raid5.c

来自「linux 内核源代码」· C语言 代码 · 共 2,325 行 · 第 1/5 页

}

static void
handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh,
				struct stripe_head_state *s, int disks,
				struct bio **return_bi)
{
	int i;
	for (i = disks; i--; ) {
		struct bio *bi;
		int bitmap_end = 0;

		if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
			mdk_rdev_t *rdev;
			rcu_read_lock();
			rdev = rcu_dereference(conf->disks[i].rdev);
			if (rdev && test_bit(In_sync, &rdev->flags))
				/* multiple read failures in one stripe */
				md_error(conf->mddev, rdev);
			rcu_read_unlock();
		}
		spin_lock_irq(&conf->device_lock);
		/* fail all writes first */
		bi = sh->dev[i].towrite;
		sh->dev[i].towrite = NULL;
		if (bi) {
			s->to_write--;
			bitmap_end = 1;
		}

		if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
			wake_up(&conf->wait_for_overlap);

		while (bi && bi->bi_sector <
			sh->dev[i].sector + STRIPE_SECTORS) {
			struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
			clear_bit(BIO_UPTODATE, &bi->bi_flags);
			if (--bi->bi_phys_segments == 0) {
				md_write_end(conf->mddev);
				bi->bi_next = *return_bi;
				*return_bi = bi;
			}
			bi = nextbi;
		}
		/* and fail all 'written' */
		bi = sh->dev[i].written;
		sh->dev[i].written = NULL;
		if (bi) bitmap_end = 1;
		while (bi && bi->bi_sector <
		       sh->dev[i].sector + STRIPE_SECTORS) {
			struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
			clear_bit(BIO_UPTODATE, &bi->bi_flags);
			if (--bi->bi_phys_segments == 0) {
				md_write_end(conf->mddev);
				bi->bi_next = *return_bi;
				*return_bi = bi;
			}
			bi = bi2;
		}

		/* fail any reads if this device is non-operational and
		 * the data has not reached the cache yet.
		 */
		if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
		    (!test_bit(R5_Insync, &sh->dev[i].flags) ||
		      test_bit(R5_ReadError, &sh->dev[i].flags))) {
			bi = sh->dev[i].toread;
			sh->dev[i].toread = NULL;
			if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
				wake_up(&conf->wait_for_overlap);
			if (bi) s->to_read--;
			while (bi && bi->bi_sector <
			       sh->dev[i].sector + STRIPE_SECTORS) {
				struct bio *nextbi =
					r5_next_bio(bi, sh->dev[i].sector);
				clear_bit(BIO_UPTODATE, &bi->bi_flags);
				if (--bi->bi_phys_segments == 0) {
					bi->bi_next = *return_bi;
					*return_bi = bi;
				}
				bi = nextbi;
			}
		}
		spin_unlock_irq(&conf->device_lock);
		if (bitmap_end)
			bitmap_endwrite(conf->mddev->bitmap, sh->sector,
					STRIPE_SECTORS, 0, 0);
	}

}

/* __handle_issuing_new_read_requests5 - returns 0 if there are no more disks
 * to process
 */
static int __handle_issuing_new_read_requests5(struct stripe_head *sh,
			struct stripe_head_state *s, int disk_idx, int disks)
{
	struct r5dev *dev = &sh->dev[disk_idx];
	struct r5dev *failed_dev = &sh->dev[s->failed_num];

	/* don't schedule compute operations or reads on the parity block while
	 * a check is in flight
	 */
	if ((disk_idx == sh->pd_idx) &&
	     test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
		return ~0;

	/* is the data in this block needed, and can we get it? */
	if (!test_bit(R5_LOCKED, &dev->flags) &&
	    !test_bit(R5_UPTODATE, &dev->flags) && (dev->toread ||
	    (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
	     s->syncing || s->expanding || (s->failed &&
	     (failed_dev->toread || (failed_dev->towrite &&
	     !test_bit(R5_OVERWRITE, &failed_dev->flags)
	     ))))) {
		/* 1/ We would like to get this block, possibly by computing it,
		 * but we might not be able to.
		 *
		 * 2/ Since parity check operations potentially make the parity
		 * block !uptodate it will need to be refreshed before any
		 * compute operations on data disks are scheduled.
		 *
		 * 3/ We hold off parity block re-reads until check operations
		 * have quiesced.
		 */
		if ((s->uptodate == disks - 1) &&
		    !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
			set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
			set_bit(R5_Wantcompute, &dev->flags);
			sh->ops.target = disk_idx;
			s->req_compute = 1;
			sh->ops.count++;
			/* Careful: from this point on 'uptodate' is in the eye
			 * of raid5_run_ops which services 'compute' operations
			 * before writes. R5_Wantcompute flags a block that will
			 * be R5_UPTODATE by the time it is needed for a
			 * subsequent operation.
			 */
			s->uptodate++;
			return 0; /* uptodate + compute == disks */
		} else if ((s->uptodate < disks - 1) &&
			test_bit(R5_Insync, &dev->flags)) {
			/* Note: we hold off compute operations while checks are
			 * in flight, but we still prefer 'compute' over 'read'
			 * hence we only read if (uptodate < * disks-1)
			 */
			set_bit(R5_LOCKED, &dev->flags);
			set_bit(R5_Wantread, &dev->flags);
			if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
				sh->ops.count++;
			s->locked++;
			pr_debug("Reading block %d (sync=%d)\n", disk_idx,
				s->syncing);
		}
	}

	return ~0;
}

static void handle_issuing_new_read_requests5(struct stripe_head *sh,
			struct stripe_head_state *s, int disks)
{
	int i;

	/* Clear completed compute operations.  Parity recovery
	 * (STRIPE_OP_MOD_REPAIR_PD) implies a write-back which is handled
	 * later on in this routine
	 */
	if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
		!test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
		clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
	}

	/* look for blocks to read/compute, skip this if a compute
	 * is already in flight, or if the stripe contents are in the
	 * midst of changing due to a write
	 */
	if (!test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending) &&
		!test_bit(STRIPE_OP_PREXOR, &sh->ops.pending) &&
		!test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
		for (i = disks; i--; )
			if (__handle_issuing_new_read_requests5(
				sh, s, i, disks) == 0)
				break;
	}
	set_bit(STRIPE_HANDLE, &sh->state);
}

static void handle_issuing_new_read_requests6(struct stripe_head *sh,
			struct stripe_head_state *s, struct r6_state *r6s,
			int disks)
{
	int i;
	for (i = disks; i--; ) {
		struct r5dev *dev = &sh->dev[i];
		if (!test_bit(R5_LOCKED, &dev->flags) &&
		    !test_bit(R5_UPTODATE, &dev->flags) &&
		    (dev->toread || (dev->towrite &&
		     !test_bit(R5_OVERWRITE, &dev->flags)) ||
		     s->syncing || s->expanding ||
		     (s->failed >= 1 &&
		      (sh->dev[r6s->failed_num[0]].toread ||
		       s->to_write)) ||
		     (s->failed >= 2 &&
		      (sh->dev[r6s->failed_num[1]].toread ||
		       s->to_write)))) {
			/* we would like to get this block, possibly
			 * by computing it, but we might not be able to
			 */
			if (s->uptodate == disks-1) {
				pr_debug("Computing stripe %llu block %d\n",
				       (unsigned long long)sh->sector, i);
				compute_block_1(sh, i, 0);
				s->uptodate++;
			} else if ( s->uptodate == disks-2 && s->failed >= 2 ) {
				/* Computing 2-failure is *very* expensive; only
				 * do it if failed >= 2
				 */
				int other;
				for (other = disks; other--; ) {
					if (other == i)
						continue;
					if (!test_bit(R5_UPTODATE,
					      &sh->dev[other].flags))
						break;
				}
				BUG_ON(other < 0);
				pr_debug("Computing stripe %llu blocks %d,%d\n",
				       (unsigned long long)sh->sector,
				       i, other);
				compute_block_2(sh, i, other);
				s->uptodate += 2;
			} else if (test_bit(R5_Insync, &dev->flags)) {
				set_bit(R5_LOCKED, &dev->flags);
				set_bit(R5_Wantread, &dev->flags);
				s->locked++;
				pr_debug("Reading block %d (sync=%d)\n",
					i, s->syncing);
			}
		}
	}
	set_bit(STRIPE_HANDLE, &sh->state);
}


/* handle_completed_write_requests
 * any written block on an uptodate or failed drive can be returned.
 * Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
 * never LOCKED, so we don't need to test 'failed' directly.
 */
static void handle_completed_write_requests(raid5_conf_t *conf,
	struct stripe_head *sh, int disks, struct bio **return_bi)
{
	int i;
	struct r5dev *dev;

	for (i = disks; i--; )
		if (sh->dev[i].written) {
			dev = &sh->dev[i];
			if (!test_bit(R5_LOCKED, &dev->flags) &&
				test_bit(R5_UPTODATE, &dev->flags)) {
				/* We can return any write requests */
				struct bio *wbi, *wbi2;
				int bitmap_end = 0;
				pr_debug("Return write for disc %d\n", i);
				spin_lock_irq(&conf->device_lock);
				wbi = dev->written;
				dev->written = NULL;
				while (wbi && wbi->bi_sector <
					dev->sector + STRIPE_SECTORS) {
					wbi2 = r5_next_bio(wbi, dev->sector);
					if (--wbi->bi_phys_segments == 0) {
						md_write_end(conf->mddev);
						wbi->bi_next = *return_bi;
						*return_bi = wbi;
					}
					wbi = wbi2;
				}
				if (dev->towrite == NULL)
					bitmap_end = 1;
				spin_unlock_irq(&conf->device_lock);
				if (bitmap_end)
					bitmap_endwrite(conf->mddev->bitmap,
							sh->sector,
							STRIPE_SECTORS,
					 !test_bit(STRIPE_DEGRADED, &sh->state),
							0);
			}
		}
}

static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
		struct stripe_head *sh,	struct stripe_head_state *s, int disks)
{
	int rmw = 0, rcw = 0, i;
	for (i = disks; i--; ) {
		/* would I have to read this buffer for read_modify_write */
		struct r5dev *dev = &sh->dev[i];
		if ((dev->towrite || i == sh->pd_idx) &&
		    !test_bit(R5_LOCKED, &dev->flags) &&
		    !(test_bit(R5_UPTODATE, &dev->flags) ||
		      test_bit(R5_Wantcompute, &dev->flags))) {
			if (test_bit(R5_Insync, &dev->flags))
				rmw++;
			else
				rmw += 2*disks;  /* cannot read it */
		}
		/* Would I have to read this buffer for reconstruct_write */
		if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx &&
		    !test_bit(R5_LOCKED, &dev->flags) &&
		    !(test_bit(R5_UPTODATE, &dev->flags) ||
		    test_bit(R5_Wantcompute, &dev->flags))) {
			if (test_bit(R5_Insync, &dev->flags)) rcw++;
			else
				rcw += 2*disks;
		}
	}
	pr_debug("for sector %llu, rmw=%d rcw=%d\n",
		(unsigned long long)sh->sector, rmw, rcw);
	set_bit(STRIPE_HANDLE, &sh->state);
	if (rmw < rcw && rmw > 0)
		/* prefer read-modify-write, but need to get some data */
		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if ((dev->towrite || i == sh->pd_idx) &&
			    !test_bit(R5_LOCKED, &dev->flags) &&
			    !(test_bit(R5_UPTODATE, &dev->flags) ||
			    test_bit(R5_Wantcompute, &dev->flags)) &&
			    test_bit(R5_Insync, &dev->flags)) {
				if (
				  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
					pr_debug("Read_old block "
						"%d for r-m-w\n", i);
					set_bit(R5_LOCKED, &dev->flags);
					set_bit(R5_Wantread, &dev->flags);
					if (!test_and_set_bit(
						STRIPE_OP_IO, &sh->ops.pending))
						sh->ops.count++;
					s->locked++;
				} else {
					set_bit(STRIPE_DELAYED, &sh->state);
					set_bit(STRIPE_HANDLE, &sh->state);
				}
			}
		}
	if (rcw <= rmw && rcw > 0)
		/* want reconstruct write, but need to get some data */
		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if (!test_bit(R5_OVERWRITE, &dev->flags) &&
			    i != sh->pd_idx &&
			    !test_bit(R5_LOCKED, &dev->flags) &&
			    !(test_bit(R5_UPTODATE, &dev->flags) ||
			    test_bit(R5_Wantcompute, &dev->flags)) &&
			    test_bit(R5_Insync, &dev->flags)) {
				if (
				  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
					pr_debug("Read_old block "
						"%d for Reconstruct\n", i);
					set_bit(R5_LOCKED, &dev->flags);
					set_bit(R5_Wantread, &dev->flags);
					if (!test_and_set_bit(
						STRIPE_OP_IO, &sh->ops.pending))
						sh->ops.count++;
					s->locked++;
				} else {
					set_bit(STRIPE_DELAYED, &sh->state);
					set_bit(STRIPE_HANDLE, &sh->state);
				}
			}
		}
	/* now if nothing is locked, and if we have enough data,
	 * we can start a write request
	 */
	/* since handle_stripe can be called at any time we need to handle the
	 * case where a compute block operation has been submitted and then a
	 * subsequent call wants to start a write request.  raid5_run_ops only
	 * handles the case where compute block and postxor are requested
	 * simultaneously.  If this is not the case then new writes need to be
	 * held off until the compute completes.
	 */
	if ((s->req_compute ||
	    !test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending)) &&
		(s->locked == 0 && (rcw == 0 || rmw == 0) &&
		!test_bit(STRIPE_BIT_DELAY, &sh->state)))
		s->locked += handle_write_operations5(sh, rcw == 0, 0);
}

static void handle_issuing_new_write_requests6(raid5_conf_t *conf,
		struct stripe_head *sh,	struct stripe_head_state *s,
		struct r6_state *r6s, int disks)
{
	int rcw = 0, must_compute = 0, pd_idx = sh->pd_idx, i;
	int qd_idx = r6s->qd_idx;
	for (i = disks; i--; ) {
		struct r5dev *dev = &sh->dev[i];
		/* Would I have to read this buffer for reconstruct_write */
		if (!test_bit(R5_OVERWRITE, &dev->flags)
		    && i != pd_idx && i != qd_idx
		    && (!test_bit(R5_LOCKED, &dev->flags)
			    ) &&
		    !test_bit(R5_UPTODATE, &dev->flags)) {
			if (test_bit(R5_Insync, &dev->flags)) rcw++;
			else {
				pr_debug("raid6: must_compute: "
					"disk %d flags=%#lx\n", i, dev->flags);
				must_compute++;
			}
		}
	}
	pr_debug("for sector %llu, rcw=%d, must_compute=%d\n",
	       (unsigned long long)sh->sector, rcw, must_compute);
	set_bit(STRIPE_HANDLE, &sh->state);

	if (rcw > 0)
		/* want reconstruct write, but need to get some data */
		for (i = disks; i--; ) {
			struct r5dev *dev = &sh->dev[i];
			if (!test_bit(R5_OVERWRITE, &dev->flags)
			    && !(s->failed == 0 && (i == pd_idx || i == qd_idx))
			    && !test_bit(R5_LOCKED, &dev->flags) &&
			    !test_bit(R5_UPTODATE, &dev->flags) &&
			    test_bit(R5_Insync, &dev->flags)) {
				if (
				  test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
					pr_debug("Read_old stripe %llu "
						"block %d for Reconstruct\n",
					     (unsigned long long)sh->sector, i);
					set_bit(R5_LOCKED, &dev->flags);
					set_bit(R5_Wantread, &dev->flags);
					s->locked++;
				} else {
					pr_debug("Request delayed stripe %llu "
						"block %d for Reconstruct\n",
					     (unsigned long long)sh->sector, i);
					set_bit(STRIPE_DELAYED, &sh->state);
					set_bit(STRIPE_HANDLE, &sh->state);
				}
			}
		}
	/* now if nothing is locked, and if we have enough data, we can start a
	 * write request
	 */
	if (s->locked == 0 && rcw == 0 &&
	    !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
		if (must_compute > 0) {
			/* We have failed blocks and need to compute them */
			switch (s->failed) {
			case 0:
				BUG();
			case 1:
				compute_block_1(sh, r6s->failed_num[0], 0);
				break;
			case 2:
				compute_block_2(sh, r6s->failed_num[0],
						r6s->failed_num[1]);
				break;
			default: /* This request should have been failed? */
				BUG();
			}
		}

		pr_debug("Com