- Add a state flag 'external' to indicate that the metadata is managed
externally (by user-space) so important changes need to be
left of user-space to handle.
Alternates are non-persistant ('none') where there is no stable metadata -
after the array is stopped there is no record of it's status - and
internal which can be version 0.90 or version 1.x
These are selected by writing to the 'metadata' attribute.
- move the updating of superblocks (sync_sbs) to after we have checked if
there are any superblocks or not.
- New array state 'write_pending'. This means that the metadata records
the array as 'clean', but a write has been requested, so the metadata has
to be updated to record a 'dirty' array before the write can continue.
This change is reported to md by writing 'active' to the array_state
attribute.
- tidy up marking of sb_dirty:
- don't set sb_dirty when resync finishes as md_check_recovery
calls md_update_sb when the sync thread finishes anyway.
- Don't set sb_dirty in multipath_run as the array might not be dirty.
- don't mark superblock dirty when switching to 'clean' if there
is no internal superblock (if external, userspace can choose to
update the superblock whenever it chooses to).
Signed-off-by: Neil Brown <[EMAIL PROTECTED]>
### Diffstat output
./drivers/md/md.c | 77 +++++++++++++++++++++++++++++++++-----------
./include/linux/raid/md_k.h | 3 +
2 files changed, 61 insertions(+), 19 deletions(-)
diff .prev/drivers/md/md.c ./drivers/md/md.c
--- .prev/drivers/md/md.c 2007-12-14 16:07:51.000000000 +1100
+++ ./drivers/md/md.c 2007-12-14 16:08:28.000000000 +1100
@@ -778,7 +778,8 @@ static int super_90_validate(mddev_t *md
mddev->major_version = 0;
mddev->minor_version = sb->minor_version;
mddev->patch_version = sb->patch_version;
- mddev->persistent = ! sb->not_persistent;
+ mddev->persistent = 1;
+ mddev->external = 0;
mddev->chunk_size = sb->chunk_size;
mddev->ctime = sb->ctime;
mddev->utime = sb->utime;
@@ -904,7 +905,7 @@ static void super_90_sync(mddev_t *mddev
sb->size = mddev->size;
sb->raid_disks = mddev->raid_disks;
sb->md_minor = mddev->md_minor;
- sb->not_persistent = !mddev->persistent;
+ sb->not_persistent = 0;
sb->utime = mddev->utime;
sb->state = 0;
sb->events_hi = (mddev->events>>32);
@@ -1158,6 +1159,7 @@ static int super_1_validate(mddev_t *mdd
mddev->major_version = 1;
mddev->patch_version = 0;
mddev->persistent = 1;
+ mddev->external = 0;
mddev->chunk_size = le32_to_cpu(sb->chunksize) << 9;
mddev->ctime = le64_to_cpu(sb->ctime) & ((1ULL << 32)-1);
mddev->utime = le64_to_cpu(sb->utime) & ((1ULL << 32)-1);
@@ -1699,18 +1701,20 @@ repeat:
MD_BUG();
mddev->events --;
}
- sync_sbs(mddev, nospares);
/*
* do not write anything to disk if using
* nonpersistent superblocks
*/
if (!mddev->persistent) {
- clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+ if (!mddev->external)
+ clear_bit(MD_CHANGE_PENDING, &mddev->flags);
+
spin_unlock_irq(&mddev->write_lock);
wake_up(&mddev->sb_wait);
return;
}
+ sync_sbs(mddev, nospares);
spin_unlock_irq(&mddev->write_lock);
dprintk(KERN_INFO
@@ -2430,6 +2434,8 @@ array_state_show(mddev_t *mddev, char *p
case 0:
if (mddev->in_sync)
st = clean;
+ else if (test_bit(MD_CHANGE_CLEAN, &mddev->flags))
+ st = write_pending;
else if (mddev->safemode)
st = active_idle;
else
@@ -2460,11 +2466,9 @@ array_state_store(mddev_t *mddev, const
break;
case clear:
/* stopping an active array */
- if (mddev->pers) {
- if (atomic_read(&mddev->active) > 1)
- return -EBUSY;
- err = do_md_stop(mddev, 0);
- }
+ if (atomic_read(&mddev->active) > 1)
+ return -EBUSY;
+ err = do_md_stop(mddev, 0);
break;
case inactive:
/* stopping an active array */
@@ -2472,7 +2476,8 @@ array_state_store(mddev_t *mddev, const
if (atomic_read(&mddev->active) > 1)
return -EBUSY;
err = do_md_stop(mddev, 2);
- }
+ } else
+ err = 0; /* already inactive */
break;
case suspended:
break; /* not supported yet */
@@ -2500,9 +2505,15 @@ array_state_store(mddev_t *mddev, const
restart_array(mddev);
spin_lock_irq(&mddev->write_lock);
if (atomic_read(&mddev->writes_pending) == 0) {
- mddev->in_sync = 1;
- set_bit(MD_CHANGE_CLEAN, &mddev->flags);
- }
+ if (mddev->in_sync == 0) {
+ mddev->in_sync = 1;
+ if (mddev->persistent)
+ set_bit(MD_CHANGE_CLEAN,
+ &mddev->flags);
+ }
+ err = 0;
+ } else
+ err = -EBUSY;
spin_unlock_irq(&mddev->write_lock);
} else {
mddev->ro = 0;
@@ -2513,7 +2524,8 @@ array_state_store(mddev_t *mddev, const
case active:
if (mddev->pers) {
restart_array(mddev);
- clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ if (mddev->external)
+ clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
wake_up(&mddev->sb_wait);
err = 0;
} else {
@@ -2664,7 +2676,9 @@ __ATTR(component_size, S_IRUGO|S_IWUSR,
/* Metdata version.
- * This is either 'none' for arrays with externally managed metadata,
+ * This is one of
+ * 'none' for arrays with no metadata (good luck...)
+ * 'external' for arrays with externally managed metadata,
* or N.M for internally known formats
*/
static ssize_t
@@ -2673,6 +2687,8 @@ metadata_show(mddev_t *mddev, char *page
if (mddev->persistent)
return sprintf(page, "%d.%d\n",
mddev->major_version, mddev->minor_version);
+ else if (mddev->external)
+ return sprintf(page, "external:%s\n", mddev->metadata_type);
else
return sprintf(page, "none\n");
}
@@ -2687,6 +2703,21 @@ metadata_store(mddev_t *mddev, const cha
if (cmd_match(buf, "none")) {
mddev->persistent = 0;
+ mddev->external = 0;
+ mddev->major_version = 0;
+ mddev->minor_version = 90;
+ return len;
+ }
+ if (strncmp(buf, "external:", 9) == 0) {
+ int namelen = len-9;
+ if (namelen >= sizeof(mddev->metadata_type))
+ namelen = sizeof(mddev->metadata_type)-1;
+ strncpy(mddev->metadata_type, buf+9, namelen);
+ mddev->metadata_type[namelen] = 0;
+ if (namelen && mddev->metadata_type[namelen-1] == '\n')
+ mddev->metadata_type[--namelen] = 0;
+ mddev->persistent = 0;
+ mddev->external = 1;
mddev->major_version = 0;
mddev->minor_version = 90;
return len;
@@ -2703,6 +2734,7 @@ metadata_store(mddev_t *mddev, const cha
mddev->major_version = major;
mddev->minor_version = minor;
mddev->persistent = 1;
+ mddev->external = 0;
return len;
}
@@ -3527,6 +3559,7 @@ static int do_md_stop(mddev_t * mddev, i
mddev->raid_disks = 0;
mddev->recovery_cp = 0;
mddev->reshape_position = MaxSector;
+ mddev->external = 0;
} else if (mddev->pers)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
@@ -4168,13 +4201,15 @@ static int set_array_info(mddev_t * mdde
else
mddev->recovery_cp = 0;
mddev->persistent = ! info->not_persistent;
+ mddev->external = 0;
mddev->layout = info->layout;
mddev->chunk_size = info->chunk_size;
mddev->max_disks = MD_SB_DISKS;
- mddev->flags = 0;
+ if (mddev->persistent)
+ mddev->flags = 0;
set_bit(MD_CHANGE_DEVS, &mddev->flags);
mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
@@ -4985,7 +5020,10 @@ static int md_seq_show(struct seq_file *
mddev->major_version,
mddev->minor_version);
}
- } else
+ } else if (mddev->external)
+ seq_printf(seq, " super external:%s",
+ mddev->metadata_type);
+ else
seq_printf(seq, " super non-persistent");
if (mddev->pers) {
@@ -5591,7 +5629,7 @@ void md_check_recovery(mddev_t *mddev)
}
if ( ! (
- mddev->flags ||
+ (mddev->flags && !mddev->external) ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
(mddev->safemode == 1) ||
@@ -5607,7 +5645,8 @@ void md_check_recovery(mddev_t *mddev)
if (mddev->safemode && !atomic_read(&mddev->writes_pending) &&
!mddev->in_sync && mddev->recovery_cp == MaxSector) {
mddev->in_sync = 1;
- set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ if (mddev->persistent)
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
}
if (mddev->safemode == 1)
mddev->safemode = 0;
diff .prev/include/linux/raid/md_k.h ./include/linux/raid/md_k.h
--- .prev/include/linux/raid/md_k.h 2007-12-14 16:07:51.000000000 +1100
+++ ./include/linux/raid/md_k.h 2007-12-14 16:07:54.000000000 +1100
@@ -130,6 +130,9 @@ struct mddev_s
minor_version,
patch_version;
int persistent;
+ int external; /* metadata is
+ * managed externally */
+ char metadata_type[17]; /* externally set*/
int chunk_size;
time_t ctime, utime;
int level, layout;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
