zfs initialize performance enhancements

PROBLEM
========

When invoking "zpool initialize" on a pool the command will
create a thread to initialize each disk. Unfortunately, it does
this serially across many transaction groups which can result
in commands taking a long time to return to the user and may
appear hung. The same thing is true when trying to suspend/cancel
the operation.

SOLUTION
=========

This change refactors the way we invoke the initialize interface
to ensure we can start or stop the intialization in just a few
transaction groups.

When stopping or cancelling a vdev initialization perform it
in two phases.  First signal each vdev initialization thread
that it should exit, then after all threads have been signaled
wait for them to exit.

On a pool with 40 leaf vdevs this reduces the vdev initialize
stop/cancel time from ~10 minutes to under a second.  The reason
for this is spa_vdev_initialize() no longer needs to wait on
multiple full TXGs per leaf vdev being stopped.

This commit additionally adds some missing checks for the passed
"initialize_vdevs" input nvlist.  The contents of the user provided
input "initialize_vdevs" nvlist must be validated to ensure all
values are uint64s.  This is done in zfs_ioc_pool_initialize() in
order to keep all of these checks in a single location.

Updated the innvl and outnvl comments to match the formatting used
for all other new sytle ioctls.

Reviewed by: Matt Ahrens <[email protected]>
Reviewed-by: loli10K <[email protected]>
Reviewed-by: Tim Chase <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Signed-off-by: George Wilson <[email protected]>
Closes #8230

3 files changed, 7 insertions, 2 deletions

diff --git a/include/sys/spa.h b/include/sys/spa.h
index 4a66260ef..febf0e8f2 100644
--- a/include/sys/spa.h
+++ b/include/sys/spa.h
@@ -788,7 +788,8 @@ extern int spa_vdev_detach(spa_t *spa, uint64_t guid, uint64_t pguid,
     int replace_done);
 extern int spa_vdev_remove(spa_t *spa, uint64_t guid, boolean_t unspare);
 extern boolean_t spa_vdev_remove_active(spa_t *spa);
-extern int spa_vdev_initialize(spa_t *spa, uint64_t guid, uint64_t cmd_type);
+extern int spa_vdev_initialize(spa_t *spa, nvlist_t *nv, uint64_t cmd_type,
+    nvlist_t *vdev_errlist);
 extern int spa_vdev_setpath(spa_t *spa, uint64_t guid, const char *newpath);
 extern int spa_vdev_setfru(spa_t *spa, uint64_t guid, const char *newfru);
 extern int spa_vdev_split_mirror(spa_t *spa, char *newname, nvlist_t *config,
diff --git a/include/sys/vdev_impl.h b/include/sys/vdev_impl.h
index ae21e037e..5fe05c54b 100644
--- a/include/sys/vdev_impl.h
+++ b/include/sys/vdev_impl.h
@@ -263,6 +263,7 @@ struct vdev {
 
 	boolean_t	vdev_initialize_exit_wanted;
 	vdev_initializing_state_t	vdev_initialize_state;
+	list_node_t	vdev_initialize_node;
 	kthread_t	*vdev_initialize_thread;
 	/* Protects vdev_initialize_thread and vdev_initialize_state. */
 	kmutex_t	vdev_initialize_lock;
diff --git a/include/sys/vdev_initialize.h b/include/sys/vdev_initialize.h
index db4b0572c..319fb9bc0 100644
--- a/include/sys/vdev_initialize.h
+++ b/include/sys/vdev_initialize.h
@@ -26,15 +26,18 @@
 #ifndef _SYS_VDEV_INITIALIZE_H
 #define	_SYS_VDEV_INITIALIZE_H
 
+#include <sys/spa.h>
+
 #ifdef	__cplusplus
 extern "C" {
 #endif
 
 extern void vdev_initialize(vdev_t *vd);
 extern void vdev_initialize_stop(vdev_t *vd,
-    vdev_initializing_state_t tgt_state);
+    vdev_initializing_state_t tgt_state, list_t *vd_list);
 extern void vdev_initialize_stop_all(vdev_t *vd,
     vdev_initializing_state_t tgt_state);
+extern void vdev_initialize_stop_wait(spa_t *spa, list_t *vd_list);
 extern void vdev_initialize_restart(vdev_t *vd);
 extern void vdev_xlate(vdev_t *vd, const range_seg_t *logical_rs,
     range_seg_t *physical_rs);