linux-sg2042/fs/gfs2/log.c

951 lines
25 KiB
C
Raw Normal View History

/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
* Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
* of the GNU General Public License version 2.
*/
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include <linux/list_sort.h>
#include "gfs2.h"
#include "incore.h"
#include "bmap.h"
#include "glock.h"
#include "log.h"
#include "lops.h"
#include "meta_io.h"
#include "util.h"
#include "dir.h"
#include "trace_gfs2.h"
/**
* gfs2_struct2blk - compute stuff
* @sdp: the filesystem
* @nstruct: the number of structures
* @ssize: the size of the structures
*
* Compute the number of log descriptor blocks needed to hold a certain number
* of structures of a certain size.
*
* Returns: the number of blocks needed (minimum is always 1)
*/
unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
unsigned int ssize)
{
unsigned int blks;
unsigned int first, second;
blks = 1;
first = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / ssize;
if (nstruct > first) {
second = (sdp->sd_sb.sb_bsize -
sizeof(struct gfs2_meta_header)) / ssize;
blks += DIV_ROUND_UP(nstruct - first, second);
}
return blks;
}
/**
* gfs2_remove_from_ail - Remove an entry from the ail lists, updating counters
* @mapping: The associated mapping (maybe NULL)
* @bd: The gfs2_bufdata to remove
*
* The ail lock _must_ be held when calling this function
*
*/
void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
{
bd->bd_tr = NULL;
list_del_init(&bd->bd_ail_st_list);
list_del_init(&bd->bd_ail_gl_list);
atomic_dec(&bd->bd_gl->gl_ail_count);
brelse(bd->bd_bh);
}
/**
* gfs2_ail1_start_one - Start I/O on a part of the AIL
* @sdp: the filesystem
* @wbc: The writeback control structure
* @ai: The ail structure
*
*/
static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
struct writeback_control *wbc,
struct gfs2_trans *tr)
__releases(&sdp->sd_ail_lock)
__acquires(&sdp->sd_ail_lock)
{
struct gfs2_glock *gl = NULL;
struct address_space *mapping;
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list, bd_ail_st_list) {
bh = bd->bd_bh;
gfs2_assert(sdp, bd->bd_tr == tr);
if (!buffer_busy(bh)) {
if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
continue;
}
if (!buffer_dirty(bh))
continue;
if (gl == bd->bd_gl)
continue;
gl = bd->bd_gl;
list_move(&bd->bd_ail_st_list, &tr->tr_ail1_list);
mapping = bh->b_page->mapping;
if (!mapping)
continue;
spin_unlock(&sdp->sd_ail_lock);
generic_writepages(mapping, wbc);
spin_lock(&sdp->sd_ail_lock);
if (wbc->nr_to_write <= 0)
break;
return 1;
}
return 0;
}
/**
* gfs2_ail1_flush - start writeback of some ail1 entries
* @sdp: The super block
* @wbc: The writeback control structure
*
* Writes back some ail1 entries, according to the limits in the
* writeback control structure
*/
void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
{
struct list_head *head = &sdp->sd_ail1_list;
struct gfs2_trans *tr;
struct blk_plug plug;
trace_gfs2_ail_flush(sdp, wbc, 1);
blk_start_plug(&plug);
spin_lock(&sdp->sd_ail_lock);
restart:
list_for_each_entry_reverse(tr, head, tr_list) {
if (wbc->nr_to_write <= 0)
break;
if (gfs2_ail1_start_one(sdp, wbc, tr))
goto restart;
}
spin_unlock(&sdp->sd_ail_lock);
blk_finish_plug(&plug);
trace_gfs2_ail_flush(sdp, wbc, 0);
}
/**
* gfs2_ail1_start - start writeback of all ail1 entries
* @sdp: The superblock
*/
static void gfs2_ail1_start(struct gfs2_sbd *sdp)
{
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = LONG_MAX,
.range_start = 0,
.range_end = LLONG_MAX,
};
return gfs2_ail1_flush(sdp, &wbc);
}
/**
* gfs2_ail1_empty_one - Check whether or not a trans in the AIL has been synced
* @sdp: the filesystem
* @ai: the AIL entry
*
*/
static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
list_for_each_entry_safe_reverse(bd, s, &tr->tr_ail1_list,
bd_ail_st_list) {
bh = bd->bd_bh;
gfs2_assert(sdp, bd->bd_tr == tr);
if (buffer_busy(bh))
continue;
if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
}
}
/**
* gfs2_ail1_empty - Try to empty the ail1 lists
* @sdp: The superblock
*
* Tries to empty the ail1 lists, starting with the oldest first
*/
static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
{
struct gfs2_trans *tr, *s;
int oldest_tr = 1;
int ret;
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
gfs2_ail1_empty_one(sdp, tr);
if (list_empty(&tr->tr_ail1_list) && oldest_tr)
list_move(&tr->tr_list, &sdp->sd_ail2_list);
else
oldest_tr = 0;
}
ret = list_empty(&sdp->sd_ail1_list);
spin_unlock(&sdp->sd_ail_lock);
return ret;
}
static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
{
struct gfs2_trans *tr;
struct gfs2_bufdata *bd;
struct buffer_head *bh;
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_reverse(tr, &sdp->sd_ail1_list, tr_list) {
list_for_each_entry(bd, &tr->tr_ail1_list, bd_ail_st_list) {
bh = bd->bd_bh;
if (!buffer_locked(bh))
continue;
get_bh(bh);
spin_unlock(&sdp->sd_ail_lock);
wait_on_buffer(bh);
brelse(bh);
return;
}
}
spin_unlock(&sdp->sd_ail_lock);
}
/**
* gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
* @sdp: the filesystem
* @ai: the AIL entry
*
*/
static void gfs2_ail2_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
struct list_head *head = &tr->tr_ail2_list;
struct gfs2_bufdata *bd;
while (!list_empty(head)) {
bd = list_entry(head->prev, struct gfs2_bufdata,
bd_ail_st_list);
gfs2_assert(sdp, bd->bd_tr == tr);
gfs2_remove_from_ail(bd);
}
}
static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
{
struct gfs2_trans *tr, *safe;
unsigned int old_tail = sdp->sd_log_tail;
int wrap = (new_tail < old_tail);
int a, b, rm;
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_safe(tr, safe, &sdp->sd_ail2_list, tr_list) {
a = (old_tail <= tr->tr_first);
b = (tr->tr_first < new_tail);
rm = (wrap) ? (a || b) : (a && b);
if (!rm)
continue;
gfs2_ail2_empty_one(sdp, tr);
list_del(&tr->tr_list);
gfs2_assert_warn(sdp, list_empty(&tr->tr_ail1_list));
gfs2_assert_warn(sdp, list_empty(&tr->tr_ail2_list));
kfree(tr);
}
spin_unlock(&sdp->sd_ail_lock);
}
GFS2: remove transaction glock GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-02 11:26:55 +08:00
/**
* gfs2_log_release - Release a given number of log blocks
* @sdp: The GFS2 superblock
* @blks: The number of blocks
*
*/
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);
}
/**
* gfs2_log_reserve - Make a log reservation
* @sdp: The GFS2 superblock
* @blks: The number of blocks to reserve
*
* Note that we never give out the last few blocks of the journal. Thats
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
* due to the fact that there is a small number of header blocks
* associated with each log flush. The exact number can't be known until
* flush time, so we ensure that we have just enough free blocks at all
* times to avoid running out during a log flush.
*
* We no longer flush the log here, instead we wake up logd to do that
* for us. To avoid the thundering herd and to ensure that we deal fairly
* with queued waiters, we use an exclusive wait. This means that when we
* get woken with enough journal space to get our reservation, we need to
* wake the next waiter on the list.
*
* Returns: errno
*/
int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
{
int ret = 0;
unsigned reserved_blks = 7 * (4096 / sdp->sd_vfs->s_blocksize);
unsigned wanted = blks + reserved_blks;
DEFINE_WAIT(wait);
int did_wait = 0;
unsigned int free_blocks;
if (gfs2_assert_warn(sdp, blks) ||
gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
return -EINVAL;
retry:
free_blocks = atomic_read(&sdp->sd_log_blks_free);
if (unlikely(free_blocks <= wanted)) {
do {
prepare_to_wait_exclusive(&sdp->sd_log_waitq, &wait,
TASK_UNINTERRUPTIBLE);
wake_up(&sdp->sd_logd_waitq);
did_wait = 1;
if (atomic_read(&sdp->sd_log_blks_free) <= wanted)
io_schedule();
free_blocks = atomic_read(&sdp->sd_log_blks_free);
} while(free_blocks <= wanted);
finish_wait(&sdp->sd_log_waitq, &wait);
}
atomic_inc(&sdp->sd_reserving_log);
if (atomic_cmpxchg(&sdp->sd_log_blks_free, free_blocks,
free_blocks - blks) != free_blocks) {
if (atomic_dec_and_test(&sdp->sd_reserving_log))
wake_up(&sdp->sd_reserving_log_wait);
goto retry;
}
trace_gfs2_log_blocks(sdp, -blks);
/*
* If we waited, then so might others, wake them up _after_ we get
* our share of the log.
*/
if (unlikely(did_wait))
wake_up(&sdp->sd_log_waitq);
down_read(&sdp->sd_log_flush_lock);
GFS2: remove transaction glock GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-02 11:26:55 +08:00
if (unlikely(!test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags))) {
gfs2_log_release(sdp, blks);
ret = -EROFS;
GFS2: remove transaction glock GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-02 11:26:55 +08:00
}
if (atomic_dec_and_test(&sdp->sd_reserving_log))
wake_up(&sdp->sd_reserving_log_wait);
return ret;
}
/**
* log_distance - Compute distance between two journal blocks
* @sdp: The GFS2 superblock
* @newer: The most recent journal block of the pair
* @older: The older journal block of the pair
*
* Compute the distance (in the journal direction) between two
* blocks in the journal
*
* Returns: the distance in blocks
*/
static inline unsigned int log_distance(struct gfs2_sbd *sdp, unsigned int newer,
unsigned int older)
{
int dist;
dist = newer - older;
if (dist < 0)
dist += sdp->sd_jdesc->jd_blocks;
return dist;
}
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
/**
* calc_reserved - Calculate the number of blocks to reserve when
* refunding a transaction's unused buffers.
* @sdp: The GFS2 superblock
*
* This is complex. We need to reserve room for all our currently used
* metadata buffers (e.g. normal file I/O rewriting file time stamps) and
* all our journaled data buffers for journaled files (e.g. files in the
* meta_fs like rindex, or files for which chattr +j was done.)
* If we don't reserve enough space, gfs2_log_refund and gfs2_log_flush
* will count it as free space (sd_log_blks_free) and corruption will follow.
*
* We can have metadata bufs and jdata bufs in the same journal. So each
* type gets its own log header, for which we need to reserve a block.
* In fact, each type has the potential for needing more than one header
* in cases where we have more buffers than will fit on a journal page.
* Metadata journal entries take up half the space of journaled buffer entries.
* Thus, metadata entries have buf_limit (502) and journaled buffers have
* databuf_limit (251) before they cause a wrap around.
*
* Also, we need to reserve blocks for revoke journal entries and one for an
* overall header for the lot.
*
* Returns: the number of blocks reserved
*/
static unsigned int calc_reserved(struct gfs2_sbd *sdp)
{
unsigned int reserved = 0;
unsigned int mbuf;
unsigned int dbuf;
struct gfs2_trans *tr = sdp->sd_log_tr;
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
if (tr) {
mbuf = tr->tr_num_buf_new - tr->tr_num_buf_rm;
dbuf = tr->tr_num_databuf_new - tr->tr_num_databuf_rm;
reserved = mbuf + dbuf;
/* Account for header blocks */
reserved += DIV_ROUND_UP(mbuf, buf_limit(sdp));
reserved += DIV_ROUND_UP(dbuf, databuf_limit(sdp));
}
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
if (sdp->sd_log_commited_revoke > 0)
reserved += gfs2_struct2blk(sdp, sdp->sd_log_commited_revoke,
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
sizeof(u64));
/* One for the overall header */
if (reserved)
reserved++;
return reserved;
}
static unsigned int current_tail(struct gfs2_sbd *sdp)
{
struct gfs2_trans *tr;
unsigned int tail;
spin_lock(&sdp->sd_ail_lock);
if (list_empty(&sdp->sd_ail1_list)) {
tail = sdp->sd_log_head;
} else {
tr = list_entry(sdp->sd_ail1_list.prev, struct gfs2_trans,
tr_list);
tail = tr->tr_first;
}
spin_unlock(&sdp->sd_ail_lock);
return tail;
}
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
{
unsigned int dist = log_distance(sdp, new_tail, sdp->sd_log_tail);
ail2_empty(sdp, new_tail);
atomic_add(dist, &sdp->sd_log_blks_free);
trace_gfs2_log_blocks(sdp, dist);
gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
sdp->sd_jdesc->jd_blocks);
sdp->sd_log_tail = new_tail;
}
static void log_flush_wait(struct gfs2_sbd *sdp)
{
DEFINE_WAIT(wait);
if (atomic_read(&sdp->sd_log_in_flight)) {
do {
prepare_to_wait(&sdp->sd_log_flush_wait, &wait,
TASK_UNINTERRUPTIBLE);
if (atomic_read(&sdp->sd_log_in_flight))
io_schedule();
} while(atomic_read(&sdp->sd_log_in_flight));
finish_wait(&sdp->sd_log_flush_wait, &wait);
}
}
static int ip_cmp(void *priv, struct list_head *a, struct list_head *b)
{
struct gfs2_inode *ipa, *ipb;
ipa = list_entry(a, struct gfs2_inode, i_ordered);
ipb = list_entry(b, struct gfs2_inode, i_ordered);
if (ipa->i_no_addr < ipb->i_no_addr)
return -1;
if (ipa->i_no_addr > ipb->i_no_addr)
return 1;
return 0;
}
static void gfs2_ordered_write(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip;
LIST_HEAD(written);
spin_lock(&sdp->sd_ordered_lock);
list_sort(NULL, &sdp->sd_log_le_ordered, &ip_cmp);
while (!list_empty(&sdp->sd_log_le_ordered)) {
ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
list_move(&ip->i_ordered, &written);
if (ip->i_inode.i_mapping->nrpages == 0)
continue;
spin_unlock(&sdp->sd_ordered_lock);
filemap_fdatawrite(ip->i_inode.i_mapping);
spin_lock(&sdp->sd_ordered_lock);
}
list_splice(&written, &sdp->sd_log_le_ordered);
spin_unlock(&sdp->sd_ordered_lock);
}
static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
{
struct gfs2_inode *ip;
spin_lock(&sdp->sd_ordered_lock);
while (!list_empty(&sdp->sd_log_le_ordered)) {
ip = list_entry(sdp->sd_log_le_ordered.next, struct gfs2_inode, i_ordered);
list_del(&ip->i_ordered);
WARN_ON(!test_and_clear_bit(GIF_ORDERED, &ip->i_flags));
if (ip->i_inode.i_mapping->nrpages == 0)
continue;
spin_unlock(&sdp->sd_ordered_lock);
filemap_fdatawait(ip->i_inode.i_mapping);
spin_lock(&sdp->sd_ordered_lock);
}
spin_unlock(&sdp->sd_ordered_lock);
}
void gfs2_ordered_del_inode(struct gfs2_inode *ip)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
spin_lock(&sdp->sd_ordered_lock);
if (test_and_clear_bit(GIF_ORDERED, &ip->i_flags))
list_del(&ip->i_ordered);
spin_unlock(&sdp->sd_ordered_lock);
}
void gfs2_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
{
struct buffer_head *bh = bd->bd_bh;
struct gfs2_glock *gl = bd->bd_gl;
bh->b_private = NULL;
bd->bd_blkno = bh->b_blocknr;
gfs2_remove_from_ail(bd); /* drops ref on bh */
bd->bd_bh = NULL;
bd->bd_ops = &gfs2_revoke_lops;
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);
}
void gfs2_write_revokes(struct gfs2_sbd *sdp)
{
struct gfs2_trans *tr;
struct gfs2_bufdata *bd, *tmp;
int have_revokes = 0;
int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
gfs2_ail1_empty(sdp);
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) {
list_for_each_entry(bd, &tr->tr_ail2_list, bd_ail_st_list) {
if (list_empty(&bd->bd_list)) {
have_revokes = 1;
goto done;
}
}
}
done:
spin_unlock(&sdp->sd_ail_lock);
if (have_revokes == 0)
return;
while (sdp->sd_log_num_revoke > max_revokes)
max_revokes += (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_meta_header)) / sizeof(u64);
max_revokes -= sdp->sd_log_num_revoke;
if (!sdp->sd_log_num_revoke) {
atomic_dec(&sdp->sd_log_blks_free);
/* If no blocks have been reserved, we need to also
* reserve a block for the header */
if (!sdp->sd_log_blks_reserved)
atomic_dec(&sdp->sd_log_blks_free);
}
gfs2_log_lock(sdp);
spin_lock(&sdp->sd_ail_lock);
list_for_each_entry(tr, &sdp->sd_ail1_list, tr_list) {
list_for_each_entry_safe(bd, tmp, &tr->tr_ail2_list, bd_ail_st_list) {
if (max_revokes == 0)
goto out_of_blocks;
if (!list_empty(&bd->bd_list))
continue;
gfs2_add_revoke(sdp, bd);
max_revokes--;
}
}
out_of_blocks:
spin_unlock(&sdp->sd_ail_lock);
gfs2_log_unlock(sdp);
if (!sdp->sd_log_num_revoke) {
atomic_inc(&sdp->sd_log_blks_free);
if (!sdp->sd_log_blks_reserved)
atomic_inc(&sdp->sd_log_blks_free);
}
}
/**
* log_write_header - Get and initialize a journal header buffer
* @sdp: The GFS2 superblock
*
* Returns: the initialized log buffer descriptor
*/
static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
{
struct gfs2_log_header *lh;
unsigned int tail;
u32 hash;
int rw = WRITE_FLUSH_FUA | REQ_META;
struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
lh = page_address(page);
clear_page(lh);
gfs2_assert_withdraw(sdp, (state != SFS_FROZEN));
tail = current_tail(sdp);
lh->lh_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
lh->lh_header.mh_type = cpu_to_be32(GFS2_METATYPE_LH);
lh->lh_header.__pad0 = cpu_to_be64(0);
lh->lh_header.mh_format = cpu_to_be32(GFS2_FORMAT_LH);
lh->lh_header.mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
lh->lh_sequence = cpu_to_be64(sdp->sd_log_sequence++);
lh->lh_flags = cpu_to_be32(flags);
lh->lh_tail = cpu_to_be32(tail);
lh->lh_blkno = cpu_to_be32(sdp->sd_log_flush_head);
hash = gfs2_disk_hash(page_address(page), sizeof(struct gfs2_log_header));
lh->lh_hash = cpu_to_be32(hash);
if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags)) {
gfs2_ordered_wait(sdp);
log_flush_wait(sdp);
rw = WRITE_SYNC | REQ_META | REQ_PRIO;
}
sdp->sd_log_idle = (tail == sdp->sd_log_flush_head);
gfs2_log_write_page(sdp, page);
gfs2_log_flush_bio(sdp, rw);
log_flush_wait(sdp);
if (sdp->sd_log_tail != tail)
log_pull_tail(sdp, tail);
}
/**
* gfs2_log_flush - flush incore transaction(s)
* @sdp: the filesystem
* @gl: The glock structure to flush. If NULL, flush the whole incore log
*
*/
GFS2: remove transaction glock GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-02 11:26:55 +08:00
void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
enum gfs2_flush_type type)
{
struct gfs2_trans *tr;
enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
down_write(&sdp->sd_log_flush_lock);
/* Log might have been flushed while we waited for the flush lock */
if (gl && !test_bit(GLF_LFLUSH, &gl->gl_flags)) {
up_write(&sdp->sd_log_flush_lock);
return;
}
trace_gfs2_log_flush(sdp, 1);
sdp->sd_log_flush_head = sdp->sd_log_head;
sdp->sd_log_flush_wrapped = 0;
tr = sdp->sd_log_tr;
if (tr) {
sdp->sd_log_tr = NULL;
INIT_LIST_HEAD(&tr->tr_ail1_list);
INIT_LIST_HEAD(&tr->tr_ail2_list);
tr->tr_first = sdp->sd_log_flush_head;
if (unlikely (state == SFS_FROZEN))
gfs2_assert_withdraw(sdp, !tr->tr_num_buf_new && !tr->tr_num_databuf_new);
}
if (unlikely(state == SFS_FROZEN))
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
gfs2_assert_withdraw(sdp,
sdp->sd_log_num_revoke == sdp->sd_log_commited_revoke);
gfs2_ordered_write(sdp);
lops_before_commit(sdp, tr);
gfs2_log_flush_bio(sdp, WRITE);
if (sdp->sd_log_head != sdp->sd_log_flush_head) {
log_flush_wait(sdp);
log_write_header(sdp, 0);
} else if (sdp->sd_log_tail != current_tail(sdp) && !sdp->sd_log_idle){
atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
trace_gfs2_log_blocks(sdp, -1);
log_write_header(sdp, 0);
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
}
lops_after_commit(sdp, tr);
gfs2_log_lock(sdp);
sdp->sd_log_head = sdp->sd_log_flush_head;
sdp->sd_log_blks_reserved = 0;
sdp->sd_log_commited_revoke = 0;
spin_lock(&sdp->sd_ail_lock);
if (tr && !list_empty(&tr->tr_ail1_list)) {
list_add(&tr->tr_list, &sdp->sd_ail1_list);
tr = NULL;
}
spin_unlock(&sdp->sd_ail_lock);
gfs2_log_unlock(sdp);
GFS2: remove transaction glock GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-02 11:26:55 +08:00
if (type != NORMAL_FLUSH) {
if (!sdp->sd_log_idle) {
for (;;) {
gfs2_ail1_start(sdp);
gfs2_ail1_wait(sdp);
if (gfs2_ail1_empty(sdp))
break;
}
atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
trace_gfs2_log_blocks(sdp, -1);
sdp->sd_log_flush_wrapped = 0;
log_write_header(sdp, 0);
sdp->sd_log_head = sdp->sd_log_flush_head;
}
if (type == SHUTDOWN_FLUSH || type == FREEZE_FLUSH)
gfs2_log_shutdown(sdp);
if (type == FREEZE_FLUSH)
atomic_set(&sdp->sd_freeze_state, SFS_FROZEN);
GFS2: remove transaction glock GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-02 11:26:55 +08:00
}
trace_gfs2_log_flush(sdp, 0);
up_write(&sdp->sd_log_flush_lock);
kfree(tr);
}
/**
* gfs2_merge_trans - Merge a new transaction into a cached transaction
* @old: Original transaction to be expanded
* @new: New transaction to be merged
*/
static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
{
WARN_ON_ONCE(old->tr_attached != 1);
old->tr_num_buf_new += new->tr_num_buf_new;
old->tr_num_databuf_new += new->tr_num_databuf_new;
old->tr_num_buf_rm += new->tr_num_buf_rm;
old->tr_num_databuf_rm += new->tr_num_databuf_rm;
old->tr_num_revoke += new->tr_num_revoke;
old->tr_num_revoke_rm += new->tr_num_revoke_rm;
list_splice_tail_init(&new->tr_databuf, &old->tr_databuf);
list_splice_tail_init(&new->tr_buf, &old->tr_buf);
}
static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
unsigned int reserved;
unsigned int unused;
unsigned int maxres;
gfs2_log_lock(sdp);
if (sdp->sd_log_tr) {
gfs2_merge_trans(sdp->sd_log_tr, tr);
} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
GFS2: remove transaction glock GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-02 11:26:55 +08:00
gfs2_assert_withdraw(sdp, tr->tr_alloced);
sdp->sd_log_tr = tr;
tr->tr_attached = 1;
}
sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
reserved = calc_reserved(sdp);
maxres = sdp->sd_log_blks_reserved + tr->tr_reserved;
gfs2_assert_withdraw(sdp, maxres >= reserved);
unused = maxres - reserved;
atomic_add(unused, &sdp->sd_log_blks_free);
trace_gfs2_log_blocks(sdp, unused);
gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
[GFS2] assertion failure after writing to journaled file, umount This patch passes all my nasty tests that were causing the code to fail under one circumstance or another. Here is a complete summary of all changes from today's git tree, in order of appearance: 1. There are now separate variables for metadata buffer accounting. 2. Variable sd_log_num_hdrs is no longer needed, since the header accounting is taken care of by the reserve/refund sequence. 3. Fixed a tiny grammatical problem in a comment. 4. Added a new function "calc_reserved" to calculate the reserved log space. This isn't entirely necessary, but it has two benefits: First, it simplifies the gfs2_log_refund function greatly. Second, it allows for easier debugging because I could sprinkle the code with calls to this function to make sure the accounting is proper (by adding asserts and printks) at strategic point of the code. 5. In log_pull_tail there apparently was a kludge to fix up the accounting based on a "pull" parameter. The buffer accounting is now done properly, so the kludge was removed. 6. File sync operations were making a call to gfs2_log_flush that writes another journal header. Since that header was unplanned for (reserved) by the reserve/refund sequence, the free space had to be decremented so that when log_pull_tail gets called, the free space is be adjusted properly. (Did I hear you call that a kludge? well, maybe, but a lot more justifiable than the one I removed). 7. In the gfs2_log_shutdown code, it optionally syncs the log by specifying the PULL parameter to log_write_header. I'm not sure this is necessary anymore. It just seems to me there could be cases where shutdown is called while there are outstanding log buffers. 8. In the (data)buf_lo_before_commit functions, I changed some offset values from being calculated on the fly to being constants. That simplified some code and we might as well let the compiler do the calculation once rather than redoing those cycles at run time. 9. This version has my rewritten databuf_lo_add function. This version is much more like its predecessor, buf_lo_add, which makes it easier to understand. Again, this might not be necessary, but it seems as if this one works as well as the previous one, maybe even better, so I decided to leave it in. 10. In databuf_lo_before_commit, a previous data corruption problem was caused by going off the end of the buffer. The proper solution is to have the proper limit in place, rather than stopping earlier. (Thus my previous attempt to fix it is wrong). If you don't wrap the buffer, you're stopping too early and that causes more log buffer accounting problems. 11. In lops.h there are two new (previously mentioned) constants for figuring out the data offset for the journal buffers. 12. There are also two new functions, buf_limit and databuf_limit to calculate how many entries will fit in the buffer. 13. In function gfs2_meta_wipe, it needs to distinguish between pinned metadata buffers and journaled data buffers for proper journal buffer accounting. It can't use the JDATA gfs2_inode flag because it's sometimes passed the "real" inode and sometimes the "metadata inode" and the inode flags will be random bits in a metadata gfs2_inode. It needs to base its decision on which was passed in. Signed-off-by: Bob Peterson <rpeterso@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2007-06-19 03:50:20 +08:00
sdp->sd_jdesc->jd_blocks);
sdp->sd_log_blks_reserved = reserved;
gfs2_log_unlock(sdp);
}
/**
* gfs2_log_commit - Commit a transaction to the log
* @sdp: the filesystem
* @tr: the transaction
*
* We wake up gfs2_logd if the number of pinned blocks exceed thresh1
* or the total number of used blocks (pinned blocks plus AIL blocks)
* is greater than thresh2.
*
* At mount time thresh1 is 1/3rd of journal size, thresh2 is 2/3rd of
* journal size.
*
* Returns: errno
*/
void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
{
log_refund(sdp, tr);
if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) ||
((sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free)) >
atomic_read(&sdp->sd_log_thresh2)))
wake_up(&sdp->sd_logd_waitq);
}
/**
* gfs2_log_shutdown - write a shutdown header into a journal
* @sdp: the filesystem
*
*/
void gfs2_log_shutdown(struct gfs2_sbd *sdp)
{
gfs2_assert_withdraw(sdp, !sdp->sd_log_blks_reserved);
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
sdp->sd_log_flush_head = sdp->sd_log_head;
sdp->sd_log_flush_wrapped = 0;
log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT);
gfs2_assert_warn(sdp, sdp->sd_log_head == sdp->sd_log_tail);
gfs2_assert_warn(sdp, list_empty(&sdp->sd_ail2_list));
sdp->sd_log_head = sdp->sd_log_flush_head;
sdp->sd_log_tail = sdp->sd_log_head;
}
static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
{
return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
}
static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
{
unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
return used_blocks >= atomic_read(&sdp->sd_log_thresh2);
}
/**
* gfs2_logd - Update log tail as Active Items get flushed to in-place blocks
* @sdp: Pointer to GFS2 superblock
*
* Also, periodically check to make sure that we're using the most recent
* journal index.
*/
int gfs2_logd(void *data)
{
struct gfs2_sbd *sdp = data;
unsigned long t = 1;
DEFINE_WAIT(wait);
while (!kthread_should_stop()) {
if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
gfs2_ail1_empty(sdp);
GFS2: remove transaction glock GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-02 11:26:55 +08:00
gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
}
if (gfs2_ail_flush_reqd(sdp)) {
gfs2_ail1_start(sdp);
gfs2_ail1_wait(sdp);
gfs2_ail1_empty(sdp);
GFS2: remove transaction glock GFS2 has a transaction glock, which must be grabbed for every transaction, whose purpose is to deal with freezing the filesystem. Aside from this involving a large amount of locking, it is very easy to make the current fsfreeze code hang on unfreezing. This patch rewrites how gfs2 handles freezing the filesystem. The transaction glock is removed. In it's place is a freeze glock, which is cached (but not held) in a shared state by every node in the cluster when the filesystem is mounted. This lock only needs to be grabbed on freezing, and actions which need to be safe from freezing, like recovery. When a node wants to freeze the filesystem, it grabs this glock exclusively. When the freeze glock state changes on the nodes (either from shared to unlocked, or shared to exclusive), the filesystem does a special log flush. gfs2_log_flush() does all the work for flushing out the and shutting down the incore log, and then it tries to grab the freeze glock in a shared state again. Since the filesystem is stuck in gfs2_log_flush, no new transaction can start, and nothing can be written to disk. Unfreezing the filesytem simply involes dropping the freeze glock, allowing gfs2_log_flush() to grab and then release the shared lock, so it is cached for next time. However, in order for the unfreezing ioctl to occur, gfs2 needs to get a shared lock on the filesystem root directory inode to check permissions. If that glock has already been grabbed exclusively, fsfreeze will be unable to get the shared lock and unfreeze the filesystem. In order to allow the unfreeze, this patch makes gfs2 grab a shared lock on the filesystem root directory during the freeze, and hold it until it unfreezes the filesystem. The functions which need to grab a shared lock in order to allow the unfreeze ioctl to be issued now use the lock grabbed by the freeze code instead. The freeze and unfreeze code take care to make sure that this shared lock will not be dropped while another process is using it. Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
2014-05-02 11:26:55 +08:00
gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
}
if (!gfs2_ail_flush_reqd(sdp))
wake_up(&sdp->sd_log_waitq);
t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
try_to_freeze();
do {
prepare_to_wait(&sdp->sd_logd_waitq, &wait,
TASK_INTERRUPTIBLE);
if (!gfs2_ail_flush_reqd(sdp) &&
!gfs2_jrnl_flush_reqd(sdp) &&
!kthread_should_stop())
t = schedule_timeout(t);
} while(t && !gfs2_ail_flush_reqd(sdp) &&
!gfs2_jrnl_flush_reqd(sdp) &&
!kthread_should_stop());
finish_wait(&sdp->sd_logd_waitq, &wait);
}
return 0;
}