static int make_resync_request()

in drbd/drbd_worker.c [588:766]

• 129 lines of code
• 32 McCabe index (conditional complexity)

static int make_resync_request(struct drbd_device *const device, int cancel)
{
	struct drbd_peer_device *const peer_device = first_peer_device(device);
	struct drbd_connection *const connection = peer_device ? peer_device->connection : NULL;
	unsigned long bit;
	sector_t sector;
	const sector_t capacity = get_capacity(device->vdisk);
	int max_bio_size;
	int number, rollback_i, size;
	int align, requeue = 0;
	int i = 0;
	int discard_granularity = 0;

	if (unlikely(cancel))
		return 0;

	if (device->rs_total == 0) {
		/* empty resync? */
		drbd_resync_finished(device);
		return 0;
	}

	if (!get_ldev(device)) {
		/* Since we only need to access device->rsync a
		   get_ldev_if_state(device,D_FAILED) would be sufficient, but
		   to continue resync with a broken disk makes no sense at
		   all */
		drbd_err(device, "Disk broke down during resync!\n");
		return 0;
	}

	if (connection->agreed_features & DRBD_FF_THIN_RESYNC) {
		rcu_read_lock();
		discard_granularity = rcu_dereference(device->ldev->disk_conf)->rs_discard_granularity;
		rcu_read_unlock();
	}

	max_bio_size = queue_max_hw_sectors(device->rq_queue) << 9;
	number = drbd_rs_number_requests(device);
	if (number <= 0)
		goto requeue;

	for (i = 0; i < number; i++) {
		/* Stop generating RS requests when half of the send buffer is filled,
		 * but notify TCP that we'd like to have more space. */
		mutex_lock(&connection->data.mutex);
		if (connection->data.socket) {
			struct sock *sk = connection->data.socket->sk;
			int queued = sk->sk_wmem_queued;
			int sndbuf = sk->sk_sndbuf;
			if (queued > sndbuf / 2) {
				requeue = 1;
				if (sk->sk_socket)
					set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
			}
		} else
			requeue = 1;
		mutex_unlock(&connection->data.mutex);
		if (requeue)
			goto requeue;

next_sector:
		size = BM_BLOCK_SIZE;
		bit  = drbd_bm_find_next(device, device->bm_resync_fo);

		if (bit == DRBD_END_OF_BITMAP) {
			device->bm_resync_fo = drbd_bm_bits(device);
			put_ldev(device);
			return 0;
		}

		sector = BM_BIT_TO_SECT(bit);

		if (drbd_try_rs_begin_io(device, sector)) {
			device->bm_resync_fo = bit;
			goto requeue;
		}
		device->bm_resync_fo = bit + 1;

		if (unlikely(drbd_bm_test_bit(device, bit) == 0)) {
			drbd_rs_complete_io(device, sector);
			goto next_sector;
		}

#if DRBD_MAX_BIO_SIZE > BM_BLOCK_SIZE
		/* try to find some adjacent bits.
		 * we stop if we have already the maximum req size.
		 *
		 * Additionally always align bigger requests, in order to
		 * be prepared for all stripe sizes of software RAIDs.
		 */
		align = 1;
		rollback_i = i;
		while (i < number) {
			if (size + BM_BLOCK_SIZE > max_bio_size)
				break;

			/* Be always aligned */
			if (sector & ((1<<(align+3))-1))
				break;

			if (discard_granularity && size == discard_granularity)
				break;

			/* do not cross extent boundaries */
			if (((bit+1) & BM_BLOCKS_PER_BM_EXT_MASK) == 0)
				break;
			/* now, is it actually dirty, after all?
			 * caution, drbd_bm_test_bit is tri-state for some
			 * obscure reason; ( b == 0 ) would get the out-of-band
			 * only accidentally right because of the "oddly sized"
			 * adjustment below */
			if (drbd_bm_test_bit(device, bit+1) != 1)
				break;
			bit++;
			size += BM_BLOCK_SIZE;
			if ((BM_BLOCK_SIZE << align) <= size)
				align++;
			i++;
		}
		/* if we merged some,
		 * reset the offset to start the next drbd_bm_find_next from */
		if (size > BM_BLOCK_SIZE)
			device->bm_resync_fo = bit + 1;
#endif

		/* adjust very last sectors, in case we are oddly sized */
		if (sector + (size>>9) > capacity)
			size = (capacity-sector)<<9;

		if (device->use_csums) {
			switch (read_for_csum(peer_device, sector, size)) {
			case -EIO: /* Disk failure */
				put_ldev(device);
				return -EIO;
			case -EAGAIN: /* allocation failed, or ldev busy */
				drbd_rs_complete_io(device, sector);
				device->bm_resync_fo = BM_SECT_TO_BIT(sector);
				i = rollback_i;
				goto requeue;
			case 0:
				/* everything ok */
				break;
			default:
				BUG();
			}
		} else {
			int err;

			inc_rs_pending(device);
			err = drbd_send_drequest(peer_device,
						 size == discard_granularity ? P_RS_THIN_REQ : P_RS_DATA_REQUEST,
						 sector, size, ID_SYNCER);
			if (err) {
				drbd_err(device, "drbd_send_drequest() failed, aborting...\n");
				dec_rs_pending(device);
				put_ldev(device);
				return err;
			}
		}
	}

	if (device->bm_resync_fo >= drbd_bm_bits(device)) {
		/* last syncer _request_ was sent,
		 * but the P_RS_DATA_REPLY not yet received.  sync will end (and
		 * next sync group will resume), as soon as we receive the last
		 * resync data block, and the last bit is cleared.
		 * until then resync "work" is "inactive" ...
		 */
		put_ldev(device);
		return 0;
	}

 requeue:
	device->rs_in_flight += (i << (BM_BLOCK_SHIFT - 9));
	mod_timer(&device->resync_timer, jiffies + SLEEP_TIME);
	put_ldev(device);
	return 0;
}