[PATCH v2 1/5] btrfs: stop sleeping for one jiffy in non-ssd mounts during log commit

From: Filipe Manana <[email protected]>

Joining/starting a log transaction tracks if we ever had more than one task
concurrently logging by setting the flag BTRFS_ROOT_MULTI_LOG_TASKS in the
respective root. Once set, this flag remains for the rest of the lifetime
of the transaction, only cleared when we don't have a log root and need to
create a new one (transaction commits drop log roots).

During log commit, if we are not on a ssd mount (or use the -o nossd mount
option) and the BTRFS_ROOT_MULTI_LOG_TASKS flag is set, we sleep for one
jiffy with the excuse to allow future log writers to join and log inodes
and then commit a larger log transaction to reduce overall IO. However
this is extremely inefficient because:

1) If at some point we had multiple tasks logging concurrently but now
   we have only one task at a time, we force it to wait for 1 jiffy;

2) One jiffy can vary between 1ms to 10ms, depending on the kernel
   config option CONFIG_HZ, which by default has a value of 250HZ and
   that corresponds to 4ms - that is a lot.

This massively reduces the latency of fsyncs for non-ssd mounts, even
on consumer grade spinning disks.

Remove this mechanism to track if we have (or ever had) multiple tasks
logging and wait for 1 jiffy.

The following fio test was used to benchmark:

   $ cat fio-buffered-fsync.sh
   DEV=/dev/sdj
   MNT=/mnt/sdj
   MOUNT_OPTIONS=""
   MKFS_OPTIONS=""

   if [ $# -ne 6 ]; then
      echo "Use $0 NUM_JOBS FILE_SIZE IO_SIZE FSYNC_FREQ BLOCK_SIZE [write|randwrite]"
      exit 1
   fi

   NUM_JOBS=$1
   FILE_SIZE=$2
   IO_SIZE=$3
   FSYNC_FREQ=$4
   BLOCK_SIZE=$5
   WRITE_MODE=$6

   if [ "$WRITE_MODE" != "write" ] && [ "$WRITE_MODE" != "randwrite" ]; then
      echo "Invalid WRITE_MODE, must be 'write' or 'randwrite'"
      exit 1
   fi

   cat <<EOF > /tmp/fio-job.ini
   [writers]
   rw=$WRITE_MODE
   fsync=$FSYNC_FREQ
   fallocate=none
   group_reporting=1
   direct=0
   bs=$BLOCK_SIZE
   ioengine=psync
   filesize=$FILE_SIZE
   io_size=$IO_SIZE
   directory=$MNT
   numjobs=$NUM_JOBS
   EOF

   echo
   echo "Using config:"
   echo
   cat /tmp/fio-job.ini
   echo

   umount $MNT &> /dev/null
   mkfs.btrfs -f $MKFS_OPTIONS $DEV
   mount $MOUNT_OPTIONS $DEV $MNT

   fio /tmp/fio-job.ini
   umount $MNT

Running the script as:  ./fio-buffered-fsync.sh 8 64M 64M 1 4K randwrite

Before patch:

  WRITE: bw=2647KiB/s (2711kB/s), 2647KiB/s-2647KiB/s (2711kB/s-2711kB/s), io=512MiB (537MB), run=198055-198055msec

After patch:

  WRITE: bw=14.9MiB/s (15.6MB/s), 14.9MiB/s-14.9MiB/s (15.6MB/s-15.6MB/s), io=512MiB (537MB), run=34471-34471msec

That's about 5.7 times faster.

Signed-off-by: Filipe Manana <[email protected]>
---
 fs/btrfs/ctree.h    |  2 --
 fs/btrfs/tree-log.c | 18 +-----------------
 2 files changed, 1 insertion(+), 19 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 6de7ad191e04..0f2653182405 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -131,7 +131,6 @@ enum {
 	BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
 	BTRFS_ROOT_DEFRAG_RUNNING,
 	BTRFS_ROOT_FORCE_COW,
-	BTRFS_ROOT_MULTI_LOG_TASKS,
 	BTRFS_ROOT_DIRTY,
 	BTRFS_ROOT_DELETING,
 
@@ -216,7 +215,6 @@ struct btrfs_root {
 	 * to access this field.
 	 */
 	int last_log_commit;
-	pid_t log_start_pid;
 
 	u64 last_trans;
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 875e4ddc68ea..ccc262833a7c 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -316,13 +316,6 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 			wait_log_commit(root, root->log_transid - 1);
 			goto again;
 		}
-
-		if (!root->log_start_pid) {
-			clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
-			root->log_start_pid = current->pid;
-		} else if (root->log_start_pid != current->pid) {
-			set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
-		}
 	} else {
 		/*
 		 * This means fs_info->log_root_tree was already created
@@ -340,8 +333,6 @@ static int start_log_trans(struct btrfs_trans_handle *trans,
 			goto out;
 
 		set_bit(BTRFS_ROOT_HAS_LOG_TREE, &root->state);
-		clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
-		root->log_start_pid = current->pid;
 	}
 
 	atomic_inc(&root->log_writers);
@@ -3347,13 +3338,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 	while (1) {
 		int batch = atomic_read(&root->log_batch);
-		/* when we're on an ssd, just kick the log commit out */
-		if (!btrfs_test_opt(fs_info, SSD) &&
-		    test_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state)) {
-			mutex_unlock(&root->log_mutex);
-			schedule_timeout_uninterruptible(1);
-			mutex_lock(&root->log_mutex);
-		}
+
 		wait_for_writer(root);
 		if (batch == atomic_read(&root->log_batch))
 			break;
@@ -3414,7 +3399,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 	btrfs_set_root_log_transid(root, root->log_transid + 1);
 	log->log_transid = root->log_transid;
-	root->log_start_pid = 0;
 	/*
 	 * IO has been started, blocks of the log tree have WRITTEN flag set
 	 * in their headers. new modifications of the log will be written to
-- 
2.47.2