This patch tries recreates missing/faulty journal in mdadm.
Example:
./mdadm --fail /dev/md1 /dev/sdb2
mdadm: set /dev/sdb2 faulty in /dev/md1
./mdadm --stop /dev/md1
mdadm: stopped /dev/md1
./mdadm -A --scan --force
mdadm: Journal is missing or stale, starting array read only.
mdadm: /dev/md/1 has been started with 15 drives.
./mdadm --add-journal /dev/md1 /dev/sdb2
mdadm: added /dev/sdb2
Signed-off-by: Song Liu <songliubraving@xxxxxx>
Signed-off-by: Shaohua Li <shli@xxxxxx>
---
Manage.c | 42 +++++++++++++++++++++++++++++++++++++++---
ReadMe.c | 1 +
mdadm.c | 8 ++++++++
mdadm.h | 1 +
super1.c | 3 ++-
5 files changed, 51 insertions(+), 4 deletions(-)
diff --git a/Manage.c b/Manage.c
index 2df303d..4540fac 100644
--- a/Manage.c
+++ b/Manage.c
@@ -825,7 +825,8 @@ int Manage_add(int fd, int tfd, struct mddev_dev *dv,
}
/* Make sure device is large enough */
- if (tst->sb &&
+ if (dv->disposition != 'j' && /* skip size check for Journal */
+ tst->sb &&
tst->ss->avail_size(tst, ldsize/512, INVALID_SECTORS) <
array_size) {
if (dv->disposition == 'M')
@@ -929,8 +930,31 @@ int Manage_add(int fd, int tfd, struct mddev_dev *dv,
else
disc.number = raid_slot;
disc.state = 0;
+
+ /* only add journal to array that supports journaling */
+ if (dv->disposition == 'j') {
+ struct mdinfo mdi;
+ struct mdinfo *mdp;
+
+ mdp = sysfs_read(fd, NULL, GET_ARRAY_STATE);
+
+ if (strncmp(mdp->sysfs_array_state, "readonly", 8) != 0) {
+ pr_err("%s is not readonly, cannot add journal.\n", devname);
+ return -1;
+ }
+
+ tst->ss->getinfo_super(tst, &mdi, NULL);
+ if (mdi.journal_device_required == 0) {
+ pr_err("%s does not support journal device.\n", devname);
+ return -1;
+ }
+ disc.raid_disk = array->raid_disks;
+ }
+
if (array->not_persistent==0) {
int dfd;
+ if (dv->disposition == 'j')
+ disc.state |= (1 << MD_DISK_JOURNAL) | (1 << MD_DISK_SYNC);
if (dv->writemostly == 1)
disc.state |= 1 << MD_DISK_WRITEMOSTLY;
dfd = dev_open(dv->devname, O_RDWR | O_EXCL|O_DIRECT);
@@ -1041,10 +1065,20 @@ int Manage_add(int fd, int tfd, struct mddev_dev *dv,
} else {
tst->ss->free_super(tst);
if (ioctl(fd, ADD_NEW_DISK, &disc)) {
- pr_err("add new device failed for %s as %d: %s\n",
- dv->devname, j, strerror(errno));
+ if (dv->disposition == 'j')
+ pr_err("Failed to hot add %s as journal, "
+ "please try restart %s.\n", dv->devname, devname);
+ else
+ pr_err("add new device failed for %s as %d: %s\n",
+ dv->devname, j, strerror(errno));
return -1;
}
+ if (dv->disposition == 'j') {
+ pr_err("Journal added successfully, making %s read-write\n", devname);
+ if (Manage_ro(devname, fd, -1))
+ pr_err("Failed to make %s read-write\n", devname);
+ }
+
}
if (verbose >= 0)
pr_err("added %s\n", dv->devname);
@@ -1277,6 +1311,7 @@ int Manage_subdevs(char *devname, int fd,
* try HOT_ADD_DISK
* If that fails EINVAL, try ADD_NEW_DISK
* 'S' - add the device as a spare - don't try re-add
+ * 'j' - add the device as a journal device
* 'A' - re-add the device
* 'r' - remove the device: HOT_REMOVE_DISK
* device can be 'faulty' or 'detached' in which case all
@@ -1509,6 +1544,7 @@ int Manage_subdevs(char *devname, int fd,
goto abort;
case 'a':
case 'S': /* --add-spare */
+ case 'j': /* --add-journal */
case 'A':
case 'M': /* --re-add missing */
case 'F': /* --re-add faulty */
diff --git a/ReadMe.c b/ReadMe.c
index fb5a671..566fc8d 100644
--- a/ReadMe.c
+++ b/ReadMe.c
@@ -157,6 +157,7 @@ struct option long_options[] = {
/* Management */
{"add", 0, 0, Add},
{"add-spare", 0, 0, AddSpare},
+ {"add-journal", 0, 0, AddJournal},
{"remove", 0, 0, Remove},
{"fail", 0, 0, Fail},
{"set-faulty",0, 0, Fail},
diff --git a/mdadm.c b/mdadm.c
index f56a8cf..feec3b7 100644
--- a/mdadm.c
+++ b/mdadm.c
@@ -190,6 +190,7 @@ int main(int argc, char *argv[])
case 'a':
case Add:
case AddSpare:
+ case AddJournal:
case 'r':
case Remove:
case Replace:
@@ -925,6 +926,13 @@ int main(int argc, char *argv[])
case O(MANAGE,AddSpare): /* add drive - never re-add */
devmode = 'S';
continue;
+ case O(MANAGE,AddJournal): /* add journal */
+ if (s.journaldisks && (s.level < 4 || s.level > 6)) {
+ pr_err("--add-journal is only supported for RAID level 4/5/6.\n");
+ exit(2);
+ }
+ devmode = 'j';
+ continue;
case O(MANAGE,ReAdd):
devmode = 'A';
continue;
diff --git a/mdadm.h b/mdadm.h
index 21fe789..477ef18 100755
--- a/mdadm.h
+++ b/mdadm.h
@@ -370,6 +370,7 @@ enum special_options {
ManageOpt,
Add,
AddSpare,
+ AddJournal,
Remove,
Fail,
Replace,
diff --git a/super1.c b/super1.c
index 1735c2d..893f9bf 100644
--- a/super1.c
+++ b/super1.c
@@ -1713,7 +1713,8 @@ static int write_init_super1(struct supertype *st)
if (rfd >= 0)
close(rfd);
- sb->events = 0;
+ if (!(di->disk.state & (1<<MD_DISK_JOURNAL)))
+ sb->events = 0;
refst = dup_super(st);
if (load_super1(refst, di->fd, NULL)==0) {
--
2.4.6
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
