bcachefs: Fix 'journal not marked as containing replicas'

This fixes the replicas_write_errors test: the patch
  bcachefs: mark journal replicas before journal write submission

partially fixed replicas marking for the journal, but it broke the case
where one replica failed - this patch re-adds marking after the journal
write completes, when we know how many replicas succeeded.

Additionally, we do not consider it a fsck error when the very last
journal entry is not correctly marked, since there is an inherent race
there.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This commit is contained in:
Kent Overstreet 2023-08-11 19:30:38 -04:00
parent 401585fe87
commit 83b3d9598a

View File

@ -1305,18 +1305,14 @@ int bch2_journal_read(struct bch_fs *c,
bch2_replicas_entry_sort(&replicas.e);
/*
* If we're mounting in degraded mode - if we didn't read all
* the devices - this is wrong:
*/
printbuf_reset(&buf);
bch2_replicas_entry_to_text(&buf, &replicas.e);
if (!degraded &&
fsck_err_on(!bch2_replicas_marked(c, &replicas.e), c,
"superblock not marked as containing replicas %s",
buf.buf)) {
!bch2_replicas_marked(c, &replicas.e) &&
(le64_to_cpu(i->j.seq) == *last_seq ||
fsck_err(c, "superblock not marked as containing replicas for journal entry %llu\n %s",
le64_to_cpu(i->j.seq), buf.buf))) {
ret = bch2_mark_replicas(c, &replicas.e);
if (ret)
goto err;
@ -1483,6 +1479,7 @@ static void journal_write_done(struct closure *cl)
struct journal *j = container_of(cl, struct journal, io);
struct bch_fs *c = container_of(j, struct bch_fs, journal);
struct journal_buf *w = journal_last_unwritten_buf(j);
struct bch_replicas_padded replicas;
union journal_res_state old, new;
u64 v, seq;
int err = 0;
@ -1494,7 +1491,13 @@ static void journal_write_done(struct closure *cl)
if (!w->devs_written.nr) {
bch_err(c, "unable to write journal to sufficient devices");
err = -EIO;
} else {
bch2_devlist_to_replicas(&replicas.e, BCH_DATA_journal,
w->devs_written);
if (bch2_mark_replicas(c, &replicas.e))
err = -EIO;
}
if (err)
bch2_fatal_error(c);