dm: add statistics support

Support the collection of I/O statistics on user-defined regions of
a DM device.  If no regions are defined no statistics are collected so
there isn't any performance impact.  Only bio-based DM devices are
currently supported.

Each user-defined region specifies a starting sector, length and step.
Individual statistics will be collected for each step-sized area within
the range specified.

The I/O statistics counters for each step-sized area of a region are
in the same format as /sys/block/*/stat or /proc/diskstats but extra
counters (12 and 13) are provided: total time spent reading and
writing in milliseconds.  All these counters may be accessed by sending
the @stats_print message to the appropriate DM device via dmsetup.

The creation of DM statistics will allocate memory via kmalloc or
fallback to using vmalloc space.  At most, 1/4 of the overall system
memory may be allocated by DM statistics.  The admin can see how much
memory is used by reading
/sys/module/dm_mod/parameters/stats_current_allocated_bytes

See Documentation/device-mapper/statistics.txt for more details.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>

Documentation/device-mapper/statistics.txt

@@ -0,0 +1,186 @@
+DM statistics
+=============
+
+Device Mapper supports the collection of I/O statistics on user-defined
+regions of a DM device.	 If no regions are defined no statistics are
+collected so there isn't any performance impact.  Only bio-based DM
+devices are currently supported.
+
+Each user-defined region specifies a starting sector, length and step.
+Individual statistics will be collected for each step-sized area within
+the range specified.
+
+The I/O statistics counters for each step-sized area of a region are
+in the same format as /sys/block/*/stat or /proc/diskstats (see:
+Documentation/iostats.txt).  But two extra counters (12 and 13) are
+provided: total time spent reading and writing in milliseconds.	 All
+these counters may be accessed by sending the @stats_print message to
+the appropriate DM device via dmsetup.
+
+Each region has a corresponding unique identifier, which we call a
+region_id, that is assigned when the region is created.	 The region_id
+must be supplied when querying statistics about the region, deleting the
+region, etc.  Unique region_ids enable multiple userspace programs to
+request and process statistics for the same DM device without stepping
+on each other's data.
+
+The creation of DM statistics will allocate memory via kmalloc or
+fallback to using vmalloc space.  At most, 1/4 of the overall system
+memory may be allocated by DM statistics.  The admin can see how much
+memory is used by reading
+/sys/module/dm_mod/parameters/stats_current_allocated_bytes
+
+Messages
+========
+
+    @stats_create <range> <step> [<program_id> [<aux_data>]]
+
+	Create a new region and return the region_id.
+
+	<range>
+	  "-" - whole device
+	  "<start_sector>+<length>" - a range of <length> 512-byte sectors
+				      starting with <start_sector>.
+
+	<step>
+	  "<area_size>" - the range is subdivided into areas each containing
+			  <area_size> sectors.
+	  "/<number_of_areas>" - the range is subdivided into the specified
+				 number of areas.
+
+	<program_id>
+	  An optional parameter.  A name that uniquely identifies
+	  the userspace owner of the range.  This groups ranges together
+	  so that userspace programs can identify the ranges they
+	  created and ignore those created by others.
+	  The kernel returns this string back in the output of
+	  @stats_list message, but it doesn't use it for anything else.
+
+	<aux_data>
+	  An optional parameter.  A word that provides auxiliary data
+	  that is useful to the client program that created the range.
+	  The kernel returns this string back in the output of
+	  @stats_list message, but it doesn't use this value for anything.
+
+    @stats_delete <region_id>
+
+	Delete the region with the specified id.
+
+	<region_id>
+	  region_id returned from @stats_create
+
+    @stats_clear <region_id>
+
+	Clear all the counters except the in-flight i/o counters.
+
+	<region_id>
+	  region_id returned from @stats_create
+
+    @stats_list [<program_id>]
+
+	List all regions registered with @stats_create.
+
+	<program_id>
+	  An optional parameter.
+	  If this parameter is specified, only matching regions
+	  are returned.
+	  If it is not specified, all regions are returned.
+
+	Output format:
+	  <region_id>: <start_sector>+<length> <step> <program_id> <aux_data>
+
+    @stats_print <region_id> [<starting_line> <number_of_lines>]
+
+	Print counters for each step-sized area of a region.
+
+	<region_id>
+	  region_id returned from @stats_create
+
+	<starting_line>
+	  The index of the starting line in the output.
+	  If omitted, all lines are returned.
+
+	<number_of_lines>
+	  The number of lines to include in the output.
+	  If omitted, all lines are returned.
+
+	Output format for each step-sized area of a region:
+
+	  <start_sector>+<length> counters
+
+	  The first 11 counters have the same meaning as
+	  /sys/block/*/stat or /proc/diskstats.
+
+	  Please refer to Documentation/iostats.txt for details.
+
+	  1. the number of reads completed
+	  2. the number of reads merged
+	  3. the number of sectors read
+	  4. the number of milliseconds spent reading
+	  5. the number of writes completed
+	  6. the number of writes merged
+	  7. the number of sectors written
+	  8. the number of milliseconds spent writing
+	  9. the number of I/Os currently in progress
+	  10. the number of milliseconds spent doing I/Os
+	  11. the weighted number of milliseconds spent doing I/Os
+
+	  Additional counters:
+	  12. the total time spent reading in milliseconds
+	  13. the total time spent writing in milliseconds
+
+    @stats_print_clear <region_id> [<starting_line> <number_of_lines>]
+
+	Atomically print and then clear all the counters except the
+	in-flight i/o counters.	 Useful when the client consuming the
+	statistics does not want to lose any statistics (those updated
+	between printing and clearing).
+
+	<region_id>
+	  region_id returned from @stats_create
+
+	<starting_line>
+	  The index of the starting line in the output.
+	  If omitted, all lines are printed and then cleared.
+
+	<number_of_lines>
+	  The number of lines to process.
+	  If omitted, all lines are printed and then cleared.
+
+    @stats_set_aux <region_id> <aux_data>
+
+	Store auxiliary data aux_data for the specified region.
+
+	<region_id>
+	  region_id returned from @stats_create
+
+	<aux_data>
+	  The string that identifies data which is useful to the client
+	  program that created the range.  The kernel returns this
+	  string back in the output of @stats_list message, but it
+	  doesn't use this value for anything.
+
+Examples
+========
+
+Subdivide the DM device 'vol' into 100 pieces and start collecting
+statistics on them:
+
+  dmsetup message vol 0 @stats_create - /100
+
+Set the auxillary data string to "foo bar baz" (the escape for each
+space must also be escaped, otherwise the shell will consume them):
+
+  dmsetup message vol 0 @stats_set_aux 0 foo\\ bar\\ baz
+
+List the statistics:
+
+  dmsetup message vol 0 @stats_list
+
+Print the statistics:
+
+  dmsetup message vol 0 @stats_print 0
+
+Delete the statistics:
+
+  dmsetup message vol 0 @stats_delete 0

drivers/md/Makefile

@@ -3,7 +3,7 @@
 #
 
 dm-mod-y	+= dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
-		   dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o
+		   dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o dm-stats.o
 dm-multipath-y	+= dm-path-selector.o dm-mpath.o
 dm-snapshot-y	+= dm-snap.o dm-exception-store.o dm-snap-transient.o \
 		    dm-snap-persistent.o

drivers/md/dm-ioctl.c

@@ -1455,20 +1455,26 @@ static int table_status(struct dm_ioctl *param, size_t param_size)
 	return 0;
 }
 
-static bool buffer_test_overflow(char *result, unsigned maxlen)
-{
-	return !maxlen || strlen(result) + 1 >= maxlen;
-}
-
 /*
- * Process device-mapper dependent messages.
+ * Process device-mapper dependent messages.  Messages prefixed with '@'
+ * are processed by the DM core.  All others are delivered to the target.
  * Returns a number <= 1 if message was processed by device mapper.
  * Returns 2 if message should be delivered to the target.
  */
 static int message_for_md(struct mapped_device *md, unsigned argc, char **argv,
 			  char *result, unsigned maxlen)
 {
-	return 2;
+	int r;
+
+	if (**argv != '@')
+		return 2; /* no '@' prefix, deliver to target */
+
+	r = dm_stats_message(md, argc, argv, result, maxlen);
+	if (r < 2)
+		return r;
+
+	DMERR("Unsupported message sent to DM core: %s", argv[0]);
+	return -EINVAL;
 }
 
 /*
@@ -1542,7 +1548,7 @@ static int target_message(struct dm_ioctl *param, size_t param_size)
 
 	if (r == 1) {
 		param->flags |= DM_DATA_OUT_FLAG;
-		if (buffer_test_overflow(result, maxlen))
+		if (dm_message_test_buffer_overflow(result, maxlen))
 			param->flags |= DM_BUFFER_FULL_FLAG;
 		else
 			param->data_size = param->data_start + strlen(result) + 1;

drivers/md/dm-stats.h

@@ -0,0 +1,40 @@
+#ifndef DM_STATS_H
+#define DM_STATS_H
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+
+int dm_statistics_init(void);
+void dm_statistics_exit(void);
+
+struct dm_stats {
+	struct mutex mutex;
+	struct list_head list;	/* list of struct dm_stat */
+	struct dm_stats_last_position __percpu *last;
+	sector_t last_sector;
+	unsigned last_rw;
+};
+
+struct dm_stats_aux {
+	bool merged;
+};
+
+void dm_stats_init(struct dm_stats *st);
+void dm_stats_cleanup(struct dm_stats *st);
+
+struct mapped_device;
+
+int dm_stats_message(struct mapped_device *md, unsigned argc, char **argv,
+		     char *result, unsigned maxlen);
+
+void dm_stats_account_io(struct dm_stats *stats, unsigned long bi_rw,
+			 sector_t bi_sector, unsigned bi_sectors, bool end,
+			 unsigned long duration, struct dm_stats_aux *aux);
+
+static inline bool dm_stats_used(struct dm_stats *st)
+{
+	return !list_empty(&st->list);
+}
+
+#endif

drivers/md/dm.c

@@ -60,6 +60,7 @@ struct dm_io {
 	struct bio *bio;
 	unsigned long start_time;
 	spinlock_t endio_lock;
+	struct dm_stats_aux stats_aux;
 };
 
 /*
@@ -198,6 +199,8 @@ struct mapped_device {
 
 	/* zero-length flush that will be cloned and submitted to targets */
 	struct bio flush_bio;
+
+	struct dm_stats stats;
 };
 
 /*
@@ -269,6 +272,7 @@ static int (*_inits[])(void) __initdata = {
 	dm_io_init,
 	dm_kcopyd_init,
 	dm_interface_init,
+	dm_statistics_init,
 };
 
 static void (*_exits[])(void) = {
@@ -279,6 +283,7 @@ static void (*_exits[])(void) = {
 	dm_io_exit,
 	dm_kcopyd_exit,
 	dm_interface_exit,
+	dm_statistics_exit,
 };
 
 static int __init dm_init(void)
@@ -384,6 +389,16 @@ int dm_lock_for_deletion(struct mapped_device *md)
 	return r;
 }
 
+sector_t dm_get_size(struct mapped_device *md)
+{
+	return get_capacity(md->disk);
+}
+
+struct dm_stats *dm_get_stats(struct mapped_device *md)
+{
+	return &md->stats;
+}
+
 static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 {
 	struct mapped_device *md = bdev->bd_disk->private_data;
@@ -466,8 +481,9 @@ static int md_in_flight(struct mapped_device *md)
 static void start_io_acct(struct dm_io *io)
 {
 	struct mapped_device *md = io->md;
+	struct bio *bio = io->bio;
 	int cpu;
-	int rw = bio_data_dir(io->bio);
+	int rw = bio_data_dir(bio);
 
 	io->start_time = jiffies;
 
@@ -476,6 +492,10 @@ static void start_io_acct(struct dm_io *io)
 	part_stat_unlock();
 	atomic_set(&dm_disk(md)->part0.in_flight[rw],
 		atomic_inc_return(&md->pending[rw]));
+
+	if (unlikely(dm_stats_used(&md->stats)))
+		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_sector,
+				    bio_sectors(bio), false, 0, &io->stats_aux);
 }
 
 static void end_io_acct(struct dm_io *io)
@@ -491,6 +511,10 @@ static void end_io_acct(struct dm_io *io)
 	part_stat_add(cpu, &dm_disk(md)->part0, ticks[rw], duration);
 	part_stat_unlock();
 
+	if (unlikely(dm_stats_used(&md->stats)))
+		dm_stats_account_io(&md->stats, bio->bi_rw, bio->bi_sector,
+				    bio_sectors(bio), true, duration, &io->stats_aux);
+
 	/*
 	 * After this is decremented the bio must not be touched if it is
 	 * a flush.
@@ -1519,7 +1543,7 @@ static void _dm_request(struct request_queue *q, struct bio *bio)
 	return;
 }
 
-static int dm_request_based(struct mapped_device *md)
+int dm_request_based(struct mapped_device *md)
 {
 	return blk_queue_stackable(md->queue);
 }
@@ -1958,6 +1982,8 @@ static struct mapped_device *alloc_dev(int minor)
 	md->flush_bio.bi_bdev = md->bdev;
 	md->flush_bio.bi_rw = WRITE_FLUSH;
 
+	dm_stats_init(&md->stats);
+
 	/* Populate the mapping, nobody knows we exist yet */
 	spin_lock(&_minor_lock);
 	old_md = idr_replace(&_minor_idr, md, minor);
@@ -2009,6 +2035,7 @@ static void free_dev(struct mapped_device *md)
 
 	put_disk(md->disk);
 	blk_cleanup_queue(md->queue);
+	dm_stats_cleanup(&md->stats);
 	module_put(THIS_MODULE);
 	kfree(md);
 }
@@ -2150,7 +2177,7 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	/*
 	 * Wipe any geometry if the size of the table changed.
 	 */
-	if (size != get_capacity(md->disk))
+	if (size != dm_get_size(md))
 		memset(&md->geometry, 0, sizeof(md->geometry));
 
 	__set_size(md, size);
@@ -2696,6 +2723,38 @@ out:
 	return r;
 }
 
+/*
+ * Internal suspend/resume works like userspace-driven suspend. It waits
+ * until all bios finish and prevents issuing new bios to the target drivers.
+ * It may be used only from the kernel.
+ *
+ * Internal suspend holds md->suspend_lock, which prevents interaction with
+ * userspace-driven suspend.
+ */
+
+void dm_internal_suspend(struct mapped_device *md)
+{
+	mutex_lock(&md->suspend_lock);
+	if (dm_suspended_md(md))
+		return;
+
+	set_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
+	synchronize_srcu(&md->io_barrier);
+	flush_workqueue(md->wq);
+	dm_wait_for_completion(md, TASK_UNINTERRUPTIBLE);
+}
+
+void dm_internal_resume(struct mapped_device *md)
+{
+	if (dm_suspended_md(md))
+		goto done;
+
+	dm_queue_flush(md);
+
+done:
+	mutex_unlock(&md->suspend_lock);
+}
+
 /*-----------------------------------------------------------------
  * Event notification.
  *---------------------------------------------------------------*/

drivers/md/dm.h

@@ -16,6 +16,8 @@
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
 
+#include "dm-stats.h"
+
 /*
  * Suspend feature flags
  */
@@ -157,10 +159,16 @@ void dm_destroy(struct mapped_device *md);
 void dm_destroy_immediate(struct mapped_device *md);
 int dm_open_count(struct mapped_device *md);
 int dm_lock_for_deletion(struct mapped_device *md);
+int dm_request_based(struct mapped_device *md);
+sector_t dm_get_size(struct mapped_device *md);
+struct dm_stats *dm_get_stats(struct mapped_device *md);
 
 int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
 		      unsigned cookie);
 
+void dm_internal_suspend(struct mapped_device *md);
+void dm_internal_resume(struct mapped_device *md);
+
 int dm_io_init(void);
 void dm_io_exit(void);
 
@@ -173,4 +181,12 @@ void dm_kcopyd_exit(void);
 struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, unsigned per_bio_data_size);
 void dm_free_md_mempools(struct dm_md_mempools *pools);
 
+/*
+ * Helpers that are used by DM core
+ */
+static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen)
+{
+	return !maxlen || strlen(result) + 1 >= maxlen;
+}
+
 #endif

include/linux/device-mapper.h

@@ -10,6 +10,7 @@
 
 #include <linux/bio.h>
 #include <linux/blkdev.h>
+#include <linux/math64.h>
 #include <linux/ratelimit.h>
 
 struct dm_dev;
@@ -550,6 +551,14 @@ extern struct ratelimit_state dm_ratelimit_state;
 #define DM_MAPIO_REMAPPED	1
 #define DM_MAPIO_REQUEUE	DM_ENDIO_REQUEUE
 
+#define dm_sector_div64(x, y)( \
+{ \
+	u64 _res; \
+	(x) = div64_u64_rem(x, y, &_res); \
+	_res; \
+} \
+)
+
 /*
  * Ceiling(n / sz)
  */

include/uapi/linux/dm-ioctl.h

@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	25
+#define DM_VERSION_MINOR	26
 #define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2013-06-26)"
+#define DM_VERSION_EXTRA	"-ioctl (2013-08-15)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */