[v8,06/12] fs: add percpu counters for significant multigrain timestamp events

Commit Message

Jeff Layton Oct. 1, 2024, 10:59 a.m. UTC

New percpu counters for counting various stats around multigrain
timestamp events, and a new debugfs file for displaying them when
CONFIG_DEBUG_FS is enabled:

- number of attempted ctime updates
- number of successful i_ctime_nsec swaps
- number of fine-grained timestamp fetches

Reviewed-by: Josef Bacik <[e-mail]>
Reviewed-by: Darrick J. Wong <[e-mail]>
Reviewed-by: Jan Kara <[e-mail]>
Tested-by: Randy Dunlap <[e-mail]> # documentation bits
Signed-off-by: Jeff Layton <[e-mail]>
---
 fs/inode.c | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 71 insertions(+), 4 deletions(-)

Patch

diff --git a/fs/inode.c b/fs/inode.c
index 1a7eff2a40e2..e46f7170851b 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -21,6 +21,8 @@ 
 #include <linux/list_lru.h>
 #include <linux/iversion.h>
 #include <linux/rw_hint.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
 #include <trace/events/writeback.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/timestamp.h>
@@ -101,6 +103,69 @@  long get_nr_dirty_inodes(void)
 	return nr_dirty > 0 ? nr_dirty : 0;
 }
 
+#ifdef CONFIG_DEBUG_FS
+static DEFINE_PER_CPU(long, mg_ctime_updates);
+static DEFINE_PER_CPU(long, mg_fine_stamps);
+static DEFINE_PER_CPU(long, mg_ctime_swaps);
+
+static unsigned long get_mg_ctime_updates(void)
+{
+	int i;
+	unsigned long sum = 0;
+
+	for_each_possible_cpu(i)
+		sum += per_cpu(mg_ctime_updates, i);
+	return sum;
+}
+
+static unsigned long get_mg_fine_stamps(void)
+{
+	int i;
+	unsigned long sum = 0;
+
+	for_each_possible_cpu(i)
+		sum += per_cpu(mg_fine_stamps, i);
+	return sum;
+}
+
+static unsigned long get_mg_ctime_swaps(void)
+{
+	int i;
+	unsigned long sum = 0;
+
+	for_each_possible_cpu(i)
+		sum += per_cpu(mg_ctime_swaps, i);
+	return sum;
+}
+
+#define mgtime_counter_inc(__var)	this_cpu_inc(__var)
+
+static int mgts_show(struct seq_file *s, void *p)
+{
+	unsigned long ctime_updates = get_mg_ctime_updates();
+	unsigned long ctime_swaps = get_mg_ctime_swaps();
+	unsigned long fine_stamps = get_mg_fine_stamps();
+
+	seq_printf(s, "%lu %lu %lu\n",
+		   ctime_updates, ctime_swaps, fine_stamps);
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mgts);
+
+static int __init mg_debugfs_init(void)
+{
+	debugfs_create_file("multigrain_timestamps", S_IFREG | S_IRUGO, NULL, NULL, &mgts_fops);
+	return 0;
+}
+late_initcall(mg_debugfs_init);
+
+#else /* ! CONFIG_DEBUG_FS */
+
+#define mgtime_counter_inc(__var)	do { } while (0)
+
+#endif /* CONFIG_DEBUG_FS */
+
 /*
  * Handle nr_inode sysctl
  */
@@ -2691,10 +2756,9 @@  EXPORT_SYMBOL(timestamp_truncate);
  *
  * If it is multigrain, then we first see if the coarse-grained timestamp is
  * distinct from what we have. If so, then we'll just use that. If we have to
- * get a fine-grained timestamp, then do so, and try to swap it into the floor.
- * We accept the new floor value regardless of the outcome of the cmpxchg.
- * After that, we try to swap the new value into i_ctime_nsec. Again, we take
- * the resulting ctime, regardless of the outcome of the swap.
+ * get a fine-grained timestamp, then do so. After that, we try to swap the new
+ * value into i_ctime_nsec. We take the resulting ctime, regardless of the
+ * outcome of the swap.
  */
 struct timespec64 inode_set_ctime_current(struct inode *inode)
 {
@@ -2723,8 +2787,10 @@  struct timespec64 inode_set_ctime_current(struct inode *inode)
 		if (timespec64_compare(&now, &ctime) <= 0) {
 			ktime_get_real_ts64_mg(&now);
 			now = timestamp_truncate(now, inode);
+			mgtime_counter_inc(mg_fine_stamps);
 		}
 	}
+	mgtime_counter_inc(mg_ctime_updates);
 
 	/* No need to cmpxchg if it's exactly the same */
 	if (cns == now.tv_nsec && inode->i_ctime_sec == now.tv_sec) {
@@ -2738,6 +2804,7 @@  struct timespec64 inode_set_ctime_current(struct inode *inode)
 		/* If swap occurred, then we're (mostly) done */
 		inode->i_ctime_sec = now.tv_sec;
 		trace_ctime_ns_xchg(inode, cns, now.tv_nsec, cur);
+		mgtime_counter_inc(mg_ctime_swaps);
 	} else {
 		/*
 		 * Was the change due to someone marking the old ctime QUERIED?