4045 zfs write throttle & i/o scheduler performance work
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Christopher Siden <christopher.siden@delphix.com>

*** 582,592 ****
          return (myspace);
  }
  
  struct tempreserve {
          list_node_t tr_node;
-         dsl_pool_t *tr_dp;
          dsl_dir_t *tr_ds;
          uint64_t tr_size;
  };
  
  static int
--- 582,591 ----
*** 733,761 ****
                  struct tempreserve *tr;
  
                  tr = kmem_zalloc(sizeof (struct tempreserve), KM_SLEEP);
                  tr->tr_size = lsize;
                  list_insert_tail(tr_list, tr);
- 
-                 err = dsl_pool_tempreserve_space(dd->dd_pool, asize, tx);
          } else {
                  if (err == EAGAIN) {
                          txg_delay(dd->dd_pool, tx->tx_txg,
                              MSEC2NSEC(10), MSEC2NSEC(10));
                          err = SET_ERROR(ERESTART);
                  }
-                 dsl_pool_memory_pressure(dd->dd_pool);
          }
  
          if (err == 0) {
-                 struct tempreserve *tr;
- 
-                 tr = kmem_zalloc(sizeof (struct tempreserve), KM_SLEEP);
-                 tr->tr_dp = dd->dd_pool;
-                 tr->tr_size = asize;
-                 list_insert_tail(tr_list, tr);
- 
                  err = dsl_dir_tempreserve_impl(dd, asize, fsize >= asize,
                      FALSE, asize > usize, tr_list, tx, TRUE);
          }
  
          if (err != 0)
--- 732,759 ----
                  struct tempreserve *tr;
  
                  tr = kmem_zalloc(sizeof (struct tempreserve), KM_SLEEP);
                  tr->tr_size = lsize;
                  list_insert_tail(tr_list, tr);
          } else {
                  if (err == EAGAIN) {
+                         /*
+                          * If arc_memory_throttle() detected that pageout
+                          * is running and we are low on memory, we delay new
+                          * non-pageout transactions to give pageout an
+                          * advantage.
+                          *
+                          * It is unfortunate to be delaying while the caller's
+                          * locks are held.
+                          */
                          txg_delay(dd->dd_pool, tx->tx_txg,
                              MSEC2NSEC(10), MSEC2NSEC(10));
                          err = SET_ERROR(ERESTART);
                  }
          }
  
          if (err == 0) {
                  err = dsl_dir_tempreserve_impl(dd, asize, fsize >= asize,
                      FALSE, asize > usize, tr_list, tx, TRUE);
          }
  
          if (err != 0)
*** 780,793 ****
          ASSERT3U(tx->tx_txg, !=, 0);
  
          if (tr_cookie == NULL)
                  return;
  
!         while (tr = list_head(tr_list)) {
!                 if (tr->tr_dp) {
!                         dsl_pool_tempreserve_clear(tr->tr_dp, tr->tr_size, tx);
!                 } else if (tr->tr_ds) {
                          mutex_enter(&tr->tr_ds->dd_lock);
                          ASSERT3U(tr->tr_ds->dd_tempreserved[txgidx], >=,
                              tr->tr_size);
                          tr->tr_ds->dd_tempreserved[txgidx] -= tr->tr_size;
                          mutex_exit(&tr->tr_ds->dd_lock);
--- 778,789 ----
          ASSERT3U(tx->tx_txg, !=, 0);
  
          if (tr_cookie == NULL)
                  return;
  
!         while ((tr = list_head(tr_list)) != NULL) {
!                 if (tr->tr_ds) {
                          mutex_enter(&tr->tr_ds->dd_lock);
                          ASSERT3U(tr->tr_ds->dd_tempreserved[txgidx], >=,
                              tr->tr_size);
                          tr->tr_ds->dd_tempreserved[txgidx] -= tr->tr_size;
                          mutex_exit(&tr->tr_ds->dd_lock);
*** 799,810 ****
          }
  
          kmem_free(tr_list, sizeof (list_t));
  }
  
! static void
! dsl_dir_willuse_space_impl(dsl_dir_t *dd, int64_t space, dmu_tx_t *tx)
  {
          int64_t parent_space;
          uint64_t est_used;
  
          mutex_enter(&dd->dd_lock);
--- 795,812 ----
          }
  
          kmem_free(tr_list, sizeof (list_t));
  }
  
! /*
!  * This should be called from open context when we think we're going to write
!  * or free space, for example when dirtying data. Be conservative; it's okay
!  * to write less space or free more, but we don't want to write more or free
!  * less than the amount specified.
!  */
! void
! dsl_dir_willuse_space(dsl_dir_t *dd, int64_t space, dmu_tx_t *tx)
  {
          int64_t parent_space;
          uint64_t est_used;
  
          mutex_enter(&dd->dd_lock);
*** 818,842 ****
          /* Make sure that we clean up dd_space_to* */
          dsl_dir_dirty(dd, tx);
  
          /* XXX this is potentially expensive and unnecessary... */
          if (parent_space && dd->dd_parent)
!                 dsl_dir_willuse_space_impl(dd->dd_parent, parent_space, tx);
  }
  
- /*
-  * Call in open context when we think we're going to write/free space,
-  * eg. when dirtying data.  Be conservative (ie. OK to write less than
-  * this or free more than this, but don't write more or free less).
-  */
- void
- dsl_dir_willuse_space(dsl_dir_t *dd, int64_t space, dmu_tx_t *tx)
- {
-         dsl_pool_willuse_space(dd->dd_pool, space, tx);
-         dsl_dir_willuse_space_impl(dd, space, tx);
- }
- 
  /* call from syncing context when we actually write/free space for this dd */
  void
  dsl_dir_diduse_space(dsl_dir_t *dd, dd_used_t type,
      int64_t used, int64_t compressed, int64_t uncompressed, dmu_tx_t *tx)
  {
--- 820,832 ----
          /* Make sure that we clean up dd_space_to* */
          dsl_dir_dirty(dd, tx);
  
          /* XXX this is potentially expensive and unnecessary... */
          if (parent_space && dd->dd_parent)
!                 dsl_dir_willuse_space(dd->dd_parent, parent_space, tx);
  }
  
  /* call from syncing context when we actually write/free space for this dd */
  void
  dsl_dir_diduse_space(dsl_dir_t *dd, dd_used_t type,
      int64_t used, int64_t compressed, int64_t uncompressed, dmu_tx_t *tx)
  {