From 2db938bee32e7469ca8ed9bfb3a05535f28c680d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 21 Feb 2011 17:25:37 +0100 Subject: jbd: Refine commit writeout logic Currently we write out all journal buffers in WRITE_SYNC mode. This improves performance for fsync heavy workloads but hinders performance when writes are mostly asynchronous, most noticably it slows down readers and users complain about slow desktop response etc. So submit writes as asynchronous in the normal case and only submit writes as WRITE_SYNC if we detect someone is waiting for current transaction commit. I've gathered some numbers to back this change. The first is the read latency test. It measures time to read 1 MB after several seconds of sleeping in presence of streaming writes. Top 10 times (out of 90) in us: Before After 2131586 697473 1709932 557487 1564598 535642 1480462 347573 1478579 323153 1408496 222181 1388960 181273 1329565 181070 1252486 172832 1223265 172278 Average: 619377 82180 So the improvement in both maximum and average latency is massive. I've measured fsync throughput by: fs_mark -n 100 -t 1 -s 16384 -d /mnt/fsync/ -S 1 -L 4 in presence of streaming reader. The numbers (fsyncs/s) are: Before After 9.9 6.3 6.8 6.0 6.3 6.2 5.8 6.1 So fsync performance seems unharmed by this change. Signed-off-by: Jan Kara --- fs/jbd/commit.c | 10 +++++++--- fs/jbd/journal.c | 2 ++ fs/jbd/transaction.c | 2 -- 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'fs/jbd') diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c index f2b9a571f4cf..9d31e6a39205 100644 --- a/fs/jbd/commit.c +++ b/fs/jbd/commit.c @@ -298,6 +298,7 @@ void journal_commit_transaction(journal_t *journal) int tag_flag; int i; struct blk_plug plug; + int write_op = WRITE; /* * First job: lock down the current transaction and wait for @@ -413,13 +414,16 @@ void journal_commit_transaction(journal_t *journal) jbd_debug (3, "JBD: commit phase 2\n"); + if (tid_geq(journal->j_commit_waited, commit_transaction->t_tid)) + write_op = WRITE_SYNC; + /* * Now start flushing things to disk, in the order they appear * on the transaction lists. Data blocks go first. */ blk_start_plug(&plug); err = journal_submit_data_buffers(journal, commit_transaction, - WRITE_SYNC); + write_op); blk_finish_plug(&plug); /* @@ -478,7 +482,7 @@ void journal_commit_transaction(journal_t *journal) blk_start_plug(&plug); - journal_write_revoke_records(journal, commit_transaction, WRITE_SYNC); + journal_write_revoke_records(journal, commit_transaction, write_op); /* * If we found any dirty or locked buffers, then we should have @@ -649,7 +653,7 @@ start_journal_io: clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; - submit_bh(WRITE_SYNC, bh); + submit_bh(write_op, bh); } cond_resched(); diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 0971e9217808..2047fd77bf38 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -563,6 +563,8 @@ int log_wait_commit(journal_t *journal, tid_t tid) spin_unlock(&journal->j_state_lock); #endif spin_lock(&journal->j_state_lock); + if (!tid_geq(journal->j_commit_waited, tid)) + journal->j_commit_waited = tid; while (tid_gt(tid, journal->j_commit_sequence)) { jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n", tid, journal->j_commit_sequence); diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c index b2a7e5244e39..febc10db5ced 100644 --- a/fs/jbd/transaction.c +++ b/fs/jbd/transaction.c @@ -1433,8 +1433,6 @@ int journal_stop(handle_t *handle) } } - if (handle->h_sync) - transaction->t_synchronous_commit = 1; current->journal_info = NULL; spin_lock(&journal->j_state_lock); spin_lock(&transaction->t_handle_lock); -- cgit v1.2.3-59-g8ed1b