summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
authorPaolo Valente <paolo.valente@linaro.org>2018-01-13 12:05:17 +0100
committerJens Axboe <axboe@kernel.dk>2018-01-18 08:21:35 -0700
commita52a69ea89dc12e6f4572f554940789c1ab23c7a (patch)
tree0406e05cbef505c74494c817069e13fa7ad83e83 /block
parent23d4ee19e789ae3dce3e04bd24e3d1537965475f (diff)
downloadlinux-a52a69ea89dc12e6f4572f554940789c1ab23c7a.tar.gz
linux-a52a69ea89dc12e6f4572f554940789c1ab23c7a.tar.bz2
linux-a52a69ea89dc12e6f4572f554940789c1ab23c7a.zip
block, bfq: limit tags for writes and async I/O
Asynchronous I/O can easily starve synchronous I/O (both sync reads and sync writes), by consuming all request tags. Similarly, storms of synchronous writes, such as those that sync(2) may trigger, can starve synchronous reads. In their turn, these two problems may also cause BFQ to loose control on latency for interactive and soft real-time applications. For example, on a PLEXTOR PX-256M5S SSD, LibreOffice Writer takes 0.6 seconds to start if the device is idle, but it takes more than 45 seconds (!) if there are sequential writes in the background. This commit addresses this issue by limiting the maximum percentage of tags that asynchronous I/O requests and synchronous write requests can consume. In particular, this commit grants a higher threshold to synchronous writes, to prevent the latter from being starved by asynchronous I/O. According to the above test, LibreOffice Writer now starts in about 1.2 seconds on average, regardless of the background workload, and apart from some rare outlier. To check this improvement, run, e.g., sudo ./comm_startup_lat.sh bfq 5 5 seq 10 "lowriter --terminate_after_init" for the comm_startup_lat benchmark in the S suite [1]. [1] https://github.com/Algodev-github/S Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name> Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com> Signed-off-by: Paolo Valente <paolo.valente@linaro.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block')
-rw-r--r--block/bfq-iosched.c77
-rw-r--r--block/bfq-iosched.h12
2 files changed, 89 insertions, 0 deletions
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index f352b1677143..a7ab0cb50733 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -417,6 +417,82 @@ static struct request *bfq_choose_req(struct bfq_data *bfqd,
}
}
+/*
+ * See the comments on bfq_limit_depth for the purpose of
+ * the depths set in the function.
+ */
+static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
+{
+ bfqd->sb_shift = bt->sb.shift;
+
+ /*
+ * In-word depths if no bfq_queue is being weight-raised:
+ * leaving 25% of tags only for sync reads.
+ *
+ * In next formulas, right-shift the value
+ * (1U<<bfqd->sb_shift), instead of computing directly
+ * (1U<<(bfqd->sb_shift - something)), to be robust against
+ * any possible value of bfqd->sb_shift, without having to
+ * limit 'something'.
+ */
+ /* no more than 50% of tags for async I/O */
+ bfqd->word_depths[0][0] = max((1U<<bfqd->sb_shift)>>1, 1U);
+ /*
+ * no more than 75% of tags for sync writes (25% extra tags
+ * w.r.t. async I/O, to prevent async I/O from starving sync
+ * writes)
+ */
+ bfqd->word_depths[0][1] = max(((1U<<bfqd->sb_shift) * 3)>>2, 1U);
+
+ /*
+ * In-word depths in case some bfq_queue is being weight-
+ * raised: leaving ~63% of tags for sync reads. This is the
+ * highest percentage for which, in our tests, application
+ * start-up times didn't suffer from any regression due to tag
+ * shortage.
+ */
+ /* no more than ~18% of tags for async I/O */
+ bfqd->word_depths[1][0] = max(((1U<<bfqd->sb_shift) * 3)>>4, 1U);
+ /* no more than ~37% of tags for sync writes (~20% extra tags) */
+ bfqd->word_depths[1][1] = max(((1U<<bfqd->sb_shift) * 6)>>4, 1U);
+}
+
+/*
+ * Async I/O can easily starve sync I/O (both sync reads and sync
+ * writes), by consuming all tags. Similarly, storms of sync writes,
+ * such as those that sync(2) may trigger, can starve sync reads.
+ * Limit depths of async I/O and sync writes so as to counter both
+ * problems.
+ */
+static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
+{
+ struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+ struct bfq_data *bfqd = data->q->elevator->elevator_data;
+ struct sbitmap_queue *bt;
+
+ if (op_is_sync(op) && !op_is_write(op))
+ return;
+
+ if (data->flags & BLK_MQ_REQ_RESERVED) {
+ if (unlikely(!tags->nr_reserved_tags)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+ bt = &tags->breserved_tags;
+ } else
+ bt = &tags->bitmap_tags;
+
+ if (unlikely(bfqd->sb_shift != bt->sb.shift))
+ bfq_update_depths(bfqd, bt);
+
+ data->shallow_depth =
+ bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)];
+
+ bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u",
+ __func__, bfqd->wr_busy_queues, op_is_sync(op),
+ data->shallow_depth);
+}
+
static struct bfq_queue *
bfq_rq_pos_tree_lookup(struct bfq_data *bfqd, struct rb_root *root,
sector_t sector, struct rb_node **ret_parent,
@@ -5285,6 +5361,7 @@ static struct elv_fs_entry bfq_attrs[] = {
static struct elevator_type iosched_bfq_mq = {
.ops.mq = {
+ .limit_depth = bfq_limit_depth,
.prepare_request = bfq_prepare_request,
.finish_request = bfq_finish_request,
.exit_icq = bfq_exit_icq,
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 5d47b58d5fc8..fcd941008127 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -629,6 +629,18 @@ struct bfq_data {
struct bfq_io_cq *bio_bic;
/* bfqq associated with the task issuing current bio for merging */
struct bfq_queue *bio_bfqq;
+
+ /*
+ * Cached sbitmap shift, used to compute depth limits in
+ * bfq_update_depths.
+ */
+ unsigned int sb_shift;
+
+ /*
+ * Depth limits used in bfq_limit_depth (see comments on the
+ * function)
+ */
+ unsigned int word_depths[2][2];
};
enum bfqq_state_flags {