ZIL: Reduce scope of zl_issuer_lock.

Before this change ZIL copied all log data while holding the lock.
It caused huge lock contention on workloads with many big parallel
writes. This change splits zil_lwb_write_issue() in two parts: first
zil_lwb_write_close() does all necessary log space estimations and
block allocations while holding the lock, then zil_lwb_write_issue()
does all heavy lifting (memory copying, zio issuing, etc) later and
out of the lock.

Signed-off-by:  Alexander Motin <mav@FreeBSD.org>
Sponsored by:   iXsystems, Inc.

include/sys/zil_impl.h

@@ -44,7 +44,7 @@ extern "C" {
  * must be held.
  *
  * After the lwb is "opened", it can transition into the "issued" state
- * via zil_lwb_write_issue(). Again, the zilog's "zl_issuer_lock" must
+ * via zil_lwb_write_close(). Again, the zilog's "zl_issuer_lock" must
  * be held when making this transition.
  *
  * After the lwb's write zio completes, it transitions into the "write
@@ -94,6 +94,7 @@ typedef struct lwb {
 	boolean_t	lwb_fastwrite;	/* is blk marked for fastwrite? */
 	boolean_t	lwb_slog;	/* lwb_blk is on SLOG device */
 	int		lwb_nused;	/* # used bytes in buffer */
+	int		lwb_nfilled;	/* # filled bytes in buffer */
 	int		lwb_sz;		/* size of block and buffer */
 	lwb_state_t	lwb_state;	/* the state of this lwb */
 	char		*lwb_buf;	/* log write buffer */
@@ -107,6 +108,7 @@ typedef struct lwb {
 	avl_tree_t	lwb_vdev_tree;	/* vdevs to flush after lwb write */
 	kmutex_t	lwb_vdev_lock;	/* protects lwb_vdev_tree */
 	hrtime_t	lwb_issued_timestamp; /* when was the lwb issued? */
+	list_node_t	lwb_issue_node;	/* linkage of lwbs ready for issue */
 } lwb_t;
 
 /*