You can trigger a 'check' with
echo check > /sys/block/mdX/md/scan_mode
or a check-and-repair errors with
echo repair > /sys/block/mdX/md/scan_mode
and read the current state from the same file.
Note: personalities need to know the different between 'check' and 'repair',
but don't yet. Until they do, 'check' will be the same as 'repair' and
will just do a normal resync pass.
Signed-off-by: Neil Brown <neilb@xxxxxxx>
### Diffstat output
./drivers/md/md.c | 77 ++++++++++++++++++++++++++++++++++++++------
./include/linux/raid/md_k.h | 4 ++
2 files changed, 72 insertions(+), 9 deletions(-)
diff ./drivers/md/md.c~current~ ./drivers/md/md.c
--- ./drivers/md/md.c~current~ 2005-10-04 12:25:36.000000000 +1000
+++ ./drivers/md/md.c 2005-10-04 14:19:35.000000000 +1000
@@ -1714,9 +1714,60 @@ static struct md_sysfs_entry md_raid_dis
.show = md_show_rdisks,
};
+static ssize_t
+md_show_scan(mddev_t *mddev, char *page)
+{
+ char *type = "none";
+ if (mddev->recovery &
+ ((1<<MD_RECOVERY_RUNNING) || (1<<MD_RECOVERY_NEEDED))) {
+ if (mddev->recovery & (1<<MD_RECOVERY_SYNC)) {
+ if (!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ type = "resync";
+ else if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
+ type = "check";
+ else
+ type = "repair";
+ } else
+ type = "recover";
+ }
+ return sprintf(page, "%s\n", type);
+}
+
+static ssize_t
+md_store_scan(mddev_t *mddev, const char *page, size_t len)
+{
+ int canscan=0;
+ if (mddev->recovery &
+ ((1<<MD_RECOVERY_RUNNING) || (1<<MD_RECOVERY_NEEDED)))
+ return -EBUSY;
+ down(&mddev->reconfig_sem);
+ if (mddev->pers && mddev->pers->sync_request)
+ canscan=1;
+ up(&mddev->reconfig_sem);
+ if (!canscan)
+ return -EINVAL;
+
+ if (strcmp(page, "check")==0 || strcmp(page, "check\n")==0)
+ set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ else if (strcmp(page, "repair")!=0 && strcmp(page, "repair\n")!=0)
+ return -EINVAL;
+ set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+ set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_wakeup_thread(mddev->thread);
+ return len;
+}
+
+static struct md_sysfs_entry md_scan_mode = {
+ .attr = {.name = "scan_mode", .mode = S_IRUGO|S_IWUSR },
+ .show = md_show_scan,
+ .store = md_store_scan,
+};
+
static struct attribute *md_default_attrs[] = {
&md_level.attr,
&md_raid_disks.attr,
+ &md_scan_mode.attr,
NULL,
};
@@ -3851,7 +3902,8 @@ static void md_do_sync(mddev_t *mddev)
is_mddev_idle(mddev); /* this also initializes IO event counters */
/* we don't use the checkpoint if there's a bitmap */
- if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !mddev->bitmap)
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !mddev->bitmap
+ && ! test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
j = mddev->recovery_cp;
else
j = 0;
@@ -4089,9 +4141,13 @@ void md_check_recovery(mddev_t *mddev)
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
goto unlock;
}
- if (mddev->recovery)
- /* probably just the RECOVERY_NEEDED flag */
- mddev->recovery = 0;
+ /* Clear some bits that don't mean anything, but
+ * might be left set
+ */
+ clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ clear_bit(MD_RECOVERY_ERR, &mddev->recovery);
+ clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
/* no recovery is running.
* remove any failed drives, then
@@ -4125,14 +4181,17 @@ void md_check_recovery(mddev_t *mddev)
}
}
- if (!spares && (mddev->recovery_cp == MaxSector )) {
- /* nothing we can do ... */
+ if (spares) {
+ clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+ } else if (mddev->recovery_cp < MaxSector) {
+ set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+ } else if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
+ /* nothing to be done ... */
goto unlock;
- }
+
if (mddev->pers->sync_request) {
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
- if (!spares)
- set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
if (spares && mddev->bitmap && ! mddev->bitmap->file) {
/* We are adding a device or devices to an array
* which has the bitmap stored on all devices.
diff ./include/linux/raid/md_k.h~current~ ./include/linux/raid/md_k.h
--- ./include/linux/raid/md_k.h~current~ 2005-10-04 12:19:17.000000000 +1000
+++ ./include/linux/raid/md_k.h 2005-10-04 14:15:54.000000000 +1000
@@ -182,6 +182,8 @@ struct mddev_s
* ERR: and IO error was detected - abort the resync/recovery
* INTR: someone requested a (clean) early abort.
* DONE: thread is done and is waiting to be reaped
+ * REQUEST: user-space has requested a sync (used with SYNC)
+ * CHECK: user-space request for for check-only, no repair
*/
#define MD_RECOVERY_RUNNING 0
#define MD_RECOVERY_SYNC 1
@@ -189,6 +191,8 @@ struct mddev_s
#define MD_RECOVERY_INTR 3
#define MD_RECOVERY_DONE 4
#define MD_RECOVERY_NEEDED 5
+#define MD_RECOVERY_REQUESTED 6
+#define MD_RECOVERY_CHECK 7
unsigned long recovery;
int in_sync; /* know to not need resync */
-
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
