For NAND based SSDs, mixing of data with different life-time reduces
efficiency of internal garbage-collection. During FS operations,
series of journal updates will follow/precede series of data/meta
updates, causing intermixing inside SSD. By passing a write-hint with
journal, its write can be isolated from other data/meta writes, leading
to endurance/performance benefit on SSD.
This patch introduces "j_writehint" member in JBD2 journal, using which
Ext4 specifies write-hint for journal.
Signed-off-by: Kanchan Joshi <joshi.k@xxxxxxxxxxx>
---
fs/ext4/ext4_jbd2.h | 1 +
fs/ext4/super.c | 2 ++
fs/jbd2/commit.c | 11 +++++++----
fs/jbd2/journal.c | 3 ++-
fs/jbd2/revoke.c | 3 ++-
include/linux/jbd2.h | 8 ++++++++
6 files changed, 22 insertions(+), 6 deletions(-)
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 75a5309..ade47b2 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -16,6 +16,7 @@
#include <linux/jbd2.h>
#include "ext4.h"
+#define EXT4_JOURNAL_WRITE_HINT (WRITE_LIFE_KERN_MIN)
#define EXT4_JOURNAL(inode) (EXT4_SB((inode)->i_sb)->s_journal)
/* Define the number of blocks we need to account to a transaction to
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 6ed4eb8..238c0b5 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4298,6 +4298,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
set_task_ioprio(sbi->s_journal->j_task, journal_ioprio);
+ sbi->s_journal->j_writehint = EXT4_JOURNAL_WRITE_HINT;
+
sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
no_journal:
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index efd0ce9..be3a0b9 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -153,10 +153,12 @@ static int journal_submit_commit_record(journal_t *journal,
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_has_feature_async_commit(journal))
- ret = submit_bh(REQ_OP_WRITE,
- REQ_SYNC | REQ_PREFLUSH | REQ_FUA, bh);
+ ret = submit_bh_write_hint(REQ_OP_WRITE,
+ REQ_SYNC | REQ_PREFLUSH | REQ_FUA, bh,
+ journal->j_writehint);
else
- ret = submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+ ret = submit_bh_write_hint(REQ_OP_WRITE, REQ_SYNC, bh,
+ journal->j_writehint);
*cbh = bh;
return ret;
@@ -713,7 +715,8 @@ void jbd2_journal_commit_transaction(journal_t *journal)
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = journal_end_buffer_io_sync;
- submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+ submit_bh_write_hint(REQ_OP_WRITE, REQ_SYNC,
+ bh, journal->j_writehint);
}
cond_resched();
stats.run.rs_blocks_logged += bufs;
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 382c030..6dc7c9a 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1372,7 +1372,8 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
sb->s_checksum = jbd2_superblock_csum(journal, sb);
get_bh(bh);
bh->b_end_io = end_buffer_write_sync;
- ret = submit_bh(REQ_OP_WRITE, write_flags, bh);
+ ret = submit_bh_write_hint(REQ_OP_WRITE, write_flags, bh,
+ journal->j_writehint);
wait_on_buffer(bh);
if (buffer_write_io_error(bh)) {
clear_buffer_write_io_error(bh);
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index a1143e5..376b1d8 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -642,7 +642,8 @@ static void flush_descriptor(journal_t *journal,
set_buffer_jwrite(descriptor);
BUFFER_TRACE(descriptor, "write");
set_buffer_dirty(descriptor);
- write_dirty_buffer(descriptor, REQ_SYNC);
+ write_dirty_buffer_with_hint(descriptor, REQ_SYNC,
+ journal->j_writehint);
}
#endif
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 0f919d5..918f21e 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1139,6 +1139,14 @@ struct journal_s
*/
__u32 j_csum_seed;
+ /**
+ * @j_writehint:
+ *
+ * write-hint for journal (set by FS).
+ */
+ enum rw_hint j_writehint;
+
+
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/**
* @j_trans_commit_map:
--
2.7.4
