MFC r266771: MFV r266766:

Add a new zfs property, "redundant_metadata" which can have values "all" or
"most".  The default will be "all", which is the current behavior.  When set
to all, ZFS stores an extra copy of all metadata.  If a single on-disk block
is corrupt, at worst a single block of user data (which is recordsize bytes
long) can be lost.

Setting to "most" will cause us to only store 1 copy of level-1 indirect
blocks of user data files.  This can improve performance of random writes,
because less metadata has to be written.  In practice,  at worst about
100 blocks (of recordsize bytes each) of user data can be lost if a single
on-disk block is corrupt.

The exact behavior of which metadata blocks are stored redundantly may change
in future releases.

Illumos issue: 3835 zfs need not store 2 copies of all metadata

1 files changed, 29 insertions, 6 deletions

diff --git a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_objset.c b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_objset.c
index 0c4fe26..ef82f17 100644
--- a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_objset.c
+++ b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/dmu_objset.c
@@ -20,7 +20,7 @@
  */
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2013 by Delphix. All rights reserved.
+ * Copyright (c) 2012, 2014 by Delphix. All rights reserved.
  * Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
  * Copyright (c) 2013, Joyent, Inc. All rights reserved.
  */
@@ -115,13 +115,13 @@ dmu_objset_id(objset_t *os)
 	return (ds ? ds->ds_object : 0);
 }
 
-uint64_t
+zfs_sync_type_t
 dmu_objset_syncprop(objset_t *os)
 {
 	return (os->os_sync);
 }
 
-uint64_t
+zfs_logbias_op_t
 dmu_objset_logbias(objset_t *os)
 {
 	return (os->os_logbias);
@@ -230,6 +230,20 @@ sync_changed_cb(void *arg, uint64_t newval)
 }
 
 static void
+redundant_metadata_changed_cb(void *arg, uint64_t newval)
+{
+	objset_t *os = arg;
+
+	/*
+	 * Inheritance and range checking should have been done by now.
+	 */
+	ASSERT(newval == ZFS_REDUNDANT_METADATA_ALL ||
+	    newval == ZFS_REDUNDANT_METADATA_MOST);
+
+	os->os_redundant_metadata = newval;
+}
+
+static void
 logbias_changed_cb(void *arg, uint64_t newval)
 {
 	objset_t *os = arg;
@@ -364,6 +378,12 @@ dmu_objset_open_impl(spa_t *spa, dsl_dataset_t *ds, blkptr_t *bp,
 				    zfs_prop_to_name(ZFS_PROP_SYNC),
 				    sync_changed_cb, os);
 			}
+			if (err == 0) {
+				err = dsl_prop_register(ds,
+				    zfs_prop_to_name(
+				    ZFS_PROP_REDUNDANT_METADATA),
+				    redundant_metadata_changed_cb, os);
+			}
 		}
 		if (err != 0) {
 			VERIFY(arc_buf_remove_ref(os->os_phys_buf,
@@ -377,9 +397,9 @@ dmu_objset_open_impl(spa_t *spa, dsl_dataset_t *ds, blkptr_t *bp,
 		os->os_compress = ZIO_COMPRESS_LZJB;
 		os->os_copies = spa_max_replication(spa);
 		os->os_dedup_checksum = ZIO_CHECKSUM_OFF;
-		os->os_dedup_verify = 0;
-		os->os_logbias = 0;
-		os->os_sync = 0;
+		os->os_dedup_verify = B_FALSE;
+		os->os_logbias = ZFS_LOGBIAS_LATENCY;
+		os->os_sync = ZFS_SYNC_STANDARD;
 		os->os_primary_cache = ZFS_CACHE_ALL;
 		os->os_secondary_cache = ZFS_CACHE_ALL;
 	}
@@ -622,6 +642,9 @@ dmu_objset_evict(objset_t *os)
 			VERIFY0(dsl_prop_unregister(ds,
 			    zfs_prop_to_name(ZFS_PROP_SYNC),
 			    sync_changed_cb, os));
+			VERIFY0(dsl_prop_unregister(ds,
+			    zfs_prop_to_name(ZFS_PROP_REDUNDANT_METADATA),
+			    redundant_metadata_changed_cb, os));
 		}
 		VERIFY0(dsl_prop_unregister(ds,
 		    zfs_prop_to_name(ZFS_PROP_PRIMARYCACHE),