X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=drivers%2Fmd%2Fraid10.c;h=82249a69014f0295055d10d750d297ac8e4291c6;hb=ac6d141dc7d1d0eeec850d1b451dca83ce649684;hp=7bf5ce281c4d49fee2499b22112a4f8a361349c4;hpb=6814d5368d68341ec6b5e4ecd10ea5947130775a;p=linux-2.6

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7bf5ce281c..82249a6901 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -429,7 +429,7 @@ static sector_t raid10_find_virt(conf_t *conf, sector_t sector, int dev)
 		if (dev < 0)
 			dev += conf->raid_disks;
 	} else {
-		while (sector > conf->stride) {
+		while (sector >= conf->stride) {
 			sector -= conf->stride;
 			if (dev < conf->near_copies)
 				dev += conf->raid_disks - conf->near_copies;
@@ -648,6 +648,26 @@ static int raid10_issue_flush(request_queue_t *q, struct gendisk *disk,
 	return ret;
 }
 
+static int raid10_congested(void *data, int bits)
+{
+	mddev_t *mddev = data;
+	conf_t *conf = mddev_to_conf(mddev);
+	int i, ret = 0;
+
+	rcu_read_lock();
+	for (i = 0; i < mddev->raid_disks && ret == 0; i++) {
+		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
+		if (rdev && !test_bit(Faulty, &rdev->flags)) {
+			request_queue_t *q = bdev_get_queue(rdev->bdev);
+
+			ret |= bdi_congested(&q->backing_dev_info, bits);
+		}
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+
 /* Barriers....
  * Sometimes we need to suspend IO while we do something else,
  * either some resync/recovery, or reconfigure the array.
@@ -762,6 +782,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	int i;
 	int chunk_sects = conf->chunk_mask + 1;
 	const int rw = bio_data_dir(bio);
+	const int do_sync = bio_sync(bio);
 	struct bio_list bl;
 	unsigned long flags;
 
@@ -843,7 +864,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 			mirror->rdev->data_offset;
 		read_bio->bi_bdev = mirror->rdev->bdev;
 		read_bio->bi_end_io = raid10_end_read_request;
-		read_bio->bi_rw = READ;
+		read_bio->bi_rw = READ | do_sync;
 		read_bio->bi_private = r10_bio;
 
 		generic_make_request(read_bio);
@@ -889,7 +910,7 @@ static int make_request(request_queue_t *q, struct bio * bio)
 			conf->mirrors[d].rdev->data_offset;
 		mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
 		mbio->bi_end_io	= raid10_end_write_request;
-		mbio->bi_rw = WRITE;
+		mbio->bi_rw = WRITE | do_sync;
 		mbio->bi_private = r10_bio;
 
 		atomic_inc(&r10_bio->remaining);
@@ -902,6 +923,9 @@ static int make_request(request_queue_t *q, struct bio * bio)
 	blk_plug_device(mddev->queue);
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
+	if (do_sync)
+		md_wakeup_thread(mddev->thread);
+
 	return 0;
 }
 
@@ -921,7 +945,7 @@ static void status(struct seq_file *seq, mddev_t *mddev)
 			seq_printf(seq, " %d far-copies", conf->far_copies);
 	}
 	seq_printf(seq, " [%d/%d] [", conf->raid_disks,
-						conf->working_disks);
+					conf->raid_disks - mddev->degraded);
 	for (i = 0; i < conf->raid_disks; i++)
 		seq_printf(seq, "%s",
 			      conf->mirrors[i].rdev &&
@@ -941,7 +965,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 	 * else mark the drive as failed
 	 */
 	if (test_bit(In_sync, &rdev->flags)
-	    && conf->working_disks == 1)
+	    && conf->raid_disks-mddev->degraded == 1)
 		/*
 		 * Don't fail the drive, just return an IO error.
 		 * The test should really be more sophisticated than
@@ -950,20 +974,21 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
 		 * really dead" tests...
 		 */
 		return;
-	if (test_bit(In_sync, &rdev->flags)) {
+	if (test_and_clear_bit(In_sync, &rdev->flags)) {
+		unsigned long flags;
+		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
-		conf->working_disks--;
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		/*
 		 * if recovery is running, make sure it aborts.
 		 */
 		set_bit(MD_RECOVERY_ERR, &mddev->recovery);
 	}
-	clear_bit(In_sync, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
-	mddev->sb_dirty = 1;
+	set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	printk(KERN_ALERT "raid10: Disk failure on %s, disabling device. \n"
 		"	Operation continuing on %d devices\n",
-		bdevname(rdev->bdev,b), conf->working_disks);
+		bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
 }
 
 static void print_conf(conf_t *conf)
@@ -976,7 +1001,7 @@ static void print_conf(conf_t *conf)
 		printk("(!conf)\n");
 		return;
 	}
-	printk(" --- wd:%d rd:%d\n", conf->working_disks,
+	printk(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
 		conf->raid_disks);
 
 	for (i = 0; i < conf->raid_disks; i++) {
@@ -1034,10 +1059,11 @@ static int raid10_spare_active(mddev_t *mddev)
 		tmp = conf->mirrors + i;
 		if (tmp->rdev
 		    && !test_bit(Faulty, &tmp->rdev->flags)
-		    && !test_bit(In_sync, &tmp->rdev->flags)) {
-			conf->working_disks++;
+		    && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
+			unsigned long flags;
+			spin_lock_irqsave(&conf->device_lock, flags);
 			mddev->degraded--;
-			set_bit(In_sync, &tmp->rdev->flags);
+			spin_unlock_irqrestore(&conf->device_lock, flags);
 		}
 	}
 
@@ -1448,8 +1474,8 @@ static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
 					       "raid10:%s: read error corrected"
 					       " (%d sectors at %llu on %s)\n",
 					       mdname(mddev), s,
-					       (unsigned long long)sect+
-					            rdev->data_offset,
+					       (unsigned long long)(sect+
+					            rdev->data_offset),
 					       bdevname(rdev->bdev, b));
 
 				rdev_dec_pending(rdev, mddev);
@@ -1541,6 +1567,7 @@ static void raid10d(mddev_t *mddev)
 				       (unsigned long long)r10_bio->sector);
 				raid_end_bio_io(r10_bio);
 			} else {
+				const int do_sync = bio_sync(r10_bio->master_bio);
 				rdev = conf->mirrors[mirror].rdev;
 				if (printk_ratelimit())
 					printk(KERN_ERR "raid10: %s: redirecting sector %llu to"
@@ -1552,7 +1579,7 @@ static void raid10d(mddev_t *mddev)
 				bio->bi_sector = r10_bio->devs[r10_bio->read_slot].addr
 					+ rdev->data_offset;
 				bio->bi_bdev = rdev->bdev;
-				bio->bi_rw = READ;
+				bio->bi_rw = READ | do_sync;
 				bio->bi_private = r10_bio;
 				bio->bi_end_io = raid10_end_read_request;
 				unplug = 1;
@@ -1763,7 +1790,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 						biolist = bio;
 						bio->bi_private = r10_bio;
 						bio->bi_end_io = end_sync_read;
-						bio->bi_rw = 0;
+						bio->bi_rw = READ;
 						bio->bi_sector = r10_bio->devs[j].addr +
 							conf->mirrors[d].rdev->data_offset;
 						bio->bi_bdev = conf->mirrors[d].rdev->bdev;
@@ -1774,12 +1801,13 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 						for (k=0; k<conf->copies; k++)
 							if (r10_bio->devs[k].devnum == i)
 								break;
+						BUG_ON(k == conf->copies);
 						bio = r10_bio->devs[1].bio;
 						bio->bi_next = biolist;
 						biolist = bio;
 						bio->bi_private = r10_bio;
 						bio->bi_end_io = end_sync_write;
-						bio->bi_rw = 1;
+						bio->bi_rw = WRITE;
 						bio->bi_sector = r10_bio->devs[k].addr +
 							conf->mirrors[i].rdev->data_offset;
 						bio->bi_bdev = conf->mirrors[i].rdev->bdev;
@@ -1848,7 +1876,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 			biolist = bio;
 			bio->bi_private = r10_bio;
 			bio->bi_end_io = end_sync_read;
-			bio->bi_rw = 0;
+			bio->bi_rw = READ;
 			bio->bi_sector = r10_bio->devs[i].addr +
 				conf->mirrors[d].rdev->data_offset;
 			bio->bi_bdev = conf->mirrors[d].rdev->bdev;
@@ -1994,19 +2022,30 @@ static int run(mddev_t *mddev)
 	if (!conf->tmppage)
 		goto out_free_conf;
 
+	conf->mddev = mddev;
+	conf->raid_disks = mddev->raid_disks;
 	conf->near_copies = nc;
 	conf->far_copies = fc;
 	conf->copies = nc*fc;
 	conf->far_offset = fo;
 	conf->chunk_mask = (sector_t)(mddev->chunk_size>>9)-1;
 	conf->chunk_shift = ffz(~mddev->chunk_size) - 9;
+	size = mddev->size >> (conf->chunk_shift-1);
+	sector_div(size, fc);
+	size = size * conf->raid_disks;
+	sector_div(size, nc);
+	/* 'size' is now the number of chunks in the array */
+	/* calculate "used chunks per device" in 'stride' */
+	stride = size * conf->copies;
+	sector_div(stride, conf->raid_disks);
+	mddev->size = stride  << (conf->chunk_shift-1);
+
 	if (fo)
-		conf->stride = 1 << conf->chunk_shift;
-	else {
-		stride = mddev->size >> (conf->chunk_shift-1);
+		stride = 1;
+	else
 		sector_div(stride, fc);
-		conf->stride = stride << conf->chunk_shift;
-	}
+	conf->stride = stride << conf->chunk_shift;
+
 	conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
 						r10bio_pool_free, conf);
 	if (!conf->r10bio_pool) {
@@ -2035,11 +2074,7 @@ static int run(mddev_t *mddev)
 			mddev->queue->max_sectors = (PAGE_SIZE>>9);
 
 		disk->head_position = 0;
-		if (!test_bit(Faulty, &rdev->flags) && test_bit(In_sync, &rdev->flags))
-			conf->working_disks++;
 	}
-	conf->raid_disks = mddev->raid_disks;
-	conf->mddev = mddev;
 	spin_lock_init(&conf->device_lock);
 	INIT_LIST_HEAD(&conf->retry_list);
 
@@ -2059,7 +2094,7 @@ static int run(mddev_t *mddev)
 		disk = conf->mirrors + i;
 
 		if (!disk->rdev ||
-		    !test_bit(In_sync, &rdev->flags)) {
+		    !test_bit(In_sync, &disk->rdev->flags)) {
 			disk->head_position = 0;
 			mddev->degraded++;
 		}
@@ -2081,19 +2116,13 @@ static int run(mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	if (conf->far_offset) {
-		size = mddev->size >> (conf->chunk_shift-1);
-		size *= conf->raid_disks;
-		size <<= conf->chunk_shift;
-		sector_div(size, conf->far_copies);
-	} else
-		size = conf->stride * conf->raid_disks;
-	sector_div(size, conf->near_copies);
-	mddev->array_size = size/2;
-	mddev->resync_max_sectors = size;
+	mddev->array_size = size << (conf->chunk_shift-1);
+	mddev->resync_max_sectors = size << conf->chunk_shift;
 
 	mddev->queue->unplug_fn = raid10_unplug;
 	mddev->queue->issue_flush_fn = raid10_issue_flush;
+	mddev->queue->backing_dev_info.congested_fn = raid10_congested;
+	mddev->queue->backing_dev_info.congested_data = mddev;
 
 	/* Calculate max read-ahead size.
 	 * We need to readahead at least twice a whole stripe....