time_stats: split stats-with-quantiles into a separate structure

Currently, struct time_stats has the optional ability to quantize the
information that it collects.  This is /probably/ useful for callers who
want to see quantized information, but it more than doubles the size of
the structure from 224 bytes to 464.  For users who don't care about
that (e.g. upcoming xfs patches) and want to avoid wasting 240 bytes per
counter, split the two into separate pieces.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

5 files changed, 12 insertions, 13 deletions

diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 92547d6fd2d9..04e4a65909a4 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -594,7 +594,7 @@ struct bch_dev {
 
 	/* The rest of this all shows up in sysfs */
 	atomic64_t		cur_latency[2];
-	struct time_stats	io_latency[2];
+	struct time_stats_quantiles	io_latency[2];
 
 #define CONGESTED_MAX		1024
 	atomic_t		congested;
diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c
index 8123a84320e3..3fa2cb1d5b13 100644
--- a/fs/bcachefs/io_write.c
+++ b/fs/bcachefs/io_write.c
@@ -88,7 +88,7 @@ void bch2_latency_acct(struct bch_dev *ca, u64 submit_time, int rw)
 
 	bch2_congested_acct(ca, io_latency, now, rw);
 
-	__time_stats_update(&ca->io_latency[rw], submit_time, now);
+	__time_stats_update(&ca->io_latency[rw].stats, submit_time, now);
 }
 
 #endif
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 647ab8ebe358..30f8b6e9af38 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1168,8 +1168,8 @@ static void bch2_dev_free(struct bch_dev *ca)
 	bch2_dev_buckets_free(ca);
 	free_page((unsigned long) ca->sb_read_scratch);
 
-	time_stats_exit(&ca->io_latency[WRITE]);
-	time_stats_exit(&ca->io_latency[READ]);
+	time_stats_quantiles_exit(&ca->io_latency[WRITE]);
+	time_stats_quantiles_exit(&ca->io_latency[READ]);
 
 	percpu_ref_exit(&ca->io_ref);
 	percpu_ref_exit(&ca->ref);
@@ -1260,10 +1260,8 @@ static struct bch_dev *__bch2_dev_alloc(struct bch_fs *c,
 
 	INIT_WORK(&ca->io_error_work, bch2_io_error_work);
 
-	time_stats_init(&ca->io_latency[READ]);
-	time_stats_init(&ca->io_latency[WRITE]);
-	ca->io_latency[READ].quantiles_enabled = true;
-	ca->io_latency[WRITE].quantiles_enabled = true;
+	time_stats_quantiles_init(&ca->io_latency[READ]);
+	time_stats_quantiles_init(&ca->io_latency[WRITE]);
 
 	ca->mi = bch2_mi_to_cpu(member);
 
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index cee80c47feea..c86a93a8d8fc 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -930,10 +930,10 @@ SHOW(bch2_dev)
 	sysfs_print(io_latency_write,		atomic64_read(&ca->cur_latency[WRITE]));
 
 	if (attr == &sysfs_io_latency_stats_read)
-		bch2_time_stats_to_text(out, &ca->io_latency[READ]);
+		bch2_time_stats_to_text(out, &ca->io_latency[READ].stats);
 
 	if (attr == &sysfs_io_latency_stats_write)
-		bch2_time_stats_to_text(out, &ca->io_latency[WRITE]);
+		bch2_time_stats_to_text(out, &ca->io_latency[WRITE].stats);
 
 	sysfs_printf(congested,			"%u%%",
 		     clamp(atomic_read(&ca->congested), 0, CONGESTED_MAX)
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index 83f95aaab565..40c30cc4db7f 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -365,6 +365,7 @@ static inline void pr_name_and_units(struct printbuf *out, const char *name, u64
 
 void bch2_time_stats_to_text(struct printbuf *out, struct time_stats *stats)
 {
+	struct quantiles *quantiles = time_stats_to_quantiles(stats);
 	s64 f_mean = 0, d_mean = 0;
 	u64 f_stddev = 0, d_stddev = 0;
 
@@ -465,17 +466,17 @@ void bch2_time_stats_to_text(struct printbuf *out, struct time_stats *stats)
 
 	printbuf_tabstops_reset(out);
 
-	if (stats->quantiles_enabled) {
+	if (quantiles) {
 		int i = eytzinger0_first(NR_QUANTILES);
 		const struct time_unit *u =
-			pick_time_units(stats->quantiles.entries[i].m);
+			pick_time_units(quantiles->entries[i].m);
 		u64 last_q = 0;
 
 		prt_printf(out, "quantiles (%s):\t", u->name);
 		eytzinger0_for_each(i, NR_QUANTILES) {
 			bool is_last = eytzinger0_next(i, NR_QUANTILES) == -1;
 
-			u64 q = max(stats->quantiles.entries[i].m, last_q);
+			u64 q = max(quantiles->entries[i].m, last_q);
 			prt_printf(out, "%llu ", div_u64(q, u->nsecs));
 			if (is_last)
 				prt_newline(out);