MFV r251519:

 * Illumos ZFS issue #3805 arc shouldn't cache freed blocks

Quote from the Illumos issue:

    ZFS should proactively evict freed blocks from the cache.

    Even though these freed blocks will never be used again, and thus
    will eventually be evicted, this causes us to use memory
    inefficiently for 2 reasons:

    1. A block that is freed has no chance of being accessed again, but
       will be kept in memory preferentially to a block that was accessed
       before it (and is thus older) but has not been freed and thus has
       at least some chance of being accessed again.

    2. We partition the ARC into several buckets:
       user data that has been accessed only once (MRU)
       metadata that has been accessed only once (MRU)
       user data that has been accessed more than once (MFU)
       metadata that has been accessed more than once (MFU)

    The user data vs metadata split is somewhat arbitrary, and the
    primary control on how much memory is used to cache data vs metadata
    is to simply try to keep the proportion the same as it has been in the
    past (each bucket "evicts against" itself).  The secondary control is
    to evict data before evicting metadata.

    Because of this bucketing, we may end up with one bucket mostly
    containing freed blocks that are very old, while another bucket has
    more recently accessed, still-allocated blocks.  Data in the useful
    bucket (with still-allocated blocks) may be evicted in preference to
    data in the useless bucket (with old, freed blocks).

    On dcenter, we saw that the MFU metadata bucket was 230MB, while the
    MFU data bucket was 27GB and the MRU metadata bucket was 256GB.
    However, the vast majority of data in the MRU metadata bucket (256GB)
    was freed blocks, and thus useless.  Meanwhile, the MFU metadata bucket
    (230MB) was constantly evicting useful blocks that will be soon needed.

    The problem of cache segmentation is a larger problem that needs more
    investigation.  However, if we stop caching freed blocks, it should
    reduce the impact of this more fundamental issue.

MFC after:	2 weeks

3 files changed, 31 insertions, 1 deletions

diff --git a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/arc.c b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/arc.c
index 2d34c8b..8396276 100644
--- a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/arc.c
+++ b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/arc.c
@@ -3372,6 +3372,34 @@ arc_set_callback(arc_buf_t *buf, arc_evict_func_t *func, void *private)
 }
 
 /*
+ * Notify the arc that a block was freed, and thus will never be used again.
+ */
+void
+arc_freed(spa_t *spa, const blkptr_t *bp)
+{
+	arc_buf_hdr_t *hdr;
+	kmutex_t *hash_lock;
+	uint64_t guid = spa_load_guid(spa);
+
+	hdr = buf_hash_find(guid, BP_IDENTITY(bp), BP_PHYSICAL_BIRTH(bp),
+	    &hash_lock);
+	if (hdr == NULL)
+		return;
+	if (HDR_BUF_AVAILABLE(hdr)) {
+		arc_buf_t *buf = hdr->b_buf;
+		add_reference(hdr, hash_lock, FTAG);
+		hdr->b_flags &= ~ARC_BUF_AVAILABLE;
+		mutex_exit(hash_lock);
+
+		arc_release(buf, FTAG);
+		(void) arc_buf_remove_ref(buf, FTAG);
+	} else {
+		mutex_exit(hash_lock);
+	}
+
+}
+
+/*
  * This is used by the DMU to let the ARC know that a buffer is
  * being evicted, so the ARC should clean up.  If this arc buf
  * is not yet in the evicted state, it will be put there.
diff --git a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/arc.h b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/arc.h
index cf13ca6..dcf86ea 100644
--- a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/arc.h
+++ b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/sys/arc.h
@@ -20,7 +20,7 @@
  */
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2013 by Delphix. All rights reserved.
  * Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
  */
 
@@ -110,6 +110,7 @@ zio_t *arc_write(zio_t *pio, spa_t *spa, uint64_t txg,
     blkptr_t *bp, arc_buf_t *buf, boolean_t l2arc, boolean_t l2arc_compress,
     const zio_prop_t *zp, arc_done_func_t *ready, arc_done_func_t *done,
     void *priv, int priority, int zio_flags, const zbookmark_t *zb);
+void arc_freed(spa_t *spa, const blkptr_t *bp);
 
 void arc_set_callback(arc_buf_t *buf, arc_evict_func_t *func, void *priv);
 int arc_buf_evict(arc_buf_t *buf);
diff --git a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio.c b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio.c
index 6bb26be..41c2485 100644
--- a/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio.c
+++ b/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/zio.c
@@ -780,6 +780,7 @@ zio_free_sync(zio_t *pio, spa_t *spa, uint64_t txg, const blkptr_t *bp,
 	ASSERT(spa_sync_pass(spa) < zfs_sync_pass_deferred_free);
 
 	metaslab_check_free(spa, bp);
+	arc_freed(spa, bp);
 
 	zio = zio_create(pio, spa, txg, bp, NULL, size,
 	    NULL, NULL, ZIO_TYPE_FREE, ZIO_PRIORITY_FREE, flags,