Improved dnode allocation and dmu_hold_impl() (#6611)

Refactor dmu_object_alloc_dnsize() and dnode_hold_impl() to simplify the
code, fix errors introduced by commit dbeb879 (PR #6117) interacting
badly with large dnodes, and improve performance.

* When allocating a new dnode in dmu_object_alloc_dnsize(), update the
percpu object ID for the core's metadnode chunk immediately.  This
eliminates most lock contention when taking the hold and creating the
dnode.

* Correct detection of the chunk boundary to work properly with large
dnodes.

* Separate the dmu_hold_impl() code for the FREE case from the code for
the ALLOCATED case to make it easier to read.

* Fully populate the dnode handle array immediately after reading a
block of the metadnode from disk.  Subsequently the dnode handle array
provides enough information to determine which dnode slots are in use
and which are free.

* Add several kstats to allow the behavior of the code to be examined.

* Verify dnode packing in large_dnode_008_pos.ksh.  Since the test is
purely creates, it should leave very few holes in the metadnode.

* Add test large_dnode_009_pos.ksh, which performs concurrent creates
and deletes, to complement existing test which does only creates.

With the above fixes, there is very little contention in a test of about
200,000 racing dnode allocations produced by tests 'large_dnode_008_pos'
and 'large_dnode_009_pos'.

name                            type data
dnode_hold_dbuf_hold            4    0
dnode_hold_dbuf_read            4    0
dnode_hold_alloc_hits           4    3804690
dnode_hold_alloc_misses         4    216
dnode_hold_alloc_interior       4    3
dnode_hold_alloc_lock_retry     4    0
dnode_hold_alloc_lock_misses    4    0
dnode_hold_alloc_type_none      4    0
dnode_hold_free_hits            4    203105
dnode_hold_free_misses          4    4
dnode_hold_free_lock_misses     4    0
dnode_hold_free_lock_retry      4    0
dnode_hold_free_overflow        4    0
dnode_hold_free_refcount        4    57
dnode_hold_free_txg             4    0
dnode_allocate                  4    203154
dnode_reallocate                4    0
dnode_buf_evict                 4    23918
dnode_alloc_next_chunk          4    4887
dnode_alloc_race                4    0
dnode_alloc_next_block          4    18

The performance is slightly improved for concurrent creates with
16+ threads, and unchanged for low thread counts.

Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Olaf Faaland <faaland1@llnl.gov>

tests/zfs-tests/tests/functional/features/large_dnode/Makefile.am

@@ -9,4 +9,5 @@ dist_pkgdata_SCRIPTS = \
 	large_dnode_005_pos.ksh \
 	large_dnode_006_pos.ksh \
 	large_dnode_007_neg.ksh \
-	large_dnode_008_pos.ksh
+	large_dnode_008_pos.ksh \
+	large_dnode_009_pos.ksh

tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_008_pos.ksh

@@ -42,6 +42,21 @@ function cleanup
 	datasetexists $TEST_FS && log_must zfs destroy $TEST_FS
 }
 
+function verify_dnode_packing
+{
+	zdb -dd $TEST_FS | grep -A 3 'Dnode slots' | awk '
+		/Total used:/ {total_used=$NF}
+		/Max used:/ {max_used=$NF}
+		/Percent empty:/ {print total_used, max_used, int($NF)}
+	' | while read total_used max_used pct_empty
+	do
+		log_note "total_used $total_used max_used $max_used pct_empty $pct_empty"
+		if [ $pct_empty -gt 5 ]; then
+			log_fail "Holes in dnode array: pct empty $pct_empty > 5"
+		fi
+	done
+}
+
 log_onexit cleanup
 log_assert "xattrtest runs concurrently on dataset with large dnodes"
 
@@ -52,9 +67,11 @@ log_must zfs set xattr=sa $TEST_FS
 for ((i=0; i < 100; i++)); do
 	dir="/$TEST_FS/dir.$i"
 	log_must mkdir "$dir"
-	log_must eval "xattrtest -R -r -y -x 1 -f 1024 -k -p $dir &"
+	log_must eval "xattrtest -R -r -y -x 1 -f 1024 -k -p $dir >/dev/null 2>&1 &"
 done
 
 log_must wait
 
+verify_dnode_packing
+
 log_pass

tests/zfs-tests/tests/functional/features/large_dnode/large_dnode_009_pos.ksh

@@ -0,0 +1,71 @@
+#!/bin/ksh -p
+#
+# CDDL HEADER START
+#
+# The contents of this file are subject to the terms of the
+# Common Development and Distribution License (the "License").
+# You may not use this file except in compliance with the License.
+#
+# You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
+# or http://www.opensolaris.org/os/licensing.
+# See the License for the specific language governing permissions
+# and limitations under the License.
+#
+# When distributing Covered Code, include this CDDL HEADER in each
+# file and include the License file at usr/src/OPENSOLARIS.LICENSE.
+# If applicable, add the following below this CDDL HEADER, with the
+# fields enclosed by brackets "[]" replaced with your own identifying
+# information: Portions Copyright [yyyy] [name of copyright owner]
+#
+# CDDL HEADER END
+#
+
+#
+# Copyright (c) 2017 by Lawrence Livermore National Security, LLC.
+# Use is subject to license terms.
+#
+
+. $STF_SUITE/include/libtest.shlib
+
+#
+# DESCRIPTION:
+# Run many xattrtests on a dataset with large dnodes and xattr=sa to
+# stress concurrent allocation of large dnodes.
+#
+
+TEST_FS=$TESTPOOL/large_dnode
+
+verify_runnable "both"
+
+function cleanup
+{
+	datasetexists $TEST_FS && log_must zfs destroy $TEST_FS
+}
+
+log_onexit cleanup
+log_assert "xattrtest runs concurrently on dataset with large dnodes"
+
+log_must zfs create $TEST_FS
+log_must zfs set dnsize=auto $TEST_FS
+log_must zfs set xattr=sa $TEST_FS
+
+for ((i=0; i < 100; i++)); do
+	dir="/$TEST_FS/dir.$i"
+	log_must mkdir "$dir"
+
+	do_unlink=""
+	if [ $((RANDOM % 2)) -eq 0 ]; then
+		do_unlink="-k -f 1024"
+	else
+		do_unlink="-f $((RANDOM % 1024))"
+	fi
+	log_must eval "xattrtest -R -r -y -x 1 $do_unlink -p $dir >/dev/null 2>&1 &"
+done
+
+log_must wait
+
+log_must zpool export $TESTPOOL
+log_must zpool import $TESTPOOL
+log_must ls -lR "/$TEST_FS/" >/dev/null 2>&1
+log_must zdb -d $TESTPOOL
+log_pass