OpenZFS 8155 - simplify dmu_write_policy handling of pre-compressed buffers

Authored by: Matthew Ahrens <[email protected]>
Reviewed by: Dan Kimmel <[email protected]>
Reviewed by: George Wilson <[email protected]>
Approved by: Robert Mustacchi <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Ported-by: Giuseppe Di Natale <[email protected]>

When writing pre-compressed buffers, arc_write() requires that
the compression algorithm used to compress the buffer matches
the compression algorithm requested by the zio_prop_t, which is
set by dmu_write_policy(). This makes dmu_write_policy() and its
callers a bit more complicated.

We simplify this by making arc_write() trust the caller to supply
the type of pre-compressed buffer that it wants to write,
and override the compression setting in the zio_prop_t.

OpenZFS-issue: https://www.illumos.org/issues/8155
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/b55ff58
Closes #6200

5 files changed, 18 insertions, 26 deletions

diff --git a/include/sys/dmu.h b/include/sys/dmu.h
index 6459047e8..ea1b116be 100644
--- a/include/sys/dmu.h
+++ b/include/sys/dmu.h
@@ -20,7 +20,7 @@
  */
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2016 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2017 by Delphix. All rights reserved.
  * Copyright 2011 Nexenta Systems, Inc. All rights reserved.
  * Copyright (c) 2012, Joyent, Inc. All rights reserved.
  * Copyright 2014 HybridCluster. All rights reserved.
@@ -430,8 +430,8 @@ dmu_write_embedded(objset_t *os, uint64_t object, uint64_t offset,
 #define	WP_DMU_SYNC	0x2
 #define	WP_SPILL	0x4
 
-void dmu_write_policy(objset_t *os, struct dnode *dn, int level, int wp,
-    enum zio_compress compress_override, struct zio_prop *zp);
+void dmu_write_policy(objset_t *os, dnode_t *dn, int level, int wp,
+    struct zio_prop *zp);
 /*
  * The bonus data is accessed more or less like a regular buffer.
  * You must dmu_bonus_hold() to get the buffer, which will give you a
diff --git a/module/zfs/arc.c b/module/zfs/arc.c
index 492a33a60..8680e9ac0 100644
--- a/module/zfs/arc.c
+++ b/module/zfs/arc.c
@@ -5977,6 +5977,7 @@ arc_write(zio_t *pio, spa_t *spa, uint64_t txg,
 	arc_buf_hdr_t *hdr = buf->b_hdr;
 	arc_write_callback_t *callback;
 	zio_t *zio;
+	zio_prop_t localprop = *zp;
 
 	ASSERT3P(ready, !=, NULL);
 	ASSERT3P(done, !=, NULL);
@@ -5987,7 +5988,13 @@ arc_write(zio_t *pio, spa_t *spa, uint64_t txg,
 	if (l2arc)
 		arc_hdr_set_flags(hdr, ARC_FLAG_L2CACHE);
 	if (ARC_BUF_COMPRESSED(buf)) {
-		ASSERT3U(zp->zp_compress, !=, ZIO_COMPRESS_OFF);
+		/*
+		 * We're writing a pre-compressed buffer.  Make the
+		 * compression algorithm requested by the zio_prop_t match
+		 * the pre-compressed buffer's compression algorithm.
+		 */
+		localprop.zp_compress = HDR_GET_COMPRESS(hdr);
+
 		ASSERT3U(HDR_GET_LSIZE(hdr), !=, arc_buf_size(buf));
 		zio_flags |= ZIO_FLAG_RAW;
 	}
@@ -6023,8 +6030,7 @@ arc_write(zio_t *pio, spa_t *spa, uint64_t txg,
 
 	zio = zio_write(pio, spa, txg, bp,
 	    abd_get_from_buf(buf->b_data, HDR_GET_LSIZE(hdr)),
-	    HDR_GET_LSIZE(hdr), arc_buf_size(buf), zp,
-	    arc_write_ready,
+	    HDR_GET_LSIZE(hdr), arc_buf_size(buf), &localprop, arc_write_ready,
 	    (children_ready != NULL) ? arc_write_children_ready : NULL,
 	    arc_write_physdone, arc_write_done, callback,
 	    priority, zio_flags, zb);
diff --git a/module/zfs/dbuf.c b/module/zfs/dbuf.c
index 1575cc1b4..611382686 100644
--- a/module/zfs/dbuf.c
+++ b/module/zfs/dbuf.c
@@ -3736,9 +3736,7 @@ dbuf_write(dbuf_dirty_record_t *dr, arc_buf_t *data, dmu_tx_t *tx)
 		wp_flag = WP_SPILL;
 	wp_flag |= (db->db_state == DB_NOFILL) ? WP_NOFILL : 0;
 
-	dmu_write_policy(os, dn, db->db_level, wp_flag,
-	    (data != NULL && arc_get_compression(data) != ZIO_COMPRESS_OFF) ?
-	    arc_get_compression(data) : ZIO_COMPRESS_INHERIT, &zp);
+	dmu_write_policy(os, dn, db->db_level, wp_flag, &zp);
 	DB_DNODE_EXIT(db);
 
 	/*
diff --git a/module/zfs/dmu.c b/module/zfs/dmu.c
index 4203ddb16..5cf09412f 100644
--- a/module/zfs/dmu.c
+++ b/module/zfs/dmu.c
@@ -20,7 +20,7 @@
  */
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2016 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2017 by Delphix. All rights reserved.
  * Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
  * Copyright (c) 2013, Joyent, Inc. All rights reserved.
  * Copyright (c) 2016, Nexenta Systems, Inc. All rights reserved.
@@ -1705,8 +1705,7 @@ dmu_sync(zio_t *pio, uint64_t txg, dmu_sync_cb_t *done, zgd_t *zgd)
 
 	DB_DNODE_ENTER(db);
 	dn = DB_DNODE(db);
-	dmu_write_policy(os, dn, db->db_level, WP_DMU_SYNC,
-	    ZIO_COMPRESS_INHERIT, &zp);
+	dmu_write_policy(os, dn, db->db_level, WP_DMU_SYNC, &zp);
 	DB_DNODE_EXIT(db);
 
 	/*
@@ -1876,8 +1875,7 @@ int zfs_mdcomp_disable = 0;
 int zfs_redundant_metadata_most_ditto_level = 2;
 
 void
-dmu_write_policy(objset_t *os, dnode_t *dn, int level, int wp,
-    enum zio_compress override_compress, zio_prop_t *zp)
+dmu_write_policy(objset_t *os, dnode_t *dn, int level, int wp, zio_prop_t *zp)
 {
 	dmu_object_type_t type = dn ? dn->dn_type : DMU_OT_OBJSET;
 	boolean_t ismd = (level > 0 || DMU_OT_IS_METADATA(type) ||
@@ -1890,9 +1888,6 @@ dmu_write_policy(objset_t *os, dnode_t *dn, int level, int wp,
 	boolean_t dedup_verify = os->os_dedup_verify;
 	int copies = os->os_copies;
 
-	IMPLY(override_compress == ZIO_COMPRESS_LZ4,
-	    spa_feature_is_active(os->os_spa, SPA_FEATURE_LZ4_COMPRESS));
-
 	/*
 	 * We maintain different write policies for each of the following
 	 * types of data:
@@ -1979,14 +1974,7 @@ dmu_write_policy(objset_t *os, dnode_t *dn, int level, int wp,
 	}
 
 	zp->zp_checksum = checksum;
-
-	/*
-	 * If we're writing a pre-compressed buffer, the compression type we use
-	 * must match the data. If it hasn't been compressed yet, then we should
-	 * use the value dictated by the policies above.
-	 */
-	zp->zp_compress = override_compress != ZIO_COMPRESS_INHERIT
-	    ? override_compress : compress;
+	zp->zp_compress = compress;
 	ASSERT3U(zp->zp_compress, !=, ZIO_COMPRESS_INHERIT);
 
 	zp->zp_type = (wp & WP_SPILL) ? dn->dn_bonustype : type;
diff --git a/module/zfs/dmu_objset.c b/module/zfs/dmu_objset.c
index 946e4602f..a50f8dcb1 100644
--- a/module/zfs/dmu_objset.c
+++ b/module/zfs/dmu_objset.c
@@ -1326,7 +1326,7 @@ dmu_objset_sync(objset_t *os, zio_t *pio, dmu_tx_t *tx)
 	    ZB_ROOT_OBJECT, ZB_ROOT_LEVEL, ZB_ROOT_BLKID);
 	arc_release(os->os_phys_buf, &os->os_phys_buf);
 
-	dmu_write_policy(os, NULL, 0, 0, ZIO_COMPRESS_INHERIT, &zp);
+	dmu_write_policy(os, NULL, 0, 0, &zp);
 
 	zio = arc_write(pio, os->os_spa, tx->tx_txg,
 	    blkptr_copy, os->os_phys_buf, DMU_OS_IS_L2CACHEABLE(os),