Illumos 5987 - zfs prefetch code needs work

5987 zfs prefetch code needs work
Reviewed by: Adam Leventhal <[email protected]>
Reviewed by: George Wilson <[email protected]>
Reviewed by: Paul Dagnelie <[email protected]>
Approved by: Gordon Ross <[email protected]>

References:
  https://www.illumos.org/issues/5987 zfs prefetch code needs work
  illumos/illumos-gate@cf6106c 5987 zfs prefetch code needs work

Porting notes:
- [module/zfs/dbuf.c]
  - 5f6d0b6 Handle block pointers with a corrupt logical size
- [module/zfs/dmu_zfetch.c]
  - c65aa5b Fix gcc missing parenthesis warnings
  - 428870f Update core ZFS code from build 121 to build 141.
  - 79c76d5 Change KM_PUSHPAGE -> KM_SLEEP
  - b8d06fc Switch KM_SLEEP to KM_PUSHPAGE
  - Account for ISO C90 - mixed declarations and code - warnings
  - Module parameters (new/changed):
    - Replaced zfetch_block_cap with zfetch_max_distance
      (Max bytes to prefetch per stream (default 8MB; 8 * 1024 * 1024))
    - Preserved zfs_prefetch_disable as 'int' for consistency with
      existing Linux module options.
- [include/sys/trace_arc.h]
  - Added new tracepoints
    - DEFINE_ARC_BUF_HDR_EVENT(zfs_arc__sync__wait__for__async);
    - DEFINE_ARC_BUF_HDR_EVENT(zfs_arc__demand__hit__predictive__prefetch);
- [man/man5/zfs-module-parameters.5]
  - Updated man page

Ported-by: kernelOfTruth [email protected]
Signed-off-by: Brian Behlendorf <[email protected]>

1 files changed, 9 insertions, 12 deletions

diff --git a/module/zfs/dbuf.c b/module/zfs/dbuf.c
index e08dcc4a3..d53d8607a 100644
--- a/module/zfs/dbuf.c
+++ b/module/zfs/dbuf.c
@@ -676,7 +676,7 @@ dbuf_read_done(zio_t *zio, arc_buf_t *buf, void *vdb)
 }
 
 static int
-dbuf_read_impl(dmu_buf_impl_t *db, zio_t *zio, uint32_t *flags)
+dbuf_read_impl(dmu_buf_impl_t *db, zio_t *zio, uint32_t flags)
 {
 	dnode_t *dn;
 	zbookmark_phys_t zb;
@@ -723,7 +723,6 @@ dbuf_read_impl(dmu_buf_impl_t *db, zio_t *zio, uint32_t *flags)
 		    db->db.db_size, db, type));
 		bzero(db->db.db_data, db->db.db_size);
 		db->db_state = DB_CACHED;
-		*flags |= DB_RF_CACHED;
 		mutex_exit(&db->db_mtx);
 		return (0);
 	}
@@ -746,10 +745,8 @@ dbuf_read_impl(dmu_buf_impl_t *db, zio_t *zio, uint32_t *flags)
 
 	err = arc_read(zio, db->db_objset->os_spa, db->db_blkptr,
 	    dbuf_read_done, db, ZIO_PRIORITY_SYNC_READ,
-	    (*flags & DB_RF_CANFAIL) ? ZIO_FLAG_CANFAIL : ZIO_FLAG_MUSTSUCCEED,
+	    (flags & DB_RF_CANFAIL) ? ZIO_FLAG_CANFAIL : ZIO_FLAG_MUSTSUCCEED,
 	    &aflags, &zb);
-	if (aflags & ARC_FLAG_CACHED)
-		*flags |= DB_RF_CACHED;
 
 	return (SET_ERROR(err));
 }
@@ -784,8 +781,7 @@ dbuf_read(dmu_buf_impl_t *db, zio_t *zio, uint32_t flags)
 	if (db->db_state == DB_CACHED) {
 		mutex_exit(&db->db_mtx);
 		if (prefetch)
-			dmu_zfetch(&dn->dn_zfetch, db->db.db_offset,
-			    db->db.db_size, TRUE);
+			dmu_zfetch(&dn->dn_zfetch, db->db_blkid, 1);
 		if ((flags & DB_RF_HAVESTRUCT) == 0)
 			rw_exit(&dn->dn_struct_rwlock);
 		DB_DNODE_EXIT(db);
@@ -795,13 +791,12 @@ dbuf_read(dmu_buf_impl_t *db, zio_t *zio, uint32_t flags)
 		if (zio == NULL)
 			zio = zio_root(spa, NULL, NULL, ZIO_FLAG_CANFAIL);
 
-		err = dbuf_read_impl(db, zio, &flags);
+		err = dbuf_read_impl(db, zio, flags);
 
 		/* dbuf_read_impl has dropped db_mtx for us */
 
 		if (!err && prefetch)
-			dmu_zfetch(&dn->dn_zfetch, db->db.db_offset,
-			    db->db.db_size, flags & DB_RF_CACHED);
+			dmu_zfetch(&dn->dn_zfetch, db->db_blkid, 1);
 
 		if ((flags & DB_RF_HAVESTRUCT) == 0)
 			rw_exit(&dn->dn_struct_rwlock);
@@ -820,8 +815,7 @@ dbuf_read(dmu_buf_impl_t *db, zio_t *zio, uint32_t flags)
 		 */
 		mutex_exit(&db->db_mtx);
 		if (prefetch)
-			dmu_zfetch(&dn->dn_zfetch, db->db.db_offset,
-			    db->db.db_size, TRUE);
+			dmu_zfetch(&dn->dn_zfetch, db->db_blkid, 1);
 		if ((flags & DB_RF_HAVESTRUCT) == 0)
 			rw_exit(&dn->dn_struct_rwlock);
 		DB_DNODE_EXIT(db);
@@ -2143,6 +2137,9 @@ dbuf_prefetch(dnode_t *dn, int64_t level, uint64_t blkid, zio_priority_t prio,
 	ASSERT(blkid != DMU_BONUS_BLKID);
 	ASSERT(RW_LOCK_HELD(&dn->dn_struct_rwlock));
 
+	if (blkid > dn->dn_maxblkid)
+		return;
+
 	if (dnode_block_freed(dn, blkid))
 		return;