jbd: fix the way the b_modified flag is cleared

commit 5bc833feaa8b2236265764e7e81f44937be46eda upstream

Currently at the start of a journal commit we loop through all of the buffers
on the committing transaction and clear the b_modified flag (the flag that is
set when a transaction modifies the buffer) under the j_list_lock.

The problem is that everywhere else this flag is modified only under the jbd
lock buffer flag, so it will race with a running transaction who could
potentially set it, and have it unset by the committing transaction.

This is also a big waste, you can have several thousands of buffers that you
are clearing the modified flag on when you may not need to.  This patch
removes this code and instead clears the b_modified flag upon entering
do_get_write_access/journal_get_create_access, so if that transaction does
indeed use the buffer then it will be accounted for properly, and if it does
not then we know we didn't use it.

That will be important for the next patch in this series.  Tested thoroughly
by myself using postmark/iozone/bonnie++.

Signed-off-by: Josef Bacik <jbacik@redhat.com>
Cc: <linux-ext4@vger.kernel.org>
Acked-by: Jan Kara <jack@ucw.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index a38c7186c5704e438236994baa18014b4bacb801..d2f652e6e22ee5be9b0e37b4686c142b7da3863e 100644 (file)
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -406,22 +406,6 @@ void journal_commit_transaction(journal_t *journal)
 
        jbd_debug (3, "JBD: commit phase 2\n");
 
-       /*
-        * First, drop modified flag: all accesses to the buffers
-        * will be tracked for a new trasaction only -bzzz
-        */
-       spin_lock(&journal->j_list_lock);
-       if (commit_transaction->t_buffers) {
-               new_jh = jh = commit_transaction->t_buffers->b_tnext;
-               do {
-                       J_ASSERT_JH(new_jh, new_jh->b_modified == 1 ||
-                                       new_jh->b_modified == 0);
-                       new_jh->b_modified = 0;
-                       new_jh = new_jh->b_tnext;
-               } while (new_jh != jh);
-       }
-       spin_unlock(&journal->j_list_lock);
-
        /*
         * Now start flushing things to disk, in the order they appear
         * on the transaction lists.  Data blocks go first.

diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index 2c9e8f5d13aae3505fce91eb78fe69396efb9aea..2e9670e2237e96650ba3d41f0e817b870e5bbb80 100644 (file)
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -608,6 +608,12 @@ repeat:
            jh->b_next_transaction == transaction)
                goto done;
 
+       /*
+        * this is the first time this transaction is touching this buffer,
+        * reset the modified flag
+        */
+       jh->b_modified = 0;
+
        /*
         * If there is already a copy-out version of this buffer, then we don't
         * need to make another one
@@ -820,9 +826,16 @@ int journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 
        if (jh->b_transaction == NULL) {
                jh->b_transaction = transaction;
+
+               /* first access by this transaction */
+               jh->b_modified = 0;
+
                JBUFFER_TRACE(jh, "file as BJ_Reserved");
                __journal_file_buffer(jh, transaction, BJ_Reserved);
        } else if (jh->b_transaction == journal->j_committing_transaction) {
+               /* first access by this transaction */
+               jh->b_modified = 0;
+
                JBUFFER_TRACE(jh, "set next transaction");
                jh->b_next_transaction = transaction;
        }