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>
2026-05-23 02:44:41 +03:00 · 2017-09-13 15:46:15 -07:00
parent 89950722c6
commit 45d1abc74d
9 changed files with 616 additions and 258 deletions
@@ -365,7 +365,7 @@ tests = ['async_destroy_001_pos']
 [tests/functional/features/large_dnode]
 tests = ['large_dnode_001_pos', 'large_dnode_002_pos', 'large_dnode_003_pos',
         'large_dnode_004_neg', 'large_dnode_005_pos', 'large_dnode_006_pos',
-         'large_dnode_007_neg', 'large_dnode_008_pos']
+         'large_dnode_007_neg', 'large_dnode_008_pos', 'large_dnode_009_pos']

 [tests/functional/grow_pool]
 tests = ['grow_pool_001_pos']
@@ -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
@@ -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
@@ -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