return cmp_int(l->journal_seq, r->journal_seq);
}
-static int bch2_btree_write_buffer_flush_one(struct btree_trans *trans,
- struct btree_iter *iter,
- struct btree_write_buffered_key *wb,
- unsigned commit_flags,
- bool *write_locked,
- size_t *fast)
+static noinline int wb_flush_one_slowpath(struct btree_trans *trans,
+ struct btree_iter *iter,
+ struct btree_write_buffered_key *wb)
+{
+ bch2_btree_node_unlock_write(trans, iter->path, iter->path->l[0].b);
+
+ trans->journal_res.seq = wb->journal_seq;
+
+ return bch2_trans_update(trans, iter, &wb->k,
+ BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
+ bch2_trans_commit(trans, NULL, NULL,
+ BCH_TRANS_COMMIT_no_enospc|
+ BCH_TRANS_COMMIT_no_check_rw|
+ BCH_TRANS_COMMIT_no_journal_res|
+ BCH_TRANS_COMMIT_journal_reclaim);
+}
+
+static inline int wb_flush_one(struct btree_trans *trans, struct btree_iter *iter,
+ struct btree_write_buffered_key *wb,
+ bool *write_locked, size_t *fast)
{
struct bch_fs *c = trans->c;
struct btree_path *path;
int ret;
+ EBUG_ON(!wb->journal_seq);
ret = bch2_btree_iter_traverse(iter);
if (ret)
return ret;
*write_locked = true;
}
- if (!bch2_btree_node_insert_fits(c, path->l[0].b, wb->k.k.u64s)) {
- bch2_btree_node_unlock_write(trans, path, path->l[0].b);
+ if (unlikely(!bch2_btree_node_insert_fits(c, path->l[0].b, wb->k.k.u64s))) {
*write_locked = false;
- goto trans_commit;
+ return wb_flush_one_slowpath(trans, iter, wb);
}
bch2_btree_insert_key_leaf(trans, path, &wb->k, wb->journal_seq);
(*fast)++;
return 0;
-trans_commit:
- trans->journal_res.seq = wb->journal_seq;
-
- return bch2_trans_update(trans, iter, &wb->k,
- BTREE_UPDATE_INTERNAL_SNAPSHOT_NODE) ?:
- bch2_trans_commit(trans, NULL, NULL,
- commit_flags|
- BCH_TRANS_COMMIT_no_check_rw|
- BCH_TRANS_COMMIT_no_enospc|
- BCH_TRANS_COMMIT_no_journal_res|
- BCH_TRANS_COMMIT_journal_reclaim);
}
static union btree_write_buffer_state btree_write_buffer_switch(struct btree_write_buffer *wb)
keys = wb->keys[s.idx];
nr = s.nr;
- if (race_fault())
- goto slowpath;
-
/*
* We first sort so that we can detect and skip redundant updates, and
* then we attempt to flush in sorted btree order, as this is most
iter.path->preserve = false;
do {
- ret = bch2_btree_write_buffer_flush_one(trans, &iter, i, 0,
- &write_locked, &fast);
+ if (race_fault()) {
+ ret = -BCH_ERR_journal_reclaim_would_deadlock;
+ break;
+ }
+
+ ret = wb_flush_one(trans, &iter, i, &write_locked, &fast);
if (!write_locked)
bch2_trans_begin(trans);
} while (bch2_err_matches(ret, BCH_ERR_transaction_restart));
- if (ret == -BCH_ERR_journal_reclaim_would_deadlock) {
+ if (!ret) {
+ i->journal_seq = 0;
+ } else if (ret == -BCH_ERR_journal_reclaim_would_deadlock) {
slowpath++;
- continue;
- }
- if (ret)
+ ret = 0;
+ } else
break;
-
- i->journal_seq = 0;
}
if (write_locked)
bch2_btree_node_unlock_write(trans, iter.path, iter.path->l[0].b);
bch2_trans_iter_exit(trans, &iter);
- trace_write_buffer_flush(trans, nr, skipped, fast, wb->size);
-
- if (slowpath)
- goto slowpath;
-
+ if (ret)
+ goto err;
+
+ if (slowpath) {
+ /*
+ * Flush in the order they were present in the journal, so that
+ * we can release journal pins:
+ * The fastpath zapped the seq of keys that were successfully flushed so
+ * we can skip those here.
+ */
+ trace_and_count(c, write_buffer_flush_slowpath, trans, slowpath, nr);
+
+ sort(keys, nr, sizeof(keys[0]),
+ btree_write_buffered_journal_cmp,
+ NULL);
+
+ for (i = keys; i < keys + nr; i++) {
+ if (!i->journal_seq)
+ continue;
+
+ bch2_journal_pin_update(j, i->journal_seq, &pin,
+ bch2_btree_write_buffer_journal_flush);
+
+ ret = commit_do(trans, NULL, NULL,
+ BCH_WATERMARK_reclaim|
+ BCH_TRANS_COMMIT_no_check_rw|
+ BCH_TRANS_COMMIT_no_enospc|
+ BCH_TRANS_COMMIT_no_journal_res|
+ BCH_TRANS_COMMIT_journal_reclaim,
+ btree_write_buffered_insert(trans, i));
+ if (ret)
+ goto err;
+ }
+ }
+err:
bch2_fs_fatal_err_on(ret, c, "%s: insert error %s", __func__, bch2_err_str(ret));
-out:
+ trace_write_buffer_flush(trans, nr, skipped, fast, wb->size);
bch2_journal_pin_drop(j, &pin);
return ret;
-slowpath:
- trace_and_count(c, write_buffer_flush_slowpath, trans, slowpath, nr);
-
- /*
- * Now sort the rest by journal seq and bump the journal pin as we go.
- * The slowpath zapped the seq of keys that were successfully flushed so
- * we can skip those here.
- */
- sort(keys, nr, sizeof(keys[0]),
- btree_write_buffered_journal_cmp,
- NULL);
-
- for (i = keys; i < keys + nr; i++) {
- if (!i->journal_seq)
- continue;
-
- bch2_journal_pin_update(j, i->journal_seq, &pin,
- bch2_btree_write_buffer_journal_flush);
-
- ret = commit_do(trans, NULL, NULL,
- BCH_WATERMARK_reclaim|
- BCH_TRANS_COMMIT_no_check_rw|
- BCH_TRANS_COMMIT_no_enospc|
- BCH_TRANS_COMMIT_no_journal_res|
- BCH_TRANS_COMMIT_journal_reclaim,
- btree_write_buffered_insert(trans, i));
- if (bch2_fs_fatal_err_on(ret, c, "%s: insert error %s", __func__, bch2_err_str(ret)))
- break;
- }
-
- goto out;
}
int bch2_btree_write_buffer_flush_sync(struct btree_trans *trans)