aboutsummaryrefslogtreecommitdiff
path: root/fs/jbd2/commit.c
diff options
context:
space:
mode:
authorJosef Bacik <jbacik@redhat.com>2008-11-26 01:14:26 -0500
committerTheodore Ts'o <tytso@mit.edu>2008-11-26 01:14:26 -0500
commite07f7183a486cf9783d1f8c9d2997b5b39eeb2d4 (patch)
tree74ed3a563add5fa57e80af03f3f712f2910ac39f /fs/jbd2/commit.c
parent032115fcef837a00336ddf7bda584e89789ea498 (diff)
jbd2: improve jbd2 fsync batching
This patch removes the static sleep time in favor of a more self optimizing approach where we measure the average amount of time it takes to commit a transaction to disk and the ammount of time a transaction has been running. If somebody does a sync write or an fsync() traditionally we would sleep for 1 jiffies, which depending on the value of HZ could be a significant amount of time compared to how long it takes to commit a transaction to the underlying storage. With this patch instead of sleeping for a jiffie, we check to see if the amount of time this transaction has been running is less than the average commit time, and if it is we sleep for the delta using schedule_hrtimeout to give us a higher precision sleep time. This greatly benefits high end storage where you could end up sleeping for longer than it takes to commit the transaction and therefore sitting idle instead of allowing the transaction to be committed by keeping the sleep time to a minimum so you are sure to always be doing something. Signed-off-by: Josef Bacik <jbacik@redhat.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Diffstat (limited to 'fs/jbd2/commit.c')
-rw-r--r--fs/jbd2/commit.c14
1 files changed, 14 insertions, 0 deletions
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6393fd0d804..f22d1828ea8 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -355,6 +355,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
int flags;
int err;
unsigned long long blocknr;
+ ktime_t start_time;
+ u64 commit_time;
char *tagp = NULL;
journal_header_t *header;
journal_block_tag_t *tag = NULL;
@@ -481,6 +483,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
commit_transaction->t_state = T_FLUSH;
journal->j_committing_transaction = commit_transaction;
journal->j_running_transaction = NULL;
+ start_time = ktime_get();
commit_transaction->t_log_start = journal->j_head;
wake_up(&journal->j_wait_transaction_locked);
spin_unlock(&journal->j_state_lock);
@@ -995,6 +998,17 @@ restart_loop:
J_ASSERT(commit_transaction == journal->j_committing_transaction);
journal->j_commit_sequence = commit_transaction->t_tid;
journal->j_committing_transaction = NULL;
+ commit_time = ktime_to_ns(ktime_sub(ktime_get(), start_time));
+
+ /*
+ * weight the commit time higher than the average time so we don't
+ * react too strongly to vast changes in the commit time
+ */
+ if (likely(journal->j_average_commit_time))
+ journal->j_average_commit_time = (commit_time +
+ journal->j_average_commit_time*3) / 4;
+ else
+ journal->j_average_commit_time = commit_time;
spin_unlock(&journal->j_state_lock);
if (journal->j_commit_callback)