Sunil Mushran
2009-Jun-19 21:45 UTC
[Ocfs2-devel] [PATCH 1/5] ocfs2: Pin journal head before accessing jh->b_committed_data
This patch adds jbd_lock_bh_state() and jbd_unlock_bh_state() around accessses
to jh->b_committed_data.
Fixes oss bugzilla#1131
http://oss.oracle.com/bugzilla/show_bug.cgi?id=1131
Signed-off-by: Sunil Mushran <sunil.mushran at oracle.com>
---
fs/ocfs2/suballoc.c | 28 ++++++++++++++++++++++++----
1 files changed, 24 insertions(+), 4 deletions(-)
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 8439f6b..73a16d4 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -923,14 +923,23 @@ static int ocfs2_test_bg_bit_allocatable(struct
buffer_head *bg_bh,
int nr)
{
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
+ int ret;
if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap))
return 0;
- if (!buffer_jbd(bg_bh) || !bh2jh(bg_bh)->b_committed_data)
+
+ if (!buffer_jbd(bg_bh))
return 1;
+ jbd_lock_bh_state(bg_bh);
bg = (struct ocfs2_group_desc *) bh2jh(bg_bh)->b_committed_data;
- return !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
+ if (bg)
+ ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
+ else
+ ret = 1;
+ jbd_unlock_bh_state(bg_bh);
+
+ return ret;
}
static int ocfs2_block_group_find_clear_bits(struct ocfs2_super *osb,
@@ -1885,6 +1894,7 @@ static inline int ocfs2_block_group_clear_bits(handle_t
*handle,
unsigned int tmp;
int journal_type = OCFS2_JOURNAL_ACCESS_WRITE;
struct ocfs2_group_desc *undo_bg = NULL;
+ int cluster_bitmap = 0;
mlog_entry_void();
@@ -1905,18 +1915,28 @@ static inline int ocfs2_block_group_clear_bits(handle_t
*handle,
}
if (ocfs2_is_cluster_bitmap(alloc_inode))
- undo_bg = (struct ocfs2_group_desc *) bh2jh(group_bh)->b_committed_data;
+ cluster_bitmap = 1;
+
+ if (cluster_bitmap) {
+ jbd_lock_bh_state(group_bh);
+ undo_bg = (struct ocfs2_group_desc *)
+ bh2jh(group_bh)->b_committed_data;
+ BUG_ON(!undo_bg);
+ }
tmp = num_bits;
while(tmp--) {
ocfs2_clear_bit((bit_off + tmp),
(unsigned long *) bg->bg_bitmap);
- if (ocfs2_is_cluster_bitmap(alloc_inode))
+ if (cluster_bitmap)
ocfs2_set_bit(bit_off + tmp,
(unsigned long *) undo_bg->bg_bitmap);
}
le16_add_cpu(&bg->bg_free_bits_count, num_bits);
+ if (cluster_bitmap)
+ jbd_unlock_bh_state(group_bh);
+
status = ocfs2_journal_dirty(handle, group_bh);
if (status < 0)
mlog_errno(status);
--
1.6.0.4
Skip printing information that is not valid for local mounts.
Signed-off-by: Sunil Mushran <sunil.mushran at oracle.com>
---
fs/ocfs2/super.c | 32 ++++++++++++++++++--------------
1 files changed, 18 insertions(+), 14 deletions(-)
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index d33767f..d64739b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -234,20 +234,24 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char
*buf, int len)
"%10s => Opts: 0x%lX AtimeQuanta: %u\n", "Mount",
osb->s_mount_opt, osb->s_atime_quantum);
- out += snprintf(buf + out, len - out,
- "%10s => Stack: %s Name: %*s Version: %d.%d\n",
- "Cluster",
- (*osb->osb_cluster_stack == '\0' ?
- "o2cb" : osb->osb_cluster_stack),
- cconn->cc_namelen, cconn->cc_name,
- cconn->cc_version.pv_major, cconn->cc_version.pv_minor);
+ if (cconn) {
+ out += snprintf(buf + out, len - out,
+ "%10s => Stack: %s Name: %*s "
+ "Version: %d.%d\n", "Cluster",
+ (*osb->osb_cluster_stack == '\0' ?
+ "o2cb" : osb->osb_cluster_stack),
+ cconn->cc_namelen, cconn->cc_name,
+ cconn->cc_version.pv_major,
+ cconn->cc_version.pv_minor);
+ }
spin_lock(&osb->dc_task_lock);
out += snprintf(buf + out, len - out,
"%10s => Pid: %d Count: %lu WakeSeq: %lu "
"WorkSeq: %lu\n", "DownCnvt",
- task_pid_nr(osb->dc_task), osb->blocked_lock_count,
- osb->dc_wake_sequence, osb->dc_work_sequence);
+ (osb->dc_task ? task_pid_nr(osb->dc_task) : -1),
+ osb->blocked_lock_count, osb->dc_wake_sequence,
+ osb->dc_work_sequence);
spin_unlock(&osb->dc_task_lock);
spin_lock(&osb->osb_lock);
@@ -267,14 +271,15 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char
*buf, int len)
out += snprintf(buf + out, len - out,
"%10s => Pid: %d Interval: %lu Needs: %d\n",
"Commit",
- task_pid_nr(osb->commit_task), osb->osb_commit_interval,
+ (osb->commit_task ? task_pid_nr(osb->commit_task) : -1),
+ osb->osb_commit_interval,
atomic_read(&osb->needs_checkpoint));
out += snprintf(buf + out, len - out,
- "%10s => State: %d NumTxns: %d TxnId: %lu\n",
+ "%10s => State: %d TxnId: %lu NumTxns: %d\n",
"Journal", osb->journal->j_state,
- atomic_read(&osb->journal->j_num_trans),
- osb->journal->j_trans_id);
+ osb->journal->j_trans_id,
+ atomic_read(&osb->journal->j_num_trans));
out += snprintf(buf + out, len - out,
"%10s => GlobalAllocs: %d LocalAllocs: %d "
@@ -302,7 +307,6 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char
*buf, int len)
out += snprintf(buf + out, len - out, "%10s => %3s %10s\n",
"Slots", "Num", "RecoGen");
-
for (i = 0; i < osb->max_slots; ++i) {
out += snprintf(buf + out, len - out,
"%10s %c %3d %10d\n",
--
1.6.0.4
Sunil Mushran
2009-Jun-19 21:45 UTC
[Ocfs2-devel] [PATCH 3/5] ocfs2: Stop orphan scan as early as possible during umount
Currently if the orphan scan fires a tick before the user issues the umount,
the umount will wait for the queued orphan scan tasks to complete.
This patch makes the umount stop the orphan scan as early as possible so as
to reduce the probability of the queued tasks slowing down the umount.
Signed-off-by: Sunil Mushran <sunil.mushran at oracle.com>
---
fs/ocfs2/journal.c | 14 ++++++++++++--
fs/ocfs2/ocfs2.h | 3 +++
fs/ocfs2/super.c | 5 +++--
3 files changed, 18 insertions(+), 4 deletions(-)
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 4a3b9e6..e690483 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1880,6 +1880,9 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
os = &osb->osb_orphan_scan;
+ if (atomic_read(&os->os_status) == ORPHAN_SCAN_INACTIVE)
+ goto out;
+
status = ocfs2_orphan_scan_lock(osb, &seqno, DLM_LOCK_EX);
if (status < 0) {
if (status != -EAGAIN)
@@ -1887,6 +1890,10 @@ void ocfs2_queue_orphan_scan(struct ocfs2_super *osb)
goto out;
}
+ /* Do no queue the tasks if the volume is being umounted */
+ if (atomic_read(&os->os_status) == ORPHAN_SCAN_INACTIVE)
+ goto unlock;
+
if (os->os_seqno != seqno) {
os->os_seqno = seqno;
goto unlock;
@@ -1920,8 +1927,9 @@ void ocfs2_orphan_scan_work(struct work_struct *work)
mutex_lock(&os->os_lock);
ocfs2_queue_orphan_scan(osb);
- schedule_delayed_work(&os->os_orphan_scan_work,
- ocfs2_orphan_scan_timeout());
+ if (atomic_read(&os->os_status) == ORPHAN_SCAN_ACTIVE)
+ schedule_delayed_work(&os->os_orphan_scan_work,
+ ocfs2_orphan_scan_timeout());
mutex_unlock(&os->os_lock);
}
@@ -1930,6 +1938,7 @@ void ocfs2_orphan_scan_stop(struct ocfs2_super *osb)
struct ocfs2_orphan_scan *os;
os = &osb->osb_orphan_scan;
+ atomic_set(&os->os_status, ORPHAN_SCAN_INACTIVE);
mutex_lock(&os->os_lock);
cancel_delayed_work(&os->os_orphan_scan_work);
mutex_unlock(&os->os_lock);
@@ -1940,6 +1949,7 @@ int ocfs2_orphan_scan_init(struct ocfs2_super *osb)
struct ocfs2_orphan_scan *os;
os = &osb->osb_orphan_scan;
+ atomic_set(&os->os_status, ORPHAN_SCAN_ACTIVE);
os->os_osb = osb;
os->os_count = 0;
os->os_scantime = CURRENT_TIME;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 18c1d9e..6930b60 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -162,6 +162,9 @@ struct ocfs2_orphan_scan {
struct timespec os_scantime; /* time this node ran the scan */
u32 os_count; /* tracks node specific scans */
u32 os_seqno; /* tracks cluster wide scans */
+#define ORPHAN_SCAN_ACTIVE 0
+#define ORPHAN_SCAN_INACTIVE 1
+ atomic_t os_status; /* ACTIVE or INACTIVE */
};
struct ocfs2_dlm_debug {
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index d64739b..3e8a68b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1814,14 +1814,15 @@ static void ocfs2_dismount_volume(struct super_block
*sb, int mnt_err)
debugfs_remove(osb->osb_ctxt);
+ /* Orphan scan should be stopped as early as possible */
+ ocfs2_orphan_scan_stop(osb);
+
ocfs2_disable_quotas(osb);
ocfs2_shutdown_local_alloc(osb);
ocfs2_truncate_log_shutdown(osb);
- ocfs2_orphan_scan_stop(osb);
-
/* This will disable recovery and flush any recovery work. */
ocfs2_recovery_exit(osb);
--
1.6.0.4
Sunil Mushran
2009-Jun-19 21:45 UTC
[Ocfs2-devel] [PATCH 4/5] ocfs2: Do not initialize lvb in ocfs2_orphan_scan_lock_res_init()
No need to call ocfs2_dlm_lvb() in ocfs2_orphan_scan_lock_res_init().
Signed-off-by: Sunil Mushran <sunil.mushran at oracle.com>
---
fs/ocfs2/dlmglue.c | 11 +++++++----
fs/ocfs2/journal.c | 1 +
2 files changed, 8 insertions(+), 4 deletions(-)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 6cdeaa7..42ef595 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -644,14 +644,10 @@ static void ocfs2_nfs_sync_lock_res_init(struct
ocfs2_lock_res *res,
static void ocfs2_orphan_scan_lock_res_init(struct ocfs2_lock_res *res,
struct ocfs2_super *osb)
{
- struct ocfs2_orphan_scan_lvb *lvb;
-
ocfs2_lock_res_init_once(res);
ocfs2_build_lock_name(OCFS2_LOCK_TYPE_ORPHAN_SCAN, 0, 0, res->l_name);
ocfs2_lock_res_init_common(osb, res, OCFS2_LOCK_TYPE_ORPHAN_SCAN,
&ocfs2_orphan_scan_lops, osb);
- lvb = ocfs2_dlm_lvb(&res->l_lksb);
- lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION;
}
void ocfs2_file_lock_res_init(struct ocfs2_lock_res *lockres,
@@ -2381,9 +2377,16 @@ int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32
*seqno, int ex)
if (status < 0)
return status;
+ /*
+ * TODO: Add handling for different lvb versions. It is blocked
+ * on being able to detect valid lvb via stackglue.
+ */
lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
if (lvb->lvb_version == OCFS2_ORPHAN_LVB_VERSION)
*seqno = be32_to_cpu(lvb->lvb_os_seqno);
+ else
+ *seqno = osb->osb_orphan_scan.os_seqno + 1;
+
return status;
}
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index e690483..03a43c3 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1952,6 +1952,7 @@ int ocfs2_orphan_scan_init(struct ocfs2_super *osb)
atomic_set(&os->os_status, ORPHAN_SCAN_ACTIVE);
os->os_osb = osb;
os->os_count = 0;
+ os->os_seqno = 0;
os->os_scantime = CURRENT_TIME;
mutex_init(&os->os_lock);
--
1.6.0.4
Sunil Mushran
2009-Jun-19 21:45 UTC
[Ocfs2-devel] [PATCH 5/5] ocfs2: Disable orphan scanning for local and hard-ro mounts
Local and Hard-RO mounts do not need orphan scanning.
Signed-off-by: Sunil Mushran <sunil.mushran at oracle.com>
---
fs/ocfs2/dlmglue.c | 18 +++++++++++++-----
fs/ocfs2/journal.c | 26 +++++++++++++++-----------
fs/ocfs2/journal.h | 2 +-
fs/ocfs2/super.c | 33 ++++++++++++++++-----------------
4 files changed, 45 insertions(+), 34 deletions(-)
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 42ef595..697a192 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -2372,6 +2372,12 @@ int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32
*seqno, int ex)
int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR;
int status = 0;
+ if (ocfs2_is_hard_readonly(osb))
+ return -EROFS;
+
+ if (ocfs2_mount_local(osb))
+ return 0;
+
lockres = &osb->osb_orphan_scan.os_lockres;
status = ocfs2_cluster_lock(osb, lockres, level, 0, 0);
if (status < 0)
@@ -2396,11 +2402,13 @@ void ocfs2_orphan_scan_unlock(struct ocfs2_super *osb,
u32 seqno, int ex)
struct ocfs2_orphan_scan_lvb *lvb;
int level = ex ? DLM_LOCK_EX : DLM_LOCK_PR;
- lockres = &osb->osb_orphan_scan.os_lockres;
- lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
- lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION;
- lvb->lvb_os_seqno = cpu_to_be32(seqno);
- ocfs2_cluster_unlock(osb, lockres, level);
+ if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb)) {
+ lockres = &osb->osb_orphan_scan.os_lockres;
+ lvb = ocfs2_dlm_lvb(&lockres->l_lksb);
+ lvb->lvb_version = OCFS2_ORPHAN_LVB_VERSION;
+ lvb->lvb_os_seqno = cpu_to_be32(seqno);
+ ocfs2_cluster_unlock(osb, lockres, level);
+ }
}
int ocfs2_super_lock(struct ocfs2_super *osb,
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 03a43c3..1e66efc 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1938,29 +1938,33 @@ void ocfs2_orphan_scan_stop(struct ocfs2_super *osb)
struct ocfs2_orphan_scan *os;
os = &osb->osb_orphan_scan;
- atomic_set(&os->os_status, ORPHAN_SCAN_INACTIVE);
- mutex_lock(&os->os_lock);
- cancel_delayed_work(&os->os_orphan_scan_work);
- mutex_unlock(&os->os_lock);
+ if (atomic_read(&os->os_status) == ORPHAN_SCAN_ACTIVE) {
+ atomic_set(&os->os_status, ORPHAN_SCAN_INACTIVE);
+ mutex_lock(&os->os_lock);
+ cancel_delayed_work(&os->os_orphan_scan_work);
+ mutex_unlock(&os->os_lock);
+ }
}
-int ocfs2_orphan_scan_init(struct ocfs2_super *osb)
+void ocfs2_orphan_scan_init(struct ocfs2_super *osb, int start)
{
struct ocfs2_orphan_scan *os;
os = &osb->osb_orphan_scan;
- atomic_set(&os->os_status, ORPHAN_SCAN_ACTIVE);
os->os_osb = osb;
os->os_count = 0;
os->os_seqno = 0;
os->os_scantime = CURRENT_TIME;
mutex_init(&os->os_lock);
+ INIT_DELAYED_WORK(&os->os_orphan_scan_work, ocfs2_orphan_scan_work);
- INIT_DELAYED_WORK(&os->os_orphan_scan_work,
- ocfs2_orphan_scan_work);
- schedule_delayed_work(&os->os_orphan_scan_work,
- ocfs2_orphan_scan_timeout());
- return 0;
+ if (!start)
+ atomic_set(&os->os_status, ORPHAN_SCAN_INACTIVE);
+ else {
+ atomic_set(&os->os_status, ORPHAN_SCAN_ACTIVE);
+ schedule_delayed_work(&os->os_orphan_scan_work,
+ ocfs2_orphan_scan_timeout());
+ }
}
struct ocfs2_orphan_filldir_priv {
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 61045ee..24df8de 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -144,7 +144,7 @@ static inline void ocfs2_inode_set_new(struct ocfs2_super
*osb,
}
/* Exported only for the journal struct init code in super.c. Do not call. */
-int ocfs2_orphan_scan_init(struct ocfs2_super *osb);
+void ocfs2_orphan_scan_init(struct ocfs2_super *osb, int start);
void ocfs2_orphan_scan_stop(struct ocfs2_super *osb);
void ocfs2_orphan_scan_exit(struct ocfs2_super *osb);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 3e8a68b..ca80d52 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -205,11 +205,10 @@ static const match_table_t tokens = {
#ifdef CONFIG_DEBUG_FS
static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
{
- int out = 0;
- int i;
struct ocfs2_cluster_connection *cconn = osb->cconn;
struct ocfs2_recovery_map *rm = osb->recovery_map;
- struct ocfs2_orphan_scan *os;
+ struct ocfs2_orphan_scan *os = &osb->osb_orphan_scan;
+ int i, out = 0;
out += snprintf(buf + out, len - out,
"%10s => Id: %-s Uuid: %-s Gen: 0x%X Label: %-s\n",
@@ -305,6 +304,16 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char
*buf, int len)
atomic_read(&osb->s_num_inodes_stolen));
spin_unlock(&osb->osb_lock);
+ out += snprintf(buf + out, len - out, "Orphan Scan=> ");
+ out += snprintf(buf + out, len - out, "Local: %u Global: %u ",
+ os->os_count, os->os_seqno);
+ out += snprintf(buf + out, len - out, " Last Scan: ");
+ if (atomic_read(&os->os_status) == ORPHAN_SCAN_INACTIVE)
+ out += snprintf(buf + out, len - out, "Disabled\n");
+ else
+ out += snprintf(buf + out, len - out, "%lu seconds ago\n",
+ (get_seconds() - os->os_scantime.tv_sec));
+
out += snprintf(buf + out, len - out, "%10s => %3s %10s\n",
"Slots", "Num", "RecoGen");
for (i = 0; i < osb->max_slots; ++i) {
@@ -315,13 +324,6 @@ static int ocfs2_osb_dump(struct ocfs2_super *osb, char
*buf, int len)
i, osb->slot_recovery_generations[i]);
}
- os = &osb->osb_orphan_scan;
- out += snprintf(buf + out, len - out, "Orphan Scan=> ");
- out += snprintf(buf + out, len - out, "Local: %u Global: %u ",
- os->os_count, os->os_seqno);
- out += snprintf(buf + out, len - out, " Last Scan: %lu seconds
ago\n",
- (get_seconds() - os->os_scantime.tv_sec));
-
return out;
}
@@ -1983,13 +1985,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
goto bail;
}
- status = ocfs2_orphan_scan_init(osb);
- if (status) {
- mlog(ML_ERROR, "Unable to initialize delayed orphan scan\n");
- mlog_errno(status);
- goto bail;
- }
-
init_waitqueue_head(&osb->checkpoint_event);
atomic_set(&osb->needs_checkpoint, 0);
@@ -2196,6 +2191,10 @@ static int ocfs2_initialize_super(struct super_block *sb,
goto bail;
}
+ /* No need to start orphan scan for local and hard-ro mounts */
+ ocfs2_orphan_scan_init(osb, (!ocfs2_is_hard_readonly(osb) &&
+ !ocfs2_mount_local(osb)));
+
bail:
mlog_exit(status);
return status;
--
1.6.0.4
Joel Becker
2009-Jun-19 23:31 UTC
[Ocfs2-devel] [PATCH 1/5] ocfs2: Pin journal head before accessing jh->b_committed_data
On Fri, Jun 19, 2009 at 02:45:54PM -0700, Sunil Mushran wrote:> This patch adds jbd_lock_bh_state() and jbd_unlock_bh_state() around accessses > to jh->b_committed_data. > > Fixes oss bugzilla#1131 > http://oss.oracle.com/bugzilla/show_bug.cgi?id=1131 > > Signed-off-by: Sunil Mushran <sunil.mushran at oracle.com>This is now in the fixes branch of ocfs2.git. Joel -- Life's Little Instruction Book #207 "Swing for the fence." Joel Becker Principal Software Developer Oracle E-mail: joel.becker at oracle.com Phone: (650) 506-8127
On Fri, Jun 19, 2009 at 02:45:55PM -0700, Sunil Mushran wrote:> Skip printing information that is not valid for local mounts. > > Signed-off-by: Sunil Mushran <sunil.mushran at oracle.com>This is now in the fixes branch of ocfs2.git. Joel -- "I inject pure kryptonite into my brain. It improves my kung fu, and it eases the pain." Joel Becker Principal Software Developer Oracle E-mail: joel.becker at oracle.com Phone: (650) 506-8127