Commit 94119eeb authored by Kent Overstreet's avatar Kent Overstreet
Browse files

bcachefs: Add IO error counts to bch_member 



We now track IO errors per device since filesystem creation.

IO error counts can be viewed in sysfs, or with the 'bcachefs
show-super' command.

Signed-off-by: default avatarKent Overstreet <kent.overstreet@linux.dev>
parent 5394fe94

fs/bcachefs/bcachefs.h

+2 −0
Original line number Diff line number Diff line
@@ -502,6 +502,8 @@ struct bch_dev { 
	 * Committed by bch2_write_super() -> bch_fs_mi_update()

	 */

	struct bch_member_cpu	mi;

	atomic64_t		errors[BCH_MEMBER_ERROR_NR];



	__uuid_t		uuid;

	char			name[BDEVNAME_SIZE];

fs/bcachefs/bcachefs_format.h

+15 −0
Original line number Diff line number Diff line
@@ -1268,6 +1268,18 @@ enum bch_iops_measurement { 
	BCH_IOPS_NR

};



#define BCH_MEMBER_ERROR_TYPES()		\

	x(read,		0)			\

	x(write,	1)			\

	x(checksum,	2)



enum bch_member_error_type {

#define x(t, n) BCH_MEMBER_ERROR_##t = n,

	BCH_MEMBER_ERROR_TYPES()

#undef x

	BCH_MEMBER_ERROR_NR

};



struct bch_member {

	__uuid_t		uuid;

	__le64			nbuckets;	/* device size */
@@ -1278,6 +1290,9 @@ struct bch_member { 


	__le64			flags;

	__le32			iops[4];

	__le64			errors[BCH_MEMBER_ERROR_NR];

	__le64			errors_at_reset[BCH_MEMBER_ERROR_NR];

	__le64			errors_reset_time;

};



#define BCH_MEMBER_V1_BYTES	56

fs/bcachefs/btree_io.c

+16 −7
Original line number Diff line number Diff line
@@ -934,8 +934,8 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, 
	while (b->written < (ptr_written ?: btree_sectors(c))) {

		unsigned sectors;

		struct nonce nonce;

		struct bch_csum csum;

		bool first = !b->written;

		bool csum_bad;



		if (!b->written) {

			i = &b->data->keys;
@@ -946,9 +946,13 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, 
				     BSET_CSUM_TYPE(i));



			nonce = btree_nonce(i, b->written << 9);

			csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data);



			btree_err_on(bch2_crc_cmp(csum, b->data->csum),

			csum_bad = bch2_crc_cmp(b->data->csum,

				csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, b->data));

			if (csum_bad)

				bch2_io_error(ca, BCH_MEMBER_ERROR_checksum);



			btree_err_on(csum_bad,

				     -BCH_ERR_btree_node_read_err_want_retry, c, ca, b, i,

				     "invalid checksum");
@@ -976,9 +980,12 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca, 
				     BSET_CSUM_TYPE(i));



			nonce = btree_nonce(i, b->written << 9);

			csum = csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne);

			csum_bad = bch2_crc_cmp(bne->csum,

				csum_vstruct(c, BSET_CSUM_TYPE(i), nonce, bne));

			if (csum_bad)

				bch2_io_error(ca, BCH_MEMBER_ERROR_checksum);



			btree_err_on(bch2_crc_cmp(csum, bne->csum),

			btree_err_on(csum_bad,

				     -BCH_ERR_btree_node_read_err_want_retry, c, ca, b, i,

				     "invalid checksum");
@@ -1168,7 +1175,8 @@ static void btree_node_read_work(struct work_struct *work) 
start:

		printbuf_reset(&buf);

		bch2_btree_pos_to_text(&buf, c, b);

		bch2_dev_io_err_on(bio->bi_status, ca, "btree read error %s for %s",

		bch2_dev_io_err_on(bio->bi_status, ca, BCH_MEMBER_ERROR_read,

				   "btree read error %s for %s",

				   bch2_blk_status_to_str(bio->bi_status), buf.buf);

		if (rb->have_ioref)

			percpu_ref_put(&ca->io_ref);
@@ -1749,7 +1757,8 @@ static void btree_node_write_endio(struct bio *bio) 
	if (wbio->have_ioref)

		bch2_latency_acct(ca, wbio->submit_time, WRITE);



	if (bch2_dev_io_err_on(bio->bi_status, ca, "btree write error: %s",

	if (bch2_dev_io_err_on(bio->bi_status, ca, BCH_MEMBER_ERROR_write,

			       "btree write error: %s",

			       bch2_blk_status_to_str(bio->bi_status)) ||

	    bch2_meta_write_fault("btree")) {

		spin_lock_irqsave(&c->btree_write_error_lock, flags);

fs/bcachefs/ec.c

+5 −1
Original line number Diff line number Diff line
@@ -373,7 +373,11 @@ static void ec_block_endio(struct bio *bio) 
	struct bch_dev *ca = ec_bio->ca;

	struct closure *cl = bio->bi_private;



	if (bch2_dev_io_err_on(bio->bi_status, ca, "erasure coding %s error: %s",

	if (bch2_dev_io_err_on(bio->bi_status, ca,

			       bio_data_dir(bio)

			       ? BCH_MEMBER_ERROR_write

			       : BCH_MEMBER_ERROR_read,

			       "erasure coding %s error: %s",

			       bio_data_dir(bio) ? "write" : "read",

			       bch2_blk_status_to_str(bio->bi_status)))

		clear_bit(ec_bio->idx, ec_bio->buf->valid);

fs/bcachefs/error.c

+2 −1
Original line number Diff line number Diff line
@@ -56,8 +56,9 @@ void bch2_io_error_work(struct work_struct *work) 
	up_write(&c->state_lock);

}



void bch2_io_error(struct bch_dev *ca)

void bch2_io_error(struct bch_dev *ca, enum bch_member_error_type type)

{

	atomic64_inc(&ca->errors[type]);

	//queue_work(system_long_wq, &ca->io_error_work);

}