Add TRIM support

UNMAP/TRIM support is a frequently-requested feature to help
prevent performance from degrading on SSDs and on various other
SAN-like storage back-ends.  By issuing UNMAP/TRIM commands for
sectors which are no longer allocated the underlying device can
often more efficiently manage itself.

This TRIM implementation is modeled on the `zpool initialize`
feature which writes a pattern to all unallocated space in the
pool.  The new `zpool trim` command uses the same vdev_xlate()
code to calculate what sectors are unallocated, the same per-
vdev TRIM thread model and locking, and the same basic CLI for
a consistent user experience.  The core difference is that
instead of writing a pattern it will issue UNMAP/TRIM commands
for those extents.

The zio pipeline was updated to accommodate this by adding a new
ZIO_TYPE_TRIM type and associated spa taskq.  This new type makes
is straight forward to add the platform specific TRIM/UNMAP calls
to vdev_disk.c and vdev_file.c.  These new ZIO_TYPE_TRIM zios are
handled largely the same way as ZIO_TYPE_READs or ZIO_TYPE_WRITEs.
This makes it possible to largely avoid changing the pipieline,
one exception is that TRIM zio's may exceed the 16M block size
limit since they contain no data.

In addition to the manual `zpool trim` command, a background
automatic TRIM was added and is controlled by the 'autotrim'
property.  It relies on the exact same infrastructure as the
manual TRIM.  However, instead of relying on the extents in a
metaslab's ms_allocatable range tree, a ms_trim tree is kept
per metaslab.  When 'autotrim=on', ranges added back to the
ms_allocatable tree are also added to the ms_free tree.  The
ms_free tree is then periodically consumed by an autotrim
thread which systematically walks a top level vdev's metaslabs.

Since the automatic TRIM will skip ranges it considers too small
there is value in occasionally running a full `zpool trim`.  This
may occur when the freed blocks are small and not enough time
was allowed to aggregate them.  An automatic TRIM and a manual
`zpool trim` may be run concurrently, in which case the automatic
TRIM will yield to the manual TRIM.

Reviewed-by: Jorgen Lundman <[email protected]>
Reviewed-by: Tim Chase <[email protected]>
Reviewed-by: Matt Ahrens <[email protected]>
Reviewed-by: George Wilson <[email protected]>
Reviewed-by: Serapheim Dimitropoulos <[email protected]>
Contributions-by: Saso Kiselkov <[email protected]>
Contributions-by: Tim Chase <[email protected]>
Contributions-by: Chunwei Chen <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Closes #8419 
Closes #598 

1 files changed, 98 insertions, 8 deletions

diff --git a/module/zfs/vdev.c b/module/zfs/vdev.c
index ae1c2bcec..085ae6873 100644
--- a/module/zfs/vdev.c
+++ b/module/zfs/vdev.c
@@ -51,6 +51,7 @@
 #include <sys/dsl_scan.h>
 #include <sys/abd.h>
 #include <sys/vdev_initialize.h>
+#include <sys/vdev_trim.h>
 #include <sys/zvol.h>
 #include <sys/zfs_ratelimit.h>
 
@@ -543,6 +544,7 @@ vdev_alloc_common(spa_t *spa, uint_t id, uint64_t guid, vdev_ops_t *ops)
 	list_link_init(&vd->vdev_state_dirty_node);
 	list_link_init(&vd->vdev_initialize_node);
 	list_link_init(&vd->vdev_leaf_node);
+	list_link_init(&vd->vdev_trim_node);
 	mutex_init(&vd->vdev_dtl_lock, NULL, MUTEX_NOLOCKDEP, NULL);
 	mutex_init(&vd->vdev_stat_lock, NULL, MUTEX_DEFAULT, NULL);
 	mutex_init(&vd->vdev_probe_lock, NULL, MUTEX_DEFAULT, NULL);
@@ -551,6 +553,12 @@ vdev_alloc_common(spa_t *spa, uint_t id, uint64_t guid, vdev_ops_t *ops)
 	mutex_init(&vd->vdev_initialize_io_lock, NULL, MUTEX_DEFAULT, NULL);
 	cv_init(&vd->vdev_initialize_cv, NULL, CV_DEFAULT, NULL);
 	cv_init(&vd->vdev_initialize_io_cv, NULL, CV_DEFAULT, NULL);
+	mutex_init(&vd->vdev_trim_lock, NULL, MUTEX_DEFAULT, NULL);
+	mutex_init(&vd->vdev_autotrim_lock, NULL, MUTEX_DEFAULT, NULL);
+	mutex_init(&vd->vdev_trim_io_lock, NULL, MUTEX_DEFAULT, NULL);
+	cv_init(&vd->vdev_trim_cv, NULL, CV_DEFAULT, NULL);
+	cv_init(&vd->vdev_autotrim_cv, NULL, CV_DEFAULT, NULL);
+	cv_init(&vd->vdev_trim_io_cv, NULL, CV_DEFAULT, NULL);
 
 	for (int t = 0; t < DTL_TYPES; t++) {
 		vd->vdev_dtl[t] = range_tree_create(NULL, NULL);
@@ -875,7 +883,10 @@ void
 vdev_free(vdev_t *vd)
 {
 	spa_t *spa = vd->vdev_spa;
+
 	ASSERT3P(vd->vdev_initialize_thread, ==, NULL);
+	ASSERT3P(vd->vdev_trim_thread, ==, NULL);
+	ASSERT3P(vd->vdev_autotrim_thread, ==, NULL);
 
 	/*
 	 * Scan queues are normally destroyed at the end of a scan. If the
@@ -906,7 +917,6 @@ vdev_free(vdev_t *vd)
 
 	ASSERT(vd->vdev_child == NULL);
 	ASSERT(vd->vdev_guid_sum == vd->vdev_guid);
-	ASSERT(vd->vdev_initialize_thread == NULL);
 
 	/*
 	 * Discard allocation state.
@@ -988,6 +998,12 @@ vdev_free(vdev_t *vd)
 	mutex_destroy(&vd->vdev_initialize_io_lock);
 	cv_destroy(&vd->vdev_initialize_io_cv);
 	cv_destroy(&vd->vdev_initialize_cv);
+	mutex_destroy(&vd->vdev_trim_lock);
+	mutex_destroy(&vd->vdev_autotrim_lock);
+	mutex_destroy(&vd->vdev_trim_io_lock);
+	cv_destroy(&vd->vdev_trim_cv);
+	cv_destroy(&vd->vdev_autotrim_cv);
+	cv_destroy(&vd->vdev_trim_io_cv);
 
 	zfs_ratelimit_fini(&vd->vdev_delay_rl);
 	zfs_ratelimit_fini(&vd->vdev_checksum_rl);
@@ -3475,6 +3491,16 @@ vdev_online(spa_t *spa, uint64_t guid, uint64_t flags, vdev_state_t *newstate)
 	}
 	mutex_exit(&vd->vdev_initialize_lock);
 
+	/* Restart trimming if necessary */
+	mutex_enter(&vd->vdev_trim_lock);
+	if (vdev_writeable(vd) &&
+	    vd->vdev_trim_thread == NULL &&
+	    vd->vdev_trim_state == VDEV_TRIM_ACTIVE) {
+		(void) vdev_trim(vd, vd->vdev_trim_rate, vd->vdev_trim_partial,
+		    vd->vdev_trim_secure);
+	}
+	mutex_exit(&vd->vdev_trim_lock);
+
 	if (wasoffline ||
 	    (oldstate < VDEV_STATE_DEGRADED &&
 	    vd->vdev_state >= VDEV_STATE_DEGRADED))
@@ -3745,8 +3771,7 @@ vdev_accessible(vdev_t *vd, zio_t *zio)
 static void
 vdev_get_child_stat(vdev_t *cvd, vdev_stat_t *vs, vdev_stat_t *cvs)
 {
-	int t;
-	for (t = 0; t < ZIO_TYPES; t++) {
+	for (int t = 0; t < VS_ZIO_TYPES; t++) {
 		vs->vs_ops[t] += cvs->vs_ops[t];
 		vs->vs_bytes[t] += cvs->vs_bytes[t];
 	}
@@ -3873,7 +3898,7 @@ vdev_get_stats_ex(vdev_t *vd, vdev_stat_t *vs, vdev_stat_ex_t *vsx)
 			vs->vs_rsize += VDEV_LABEL_START_SIZE +
 			    VDEV_LABEL_END_SIZE;
 			/*
-			 * Report intializing progress. Since we don't
+			 * Report initializing progress. Since we don't
 			 * have the initializing locks held, this is only
 			 * an estimate (although a fairly accurate one).
 			 */
@@ -3884,9 +3909,20 @@ vdev_get_stats_ex(vdev_t *vd, vdev_stat_t *vs, vdev_stat_ex_t *vsx)
 			vs->vs_initialize_state = vd->vdev_initialize_state;
 			vs->vs_initialize_action_time =
 			    vd->vdev_initialize_action_time;
+
+			/*
+			 * Report manual TRIM progress. Since we don't have
+			 * the manual TRIM locks held, this is only an
+			 * estimate (although fairly accurate one).
+			 */
+			vs->vs_trim_notsup = !vd->vdev_has_trim;
+			vs->vs_trim_bytes_done = vd->vdev_trim_bytes_done;
+			vs->vs_trim_bytes_est = vd->vdev_trim_bytes_est;
+			vs->vs_trim_state = vd->vdev_trim_state;
+			vs->vs_trim_action_time = vd->vdev_trim_action_time;
 		}
 		/*
-		 * Report expandable space on top-level, non-auxillary devices
+		 * Report expandable space on top-level, non-auxiliary devices
 		 * only. The expandable space is reported in terms of metaslab
 		 * sized units since that determines how much space the pool
 		 * can expand.
@@ -4004,9 +4040,18 @@ vdev_stat_update(zio_t *zio, uint64_t psize)
 		 */
 		if (vd->vdev_ops->vdev_op_leaf &&
 		    (zio->io_priority < ZIO_PRIORITY_NUM_QUEUEABLE)) {
+			zio_type_t vs_type = type;
+
+			/*
+			 * TRIM ops and bytes are reported to user space as
+			 * ZIO_TYPE_IOCTL.  This is done to preserve the
+			 * vdev_stat_t structure layout for user space.
+			 */
+			if (type == ZIO_TYPE_TRIM)
+				vs_type = ZIO_TYPE_IOCTL;
 
-			vs->vs_ops[type]++;
-			vs->vs_bytes[type] += psize;
+			vs->vs_ops[vs_type]++;
+			vs->vs_bytes[vs_type] += psize;
 
 			if (flags & ZIO_FLAG_DELEGATED) {
 				vsx->vsx_agg_histo[zio->io_priority]
@@ -4104,7 +4149,8 @@ vdev_deflated_space(vdev_t *vd, int64_t space)
 }
 
 /*
- * Update the in-core space usage stats for this vdev and the root vdev.
+ * Update the in-core space usage stats for this vdev, its metaslab class,
+ * and the root vdev.
  */
 void
 vdev_space_update(vdev_t *vd, int64_t alloc_delta, int64_t defer_delta,
@@ -4650,12 +4696,56 @@ vdev_set_deferred_resilver(spa_t *spa, vdev_t *vd)
 	spa->spa_resilver_deferred = B_TRUE;
 }
 
+/*
+ * Translate a logical range to the physical range for the specified vdev_t.
+ * This function is initially called with a leaf vdev and will walk each
+ * parent vdev until it reaches a top-level vdev. Once the top-level is
+ * reached the physical range is initialized and the recursive function
+ * begins to unwind. As it unwinds it calls the parent's vdev specific
+ * translation function to do the real conversion.
+ */
+void
+vdev_xlate(vdev_t *vd, const range_seg_t *logical_rs, range_seg_t *physical_rs)
+{
+	/*
+	 * Walk up the vdev tree
+	 */
+	if (vd != vd->vdev_top) {
+		vdev_xlate(vd->vdev_parent, logical_rs, physical_rs);
+	} else {
+		/*
+		 * We've reached the top-level vdev, initialize the
+		 * physical range to the logical range and start to
+		 * unwind.
+		 */
+		physical_rs->rs_start = logical_rs->rs_start;
+		physical_rs->rs_end = logical_rs->rs_end;
+		return;
+	}
+
+	vdev_t *pvd = vd->vdev_parent;
+	ASSERT3P(pvd, !=, NULL);
+	ASSERT3P(pvd->vdev_ops->vdev_op_xlate, !=, NULL);
+
+	/*
+	 * As this recursive function unwinds, translate the logical
+	 * range into its physical components by calling the
+	 * vdev specific translate function.
+	 */
+	range_seg_t intermediate = { { { 0, 0 } } };
+	pvd->vdev_ops->vdev_op_xlate(vd, physical_rs, &intermediate);
+
+	physical_rs->rs_start = intermediate.rs_start;
+	physical_rs->rs_end = intermediate.rs_end;
+}
+
 #if defined(_KERNEL)
 EXPORT_SYMBOL(vdev_fault);
 EXPORT_SYMBOL(vdev_degrade);
 EXPORT_SYMBOL(vdev_online);
 EXPORT_SYMBOL(vdev_offline);
 EXPORT_SYMBOL(vdev_clear);
+
 /* BEGIN CSTYLED */
 module_param(zfs_vdev_default_ms_count, int, 0644);
 MODULE_PARM_DESC(zfs_vdev_default_ms_count,