#include <linux/crc32.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <trace/events/jbd2.h>
/*
* Default IO end handler for temporary BJ_IO buffer_heads.
goto nope;
/* OK, it's a truncated page */
- if (TestSetPageLocked(page))
+ if (!trylock_page(page))
goto nope;
page_cache_get(page);
JBUFFER_TRACE(descriptor, "submit commit block");
lock_buffer(bh);
- get_bh(bh);
- set_buffer_dirty(bh);
+ clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = journal_end_buffer_io_sync;
if (journal->j_flags & JBD2_BARRIER &&
- !JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+ !JBD2_HAS_INCOMPAT_FEATURE(journal,
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
set_buffer_ordered(bh);
barrier_done = 1;
}
- ret = submit_bh(WRITE, bh);
+ ret = submit_bh(WRITE_SYNC_PLUG, bh);
if (barrier_done)
clear_buffer_ordered(bh);
* to remember if we sent a barrier request
*/
if (ret == -EOPNOTSUPP && barrier_done) {
- char b[BDEVNAME_SIZE];
-
printk(KERN_WARNING
- "JBD: barrier-based sync failed on %s - "
- "disabling barriers\n",
- bdevname(journal->j_dev, b));
+ "JBD: barrier-based sync failed on %s - "
+ "disabling barriers\n", journal->j_devname);
spin_lock(&journal->j_state_lock);
journal->j_flags &= ~JBD2_BARRIER;
spin_unlock(&journal->j_state_lock);
/* And try again, without the barrier */
lock_buffer(bh);
set_buffer_uptodate(bh);
- set_buffer_dirty(bh);
- ret = submit_bh(WRITE, bh);
+ clear_buffer_dirty(bh);
+ ret = submit_bh(WRITE_SYNC_PLUG, bh);
}
*cbh = bh;
return ret;
* This function along with journal_submit_commit_record
* allows to write the commit record asynchronously.
*/
-static int journal_wait_on_commit_record(struct buffer_head *bh)
+static int journal_wait_on_commit_record(journal_t *journal,
+ struct buffer_head *bh)
{
int ret = 0;
+retry:
clear_buffer_dirty(bh);
wait_on_buffer(bh);
+ if (buffer_eopnotsupp(bh) && (journal->j_flags & JBD2_BARRIER)) {
+ printk(KERN_WARNING
+ "JBD2: wait_on_commit_record: sync failed on %s - "
+ "disabling barriers\n", journal->j_devname);
+ spin_lock(&journal->j_state_lock);
+ journal->j_flags &= ~JBD2_BARRIER;
+ spin_unlock(&journal->j_state_lock);
+
+ lock_buffer(bh);
+ clear_buffer_dirty(bh);
+ set_buffer_uptodate(bh);
+ bh->b_end_io = journal_end_buffer_io_sync;
+
+ ret = submit_bh(WRITE_SYNC_PLUG, bh);
+ if (ret) {
+ unlock_buffer(bh);
+ return ret;
+ }
+ goto retry;
+ }
if (unlikely(!buffer_uptodate(bh)))
ret = -EIO;
.nr_to_write = mapping->nrpages * 2,
.range_start = 0,
.range_end = i_size_read(mapping->host),
- .for_writepages = 1,
};
ret = generic_writepages(mapping, &wbc);
* block allocation with delalloc. We need to write
* only allocated blocks here.
*/
+ trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
err = journal_submit_inode_data_buffers(mapping);
if (!ret)
ret = err;
spin_lock(&journal->j_list_lock);
J_ASSERT(jinode->i_transaction == commit_transaction);
+ commit_transaction->t_flushed_data_blocks = 1;
jinode->i_flags &= ~JI_COMMIT_RUNNING;
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}
jinode->i_flags |= JI_COMMIT_RUNNING;
spin_unlock(&journal->j_list_lock);
err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
- if (!ret)
- ret = err;
+ if (err) {
+ /*
+ * Because AS_EIO is cleared by
+ * filemap_fdatawait_range(), set it again so
+ * that user process can get -EIO from fsync().
+ */
+ set_bit(AS_EIO,
+ &jinode->i_vfs_inode->i_mapping->flags);
+
+ if (!ret)
+ ret = err;
+ }
spin_lock(&journal->j_list_lock);
jinode->i_flags &= ~JI_COMMIT_RUNNING;
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
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;
int space_left = 0;
int first_tag = 0;
int tag_flag;
- int i;
+ int i, to_free = 0;
int tag_bytes = journal_tag_bytes(journal);
struct buffer_head *cbh = NULL; /* For transactional checksums */
__u32 crc32_sum = ~0;
+ int write_op = WRITE;
/*
* First job: lock down the current transaction and wait for
commit_transaction = journal->j_running_transaction;
J_ASSERT(commit_transaction->t_state == T_RUNNING);
+ trace_jbd2_start_commit(journal, commit_transaction);
jbd_debug(1, "JBD: starting commit of transaction %d\n",
commit_transaction->t_tid);
spin_lock(&journal->j_state_lock);
commit_transaction->t_state = T_LOCKED;
- stats.u.run.rs_wait = commit_transaction->t_max_wait;
- stats.u.run.rs_locked = jiffies;
- stats.u.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
- stats.u.run.rs_locked);
+ /*
+ * Use plugged writes here, since we want to submit several before
+ * we unplug the device. We don't do explicit unplugging in here,
+ * instead we rely on sync_buffer() doing the unplug for us.
+ */
+ if (commit_transaction->t_synchronous_commit)
+ write_op = WRITE_SYNC_PLUG;
+ trace_jbd2_commit_locking(journal, commit_transaction);
+ stats.run.rs_wait = commit_transaction->t_max_wait;
+ stats.run.rs_locked = jiffies;
+ stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start,
+ stats.run.rs_locked);
spin_lock(&commit_transaction->t_handle_lock);
while (commit_transaction->t_updates) {
*/
jbd2_journal_switch_revoke_table(journal);
- stats.u.run.rs_flushing = jiffies;
- stats.u.run.rs_locked = jbd2_time_diff(stats.u.run.rs_locked,
- stats.u.run.rs_flushing);
+ trace_jbd2_commit_flushing(journal, commit_transaction);
+ stats.run.rs_flushing = jiffies;
+ stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked,
+ stats.run.rs_flushing);
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);
if (err)
jbd2_journal_abort(journal, err);
- jbd2_journal_write_revoke_records(journal, commit_transaction);
+ jbd2_journal_write_revoke_records(journal, commit_transaction,
+ write_op);
jbd_debug(3, "JBD: commit phase 2\n");
commit_transaction->t_state = T_COMMIT;
spin_unlock(&journal->j_state_lock);
- stats.u.run.rs_logging = jiffies;
- stats.u.run.rs_flushing = jbd2_time_diff(stats.u.run.rs_flushing,
- stats.u.run.rs_logging);
- stats.u.run.rs_blocks = commit_transaction->t_outstanding_credits;
- stats.u.run.rs_blocks_logged = 0;
+ trace_jbd2_commit_logging(journal, commit_transaction);
+ stats.run.rs_logging = jiffies;
+ stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing,
+ stats.run.rs_logging);
+ stats.run.rs_blocks = commit_transaction->t_outstanding_credits;
+ stats.run.rs_blocks_logged = 0;
J_ASSERT(commit_transaction->t_nr_buffers <=
commit_transaction->t_outstanding_credits);
jh = commit_transaction->t_buffers;
/* If we're in abort mode, we just un-journal the buffer and
- release it for background writing. */
+ release it. */
if (is_journal_aborted(journal)) {
+ clear_buffer_jbddirty(jh2bh(jh));
JBUFFER_TRACE(jh, "journal is aborting: refile");
+ jbd2_buffer_abort_trigger(jh,
+ jh->b_frozen_data ?
+ jh->b_frozen_triggers :
+ jh->b_triggers);
jbd2_journal_refile_buffer(journal, jh);
/* If that was the last one, we need to clean up
* any descriptor buffers which may have been
JBUFFER_TRACE(jh, "ph3: write metadata");
flags = jbd2_journal_write_metadata_buffer(commit_transaction,
jh, &new_jh, blocknr);
+ if (flags < 0) {
+ jbd2_journal_abort(journal, flags);
+ continue;
+ }
set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
wbuf[bufs++] = jh2bh(new_jh);
clear_buffer_dirty(bh);
set_buffer_uptodate(bh);
bh->b_end_io = journal_end_buffer_io_sync;
- submit_bh(WRITE, bh);
+ submit_bh(write_op, bh);
}
cond_resched();
- stats.u.run.rs_blocks_logged += bufs;
+ stats.run.rs_blocks_logged += bufs;
/* Force a new descriptor to be generated next
time round the loop. */
}
}
- /* Done it all: now write the commit record asynchronously. */
+ /*
+ * If the journal is not located on the file system device,
+ * then we must flush the file system device before we issue
+ * the commit record
+ */
+ if (commit_transaction->t_flushed_data_blocks &&
+ (journal->j_fs_dev != journal->j_dev) &&
+ (journal->j_flags & JBD2_BARRIER))
+ blkdev_issue_flush(journal->j_fs_dev, NULL);
+ /* Done it all: now write the commit record asynchronously. */
if (JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
__jbd2_journal_abort_hard(journal);
+ if (journal->j_flags & JBD2_BARRIER)
+ blkdev_issue_flush(journal->j_dev, NULL);
}
- /*
- * This is the right place to wait for data buffers both for ASYNC
- * and !ASYNC commit. If commit is ASYNC, we need to wait only after
- * the commit block went to disk (which happens above). If commit is
- * SYNC, we need to wait for data buffers before we start writing
- * commit block, which happens below in such setting.
- */
err = journal_finish_inode_data_buffers(journal, commit_transaction);
- if (err)
- jbd2_journal_abort(journal, err);
+ if (err) {
+ printk(KERN_WARNING
+ "JBD2: Detected IO errors while flushing file data "
+ "on %s\n", journal->j_devname);
+ if (journal->j_flags & JBD2_ABORT_ON_SYNCDATA_ERR)
+ jbd2_journal_abort(journal, err);
+ err = 0;
+ }
/* Lo and behold: we have just managed to send a transaction to
the log. Before we can commit it, wait for the IO so far to
/* AKPM: bforget here */
}
+ if (err)
+ jbd2_journal_abort(journal, err);
+
jbd_debug(3, "JBD: commit phase 5\n");
if (!JBD2_HAS_INCOMPAT_FEATURE(journal,
- JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
+ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) {
err = journal_submit_commit_record(journal, commit_transaction,
&cbh, crc32_sum);
if (err)
__jbd2_journal_abort_hard(journal);
}
if (!err && !is_journal_aborted(journal))
- err = journal_wait_on_commit_record(cbh);
+ err = journal_wait_on_commit_record(journal, cbh);
if (err)
jbd2_journal_abort(journal, err);
spin_unlock(&journal->j_list_lock);
bh = jh2bh(jh);
jbd_lock_bh_state(bh);
- J_ASSERT_JH(jh, jh->b_transaction == commit_transaction ||
- jh->b_transaction == journal->j_running_transaction);
+ J_ASSERT_JH(jh, jh->b_transaction == commit_transaction);
/*
* If there is undo-protected committed data against
* data.
*
* Otherwise, we can just throw away the frozen data now.
+ *
+ * We also know that the frozen data has already fired
+ * its triggers if they exist, so we can clear that too.
*/
if (jh->b_committed_data) {
jbd2_free(jh->b_committed_data, bh->b_size);
if (jh->b_frozen_data) {
jh->b_committed_data = jh->b_frozen_data;
jh->b_frozen_data = NULL;
+ jh->b_frozen_triggers = NULL;
}
} else if (jh->b_frozen_data) {
jbd2_free(jh->b_frozen_data, bh->b_size);
jh->b_frozen_data = NULL;
+ jh->b_frozen_triggers = NULL;
}
spin_lock(&journal->j_list_lock);
/* A buffer which has been freed while still being
* journaled by a previous transaction may end up still
* being dirty here, but we want to avoid writing back
- * that buffer in the future now that the last use has
- * been committed. That's not only a performance gain,
- * it also stops aliasing problems if the buffer is left
- * behind for writeback and gets reallocated for another
+ * that buffer in the future after the "add to orphan"
+ * operation been committed, That's not only a performance
+ * gain, it also stops aliasing problems if the buffer is
+ * left behind for writeback and gets reallocated for another
* use in a different page. */
- if (buffer_freed(bh)) {
+ if (buffer_freed(bh) && !jh->b_next_transaction) {
clear_buffer_freed(bh);
clear_buffer_jbddirty(bh);
}
if (buffer_jbddirty(bh)) {
JBUFFER_TRACE(jh, "add to new checkpointing trans");
__jbd2_journal_insert_checkpoint(jh, commit_transaction);
+ if (is_journal_aborted(journal))
+ clear_buffer_jbddirty(bh);
JBUFFER_TRACE(jh, "refile for checkpoint writeback");
__jbd2_journal_refile_buffer(jh);
jbd_unlock_bh_state(bh);
J_ASSERT(commit_transaction->t_state == T_COMMIT);
commit_transaction->t_start = jiffies;
- stats.u.run.rs_logging = jbd2_time_diff(stats.u.run.rs_logging,
- commit_transaction->t_start);
+ stats.run.rs_logging = jbd2_time_diff(stats.run.rs_logging,
+ commit_transaction->t_start);
/*
- * File the transaction for history
+ * File the transaction statistics
*/
- stats.ts_type = JBD2_STATS_RUN;
stats.ts_tid = commit_transaction->t_tid;
- stats.u.run.rs_handle_count = commit_transaction->t_handle_count;
- spin_lock(&journal->j_history_lock);
- memcpy(journal->j_history + journal->j_history_cur, &stats,
- sizeof(stats));
- if (++journal->j_history_cur == journal->j_history_max)
- journal->j_history_cur = 0;
+ stats.run.rs_handle_count = commit_transaction->t_handle_count;
+ trace_jbd2_run_stats(journal->j_fs_dev->bd_dev,
+ commit_transaction->t_tid, &stats.run);
/*
* Calculate overall stats
*/
+ spin_lock(&journal->j_history_lock);
journal->j_stats.ts_tid++;
- journal->j_stats.u.run.rs_wait += stats.u.run.rs_wait;
- journal->j_stats.u.run.rs_running += stats.u.run.rs_running;
- journal->j_stats.u.run.rs_locked += stats.u.run.rs_locked;
- journal->j_stats.u.run.rs_flushing += stats.u.run.rs_flushing;
- journal->j_stats.u.run.rs_logging += stats.u.run.rs_logging;
- journal->j_stats.u.run.rs_handle_count += stats.u.run.rs_handle_count;
- journal->j_stats.u.run.rs_blocks += stats.u.run.rs_blocks;
- journal->j_stats.u.run.rs_blocks_logged += stats.u.run.rs_blocks_logged;
+ journal->j_stats.run.rs_wait += stats.run.rs_wait;
+ journal->j_stats.run.rs_running += stats.run.rs_running;
+ journal->j_stats.run.rs_locked += stats.run.rs_locked;
+ journal->j_stats.run.rs_flushing += stats.run.rs_flushing;
+ journal->j_stats.run.rs_logging += stats.run.rs_logging;
+ journal->j_stats.run.rs_handle_count += stats.run.rs_handle_count;
+ journal->j_stats.run.rs_blocks += stats.run.rs_blocks;
+ journal->j_stats.run.rs_blocks_logged += stats.run.rs_blocks_logged;
spin_unlock(&journal->j_history_lock);
commit_transaction->t_state = T_FINISHED;
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 (commit_transaction->t_checkpoint_list == NULL &&
commit_transaction->t_checkpoint_io_list == NULL) {
__jbd2_journal_drop_transaction(journal, commit_transaction);
+ to_free = 1;
} else {
if (journal->j_checkpoint_transactions == NULL) {
journal->j_checkpoint_transactions = commit_transaction;
}
spin_unlock(&journal->j_list_lock);
+ if (journal->j_commit_callback)
+ journal->j_commit_callback(journal, commit_transaction);
+
+ trace_jbd2_end_commit(journal, commit_transaction);
jbd_debug(1, "JBD: commit %d complete, head %d\n",
journal->j_commit_sequence, journal->j_tail_sequence);
+ if (to_free)
+ kfree(commit_transaction);
wake_up(&journal->j_wait_done_commit);
}