From 41dcf197ad5373a7dd0a4b6572aec2e3ec6a0e49 Mon Sep 17 00:00:00 2001 From: Jonathan Brassow Date: Mon, 2 Oct 2017 17:17:35 -0500 Subject: [PATCH] dm raid: fix incorrect status output at the end of a "recover" process There are three important fields that indicate the overall health and status of an array: dev_health, sync_ratio, and sync_action. They tell us the condition of the devices in the array, and the degree to which the array is synchronized. This commit fixes a condition that is reported incorrectly. When a member of the array is being rebuilt or a new device is added, the "recover" process is used to synchronize it with the rest of the array. When the process is complete, but the sync thread hasn't yet been reaped, it is possible for the state of MD to be: mddev->recovery = [ MD_RECOVERY_RUNNING MD_RECOVERY_RECOVER MD_RECOVERY_DONE ] curr_resync_completed = (but not MaxSector) and all rdevs to be In_sync. This causes the 'array_in_sync' output parameter that is passed to rs_get_progress() to be computed incorrectly and reported as 'false' -- or not in-sync. This in turn causes the dev_health status characters to be reported as all 'a', rather than the proper 'A'. This can cause erroneous output for several seconds at a time when tools will want to be checking the condition due to events that are raised at the end of a sync process. Fix this by properly calculating the 'array_in_sync' return parameter in rs_get_progress(). Also, remove an unnecessary intermediate 'recovery_cp' variable in rs_get_progress(). Signed-off-by: Jonathan Brassow Signed-off-by: Mike Snitzer --- Documentation/device-mapper/dm-raid.txt | 1 + drivers/md/dm-raid.c | 11 ++++++----- 2 files changed, 7 insertions(+), 5 deletions(-) diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt index 4a0a7469fdd7..32df07e29f68 100644 --- a/Documentation/device-mapper/dm-raid.txt +++ b/Documentation/device-mapper/dm-raid.txt @@ -344,3 +344,4 @@ Version History (wrong raid10_copies/raid10_format sequence) 1.11.1 Add raid4/5/6 journal write-back support via journal_mode option 1.12.1 fix for MD deadlock between mddev_suspend() and md_write_start() available +1.13.0 Fix dev_health status at end of "recover" (was 'a', now 'A') diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 5bfe285ea9d1..43094ea89e37 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3297,11 +3297,10 @@ static const char *__raid_dev_status(struct raid_set *rs, struct md_rdev *rdev, static sector_t rs_get_progress(struct raid_set *rs, sector_t resync_max_sectors, bool *array_in_sync) { - sector_t r, recovery_cp, curr_resync_completed; + sector_t r, curr_resync_completed; struct mddev *mddev = &rs->md; curr_resync_completed = mddev->curr_resync_completed ?: mddev->recovery_cp; - recovery_cp = mddev->recovery_cp; *array_in_sync = false; if (rs_is_raid0(rs)) { @@ -3330,9 +3329,11 @@ static sector_t rs_get_progress(struct raid_set *rs, } else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) r = curr_resync_completed; else - r = recovery_cp; + r = mddev->recovery_cp; - if (r == MaxSector) { + if ((r == MaxSector) || + (test_bit(MD_RECOVERY_DONE, &mddev->recovery) && + (mddev->curr_resync_completed == resync_max_sectors))) { /* * Sync complete. */ @@ -3892,7 +3893,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 12, 1}, + .version = {1, 13, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, -- 2.20.1