ocfs2: Switch over to JBD2.

ocfs2 wants JBD2 for many reasons, not the least of which is that JBD is
limiting our maximum filesystem size.

It's a pretty trivial change.  Most functions are just renamed.  The
only functional change is moving to Jan's inode-based ordered data mode.
It's better, too.

Because JBD2 reads and writes JBD journals, this is compatible with any
existing filesystem.  It can even interact with JBD-based ocfs2 as long
as the journal is formated for JBD.

We provide a compatibility option so that paranoid people can still use
JBD for the time being.  This will go away shortly.

[ Moved call of ocfs2_begin_ordered_truncate() from ocfs2_delete_inode() to
  ocfs2_truncate_for_delete(). --Mark ]

Signed-off-by: Joel Becker <joel.becker@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>
This commit is contained in:
Joel Becker
2008-09-03 20:03:41 -07:00
committed by Mark Fasheh
parent 12462f1d9f
commit 2b4e30fbde
12 changed files with 224 additions and 81 deletions

View File

@@ -6421,20 +6421,13 @@ bail:
return status;
}
static int ocfs2_writeback_zero_func(handle_t *handle, struct buffer_head *bh)
static int ocfs2_zero_func(handle_t *handle, struct buffer_head *bh)
{
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
return 0;
}
static int ocfs2_ordered_zero_func(handle_t *handle, struct buffer_head *bh)
{
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
return ocfs2_journal_dirty_data(handle, bh);
}
static void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
unsigned int from, unsigned int to,
struct page *page, int zero, u64 *phys)
@@ -6453,17 +6446,18 @@ static void ocfs2_map_and_dirty_page(struct inode *inode, handle_t *handle,
* here if they aren't - ocfs2_map_page_blocks()
* might've skipped some
*/
if (ocfs2_should_order_data(inode)) {
ret = walk_page_buffers(handle,
page_buffers(page),
from, to, &partial,
ocfs2_ordered_zero_func);
if (ret < 0)
mlog_errno(ret);
} else {
ret = walk_page_buffers(handle, page_buffers(page),
from, to, &partial,
ocfs2_zero_func);
if (ret < 0)
mlog_errno(ret);
else if (ocfs2_should_order_data(inode)) {
ret = ocfs2_jbd2_file_inode(handle, inode);
#ifdef CONFIG_OCFS2_COMPAT_JBD
ret = walk_page_buffers(handle, page_buffers(page),
from, to, &partial,
ocfs2_writeback_zero_func);
ocfs2_journal_dirty_data);
#endif
if (ret < 0)
mlog_errno(ret);
}

View File

@@ -485,11 +485,14 @@ handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
}
if (ocfs2_should_order_data(inode)) {
ret = ocfs2_jbd2_file_inode(handle, inode);
#ifdef CONFIG_OCFS2_COMPAT_JBD
ret = walk_page_buffers(handle,
page_buffers(page),
from, to, NULL,
ocfs2_journal_dirty_data);
if (ret < 0)
#endif
if (ret < 0)
mlog_errno(ret);
}
out:
@@ -669,7 +672,7 @@ static void ocfs2_invalidatepage(struct page *page, unsigned long offset)
{
journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal;
journal_invalidatepage(journal, page, offset);
jbd2_journal_invalidatepage(journal, page, offset);
}
static int ocfs2_releasepage(struct page *page, gfp_t wait)
@@ -678,7 +681,7 @@ static int ocfs2_releasepage(struct page *page, gfp_t wait)
if (!page_has_buffers(page))
return 0;
return journal_try_to_free_buffers(journal, page, wait);
return jbd2_journal_try_to_free_buffers(journal, page, wait);
}
static ssize_t ocfs2_direct_IO(int rw,
@@ -1074,11 +1077,15 @@ static void ocfs2_write_failure(struct inode *inode,
tmppage = wc->w_pages[i];
if (page_has_buffers(tmppage)) {
if (ocfs2_should_order_data(inode))
if (ocfs2_should_order_data(inode)) {
ocfs2_jbd2_file_inode(wc->w_handle, inode);
#ifdef CONFIG_OCFS2_COMPAT_JBD
walk_page_buffers(wc->w_handle,
page_buffers(tmppage),
from, to, NULL,
ocfs2_journal_dirty_data);
#endif
}
block_commit_write(tmppage, from, to);
}
@@ -1917,11 +1924,15 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
}
if (page_has_buffers(tmppage)) {
if (ocfs2_should_order_data(inode))
if (ocfs2_should_order_data(inode)) {
ocfs2_jbd2_file_inode(wc->w_handle, inode);
#ifdef CONFIG_OCFS2_COMPAT_JBD
walk_page_buffers(wc->w_handle,
page_buffers(tmppage),
from, to, NULL,
ocfs2_journal_dirty_data);
#endif
}
block_commit_write(tmppage, from, to);
}
}

View File

@@ -185,7 +185,7 @@ static int ocfs2_sync_file(struct file *file,
goto bail;
journal = osb->journal->j_journal;
err = journal_force_commit(journal);
err = jbd2_journal_force_commit(journal);
bail:
mlog_exit(err);
@@ -941,9 +941,15 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
goto bail_unlock;
}
if (i_size_read(inode) > attr->ia_size)
if (i_size_read(inode) > attr->ia_size) {
if (ocfs2_should_order_data(inode)) {
status = ocfs2_begin_ordered_truncate(inode,
attr->ia_size);
if (status)
goto bail_unlock;
}
status = ocfs2_truncate_file(inode, bh, attr->ia_size);
else
} else
status = ocfs2_extend_file(inode, bh, attr->ia_size);
if (status < 0) {
if (status != -ENOSPC)
@@ -1888,7 +1894,7 @@ out_dio:
*/
if (old_size != i_size_read(inode) ||
old_clusters != OCFS2_I(inode)->ip_clusters) {
ret = journal_force_commit(osb->journal->j_journal);
ret = jbd2_journal_force_commit(osb->journal->j_journal);
if (ret < 0)
written = ret;
}

View File

@@ -534,6 +534,9 @@ static int ocfs2_truncate_for_delete(struct ocfs2_super *osb,
* data and fast symlinks.
*/
if (fe->i_clusters) {
if (ocfs2_should_order_data(inode))
ocfs2_begin_ordered_truncate(inode, 0);
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
@@ -1100,6 +1103,8 @@ void ocfs2_clear_inode(struct inode *inode)
oi->ip_last_trans = 0;
oi->ip_dir_start_lookup = 0;
oi->ip_blkno = 0ULL;
jbd2_journal_release_jbd_inode(OCFS2_SB(inode->i_sb)->journal->j_journal,
&oi->ip_jinode);
bail:
mlog_exit_void();

View File

@@ -71,6 +71,7 @@ struct ocfs2_inode_info
struct ocfs2_extent_map ip_extent_map;
struct inode vfs_inode;
struct jbd2_inode ip_jinode;
};
/*

View File

@@ -215,9 +215,9 @@ static int ocfs2_commit_cache(struct ocfs2_super *osb)
goto finally;
}
journal_lock_updates(journal->j_journal);
status = journal_flush(journal->j_journal);
journal_unlock_updates(journal->j_journal);
jbd2_journal_lock_updates(journal->j_journal);
status = jbd2_journal_flush(journal->j_journal);
jbd2_journal_unlock_updates(journal->j_journal);
if (status < 0) {
up_write(&journal->j_trans_barrier);
mlog_errno(status);
@@ -264,7 +264,7 @@ handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
down_read(&osb->journal->j_trans_barrier);
handle = journal_start(journal, max_buffs);
handle = jbd2_journal_start(journal, max_buffs);
if (IS_ERR(handle)) {
up_read(&osb->journal->j_trans_barrier);
@@ -290,7 +290,7 @@ int ocfs2_commit_trans(struct ocfs2_super *osb,
BUG_ON(!handle);
ret = journal_stop(handle);
ret = jbd2_journal_stop(handle);
if (ret < 0)
mlog_errno(ret);
@@ -304,7 +304,7 @@ int ocfs2_commit_trans(struct ocfs2_super *osb,
* transaction. extend_trans will either extend the current handle by
* nblocks, or commit it and start a new one with nblocks credits.
*
* This might call journal_restart() which will commit dirty buffers
* This might call jbd2_journal_restart() which will commit dirty buffers
* and then restart the transaction. Before calling
* ocfs2_extend_trans(), any changed blocks should have been
* dirtied. After calling it, all blocks which need to be changed must
@@ -332,7 +332,7 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks)
#ifdef CONFIG_OCFS2_DEBUG_FS
status = 1;
#else
status = journal_extend(handle, nblocks);
status = jbd2_journal_extend(handle, nblocks);
if (status < 0) {
mlog_errno(status);
goto bail;
@@ -340,8 +340,10 @@ int ocfs2_extend_trans(handle_t *handle, int nblocks)
#endif
if (status > 0) {
mlog(0, "journal_extend failed, trying journal_restart\n");
status = journal_restart(handle, nblocks);
mlog(0,
"jbd2_journal_extend failed, trying "
"jbd2_journal_restart\n");
status = jbd2_journal_restart(handle, nblocks);
if (status < 0) {
mlog_errno(status);
goto bail;
@@ -393,11 +395,11 @@ int ocfs2_journal_access(handle_t *handle,
switch (type) {
case OCFS2_JOURNAL_ACCESS_CREATE:
case OCFS2_JOURNAL_ACCESS_WRITE:
status = journal_get_write_access(handle, bh);
status = jbd2_journal_get_write_access(handle, bh);
break;
case OCFS2_JOURNAL_ACCESS_UNDO:
status = journal_get_undo_access(handle, bh);
status = jbd2_journal_get_undo_access(handle, bh);
break;
default:
@@ -422,7 +424,7 @@ int ocfs2_journal_dirty(handle_t *handle,
mlog_entry("(bh->b_blocknr=%llu)\n",
(unsigned long long)bh->b_blocknr);
status = journal_dirty_metadata(handle, bh);
status = jbd2_journal_dirty_metadata(handle, bh);
if (status < 0)
mlog(ML_ERROR, "Could not dirty metadata buffer. "
"(bh->b_blocknr=%llu)\n",
@@ -432,6 +434,7 @@ int ocfs2_journal_dirty(handle_t *handle,
return status;
}
#ifdef CONFIG_OCFS2_COMPAT_JBD
int ocfs2_journal_dirty_data(handle_t *handle,
struct buffer_head *bh)
{
@@ -443,8 +446,9 @@ int ocfs2_journal_dirty_data(handle_t *handle,
return err;
}
#endif
#define OCFS2_DEFAULT_COMMIT_INTERVAL (HZ * JBD_DEFAULT_MAX_COMMIT_AGE)
#define OCFS2_DEFAULT_COMMIT_INTERVAL (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE)
void ocfs2_set_journal_params(struct ocfs2_super *osb)
{
@@ -457,9 +461,9 @@ void ocfs2_set_journal_params(struct ocfs2_super *osb)
spin_lock(&journal->j_state_lock);
journal->j_commit_interval = commit_interval;
if (osb->s_mount_opt & OCFS2_MOUNT_BARRIER)
journal->j_flags |= JFS_BARRIER;
journal->j_flags |= JBD2_BARRIER;
else
journal->j_flags &= ~JFS_BARRIER;
journal->j_flags &= ~JBD2_BARRIER;
spin_unlock(&journal->j_state_lock);
}
@@ -524,14 +528,14 @@ int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
mlog(0, "inode->ip_clusters = %u\n", OCFS2_I(inode)->ip_clusters);
/* call the kernels journal init function now */
j_journal = journal_init_inode(inode);
j_journal = jbd2_journal_init_inode(inode);
if (j_journal == NULL) {
mlog(ML_ERROR, "Linux journal layer error\n");
status = -EINVAL;
goto done;
}
mlog(0, "Returned from journal_init_inode\n");
mlog(0, "Returned from jbd2_journal_init_inode\n");
mlog(0, "j_journal->j_maxlen = %u\n", j_journal->j_maxlen);
*dirty = (le32_to_cpu(di->id1.journal1.ij_flags) &
@@ -639,7 +643,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
if (journal->j_state != OCFS2_JOURNAL_LOADED)
goto done;
/* need to inc inode use count as journal_destroy will iput. */
/* need to inc inode use count - jbd2_journal_destroy will iput. */
if (!igrab(inode))
BUG();
@@ -668,9 +672,9 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
BUG_ON(atomic_read(&(osb->journal->j_num_trans)) != 0);
if (ocfs2_mount_local(osb)) {
journal_lock_updates(journal->j_journal);
status = journal_flush(journal->j_journal);
journal_unlock_updates(journal->j_journal);
jbd2_journal_lock_updates(journal->j_journal);
status = jbd2_journal_flush(journal->j_journal);
jbd2_journal_unlock_updates(journal->j_journal);
if (status < 0)
mlog_errno(status);
}
@@ -686,7 +690,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
}
/* Shutdown the kernel journal system */
journal_destroy(journal->j_journal);
jbd2_journal_destroy(journal->j_journal);
OCFS2_I(inode)->ip_open_count--;
@@ -711,15 +715,15 @@ static void ocfs2_clear_journal_error(struct super_block *sb,
{
int olderr;
olderr = journal_errno(journal);
olderr = jbd2_journal_errno(journal);
if (olderr) {
mlog(ML_ERROR, "File system error %d recorded in "
"journal %u.\n", olderr, slot);
mlog(ML_ERROR, "File system on device %s needs checking.\n",
sb->s_id);
journal_ack_err(journal);
journal_clear_err(journal);
jbd2_journal_ack_err(journal);
jbd2_journal_clear_err(journal);
}
}
@@ -734,7 +738,7 @@ int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
osb = journal->j_osb;
status = journal_load(journal->j_journal);
status = jbd2_journal_load(journal->j_journal);
if (status < 0) {
mlog(ML_ERROR, "Failed to load journal!\n");
goto done;
@@ -778,7 +782,7 @@ int ocfs2_journal_wipe(struct ocfs2_journal *journal, int full)
BUG_ON(!journal);
status = journal_wipe(journal->j_journal, full);
status = jbd2_journal_wipe(journal->j_journal, full);
if (status < 0) {
mlog_errno(status);
goto bail;
@@ -1229,19 +1233,19 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
}
mlog(0, "calling journal_init_inode\n");
journal = journal_init_inode(inode);
journal = jbd2_journal_init_inode(inode);
if (journal == NULL) {
mlog(ML_ERROR, "Linux journal layer error\n");
status = -EIO;
goto done;
}
status = journal_load(journal);
status = jbd2_journal_load(journal);
if (status < 0) {
mlog_errno(status);
if (!igrab(inode))
BUG();
journal_destroy(journal);
jbd2_journal_destroy(journal);
goto done;
}
@@ -1249,9 +1253,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
/* wipe the journal */
mlog(0, "flushing the journal.\n");
journal_lock_updates(journal);
status = journal_flush(journal);
journal_unlock_updates(journal);
jbd2_journal_lock_updates(journal);
status = jbd2_journal_flush(journal);
jbd2_journal_unlock_updates(journal);
if (status < 0)
mlog_errno(status);
@@ -1272,7 +1276,7 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
if (!igrab(inode))
BUG();
journal_destroy(journal);
jbd2_journal_destroy(journal);
done:
/* drop the lock on this nodes journal */

View File

@@ -27,7 +27,12 @@
#define OCFS2_JOURNAL_H
#include <linux/fs.h>
#include <linux/jbd.h>
#ifndef CONFIG_OCFS2_COMPAT_JBD
# include <linux/jbd2.h>
#else
# include <linux/jbd.h>
# include "ocfs2_jbd_compat.h"
#endif
enum ocfs2_journal_state {
OCFS2_JOURNAL_FREE = 0,
@@ -215,8 +220,8 @@ static inline void ocfs2_checkpoint_inode(struct inode *inode)
* buffer. Will have to call ocfs2_journal_dirty once
* we've actually dirtied it. Type is one of . or .
* ocfs2_journal_dirty - Mark a journalled buffer as having dirty data.
* ocfs2_journal_dirty_data - Indicate that a data buffer should go out before
* the current handle commits.
* ocfs2_jbd2_file_inode - Mark an inode so that its data goes out before
* the current handle commits.
*/
/* You must always start_trans with a number of buffs > 0, but it's
@@ -268,8 +273,10 @@ int ocfs2_journal_access(handle_t *handle,
*/
int ocfs2_journal_dirty(handle_t *handle,
struct buffer_head *bh);
#ifdef CONFIG_OCFS2_COMPAT_JBD
int ocfs2_journal_dirty_data(handle_t *handle,
struct buffer_head *bh);
#endif
/*
* Credit Macros:
@@ -430,4 +437,16 @@ static inline int ocfs2_calc_tree_trunc_credits(struct super_block *sb,
return credits;
}
static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
{
return jbd2_journal_file_inode(handle, &OCFS2_I(inode)->ip_jinode);
}
static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
loff_t new_size)
{
return jbd2_journal_begin_ordered_truncate(&OCFS2_I(inode)->ip_jinode,
new_size);
}
#endif /* OCFS2_JOURNAL_H */

View File

@@ -34,7 +34,12 @@
#include <linux/workqueue.h>
#include <linux/kref.h>
#include <linux/mutex.h>
#include <linux/jbd.h>
#ifndef CONFIG_OCFS2_COMPAT_JBD
# include <linux/jbd2.h>
#else
# include <linux/jbd.h>
# include "ocfs2_jbd_compat.h"
#endif
/* For union ocfs2_dlm_lksb */
#include "stackglue.h"

View File

@@ -0,0 +1,82 @@
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* ocfs2_jbd_compat.h
*
* Compatibility defines for JBD.
*
* Copyright (C) 2008 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License version 2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*/
#ifndef OCFS2_JBD_COMPAT_H
#define OCFS2_JBD_COMPAT_H
#ifndef CONFIG_OCFS2_COMPAT_JBD
# error Should not have been included
#endif
struct jbd2_inode {
unsigned int dummy;
};
#define JBD2_BARRIER JFS_BARRIER
#define JBD2_DEFAULT_MAX_COMMIT_AGE JBD_DEFAULT_MAX_COMMIT_AGE
#define jbd2_journal_ack_err journal_ack_err
#define jbd2_journal_clear_err journal_clear_err
#define jbd2_journal_destroy journal_destroy
#define jbd2_journal_dirty_metadata journal_dirty_metadata
#define jbd2_journal_errno journal_errno
#define jbd2_journal_extend journal_extend
#define jbd2_journal_flush journal_flush
#define jbd2_journal_force_commit journal_force_commit
#define jbd2_journal_get_write_access journal_get_write_access
#define jbd2_journal_get_undo_access journal_get_undo_access
#define jbd2_journal_init_inode journal_init_inode
#define jbd2_journal_invalidatepage journal_invalidatepage
#define jbd2_journal_load journal_load
#define jbd2_journal_lock_updates journal_lock_updates
#define jbd2_journal_restart journal_restart
#define jbd2_journal_start journal_start
#define jbd2_journal_start_commit journal_start_commit
#define jbd2_journal_stop journal_stop
#define jbd2_journal_try_to_free_buffers journal_try_to_free_buffers
#define jbd2_journal_unlock_updates journal_unlock_updates
#define jbd2_journal_wipe journal_wipe
#define jbd2_log_wait_commit log_wait_commit
static inline int jbd2_journal_file_inode(handle_t *handle,
struct jbd2_inode *inode)
{
return 0;
}
static inline int jbd2_journal_begin_ordered_truncate(struct jbd2_inode *inode,
loff_t new_size)
{
return 0;
}
static inline void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode,
struct inode *inode)
{
return;
}
static inline void jbd2_journal_release_jbd_inode(journal_t *journal,
struct jbd2_inode *jinode)
{
return;
}
#endif /* OCFS2_JBD_COMPAT_H */

View File

@@ -212,10 +212,11 @@ static int ocfs2_sync_fs(struct super_block *sb, int wait)
ocfs2_schedule_truncate_log_flush(osb, 0);
}
if (journal_start_commit(OCFS2_SB(sb)->journal->j_journal, &target)) {
if (jbd2_journal_start_commit(OCFS2_SB(sb)->journal->j_journal,
&target)) {
if (wait)
log_wait_commit(OCFS2_SB(sb)->journal->j_journal,
target);
jbd2_log_wait_commit(OCFS2_SB(sb)->journal->j_journal,
target);
}
return 0;
}
@@ -332,6 +333,7 @@ static struct inode *ocfs2_alloc_inode(struct super_block *sb)
if (!oi)
return NULL;
jbd2_journal_init_jbd_inode(&oi->ip_jinode, &oi->vfs_inode);
return &oi->vfs_inode;
}
@@ -896,7 +898,7 @@ static int ocfs2_parse_options(struct super_block *sb,
if (option < 0)
return 0;
if (option == 0)
option = JBD_DEFAULT_MAX_COMMIT_AGE;
option = JBD2_DEFAULT_MAX_COMMIT_AGE;
mopt->commit_interval = HZ * option;
break;
case Opt_localalloc:

View File

@@ -53,7 +53,11 @@
#include <linux/highmem.h>
#include <linux/buffer_head.h>
#include <linux/rbtree.h>
#include <linux/jbd.h>
#ifndef CONFIG_OCFS2_COMPAT_JBD
# include <linux/jbd2.h>
#else
# include <linux/jbd.h>
#endif
#define MLOG_MASK_PREFIX ML_UPTODATE