Commit 4102d9de authored by Heinz Mauelshagen's avatar Heinz Mauelshagen Committed by Mike Snitzer

dm raid: fix rs_get_progress() synchronization state/ratio

Fix various sync state issues causing racy/bogus sync ratio,
sync_action ad health chars in dm_status() info output.

Sync ratio could be N/N (i.e. 100%) shortly after raid set
creation, i.e. creating a new RaidLV or upconverting a linear LV to
raid1 thus:
  "0 2097152 raid raid1 2 Aa 2097162/2097152 recover 0 0 -"
instead of:
  "0 2097152 raid raid1 2 Aa 0/2097152 idle 0 0 -"

Sync action could be non-idle, when the MD thread was done with io.

Health chars could be 'A' when they should be 'a' for a short time
before a resynchonization started.
Signed-off-by: default avatarHeinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: default avatarMike Snitzer <snitzer@redhat.com>
parent 242ea5ad
...@@ -210,6 +210,7 @@ struct raid_dev { ...@@ -210,6 +210,7 @@ struct raid_dev {
#define RT_FLAG_RESHAPE_RS 4 #define RT_FLAG_RESHAPE_RS 4
#define RT_FLAG_RS_SUSPENDED 5 #define RT_FLAG_RS_SUSPENDED 5
#define RT_FLAG_RS_IN_SYNC 6 #define RT_FLAG_RS_IN_SYNC 6
#define RT_FLAG_RS_RESYNCING 7
/* Array elements of 64 bit needed for rebuild/failed disk bits */ /* Array elements of 64 bit needed for rebuild/failed disk bits */
#define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8) #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
...@@ -3306,8 +3307,10 @@ static const char *decipher_sync_action(struct mddev *mddev, unsigned long recov ...@@ -3306,8 +3307,10 @@ static const char *decipher_sync_action(struct mddev *mddev, unsigned long recov
if (test_bit(MD_RECOVERY_FROZEN, &recovery)) if (test_bit(MD_RECOVERY_FROZEN, &recovery))
return "frozen"; return "frozen";
if (test_bit(MD_RECOVERY_RUNNING, &recovery) || /* The MD sync thread can be done with io but still be running */
(!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &recovery))) { if (!test_bit(MD_RECOVERY_DONE, &recovery) &&
(test_bit(MD_RECOVERY_RUNNING, &recovery) ||
(!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &recovery)))) {
if (test_bit(MD_RECOVERY_RESHAPE, &recovery)) if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
return "reshape"; return "reshape";
...@@ -3344,8 +3347,9 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev) ...@@ -3344,8 +3347,9 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev)
return "D"; return "D";
else if (test_bit(Journal, &rdev->flags)) else if (test_bit(Journal, &rdev->flags))
return (rs->journal_dev.mode == R5C_JOURNAL_MODE_WRITE_THROUGH) ? "A" : "a"; return (rs->journal_dev.mode == R5C_JOURNAL_MODE_WRITE_THROUGH) ? "A" : "a";
else if (!test_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags) && else if (test_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags) ||
!test_bit(In_sync, &rdev->flags)) (!test_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags) &&
!test_bit(In_sync, &rdev->flags)))
return "a"; return "a";
else else
return "A"; return "A";
...@@ -3355,49 +3359,70 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev) ...@@ -3355,49 +3359,70 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev)
static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
sector_t resync_max_sectors) sector_t resync_max_sectors)
{ {
sector_t r, curr_resync_completed; sector_t r;
struct mddev *mddev = &rs->md; struct mddev *mddev = &rs->md;
clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
clear_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
curr_resync_completed = mddev->curr_resync_completed ?: mddev->recovery_cp;
if (rs_is_raid0(rs)) { if (rs_is_raid0(rs)) {
r = resync_max_sectors; r = resync_max_sectors;
set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
} else { } else {
r = mddev->reshape_position;
/* Reshape is relative to the array size */ /* Reshape is relative to the array size */
if (test_bit(MD_RECOVERY_RESHAPE, &recovery) || if (test_bit(MD_RECOVERY_RESHAPE, &recovery)) {
r != MaxSector) { r = mddev->reshape_position;
if (r == MaxSector) { if (r != MaxSector) {
set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
r = resync_max_sectors;
} else {
/* Got to reverse on backward reshape */ /* Got to reverse on backward reshape */
if (mddev->reshape_backwards) if (mddev->reshape_backwards)
r = mddev->array_sectors - r; r = mddev->array_sectors - r;
/* Devide by # of data stripes */ /* Divide by # of data stripes unless raid1 */
sector_div(r, mddev_data_stripes(rs)); if (!rs_is_raid1(rs))
sector_div(r, mddev_data_stripes(rs));
} }
/* Sync is relative to the component device size */ /*
} else if (test_bit(MD_RECOVERY_RUNNING, &recovery)) * Sync/recover is relative to the component device size.
r = curr_resync_completed; *
* MD_RECOVERY_NEEDED for https://bugzilla.redhat.com/show_bug.cgi?id=1508070
*/
} else if (test_bit(MD_RECOVERY_NEEDED, &recovery) ||
test_bit(MD_RECOVERY_RUNNING, &recovery))
r = mddev->curr_resync_completed;
else else
r = mddev->recovery_cp; r = mddev->recovery_cp;
if ((r == MaxSector) || if (r >= resync_max_sectors &&
(test_bit(MD_RECOVERY_DONE, &recovery) && (!test_bit(MD_RECOVERY_REQUESTED, &recovery) ||
(mddev->curr_resync_completed == resync_max_sectors))) { (!test_bit(MD_RECOVERY_FROZEN, &recovery) &&
!test_bit(MD_RECOVERY_NEEDED, &recovery) &&
!test_bit(MD_RECOVERY_RUNNING, &recovery)))) {
/* /*
* Sync complete. * Sync complete.
*/ */
set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); /* In case we have finished recovering, the array is in sync. */
r = resync_max_sectors; if (test_bit(MD_RECOVERY_RECOVER, &recovery))
set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
} else if (test_bit(MD_RECOVERY_RECOVER, &recovery)) {
/*
* In case we are recovering, the array is not in sync
* and health chars should show the recovering legs.
*/
;
} else if (test_bit(MD_RECOVERY_SYNC, &recovery) &&
!test_bit(MD_RECOVERY_REQUESTED, &recovery)) {
/*
* If "resync" is occurring, the raid set
* is or may be out of sync hence the health
* characters shall be 'a'.
*/
set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
} else if (test_bit(MD_RECOVERY_REQUESTED, &recovery)) { } else if (test_bit(MD_RECOVERY_REQUESTED, &recovery)) {
/* /*
* If "check" or "repair" is occurring, the raid set has * If "check" or "repair" is occurring, the raid set has
...@@ -3405,26 +3430,34 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, ...@@ -3405,26 +3430,34 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery,
* should not be 'a' anymore. * should not be 'a' anymore.
*/ */
set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
} else { } else {
struct md_rdev *rdev; struct md_rdev *rdev;
/*
* We are idle and recovery is needed, prevent 'A' chars race
* caused by components still set to in-sync by constrcuctor.
*/
if (test_bit(MD_RECOVERY_NEEDED, &recovery))
set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags);
/* /*
* The raid set may be doing an initial sync, or it may * The raid set may be doing an initial sync, or it may
* be rebuilding individual components. If all the * be rebuilding individual components. If all the
* devices are In_sync, then it is the raid set that is * devices are In_sync, then it is the raid set that is
* being initialized. * being initialized.
*/ */
set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
rdev_for_each(rdev, mddev) rdev_for_each(rdev, mddev)
if (!test_bit(Journal, &rdev->flags) && if (!test_bit(Journal, &rdev->flags) &&
!test_bit(In_sync, &rdev->flags)) !test_bit(In_sync, &rdev->flags)) {
set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags);
#if 0 break;
r = 0; /* HM FIXME: TESTME: https://bugzilla.redhat.com/show_bug.cgi?id=1210637 ? */ }
#endif
} }
} }
return r; return min(r, resync_max_sectors);
} }
/* Helper to return @dev name or "-" if !@dev */ /* Helper to return @dev name or "-" if !@dev */
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment