[PATCH 1/3] block/diskstats: accumulate all per-cpu counters in one pass
From: Konstantin Khlebnikov
Date: Mon Apr 01 2019 - 11:59:52 EST
This is faster and makes code much smaller:
./scripts/bloat-o-meter vmlinux.before vmlinux.after
add/remove: 1/0 grow/shrink: 0/2 up/down: 176/-1348 (-1172)
Function old new delta
part_stat_read_all - 176 +176
diskstats_show 1190 569 -621
part_stat_show 1064 337 -727
Total: Before=13762189, After=13761017, chg -0.01%
Signed-off-by: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>
---
block/genhd.c | 62 +++++++++++++++++++++++++++++++++++----------
block/partition-generic.c | 31 ++++++++++++-----------
include/linux/genhd.h | 5 +---
3 files changed, 67 insertions(+), 31 deletions(-)
diff --git a/block/genhd.c b/block/genhd.c
index 703267865f14..2f986af81ba1 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -45,6 +45,34 @@ static void disk_add_events(struct gendisk *disk);
static void disk_del_events(struct gendisk *disk);
static void disk_release_events(struct gendisk *disk);
+#ifdef CONFIG_SMP
+void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
+{
+ int cpu;
+
+ memset(stat, 0, sizeof(struct disk_stats));
+ for_each_possible_cpu(cpu) {
+ struct disk_stats *ptr = per_cpu_ptr(part->dkstats, cpu);
+ int group;
+
+ for (group = 0; group < NR_STAT_GROUPS; group++) {
+ stat->nsecs[group] += ptr->nsecs[group];
+ stat->sectors[group] += ptr->sectors[group];
+ stat->ios[group] += ptr->ios[group];
+ stat->merges[group] += ptr->merges[group];
+ }
+
+ stat->io_ticks += ptr->io_ticks;
+ stat->time_in_queue += ptr->time_in_queue;
+ }
+}
+#else /* CONFIG_SMP */
+void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
+{
+ memcpy(stat, &part->dkstats, sizeof(struct disk_stats));
+}
+#endif /* CONFIG_SMP */
+
void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
{
if (queue_is_mq(q))
@@ -1341,6 +1369,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
struct hd_struct *hd;
char buf[BDEVNAME_SIZE];
unsigned int inflight;
+ struct disk_stats stat;
/*
if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next)
@@ -1352,7 +1381,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
while ((hd = disk_part_iter_next(&piter))) {
+ part_stat_read_all(hd, &stat);
inflight = part_in_flight(gp->queue, hd);
+
seq_printf(seqf, "%4d %7d %s "
"%lu %lu %lu %u "
"%lu %lu %lu %u "
@@ -1360,21 +1391,24 @@ static int diskstats_show(struct seq_file *seqf, void *v)
"%lu %lu %lu %u\n",
MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
disk_name(gp, hd->partno, buf),
- part_stat_read(hd, ios[STAT_READ]),
- part_stat_read(hd, merges[STAT_READ]),
- part_stat_read(hd, sectors[STAT_READ]),
- (unsigned int)part_stat_read_msecs(hd, STAT_READ),
- part_stat_read(hd, ios[STAT_WRITE]),
- part_stat_read(hd, merges[STAT_WRITE]),
- part_stat_read(hd, sectors[STAT_WRITE]),
- (unsigned int)part_stat_read_msecs(hd, STAT_WRITE),
+ stat.ios[STAT_READ],
+ stat.merges[STAT_READ],
+ stat.sectors[STAT_READ],
+ (unsigned int)div_u64(stat.nsecs[STAT_READ],
+ NSEC_PER_MSEC),
+ stat.ios[STAT_WRITE],
+ stat.merges[STAT_WRITE],
+ stat.sectors[STAT_WRITE],
+ (unsigned int)div_u64(stat.nsecs[STAT_WRITE],
+ NSEC_PER_MSEC),
inflight,
- jiffies_to_msecs(part_stat_read(hd, io_ticks)),
- jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
- part_stat_read(hd, ios[STAT_DISCARD]),
- part_stat_read(hd, merges[STAT_DISCARD]),
- part_stat_read(hd, sectors[STAT_DISCARD]),
- (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD)
+ jiffies_to_msecs(stat.io_ticks),
+ jiffies_to_msecs(stat.time_in_queue),
+ stat.ios[STAT_DISCARD],
+ stat.merges[STAT_DISCARD],
+ stat.sectors[STAT_DISCARD],
+ (unsigned int)div_u64(stat.nsecs[STAT_DISCARD],
+ NSEC_PER_MSEC)
);
}
disk_part_iter_exit(&piter);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 8e596a8dff32..621e0d9f3c92 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -120,30 +120,33 @@ ssize_t part_stat_show(struct device *dev,
{
struct hd_struct *p = dev_to_part(dev);
struct request_queue *q = part_to_disk(p)->queue;
+ struct disk_stats stat;
unsigned int inflight;
+ part_stat_read_all(p, &stat);
inflight = part_in_flight(q, p);
+
return sprintf(buf,
"%8lu %8lu %8llu %8u "
"%8lu %8lu %8llu %8u "
"%8u %8u %8u "
"%8lu %8lu %8llu %8u"
"\n",
- part_stat_read(p, ios[STAT_READ]),
- part_stat_read(p, merges[STAT_READ]),
- (unsigned long long)part_stat_read(p, sectors[STAT_READ]),
- (unsigned int)part_stat_read_msecs(p, STAT_READ),
- part_stat_read(p, ios[STAT_WRITE]),
- part_stat_read(p, merges[STAT_WRITE]),
- (unsigned long long)part_stat_read(p, sectors[STAT_WRITE]),
- (unsigned int)part_stat_read_msecs(p, STAT_WRITE),
+ stat.ios[STAT_READ],
+ stat.merges[STAT_READ],
+ (unsigned long long)stat.sectors[STAT_READ],
+ (unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC),
+ stat.ios[STAT_WRITE],
+ stat.merges[STAT_WRITE],
+ (unsigned long long)stat.sectors[STAT_WRITE],
+ (unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC),
inflight,
- jiffies_to_msecs(part_stat_read(p, io_ticks)),
- jiffies_to_msecs(part_stat_read(p, time_in_queue)),
- part_stat_read(p, ios[STAT_DISCARD]),
- part_stat_read(p, merges[STAT_DISCARD]),
- (unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
- (unsigned int)part_stat_read_msecs(p, STAT_DISCARD));
+ jiffies_to_msecs(stat.io_ticks),
+ jiffies_to_msecs(stat.time_in_queue),
+ stat.ios[STAT_DISCARD],
+ stat.merges[STAT_DISCARD],
+ (unsigned long long)stat.sectors[STAT_DISCARD],
+ (unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC));
}
ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 06c0fd594097..7f981be190b4 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -357,9 +357,6 @@ static inline void free_part_stats(struct hd_struct *part)
#endif /* CONFIG_SMP */
-#define part_stat_read_msecs(part, which) \
- div_u64(part_stat_read(part, nsecs[which]), NSEC_PER_MSEC)
-
#define part_stat_read_accum(part, field) \
(part_stat_read(part, field[STAT_READ]) + \
part_stat_read(part, field[STAT_WRITE]) + \
@@ -391,6 +388,8 @@ static inline void free_part_stats(struct hd_struct *part)
#define part_stat_local_read_cpu(gendiskp, field, cpu) \
local_read(&(part_stat_get_cpu(gendiskp, field, cpu)))
+void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat);
+
unsigned int part_in_flight(struct request_queue *q, struct hd_struct *part);
void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
unsigned int inflight[2]);