2006-01-17 00:50:04 +08:00
|
|
|
/*
|
|
|
|
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
|
2006-05-19 03:09:15 +08:00
|
|
|
* Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
|
|
|
* This copyrighted material is made available to anyone wishing to use,
|
|
|
|
* modify, copy, or redistribute it subject to the terms and conditions
|
2006-09-01 23:05:15 +08:00
|
|
|
* of the GNU General Public License version 2.
|
2006-01-17 00:50:04 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/completion.h>
|
|
|
|
#include <linux/buffer_head.h>
|
2006-03-30 03:36:49 +08:00
|
|
|
#include <linux/kallsyms.h>
|
2009-01-12 18:43:39 +08:00
|
|
|
#include <linux/gfs2_ondisk.h>
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
#include "gfs2.h"
|
2006-02-28 06:23:27 +08:00
|
|
|
#include "incore.h"
|
2006-01-17 00:50:04 +08:00
|
|
|
#include "glock.h"
|
2012-12-14 20:52:14 +08:00
|
|
|
#include "inode.h"
|
2006-01-17 00:50:04 +08:00
|
|
|
#include "log.h"
|
|
|
|
#include "lops.h"
|
|
|
|
#include "meta_io.h"
|
|
|
|
#include "trans.h"
|
2006-02-28 06:23:27 +08:00
|
|
|
#include "util.h"
|
GFS2: Various gfs2_logd improvements
This patch contains various tweaks to how log flushes and active item writeback
work. gfs2_logd is now managed by a waitqueue, and gfs2_log_reseve now waits
for gfs2_logd to do the log flushing. Multiple functions were rewritten to
remove the need to call gfs2_log_lock(). Instead of using one test to see if
gfs2_logd had work to do, there are now seperate tests to check if there
are two many buffers in the incore log or if there are two many items on the
active items list.
This patch is a port of a patch Steve Whitehouse wrote about a year ago, with
some minor changes. Since gfs2_ail1_start always submits all the active items,
it no longer needs to keep track of the first ai submitted, so this has been
removed. In gfs2_log_reserve(), the order of the calls to
prepare_to_wait_exclusive() and wake_up() when firing off the logd thread has
been switched. If it called wake_up first there was a small window for a race,
where logd could run and return before gfs2_log_reserve was ready to get woken
up. If gfs2_logd ran, but did not free up enough blocks, gfs2_log_reserve()
would be left waiting for gfs2_logd to eventualy run because it timed out.
Finally, gt_logd_secs, which controls how long to wait before gfs2_logd times
out, and flushes the log, can now be set on mount with ar_commit.
Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2010-05-05 03:29:16 +08:00
|
|
|
#include "trace_gfs2.h"
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2006-03-30 03:36:49 +08:00
|
|
|
int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
|
|
|
|
unsigned int revokes)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
|
|
|
struct gfs2_trans *tr;
|
|
|
|
int error;
|
|
|
|
|
2006-03-30 03:36:49 +08:00
|
|
|
BUG_ON(current->journal_info);
|
|
|
|
BUG_ON(blocks == 0 && revokes == 0);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2009-05-13 17:56:52 +08:00
|
|
|
if (!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))
|
|
|
|
return -EROFS;
|
|
|
|
|
2006-02-21 20:51:39 +08:00
|
|
|
tr = kzalloc(sizeof(struct gfs2_trans), GFP_NOFS);
|
2006-01-17 00:50:04 +08:00
|
|
|
if (!tr)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2006-03-30 03:36:49 +08:00
|
|
|
tr->tr_ip = (unsigned long)__builtin_return_address(0);
|
2006-01-17 00:50:04 +08:00
|
|
|
tr->tr_blocks = blocks;
|
|
|
|
tr->tr_revokes = revokes;
|
|
|
|
tr->tr_reserved = 1;
|
|
|
|
if (blocks)
|
2006-04-12 02:49:06 +08:00
|
|
|
tr->tr_reserved += 6 + blocks;
|
2006-01-17 00:50:04 +08:00
|
|
|
if (revokes)
|
|
|
|
tr->tr_reserved += gfs2_struct2blk(sdp, revokes,
|
2006-09-05 00:49:07 +08:00
|
|
|
sizeof(u64));
|
2012-06-12 22:20:41 +08:00
|
|
|
sb_start_intwrite(sdp->sd_vfs);
|
2006-04-27 02:58:26 +08:00
|
|
|
gfs2_holder_init(sdp->sd_trans_gl, LM_ST_SHARED, 0, &tr->tr_t_gh);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2006-03-02 00:39:37 +08:00
|
|
|
error = gfs2_glock_nq(&tr->tr_t_gh);
|
2006-01-17 00:50:04 +08:00
|
|
|
if (error)
|
2006-03-02 00:39:37 +08:00
|
|
|
goto fail_holder_uninit;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
error = gfs2_log_reserve(sdp, tr->tr_reserved);
|
|
|
|
if (error)
|
|
|
|
goto fail_gunlock;
|
|
|
|
|
2006-02-28 06:23:27 +08:00
|
|
|
current->journal_info = tr;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
2006-03-29 22:12:12 +08:00
|
|
|
fail_gunlock:
|
2006-03-02 00:39:37 +08:00
|
|
|
gfs2_glock_dq(&tr->tr_t_gh);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2006-03-29 22:12:12 +08:00
|
|
|
fail_holder_uninit:
|
2012-06-12 22:20:41 +08:00
|
|
|
sb_end_intwrite(sdp->sd_vfs);
|
2006-03-02 00:39:37 +08:00
|
|
|
gfs2_holder_uninit(&tr->tr_t_gh);
|
2006-01-17 00:50:04 +08:00
|
|
|
kfree(tr);
|
|
|
|
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
GFS2: Various gfs2_logd improvements
This patch contains various tweaks to how log flushes and active item writeback
work. gfs2_logd is now managed by a waitqueue, and gfs2_log_reseve now waits
for gfs2_logd to do the log flushing. Multiple functions were rewritten to
remove the need to call gfs2_log_lock(). Instead of using one test to see if
gfs2_logd had work to do, there are now seperate tests to check if there
are two many buffers in the incore log or if there are two many items on the
active items list.
This patch is a port of a patch Steve Whitehouse wrote about a year ago, with
some minor changes. Since gfs2_ail1_start always submits all the active items,
it no longer needs to keep track of the first ai submitted, so this has been
removed. In gfs2_log_reserve(), the order of the calls to
prepare_to_wait_exclusive() and wake_up() when firing off the logd thread has
been switched. If it called wake_up first there was a small window for a race,
where logd could run and return before gfs2_log_reserve was ready to get woken
up. If gfs2_logd ran, but did not free up enough blocks, gfs2_log_reserve()
would be left waiting for gfs2_logd to eventualy run because it timed out.
Finally, gt_logd_secs, which controls how long to wait before gfs2_logd times
out, and flushes the log, can now be set on mount with ar_commit.
Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2010-05-05 03:29:16 +08:00
|
|
|
/**
|
|
|
|
* gfs2_log_release - Release a given number of log blocks
|
|
|
|
* @sdp: The GFS2 superblock
|
|
|
|
* @blks: The number of blocks
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
|
|
|
static void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
|
|
|
|
{
|
|
|
|
|
|
|
|
atomic_add(blks, &sdp->sd_log_blks_free);
|
|
|
|
trace_gfs2_log_blocks(sdp, blks);
|
|
|
|
gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
|
|
|
|
sdp->sd_jdesc->jd_blocks);
|
|
|
|
up_read(&sdp->sd_log_flush_lock);
|
|
|
|
}
|
|
|
|
|
2012-04-16 23:40:56 +08:00
|
|
|
static void gfs2_print_trans(const struct gfs2_trans *tr)
|
|
|
|
{
|
|
|
|
print_symbol(KERN_WARNING "GFS2: Transaction created at: %s\n", tr->tr_ip);
|
|
|
|
printk(KERN_WARNING "GFS2: blocks=%u revokes=%u reserved=%u touched=%d\n",
|
|
|
|
tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched);
|
|
|
|
printk(KERN_WARNING "GFS2: Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
|
|
|
|
tr->tr_num_buf_new, tr->tr_num_buf_rm,
|
|
|
|
tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
|
|
|
|
tr->tr_num_revoke, tr->tr_num_revoke_rm);
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
void gfs2_trans_end(struct gfs2_sbd *sdp)
|
|
|
|
{
|
2006-04-12 02:49:06 +08:00
|
|
|
struct gfs2_trans *tr = current->journal_info;
|
2012-04-16 23:40:56 +08:00
|
|
|
s64 nbuf;
|
2006-04-12 02:49:06 +08:00
|
|
|
BUG_ON(!tr);
|
2006-02-28 06:23:27 +08:00
|
|
|
current->journal_info = NULL;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
if (!tr->tr_touched) {
|
|
|
|
gfs2_log_release(sdp, tr->tr_reserved);
|
2009-02-05 18:12:38 +08:00
|
|
|
if (tr->tr_t_gh.gh_gl) {
|
|
|
|
gfs2_glock_dq(&tr->tr_t_gh);
|
|
|
|
gfs2_holder_uninit(&tr->tr_t_gh);
|
|
|
|
kfree(tr);
|
|
|
|
}
|
2012-06-12 22:20:41 +08:00
|
|
|
sb_end_intwrite(sdp->sd_vfs);
|
2006-01-17 00:50:04 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2012-04-16 23:40:56 +08:00
|
|
|
nbuf = tr->tr_num_buf_new + tr->tr_num_databuf_new;
|
|
|
|
nbuf -= tr->tr_num_buf_rm;
|
|
|
|
nbuf -= tr->tr_num_databuf_rm;
|
|
|
|
|
|
|
|
if (gfs2_assert_withdraw(sdp, (nbuf <= tr->tr_blocks) &&
|
|
|
|
(tr->tr_num_revoke <= tr->tr_revokes)))
|
|
|
|
gfs2_print_trans(tr);
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
gfs2_log_commit(sdp, tr);
|
2009-02-05 18:12:38 +08:00
|
|
|
if (tr->tr_t_gh.gh_gl) {
|
|
|
|
gfs2_glock_dq(&tr->tr_t_gh);
|
|
|
|
gfs2_holder_uninit(&tr->tr_t_gh);
|
|
|
|
kfree(tr);
|
|
|
|
}
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
|
2006-04-07 23:17:32 +08:00
|
|
|
gfs2_log_flush(sdp, NULL);
|
2012-06-12 22:20:41 +08:00
|
|
|
sb_end_intwrite(sdp->sd_vfs);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
2012-12-15 01:54:21 +08:00
|
|
|
static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl,
|
|
|
|
struct buffer_head *bh,
|
|
|
|
const struct gfs2_log_operations *lops)
|
|
|
|
{
|
|
|
|
struct gfs2_bufdata *bd;
|
|
|
|
|
|
|
|
bd = kmem_cache_zalloc(gfs2_bufdata_cachep, GFP_NOFS | __GFP_NOFAIL);
|
|
|
|
bd->bd_bh = bh;
|
|
|
|
bd->bd_gl = gl;
|
|
|
|
bd->bd_ops = lops;
|
|
|
|
INIT_LIST_HEAD(&bd->bd_list);
|
|
|
|
bh->b_private = bd;
|
|
|
|
return bd;
|
|
|
|
}
|
|
|
|
|
2006-01-17 00:50:04 +08:00
|
|
|
/**
|
2013-01-28 17:30:07 +08:00
|
|
|
* gfs2_trans_add_data - Add a databuf to the transaction.
|
|
|
|
* @gl: The inode glock associated with the buffer
|
|
|
|
* @bh: The buffer to add
|
2006-01-17 00:50:04 +08:00
|
|
|
*
|
2012-12-14 20:52:14 +08:00
|
|
|
* This is used in two distinct cases:
|
|
|
|
* i) In ordered write mode
|
|
|
|
* We put the data buffer on a list so that we can ensure that its
|
|
|
|
* synced to disk at the right time
|
|
|
|
* ii) In journaled data mode
|
|
|
|
* We need to journal the data block in the same way as metadata in
|
|
|
|
* the functions above. The difference is that here we have a tag
|
|
|
|
* which is two __be64's being the block number (as per meta data)
|
|
|
|
* and a flag which says whether the data block needs escaping or
|
|
|
|
* not. This means we need a new log entry for each 251 or so data
|
|
|
|
* blocks, which isn't an enormous overhead but twice as much as
|
|
|
|
* for normal metadata blocks.
|
2006-01-17 00:50:04 +08:00
|
|
|
*/
|
2013-01-28 17:30:07 +08:00
|
|
|
void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
|
2012-12-14 20:52:14 +08:00
|
|
|
{
|
|
|
|
struct gfs2_trans *tr = current->journal_info;
|
2013-01-28 17:30:07 +08:00
|
|
|
struct gfs2_sbd *sdp = gl->gl_sbd;
|
|
|
|
struct address_space *mapping = bh->b_page->mapping;
|
2012-12-14 20:52:14 +08:00
|
|
|
struct gfs2_inode *ip = GFS2_I(mapping->host);
|
2013-01-28 17:30:07 +08:00
|
|
|
struct gfs2_bufdata *bd;
|
2012-12-14 20:52:14 +08:00
|
|
|
|
2013-01-28 17:30:07 +08:00
|
|
|
if (!gfs2_is_jdata(ip)) {
|
|
|
|
gfs2_ordered_add_inode(ip);
|
2012-12-14 20:52:14 +08:00
|
|
|
return;
|
|
|
|
}
|
2006-01-17 00:50:04 +08:00
|
|
|
|
2012-11-07 14:38:06 +08:00
|
|
|
lock_buffer(bh);
|
|
|
|
gfs2_log_lock(sdp);
|
2006-02-28 06:23:27 +08:00
|
|
|
bd = bh->b_private;
|
2012-12-15 01:54:21 +08:00
|
|
|
if (bd == NULL) {
|
2012-11-07 14:38:06 +08:00
|
|
|
gfs2_log_unlock(sdp);
|
|
|
|
unlock_buffer(bh);
|
2012-12-15 01:54:21 +08:00
|
|
|
if (bh->b_private == NULL)
|
|
|
|
bd = gfs2_alloc_bufdata(gl, bh, &gfs2_databuf_lops);
|
2012-11-07 14:38:06 +08:00
|
|
|
lock_buffer(bh);
|
|
|
|
gfs2_log_lock(sdp);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
2012-12-15 01:54:21 +08:00
|
|
|
gfs2_assert(sdp, bd->bd_gl == gl);
|
2013-01-28 17:30:07 +08:00
|
|
|
tr->tr_touched = 1;
|
|
|
|
if (list_empty(&bd->bd_list)) {
|
|
|
|
set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
|
|
|
|
set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
|
|
|
|
gfs2_pin(sdp, bd->bd_bh);
|
|
|
|
tr->tr_num_databuf_new++;
|
|
|
|
sdp->sd_log_num_databuf++;
|
|
|
|
list_add_tail(&bd->bd_list, &sdp->sd_log_le_databuf);
|
|
|
|
}
|
2012-11-07 14:38:06 +08:00
|
|
|
gfs2_log_unlock(sdp);
|
|
|
|
unlock_buffer(bh);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
2012-12-14 20:52:14 +08:00
|
|
|
static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
|
2012-12-14 20:36:02 +08:00
|
|
|
{
|
2012-12-14 20:52:14 +08:00
|
|
|
struct gfs2_meta_header *mh;
|
|
|
|
struct gfs2_trans *tr;
|
|
|
|
|
|
|
|
tr = current->journal_info;
|
|
|
|
tr->tr_touched = 1;
|
|
|
|
if (!list_empty(&bd->bd_list))
|
|
|
|
return;
|
|
|
|
set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
|
|
|
|
set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
|
|
|
|
mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
|
|
|
|
if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
|
|
|
|
printk(KERN_ERR
|
|
|
|
"Attempting to add uninitialised block to journal (inplace block=%lld)\n",
|
|
|
|
(unsigned long long)bd->bd_bh->b_blocknr);
|
|
|
|
BUG();
|
|
|
|
}
|
|
|
|
gfs2_pin(sdp, bd->bd_bh);
|
|
|
|
mh->__pad0 = cpu_to_be64(0);
|
|
|
|
mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
|
|
|
|
sdp->sd_log_num_buf++;
|
|
|
|
list_add(&bd->bd_list, &sdp->sd_log_le_buf);
|
|
|
|
tr->tr_num_buf_new++;
|
2012-12-14 20:36:02 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
|
|
|
|
{
|
2012-12-14 20:52:14 +08:00
|
|
|
|
|
|
|
struct gfs2_sbd *sdp = gl->gl_sbd;
|
|
|
|
struct gfs2_bufdata *bd;
|
|
|
|
|
|
|
|
lock_buffer(bh);
|
|
|
|
gfs2_log_lock(sdp);
|
|
|
|
bd = bh->b_private;
|
2012-12-15 01:54:21 +08:00
|
|
|
if (bd == NULL) {
|
2012-12-14 20:52:14 +08:00
|
|
|
gfs2_log_unlock(sdp);
|
|
|
|
unlock_buffer(bh);
|
2012-12-15 01:54:21 +08:00
|
|
|
lock_page(bh->b_page);
|
|
|
|
if (bh->b_private == NULL)
|
|
|
|
bd = gfs2_alloc_bufdata(gl, bh, &gfs2_buf_lops);
|
|
|
|
unlock_page(bh->b_page);
|
2012-12-14 20:52:14 +08:00
|
|
|
lock_buffer(bh);
|
|
|
|
gfs2_log_lock(sdp);
|
|
|
|
}
|
2012-12-15 01:54:21 +08:00
|
|
|
gfs2_assert(sdp, bd->bd_gl == gl);
|
2012-12-14 20:52:14 +08:00
|
|
|
meta_lo_add(sdp, bd);
|
|
|
|
gfs2_log_unlock(sdp);
|
|
|
|
unlock_buffer(bh);
|
2012-12-14 20:36:02 +08:00
|
|
|
}
|
|
|
|
|
2007-09-03 18:01:33 +08:00
|
|
|
void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
2012-12-14 20:29:56 +08:00
|
|
|
struct gfs2_glock *gl = bd->bd_gl;
|
|
|
|
struct gfs2_trans *tr = current->journal_info;
|
|
|
|
|
2012-05-02 00:00:34 +08:00
|
|
|
BUG_ON(!list_empty(&bd->bd_list));
|
2007-09-03 18:01:33 +08:00
|
|
|
BUG_ON(!list_empty(&bd->bd_ail_st_list));
|
|
|
|
BUG_ON(!list_empty(&bd->bd_ail_gl_list));
|
2012-12-15 01:54:21 +08:00
|
|
|
bd->bd_ops = &gfs2_revoke_lops;
|
2012-12-14 20:29:56 +08:00
|
|
|
tr->tr_touched = 1;
|
|
|
|
tr->tr_num_revoke++;
|
|
|
|
sdp->sd_log_num_revoke++;
|
|
|
|
atomic_inc(&gl->gl_revokes);
|
|
|
|
set_bit(GLF_LFLUSH, &gl->gl_flags);
|
|
|
|
list_add(&bd->bd_list, &sdp->sd_log_le_revoke);
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
|
2008-02-01 21:16:55 +08:00
|
|
|
void gfs2_trans_add_unrevoke(struct gfs2_sbd *sdp, u64 blkno, unsigned int len)
|
2006-01-17 00:50:04 +08:00
|
|
|
{
|
2008-02-01 21:16:55 +08:00
|
|
|
struct gfs2_bufdata *bd, *tmp;
|
|
|
|
struct gfs2_trans *tr = current->journal_info;
|
|
|
|
unsigned int n = len;
|
2006-01-17 00:50:04 +08:00
|
|
|
|
|
|
|
gfs2_log_lock(sdp);
|
2012-05-02 00:00:34 +08:00
|
|
|
list_for_each_entry_safe(bd, tmp, &sdp->sd_log_le_revoke, bd_list) {
|
2008-02-01 21:16:55 +08:00
|
|
|
if ((bd->bd_blkno >= blkno) && (bd->bd_blkno < (blkno + len))) {
|
2012-05-02 00:00:34 +08:00
|
|
|
list_del_init(&bd->bd_list);
|
2006-01-17 00:50:04 +08:00
|
|
|
gfs2_assert_withdraw(sdp, sdp->sd_log_num_revoke);
|
|
|
|
sdp->sd_log_num_revoke--;
|
2008-02-01 21:16:55 +08:00
|
|
|
kmem_cache_free(gfs2_bufdata_cachep, bd);
|
|
|
|
tr->tr_num_revoke_rm++;
|
|
|
|
if (--n == 0)
|
|
|
|
break;
|
2006-01-17 00:50:04 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
gfs2_log_unlock(sdp);
|
|
|
|
}
|
|
|
|
|