue wide instead of per context, which seems more sensible to me anyway. Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
This commit is contained in:
parent
87ee7b1121
commit
3853520163
|
@ -203,42 +203,6 @@ static ssize_t blk_mq_hw_sysfs_rq_list_show(struct blk_mq_hw_ctx *hctx,
|
|||
return ret;
|
||||
}
|
||||
|
||||
static ssize_t blk_mq_hw_sysfs_ipi_show(struct blk_mq_hw_ctx *hctx, char *page)
|
||||
{
|
||||
ssize_t ret;
|
||||
|
||||
spin_lock(&hctx->lock);
|
||||
ret = sprintf(page, "%u\n", !!(hctx->flags & BLK_MQ_F_SHOULD_IPI));
|
||||
spin_unlock(&hctx->lock);
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
static ssize_t blk_mq_hw_sysfs_ipi_store(struct blk_mq_hw_ctx *hctx,
|
||||
const char *page, size_t len)
|
||||
{
|
||||
struct blk_mq_ctx *ctx;
|
||||
unsigned long ret;
|
||||
unsigned int i;
|
||||
|
||||
if (kstrtoul(page, 10, &ret)) {
|
||||
pr_err("blk-mq-sysfs: invalid input '%s'\n", page);
|
||||
return -EINVAL;
|
||||
}
|
||||
|
||||
spin_lock(&hctx->lock);
|
||||
if (ret)
|
||||
hctx->flags |= BLK_MQ_F_SHOULD_IPI;
|
||||
else
|
||||
hctx->flags &= ~BLK_MQ_F_SHOULD_IPI;
|
||||
spin_unlock(&hctx->lock);
|
||||
|
||||
hctx_for_each_ctx(hctx, ctx, i)
|
||||
ctx->ipi_redirect = !!ret;
|
||||
|
||||
return len;
|
||||
}
|
||||
|
||||
static ssize_t blk_mq_hw_sysfs_tags_show(struct blk_mq_hw_ctx *hctx, char *page)
|
||||
{
|
||||
return blk_mq_tag_sysfs_show(hctx->tags, page);
|
||||
|
@ -307,11 +271,6 @@ static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_pending = {
|
|||
.attr = {.name = "pending", .mode = S_IRUGO },
|
||||
.show = blk_mq_hw_sysfs_rq_list_show,
|
||||
};
|
||||
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_ipi = {
|
||||
.attr = {.name = "ipi_redirect", .mode = S_IRUGO | S_IWUSR},
|
||||
.show = blk_mq_hw_sysfs_ipi_show,
|
||||
.store = blk_mq_hw_sysfs_ipi_store,
|
||||
};
|
||||
static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_tags = {
|
||||
.attr = {.name = "tags", .mode = S_IRUGO },
|
||||
.show = blk_mq_hw_sysfs_tags_show,
|
||||
|
@ -326,7 +285,6 @@ static struct attribute *default_hw_ctx_attrs[] = {
|
|||
&blk_mq_hw_sysfs_run.attr,
|
||||
&blk_mq_hw_sysfs_dispatched.attr,
|
||||
&blk_mq_hw_sysfs_pending.attr,
|
||||
&blk_mq_hw_sysfs_ipi.attr,
|
||||
&blk_mq_hw_sysfs_tags.attr,
|
||||
&blk_mq_hw_sysfs_cpus.attr,
|
||||
NULL,
|
||||
|
|
|
@ -326,15 +326,19 @@ static void __blk_mq_complete_request_remote(void *data)
|
|||
void __blk_mq_complete_request(struct request *rq)
|
||||
{
|
||||
struct blk_mq_ctx *ctx = rq->mq_ctx;
|
||||
bool shared = false;
|
||||
int cpu;
|
||||
|
||||
if (!ctx->ipi_redirect) {
|
||||
if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) {
|
||||
rq->q->softirq_done_fn(rq);
|
||||
return;
|
||||
}
|
||||
|
||||
cpu = get_cpu();
|
||||
if (cpu != ctx->cpu && cpu_online(ctx->cpu)) {
|
||||
if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags))
|
||||
shared = cpus_share_cache(cpu, ctx->cpu);
|
||||
|
||||
if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
|
||||
rq->csd.func = __blk_mq_complete_request_remote;
|
||||
rq->csd.info = rq;
|
||||
rq->csd.flags = 0;
|
||||
|
|
|
@ -11,7 +11,6 @@ struct blk_mq_ctx {
|
|||
|
||||
unsigned int cpu;
|
||||
unsigned int index_hw;
|
||||
unsigned int ipi_redirect;
|
||||
|
||||
/* incremented at dispatch time */
|
||||
unsigned long rq_dispatched[2];
|
||||
|
|
|
@ -122,7 +122,6 @@ enum {
|
|||
|
||||
BLK_MQ_F_SHOULD_MERGE = 1 << 0,
|
||||
BLK_MQ_F_SHOULD_SORT = 1 << 1,
|
||||
BLK_MQ_F_SHOULD_IPI = 1 << 2,
|
||||
|
||||
BLK_MQ_S_STOPPED = 0,
|
||||
|
||||
|
|
Loading…
Reference in New Issue