[illumos-gate merge]

commit 69962b5647e4a8b9b14998733b765925381b727e
    4045 zfs write throttle & i/o scheduler performance work
commit 7e0e2549bfaa531aff576083ab0c07f84fa8fb27
    3845 beadm doesn't work in non-global zones
commit dc986d9f4cb40f3ff88fe0d9c9fb3a51ad50f0d9
    4054 dis sometimes decides random symbols are functions
commit edd4ab01432cfb07428329ad6e8071e8923d0b20
    3194 dis crashes disassembling aes

    Conflicts:
	usr/src/uts/common/fs/zfs/vdev_queue.c
	usr/src/uts/common/fs/zfs/sys/zio.h
	usr/src/uts/common/fs/zfs/sys/vdev_impl.h
	usr/src/uts/common/fs/zfs/sys/dsl_dir.h
	usr/src/uts/common/fs/zfs/dsl_pool.c
	usr/src/uts/common/fs/zfs/arc.c
	usr/src/lib/libbe/common/be_list.c

1 files changed, 58 insertions, 36 deletions

diff --git a/usr/src/uts/common/fs/zfs/spa.c b/usr/src/uts/common/fs/zfs/spa.c
index 13eaaecbf7..6099899e78 100644
--- a/usr/src/uts/common/fs/zfs/spa.c
+++ b/usr/src/uts/common/fs/zfs/spa.c
@@ -87,14 +87,12 @@ static int zfs_ccw_retry_interval = 300;
 
 typedef enum zti_modes {
 	ZTI_MODE_FIXED,			/* value is # of threads (min 1) */
-	ZTI_MODE_ONLINE_PERCENT,	/* value is % of online CPUs */
 	ZTI_MODE_BATCH,			/* cpu-intensive; value is ignored */
 	ZTI_MODE_NULL,			/* don't create a taskq */
 	ZTI_NMODES
 } zti_modes_t;
 
 #define	ZTI_P(n, q)	{ ZTI_MODE_FIXED, (n), (q) }
-#define	ZTI_PCT(n)	{ ZTI_MODE_ONLINE_PERCENT, (n), 1 }
 #define	ZTI_BATCH	{ ZTI_MODE_BATCH, 0, 1 }
 #define	ZTI_NULL	{ ZTI_MODE_NULL, 0, 0 }
 
@@ -146,7 +144,7 @@ static int spa_load_impl(spa_t *spa, uint64_t, nvlist_t *config,
     char **ereport);
 static void spa_vdev_resilver_done(spa_t *spa);
 
-uint_t		zio_taskq_batch_pct = 100;	/* 1 thread per cpu in pset */
+uint_t		zio_taskq_batch_pct = 75;	/* 1 thread per cpu in pset */
 id_t		zio_taskq_psrset_bind = PS_NONE;
 boolean_t	zio_taskq_sysdc = B_TRUE;	/* use SDC scheduling class */
 uint_t		zio_taskq_basedc = 80;		/* base duty cycle */
@@ -842,31 +840,27 @@ spa_taskqs_init(spa_t *spa, zio_type_t t, zio_taskq_type_t q)
 	tqs->stqs_count = count;
 	tqs->stqs_taskq = kmem_alloc(count * sizeof (taskq_t *), KM_SLEEP);
 
-	for (uint_t i = 0; i < count; i++) {
-		taskq_t *tq;
-
-		switch (mode) {
-		case ZTI_MODE_FIXED:
-			ASSERT3U(value, >=, 1);
-			value = MAX(value, 1);
-			break;
+	switch (mode) {
+	case ZTI_MODE_FIXED:
+		ASSERT3U(value, >=, 1);
+		value = MAX(value, 1);
+		break;
 
-		case ZTI_MODE_BATCH:
-			batch = B_TRUE;
-			flags |= TASKQ_THREADS_CPU_PCT;
-			value = zio_taskq_batch_pct;
-			break;
+	case ZTI_MODE_BATCH:
+		batch = B_TRUE;
+		flags |= TASKQ_THREADS_CPU_PCT;
+		value = zio_taskq_batch_pct;
+		break;
 
-		case ZTI_MODE_ONLINE_PERCENT:
-			flags |= TASKQ_THREADS_CPU_PCT;
-			break;
+	default:
+		panic("unrecognized mode for %s_%s taskq (%u:%u) in "
+		    "spa_activate()",
+		    zio_type_name[t], zio_taskq_types[q], mode, value);
+		break;
+	}
 
-		default:
-			panic("unrecognized mode for %s_%s taskq (%u:%u) in "
-			    "spa_activate()",
-			    zio_type_name[t], zio_taskq_types[q], mode, value);
-			break;
-		}
+	for (uint_t i = 0; i < count; i++) {
+		taskq_t *tq;
 
 		if (count > 1) {
 			(void) snprintf(name, sizeof (name), "%s_%s_%u",
@@ -883,7 +877,16 @@ spa_taskqs_init(spa_t *spa, zio_type_t t, zio_taskq_type_t q)
 			tq = taskq_create_sysdc(name, value, 50, INT_MAX,
 			    spa->spa_proc, zio_taskq_basedc, flags);
 		} else {
-			tq = taskq_create_proc(name, value, maxclsyspri, 50,
+			pri_t pri = maxclsyspri;
+			/*
+			 * The write issue taskq can be extremely CPU
+			 * intensive.  Run it at slightly lower priority
+			 * than the other taskqs.
+			 */
+			if (t == ZIO_TYPE_WRITE && q == ZIO_TASKQ_ISSUE)
+				pri--;
+
+			tq = taskq_create_proc(name, value, pri, 50,
 			    INT_MAX, spa->spa_proc, flags);
 		}
 
@@ -5737,6 +5740,32 @@ spa_free_sync_cb(void *arg, const blkptr_t *bp, dmu_tx_t *tx)
 	return (0);
 }
 
+/*
+ * Note: this simple function is not inlined to make it easier to dtrace the
+ * amount of time spent syncing frees.
+ */
+static void
+spa_sync_frees(spa_t *spa, bplist_t *bpl, dmu_tx_t *tx)
+{
+	zio_t *zio = zio_root(spa, NULL, NULL, 0);
+	bplist_iterate(bpl, spa_free_sync_cb, zio, tx);
+	VERIFY(zio_wait(zio) == 0);
+}
+
+/*
+ * Note: this simple function is not inlined to make it easier to dtrace the
+ * amount of time spent syncing deferred frees.
+ */
+static void
+spa_sync_deferred_frees(spa_t *spa, dmu_tx_t *tx)
+{
+	zio_t *zio = zio_root(spa, NULL, NULL, 0);
+	VERIFY3U(bpobj_iterate(&spa->spa_deferred_bpobj,
+	    spa_free_sync_cb, zio, tx), ==, 0);
+	VERIFY0(zio_wait(zio));
+}
+
+
 static void
 spa_sync_nvlist(spa_t *spa, uint64_t obj, nvlist_t *nv, dmu_tx_t *tx)
 {
@@ -6063,7 +6092,6 @@ spa_sync(spa_t *spa, uint64_t txg)
 {
 	dsl_pool_t *dp = spa->spa_dsl_pool;
 	objset_t *mos = spa->spa_meta_objset;
-	bpobj_t *defer_bpo = &spa->spa_deferred_bpobj;
 	bplist_t *free_bpl = &spa->spa_free_bplist[txg & TXG_MASK];
 	vdev_t *rvd = spa->spa_root_vdev;
 	vdev_t *vd;
@@ -6143,10 +6171,7 @@ spa_sync(spa_t *spa, uint64_t txg)
 	    !txg_list_empty(&dp->dp_sync_tasks, txg) ||
 	    ((dsl_scan_active(dp->dp_scan) ||
 	    txg_sync_waiting(dp)) && !spa_shutting_down(spa))) {
-		zio_t *zio = zio_root(spa, NULL, NULL, 0);
-		VERIFY3U(bpobj_iterate(defer_bpo,
-		    spa_free_sync_cb, zio, tx), ==, 0);
-		VERIFY0(zio_wait(zio));
+		spa_sync_deferred_frees(spa, tx);
 	}
 
 	/*
@@ -6164,13 +6189,10 @@ spa_sync(spa_t *spa, uint64_t txg)
 		dsl_pool_sync(dp, txg);
 
 		if (pass < zfs_sync_pass_deferred_free) {
-			zio_t *zio = zio_root(spa, NULL, NULL, 0);
-			bplist_iterate(free_bpl, spa_free_sync_cb,
-			    zio, tx);
-			VERIFY(zio_wait(zio) == 0);
+			spa_sync_frees(spa, free_bpl, tx);
 		} else {
 			bplist_iterate(free_bpl, bpobj_enqueue_cb,
-			    defer_bpo, tx);
+			    &spa->spa_deferred_bpobj, tx);
 		}
 
 		ddt_sync(spa, txg);