block, bfq: lower-bound the estimated peak rate to 1

If a storage device handled by BFQ happens to be slower than 7.5 KB/s
for a certain amount of time (in the order of a second), then the
estimated peak rate of the device, maintained in BFQ, becomes equal to
0. The reason is the limited precision with which the rate is
represented (details on the range of representable values in the
comments introduced by this commit). This leads to a division-by-zero
error where the estimated peak rate is used as divisor. Such a type of
failure has been reported in [1].

This commit addresses this issue by:
1. Lower-bounding the estimated peak rate to 1
2. Adding and improving comments on the range of rates representable

[1] https://www.spinics.net/lists/kernel/msg2739205.html

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 25 insertions, 2 deletions

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index aeca22d911010..f0ecd98509d84 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -201,7 +201,20 @@ static struct kmem_cache *bfq_pool;
 /* Target observation time interval for a peak-rate update (ns) */
 #define BFQ_RATE_REF_INTERVAL	NSEC_PER_SEC
 
-/* Shift used for peak rate fixed precision calculations. */
+/*
+ * Shift used for peak-rate fixed precision calculations.
+ * With
+ * - the current shift: 16 positions
+ * - the current type used to store rate: u32
+ * - the current unit of measure for rate: [sectors/usec], or, more precisely,
+ *   [(sectors/usec) / 2^BFQ_RATE_SHIFT] to take into account the shift,
+ * the range of rates that can be stored is
+ * [1 / 2^BFQ_RATE_SHIFT, 2^(32 - BFQ_RATE_SHIFT)] sectors/usec =
+ * [1 / 2^16, 2^16] sectors/usec = [15e-6, 65536] sectors/usec =
+ * [15, 65G] sectors/sec
+ * Which, assuming a sector size of 512B, corresponds to a range of
+ * [7.5K, 33T] B/sec
+ */
 #define BFQ_RATE_SHIFT		16
 
 /*
@@ -2637,6 +2650,16 @@ static void bfq_update_rate_reset(struct bfq_data *bfqd, struct request *rq)
 	rate /= divisor; /* smoothing constant alpha = 1/divisor */
 
 	bfqd->peak_rate += rate;
+
+	/*
+	 * For a very slow device, bfqd->peak_rate can reach 0 (see
+	 * the minimum representable values reported in the comments
+	 * on BFQ_RATE_SHIFT). Push to 1 if this happens, to avoid
+	 * divisions by zero where bfqd->peak_rate is used as a
+	 * divisor.
+	 */
+	bfqd->peak_rate = max_t(u32, 1, bfqd->peak_rate);
+
 	update_thr_responsiveness_params(bfqd);
 
 reset_computation:
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 350c39ae2896e..ae2f3dadec441 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -499,7 +499,7 @@ struct bfq_data {
 	u64 delta_from_first;
 	/*
 	 * Current estimate of the device peak rate, measured in
-	 * [BFQ_RATE_SHIFT * sectors/usec]. The left-shift by
+	 * [(sectors/usec) / 2^BFQ_RATE_SHIFT]. The left-shift by
 	 * BFQ_RATE_SHIFT is performed to increase precision in
 	 * fixed-point calculations.
 	 */