Speed up WB_SYNC_NONE when a WB_SYNC_ALL occurs simultaneously

Page writebacks with WB_SYNC_NONE can take several seconds to complete
since they wait for the transaction group to close before being
committed. This is usually not a problem since the caller does not
need to wait. However, if we're simultaneously doing a writeback
with WB_SYNC_ALL (e.g via msync), the latter can block for several
seconds (up to zfs_txg_timeout) due to the active WB_SYNC_NONE
writeback since it needs to wait for the transaction to complete
and the PG_writeback bit to be cleared.

This commit deals with 2 cases:

- No page writeback is active. A WB_SYNC_ALL page writeback starts
  and even completes. But when it's about to check if the PG_writeback
  bit has been cleared, another writeback with WB_SYNC_NONE starts.
  The sync page writeback ends up waiting for the non-sync page
  writeback to complete.

- A page writeback with WB_SYNC_NONE is already active when a
  WB_SYNC_ALL writeback starts. The WB_SYNC_ALL writeback ends up
  waiting for the WB_SYNC_NONE writeback.

The fix works by carefully keeping track of active sync/non-sync
writebacks and committing when beneficial.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Shaan Nobee <sniper111@gmail.com>
Closes #12662
Closes #12790

tests/runfiles/common.run

@@ -672,7 +672,7 @@ tags = ['functional', 'migration']
 
 [tests/functional/mmap]
 tests = ['mmap_mixed', 'mmap_read_001_pos', 'mmap_seek_001_pos',
-    'mmap_write_001_pos']
+    'mmap_write_001_pos', 'mmap_sync_001_pos']
 tags = ['functional', 'mmap']
 
 [tests/functional/mount]

tests/test-runner/bin/zts-report.py.in

@@ -189,6 +189,7 @@ if sys.platform.startswith('freebsd'):
         'cli_root/zpool_wait/zpool_wait_trim_cancel': ['SKIP', trim_reason],
         'cli_root/zpool_wait/zpool_wait_trim_flag': ['SKIP', trim_reason],
         'link_count/link_count_001': ['SKIP', na_reason],
+        'mmap/mmap_sync_001_pos': ['SKIP', na_reason],
     })
 elif sys.platform.startswith('linux'):
     known.update({

tests/zfs-tests/cmd/Makefile.am

@@ -20,6 +20,7 @@ SUBDIRS = \
 	mmap_exec \
 	mmap_libaio \
 	mmap_seek \
+	mmap_sync \
 	mmapwrite \
 	nvlist_to_lua \
 	randwritecomp \

tests/zfs-tests/cmd/mmap_sync/.gitignore

@@ -0,0 +1 @@
+/mmap_sync

tests/zfs-tests/cmd/mmap_sync/Makefile.am

@@ -0,0 +1,6 @@
+include $(top_srcdir)/config/Rules.am
+
+pkgexecdir = $(datadir)/@PACKAGE@/zfs-tests/bin
+
+pkgexec_PROGRAMS = mmap_sync
+mmap_sync_SOURCES = mmap_sync.c

tests/zfs-tests/include/commands.cfg

@@ -207,6 +207,7 @@ export ZFSTEST_FILES='badsend
     mmap_exec
     mmap_libaio
     mmap_seek
+    mmap_sync
     mmapwrite
     nvlist_to_lua
     randfree_file

tests/zfs-tests/tests/functional/mmap/Makefile.am

@@ -6,7 +6,8 @@ dist_pkgdata_SCRIPTS = \
 	mmap_read_001_pos.ksh \
 	mmap_write_001_pos.ksh \
 	mmap_libaio_001_pos.ksh \
-	mmap_seek_001_pos.ksh
+	mmap_seek_001_pos.ksh \
+	mmap_sync_001_pos.ksh
 
 dist_pkgdata_DATA = \
 	mmap.cfg

tests/zfs-tests/tests/functional/mmap/mmap_sync_001_pos.ksh

@@ -0,0 +1,63 @@
+#!/bin/ksh -p
+
+#
+# This file and its contents are supplied under the terms of the
+# Common Development and Distribution License ("CDDL"), version 1.0.
+# You may only use this file in accordance with the terms of version
+# 1.0 of the CDDL.
+#
+# A full copy of the text of the CDDL should have accompanied this
+# source.  A copy of the CDDL is also available via the Internet at
+# http://www.illumos.org/license/CDDL.
+#
+
+#
+# Copyright (c) 2015, 2016 by Delphix. All rights reserved.
+#
+
+. $STF_SUITE/include/libtest.shlib
+
+#
+# DESCRIPTION:
+# msync()s of mmap()'ed file should complete quickly during
+# background dirty page writebacks by the kernel.
+#
+
+function cleanup
+{
+	log_must eval "echo $saved_vm_dirty_expire_centisecs > /proc/sys/vm/dirty_expire_centisecs"
+	log_must eval "echo $saved_vm_dirty_background_ratio > /proc/sys/vm/dirty_background_ratio"
+	log_must eval "echo $saved_vm_dirty_writeback_centisecs > /proc/sys/vm/dirty_writeback_centisecs"
+
+	# revert to some sensible defaults if the values we saved
+	# were incorrect due to a previous run being interrupted
+	if [ $(</proc/sys/vm/dirty_expire_centisecs) -eq 1 ]; then
+		log_must eval "echo 3000 > /proc/sys/vm/dirty_expire_centisecs"
+	fi
+
+	if [ $(</proc/sys/vm/dirty_background_ratio) -eq 0 ]; then
+		log_must eval "echo 10 > /proc/sys/vm/dirty_background_ratio"
+	fi
+
+	if [ $(</proc/sys/vm/dirty_writeback_centisecs) -eq 1 ]; then
+		log_must eval "echo 500 > /proc/sys/vm/dirty_writeback_centisecs"
+	fi
+}
+
+if ! is_linux; then
+	log_unsupported "Only supported on Linux, requires /proc/sys/vm/ tunables"
+fi
+
+log_onexit cleanup
+log_assert "Run the tests for mmap_sync"
+
+read -r saved_vm_dirty_expire_centisecs < /proc/sys/vm/dirty_expire_centisecs
+read -r saved_vm_dirty_background_ratio < /proc/sys/vm/dirty_background_ratio
+read -r saved_vm_dirty_writeback_centisecs < /proc/sys/vm/dirty_writeback_centisecs
+
+log_must eval "echo 1 > /proc/sys/vm/dirty_expire_centisecs"
+log_must eval "echo 1 > /proc/sys/vm/dirty_background_bytes"
+log_must eval "echo 1 > /proc/sys/vm/dirty_writeback_centisecs"
+
+log_must mmap_sync
+log_pass "mmap_sync tests passed."