Commit f5d26fa3 authored by Kent Overstreet's avatar Kent Overstreet
Browse files

bcachefs: bch_sb_field_errors 



Add a new superblock section to keep counts of errors seen since
filesystem creation: we'll be addingcounters for every distinct fsck
error.

The new superblock section has entries of the for [ id, count,
time_of_last_error ]; this is intended to let us see what errors are
occuring - and getting fixed - via show-super output.

Signed-off-by: default avatarKent Overstreet <kent.overstreet@linux.dev>
parent 94119eeb

fs/bcachefs/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -70,6 +70,7 @@ bcachefs-y := \ 
	reflink.o		\

	replicas.o		\

	sb-clean.o		\

	sb-errors.o		\

	sb-members.o		\

	siphash.o		\

	six.o			\

fs/bcachefs/bcachefs.h

+9 −5
Original line number Diff line number Diff line
@@ -209,6 +209,7 @@ 
#include "nocow_locking_types.h"

#include "opts.h"

#include "recovery_types.h"

#include "sb-errors_types.h"

#include "seqmutex.h"

#include "util.h"
@@ -992,11 +993,6 @@ struct bch_fs { 
	struct bio_set		dio_read_bioset;

	struct bio_set		nocow_flush_bioset;



	/* ERRORS */

	struct list_head	fsck_errors;

	struct mutex		fsck_error_lock;

	bool			fsck_alloc_err;



	/* QUOTAS */

	struct bch_memquota_type quotas[QTYP_NR];
@@ -1045,6 +1041,14 @@ struct bch_fs { 
	struct bch2_time_stats	times[BCH_TIME_STAT_NR];



	struct btree_transaction_stats btree_transaction_stats[BCH_TRANSACTIONS_NR];



	/* ERRORS */

	struct list_head	fsck_error_msgs;

	struct mutex		fsck_error_msgs_lock;

	bool			fsck_alloc_msgs_err;



	bch_sb_errors_cpu	fsck_error_counts;

	struct mutex		fsck_error_counts_lock;

};



extern struct wait_queue_head bch2_read_only_wait;

fs/bcachefs/bcachefs_format.h

+13 −1
Original line number Diff line number Diff line
@@ -1218,7 +1218,8 @@ struct bch_sb_field { 
	x(journal_seq_blacklist, 8)		\

	x(journal_v2,	9)			\

	x(counters,	10)			\

	x(members_v2,	11)

	x(members_v2,	11)			\

	x(errors,	12)



enum bch_sb_field_type {

#define x(f, nr)	BCH_SB_FIELD_##f = nr,
@@ -1621,6 +1622,17 @@ struct bch_sb_field_journal_seq_blacklist { 
	__u64			_data[];

};



struct bch_sb_field_errors {

	struct bch_sb_field	field;

	struct bch_sb_field_error_entry {

		__le64		v;

		__le64		last_error_time;

	}			entries[];

};



LE64_BITMASK(BCH_SB_ERROR_ENTRY_ID,	struct bch_sb_field_error_entry, v,  0, 16);

LE64_BITMASK(BCH_SB_ERROR_ENTRY_NR,	struct bch_sb_field_error_entry, v, 16, 64);



/* Superblock: */



/*

fs/bcachefs/errcode.h

+1 −0
Original line number Diff line number Diff line
@@ -213,6 +213,7 @@ 
	x(BCH_ERR_invalid_sb,		invalid_sb_crypt)			\

	x(BCH_ERR_invalid_sb,		invalid_sb_clean)			\

	x(BCH_ERR_invalid_sb,		invalid_sb_quota)			\

	x(BCH_ERR_invalid_sb,		invalid_sb_errors)			\

	x(BCH_ERR_invalid_sb,		invalid_sb_opt_compression)		\

	x(BCH_ERR_invalid,		invalid_bkey)				\

	x(BCH_ERR_operation_blocked,    nocow_lock_blocked)			\

fs/bcachefs/error.c

+11 −11
Original line number Diff line number Diff line
@@ -117,27 +117,27 @@ static struct fsck_err_state *fsck_err_get(struct bch_fs *c, const char *fmt) 
	if (test_bit(BCH_FS_FSCK_DONE, &c->flags))

		return NULL;



	list_for_each_entry(s, &c->fsck_errors, list)

	list_for_each_entry(s, &c->fsck_error_msgs, list)

		if (s->fmt == fmt) {

			/*

			 * move it to the head of the list: repeated fsck errors

			 * are common

			 */

			list_move(&s->list, &c->fsck_errors);

			list_move(&s->list, &c->fsck_error_msgs);

			return s;

		}



	s = kzalloc(sizeof(*s), GFP_NOFS);

	if (!s) {

		if (!c->fsck_alloc_err)

		if (!c->fsck_alloc_msgs_err)

			bch_err(c, "kmalloc err, cannot ratelimit fsck errs");

		c->fsck_alloc_err = true;

		c->fsck_alloc_msgs_err = true;

		return NULL;

	}



	INIT_LIST_HEAD(&s->list);

	s->fmt = fmt;

	list_add(&s->list, &c->fsck_errors);

	list_add(&s->list, &c->fsck_error_msgs);

	return s;

}
@@ -153,7 +153,7 @@ int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...) 
	prt_vprintf(out, fmt, args);

	va_end(args);



	mutex_lock(&c->fsck_error_lock);

	mutex_lock(&c->fsck_error_msgs_lock);

	s = fsck_err_get(c, fmt);

	if (s) {

		/*
@@ -163,7 +163,7 @@ int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...) 
		 */

		if (s->last_msg && !strcmp(buf.buf, s->last_msg)) {

			ret = s->ret;

			mutex_unlock(&c->fsck_error_lock);

			mutex_unlock(&c->fsck_error_msgs_lock);

			printbuf_exit(&buf);

			return ret;

		}
@@ -258,7 +258,7 @@ int bch2_fsck_err(struct bch_fs *c, unsigned flags, const char *fmt, ...) 
	if (s)

		s->ret = ret;



	mutex_unlock(&c->fsck_error_lock);

	mutex_unlock(&c->fsck_error_msgs_lock);



	printbuf_exit(&buf);
@@ -279,9 +279,9 @@ void bch2_flush_fsck_errs(struct bch_fs *c) 
{

	struct fsck_err_state *s, *n;



	mutex_lock(&c->fsck_error_lock);

	mutex_lock(&c->fsck_error_msgs_lock);



	list_for_each_entry_safe(s, n, &c->fsck_errors, list) {

	list_for_each_entry_safe(s, n, &c->fsck_error_msgs, list) {

		if (s->ratelimited && s->last_msg)

			bch_err(c, "Saw %llu errors like:\n    %s", s->nr, s->last_msg);
@@ -290,5 +290,5 @@ void bch2_flush_fsck_errs(struct bch_fs *c) 
		kfree(s);

	}



	mutex_unlock(&c->fsck_error_lock);

	mutex_unlock(&c->fsck_error_msgs_lock);

}