diff options
Diffstat (limited to 'drivers/md/raid5.c')
-rw-r--r-- | drivers/md/raid5.c | 35 |
1 files changed, 29 insertions, 6 deletions
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 16f5c21963db..1c829a0b234b 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -64,6 +64,10 @@ #define cpu_to_group(cpu) cpu_to_node(cpu) #define ANY_GROUP NUMA_NO_NODE +static bool devices_handle_discard_safely = false; +module_param(devices_handle_discard_safely, bool, 0644); +MODULE_PARM_DESC(devices_handle_discard_safely, + "Set to Y if all devices in each array reliably return zeroes on reads from discarded regions"); static struct workqueue_struct *raid5_wq; /* * Stripe cache @@ -1910,7 +1914,8 @@ static int resize_stripes(struct r5conf *conf, int newsize) conf->slab_cache = sc; conf->active_name = 1-conf->active_name; - conf->pool_size = newsize; + if (!err) + conf->pool_size = newsize; return err; } @@ -2892,7 +2897,8 @@ static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s, (s->failed >= 2 && fdev[1]->toread) || (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite && !test_bit(R5_OVERWRITE, &fdev[0]->flags)) || - (sh->raid_conf->level == 6 && s->failed && s->to_write))) { + ((sh->raid_conf->level == 6 || sh->sector >= sh->raid_conf->mddev->recovery_cp) + && s->failed && s->to_write))) { /* we would like to get this block, possibly by computing it, * otherwise read it if the backing disk is insync */ @@ -3023,6 +3029,8 @@ static void handle_stripe_clean_event(struct r5conf *conf, } if (!discard_pending && test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) { + int hash = sh->hash_lock_index; + clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags); if (sh->qd_idx >= 0) { @@ -3036,9 +3044,9 @@ static void handle_stripe_clean_event(struct r5conf *conf, * no updated data, so remove it from hash list and the stripe * will be reinitialized */ - spin_lock_irq(&conf->device_lock); + spin_lock_irq(conf->hash_locks + hash); remove_hash(sh); - spin_unlock_irq(&conf->device_lock); + spin_unlock_irq(conf->hash_locks + hash); if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) set_bit(STRIPE_HANDLE, &sh->state); @@ -3066,7 +3074,8 @@ static void handle_stripe_dirtying(struct r5conf *conf, * generate correct data from the parity. */ if (conf->max_degraded == 2 || - (recovery_cp < MaxSector && sh->sector >= recovery_cp)) { + (recovery_cp < MaxSector && sh->sector >= recovery_cp && + s->failed == 0)) { /* Calculate the real rcw later - for now make it * look like rcw is cheaper */ @@ -3779,6 +3788,8 @@ static void handle_stripe(struct stripe_head *sh) set_bit(R5_Wantwrite, &dev->flags); if (prexor) continue; + if (s.failed > 1) + continue; if (!test_bit(R5_Insync, &dev->flags) || ((i == sh->pd_idx || i == sh->qd_idx) && s.failed == 0)) @@ -6115,7 +6126,7 @@ static int run(struct mddev *mddev) mddev->queue->limits.discard_granularity = stripe; /* * unaligned part of discard request will be ignored, so can't - * guarantee discard_zerors_data + * guarantee discard_zeroes_data */ mddev->queue->limits.discard_zeroes_data = 0; @@ -6140,6 +6151,18 @@ static int run(struct mddev *mddev) !bdev_get_queue(rdev->bdev)-> limits.discard_zeroes_data) discard_supported = false; + /* Unfortunately, discard_zeroes_data is not currently + * a guarantee - just a hint. So we only allow DISCARD + * if the sysadmin has confirmed that only safe devices + * are in use by setting a module parameter. + */ + if (!devices_handle_discard_safely) { + if (discard_supported) { + pr_info("md/raid456: discard support disabled due to uncertainty.\n"); + pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n"); + } + discard_supported = false; + } } if (discard_supported && |