summaryrefslogtreecommitdiffstats
path: root/fs/jbd/commit.c
diff options
context:
space:
mode:
authorToshiyuki Okajima <toshi.okajima@jp.fujitsu.com>2008-07-25 01:46:29 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2008-07-25 10:53:32 -0700
commitfc80c44277b3c92d808b73e9d40e120229aa4b6a (patch)
treedb0848f89305aa3c90b07ad773badc17f858405e /fs/jbd/commit.c
parenta10320e8f7c4dcfa050aac566092f29b40458d5a (diff)
downloadlinux-fc80c44277b3c92d808b73e9d40e120229aa4b6a.tar.bz2
jbd: positively dispose the unmapped data buffers in journal_commit_transaction()
After ext3-ordered files are truncated, there is a possibility that the pages which cannot be estimated still remain. Remaining pages can be released when the system has really few memory. So, it is not memory leakage. But the resource management software etc. may not work correctly. It is possible that journal_unmap_buffer() cannot release the buffers, and the pages to which they belong because they are attached to a commiting transaction and journal_unmap_buffer() cannot release them. To release such the buffers and the pages later, journal_unmap_buffer() leaves it to journal_commit_transaction(). (journal_unmap_buffer() puts the mark 'BH_Freed' to the buffers so that journal_commit_transaction() can identify whether they can be released or not.) In the journalled mode and the writeback mode, jbd does with only metadata buffers. But in the ordered mode, jbd does with metadata buffers and also data buffers. Actually, journal_commit_transaction() releases only the metadata buffers of which release is demanded by journal_unmap_buffer(), and also releases the pages to which they belong if possible. As a result, the data buffers of which release is demanded by journal_unmap_buffer() remain after a transaction commits. And also the pages to which they belong remain. Such the remained pages don't have mapping any longer. Due to this fact, there is a possibility that the pages which cannot be estimated remain. The metadata buffers marked 'BH_Freed' and the pages to which they belong can be released at 'JBD: commit phase 7'. Therefore, by applying the same code into 'JBD: commit phase 2' (where the data buffers are done with), journal_commit_transaction() can also release the data buffers marked 'BH_Freed' and the pages to which they belong. As a result, all the buffers marked 'BH_Freed' can be released, and also all the pages to which these buffers belong can be released at journal_commit_transaction(). So, the page which cannot be estimated is lost. <<Excerpt of code at 'JBD: commit phase 7'>> > spin_lock(&journal->j_list_lock); > while (commit_transaction->t_forget) { > transaction_t *cp_transaction; > struct buffer_head *bh; > > jh = commit_transaction->t_forget; >... > if (buffer_freed(bh)) { > ^^^^^^^^^^^^^^^^^^^^^^^^ > clear_buffer_freed(bh); > ^^^^^^^^^^^^^^^^^^^^^^^^ > clear_buffer_jbddirty(bh); > } > > if (buffer_jbddirty(bh)) { > JBUFFER_TRACE(jh, "add to new checkpointing trans"); > __journal_insert_checkpoint(jh, commit_transaction); > JBUFFER_TRACE(jh, "refile for checkpoint writeback"); > __journal_refile_buffer(jh); > jbd_unlock_bh_state(bh); > } else { > J_ASSERT_BH(bh, !buffer_dirty(bh)); > ... > JBUFFER_TRACE(jh, "refile or unfile freed buffer"); > __journal_refile_buffer(jh); > if (!jh->b_transaction) { > jbd_unlock_bh_state(bh); > /* needs a brelse */ > journal_remove_journal_head(bh); > release_buffer_page(bh); > ^^^^^^^^^^^^^^^^^^^^^^^^ > } else > } **************************************************************** * Apply the code of "^^^^^^" lines into 'JBD: commit phase 2' * **************************************************************** At journal_commit_transaction() code, there is one extra message in the series of jbd debug messages. ("JBD: commit phase 2") This patch fixes it, too. Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com> Acked-by: Jan Kara <jack@suse.cz> Cc: <linux-ext4@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/jbd/commit.c')
-rw-r--r--fs/jbd/commit.c29
1 files changed, 20 insertions, 9 deletions
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 5a8ca61498ca..f943b9b3f208 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -36,7 +36,7 @@ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
/*
* When an ext3-ordered file is truncated, it is possible that many pages are
- * not sucessfully freed, because they are attached to a committing transaction.
+ * not successfully freed, because they are attached to a committing transaction.
* After the transaction commits, these pages are left on the LRU, with no
* ->mapping, and with attached buffers. These pages are trivially reclaimable
* by the VM, but their apparent absence upsets the VM accounting, and it makes
@@ -45,8 +45,8 @@ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
* So here, we have a buffer which has just come off the forget list. Look to
* see if we can strip all buffers from the backing page.
*
- * Called under lock_journal(), and possibly under journal_datalist_lock. The
- * caller provided us with a ref against the buffer, and we drop that here.
+ * Called under journal->j_list_lock. The caller provided us with a ref
+ * against the buffer, and we drop that here.
*/
static void release_buffer_page(struct buffer_head *bh)
{
@@ -78,6 +78,19 @@ nope:
}
/*
+ * Decrement reference counter for data buffer. If it has been marked
+ * 'BH_Freed', release it and the page to which it belongs if possible.
+ */
+static void release_data_buffer(struct buffer_head *bh)
+{
+ if (buffer_freed(bh)) {
+ clear_buffer_freed(bh);
+ release_buffer_page(bh);
+ } else
+ put_bh(bh);
+}
+
+/*
* Try to acquire jbd_lock_bh_state() against the buffer, when j_list_lock is
* held. For ranking reasons we must trylock. If we lose, schedule away and
* return 0. j_list_lock is dropped in this case.
@@ -231,7 +244,7 @@ write_out_data:
if (locked)
unlock_buffer(bh);
BUFFER_TRACE(bh, "already cleaned up");
- put_bh(bh);
+ release_data_buffer(bh);
continue;
}
if (locked && test_clear_buffer_dirty(bh)) {
@@ -258,10 +271,10 @@ write_out_data:
if (locked)
unlock_buffer(bh);
journal_remove_journal_head(bh);
- /* Once for our safety reference, once for
+ /* One for our safety reference, other for
* journal_remove_journal_head() */
put_bh(bh);
- put_bh(bh);
+ release_data_buffer(bh);
}
if (need_resched() || spin_needbreak(&journal->j_list_lock)) {
@@ -443,7 +456,7 @@ void journal_commit_transaction(journal_t *journal)
} else {
jbd_unlock_bh_state(bh);
}
- put_bh(bh);
+ release_data_buffer(bh);
cond_resched_lock(&journal->j_list_lock);
}
spin_unlock(&journal->j_list_lock);
@@ -453,8 +466,6 @@ void journal_commit_transaction(journal_t *journal)
journal_write_revoke_records(journal, commit_transaction);
- jbd_debug(3, "JBD: commit phase 2\n");
-
/*
* If we found any dirty or locked buffers, then we should have
* looped back up to the write_out_data label. If there weren't