Unlike JBD2 based full commits, there is no dedicated journal thread
for fast commits. Thus to reduce scheduling delays between IO
submission and completion, temporarily elevate the committer thread's
priority to match the configured priority of the JBD2 journal
thread.
Signed-off-by: Harshad Shirwadkar <harshadshirwadkar@xxxxxxxxx>
Reviewed-by: Jan Kara <jack@xxxxxxx>
---
fs/ext4/ext4.h | 4 +++-
fs/ext4/fast_commit.c | 13 +++++++++++++
fs/ext4/super.c | 5 ++---
3 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 03734c523..4ecb63f95 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2279,10 +2279,12 @@ static inline int ext4_forced_shutdown(struct super_block *sb)
#define EXT4_DEFM_NODELALLOC 0x0800
/*
- * Default journal batch times
+ * Default journal batch times and ioprio.
*/
#define EXT4_DEF_MIN_BATCH_TIME 0
#define EXT4_DEF_MAX_BATCH_TIME 15000 /* 15ms */
+#define EXT4_DEF_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
+
/*
* Minimum number of groups in a flexgroup before we separate out
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 71cf8dc8a..2fc43b1e2 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1196,6 +1196,7 @@ int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
int subtid = atomic_read(&sbi->s_fc_subtid);
int status = EXT4_FC_STATUS_OK, fc_bufs_before = 0;
ktime_t start_time, commit_time;
+ int old_ioprio, journal_ioprio;
if (!test_opt2(sb, JOURNAL_FAST_COMMIT))
return jbd2_complete_transaction(journal, commit_tid);
@@ -1203,6 +1204,7 @@ int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
trace_ext4_fc_commit_start(sb, commit_tid);
start_time = ktime_get();
+ old_ioprio = get_current_ioprio();
restart_fc:
ret = jbd2_fc_begin_commit(journal, commit_tid);
@@ -1233,6 +1235,15 @@ int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
goto fallback;
}
+ /*
+ * Now that we know that this thread is going to do a fast commit,
+ * elevate the priority to match that of the journal thread.
+ */
+ if (journal->j_task->io_context)
+ journal_ioprio = sbi->s_journal->j_task->io_context->ioprio;
+ else
+ journal_ioprio = EXT4_DEF_JOURNAL_IOPRIO;
+ set_task_ioprio(current, journal_ioprio);
fc_bufs_before = (sbi->s_fc_bytes + bsize - 1) / bsize;
ret = ext4_fc_perform_commit(journal);
if (ret < 0) {
@@ -1247,6 +1258,7 @@ int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
}
atomic_inc(&sbi->s_fc_subtid);
ret = jbd2_fc_end_commit(journal);
+ set_task_ioprio(current, old_ioprio);
/*
* weight the commit time higher than the average time so we
* don't react too strongly to vast changes in the commit time
@@ -1256,6 +1268,7 @@ int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
return ret;
fallback:
+ set_task_ioprio(current, old_ioprio);
ret = jbd2_fc_end_commit_fallback(journal);
ext4_fc_update_stats(sb, status, 0, 0, commit_tid);
return ret;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index d37944839..4f38a34b0 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1817,7 +1817,6 @@ static const struct fs_parameter_spec ext4_param_specs[] = {
{}
};
-#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
#define MOPT_SET 0x0001
#define MOPT_CLEAR 0x0002
@@ -5179,7 +5178,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
/* Set defaults for the variables that will be set during parsing */
if (!(ctx->spec & EXT4_SPEC_JOURNAL_IOPRIO))
- ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+ ctx->journal_ioprio = EXT4_DEF_JOURNAL_IOPRIO;
sbi->s_inode_readahead_blks = EXT4_DEF_INODE_READAHEAD_BLKS;
sbi->s_sectors_written_start =
@@ -6437,7 +6436,7 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
ctx->journal_ioprio =
sbi->s_journal->j_task->io_context->ioprio;
else
- ctx->journal_ioprio = DEFAULT_JOURNAL_IOPRIO;
+ ctx->journal_ioprio = EXT4_DEF_JOURNAL_IOPRIO;
}
--
2.46.0.184.g6999bdac58-goog
