else
root = &mdev->read_requests;
drbd_remove_request_interval(root, req);
- } else if (!(s & RQ_POSTPONED))
- D_ASSERT((s & (RQ_NET_MASK & ~RQ_NET_DONE)) == 0);
+ }
/* Before we can signal completion to the upper layers,
* we may need to close the current transfer log epoch.
D_ASSERT(req->rq_state & RQ_NET_PENDING);
mod_rq_state(req, m, RQ_NET_PENDING, RQ_NET_OK|RQ_NET_DONE);
break;
+
+ case QUEUE_AS_DRBD_BARRIER:
+ start_new_tl_epoch(mdev->tconn);
+ mod_rq_state(req, m, 0, RQ_NET_OK|RQ_NET_DONE);
+ break;
};
return rv;
bool congested = false;
enum drbd_on_congestion on_congestion;
+ rcu_read_lock();
nc = rcu_dereference(tconn->net_conf);
on_congestion = nc ? nc->on_congestion : OC_BLOCK;
+ rcu_read_unlock();
if (on_congestion == OC_BLOCK ||
tconn->agreed_pro_version < 96)
return;
struct drbd_conf *mdev = req->w.mdev;
int remote, send_oos;
- rcu_read_lock();
remote = drbd_should_do_remote(mdev->state);
- if (remote) {
- maybe_pull_ahead(mdev);
- remote = drbd_should_do_remote(mdev->state);
- }
send_oos = drbd_should_send_out_of_sync(mdev->state);
- rcu_read_unlock();
/* Need to replicate writes. Unless it is an empty flush,
* which is better mapped to a DRBD P_BARRIER packet,
/* The only size==0 bios we expect are empty flushes. */
D_ASSERT(req->master_bio->bi_rw & REQ_FLUSH);
if (remote)
- start_new_tl_epoch(mdev->tconn);
- return 0;
+ _req_mod(req, QUEUE_AS_DRBD_BARRIER);
+ return remote;
}
if (!remote && !send_oos)
bio_endio(bio, -EIO);
}
+static void drbd_queue_write(struct drbd_conf *mdev, struct drbd_request *req)
+{
+ spin_lock(&mdev->submit.lock);
+ list_add_tail(&req->tl_requests, &mdev->submit.writes);
+ spin_unlock(&mdev->submit.lock);
+ queue_work(mdev->submit.wq, &mdev->submit.worker);
+}
+
/* returns the new drbd_request pointer, if the caller is expected to
* drbd_send_and_submit() it (to save latency), or NULL if we queued the
* request on the submitter thread.
req->private_bio = NULL;
}
- /* For WRITES going to the local disk, grab a reference on the target
- * extent. This waits for any resync activity in the corresponding
- * resync extent to finish, and, if necessary, pulls in the target
- * extent into the activity log, which involves further disk io because
- * of transactional on-disk meta data updates.
- * Empty flushes don't need to go into the activity log, they can only
- * flush data for pending writes which are already in there. */
+ /* Update disk stats */
+ _drbd_start_io_acct(mdev, req);
+
if (rw == WRITE && req->private_bio && req->i.size
&& !test_bit(AL_SUSPENDED, &mdev->flags)) {
+ if (!drbd_al_begin_io_fastpath(mdev, &req->i)) {
+ drbd_queue_write(mdev, req);
+ return NULL;
+ }
req->rq_state |= RQ_IN_ACT_LOG;
- drbd_al_begin_io(mdev, &req->i, true);
}
return req;
* but will re-aquire it before it returns here.
* Needs to be before the check on drbd_suspended() */
complete_conflicting_writes(req);
+ /* no more giving up req_lock from now on! */
+
+ /* check for congestion, and potentially stop sending
+ * full data updates, but start sending "dirty bits" only. */
+ maybe_pull_ahead(mdev);
}
- /* no more giving up req_lock from now on! */
if (drbd_suspended(mdev)) {
/* push back and retry: */
goto out;
}
- /* Update disk stats */
- _drbd_start_io_acct(mdev, req);
-
/* We fail READ/READA early, if we can not serve it.
* We must do this before req is registered on any lists.
* Otherwise, drbd_req_complete() will queue failed READ for retry. */
drbd_send_and_submit(mdev, req);
}
-void __drbd_make_request_from_worker(struct drbd_conf *mdev, struct drbd_request *req)
+static void submit_fast_path(struct drbd_conf *mdev, struct list_head *incoming)
{
- const int rw = bio_rw(req->master_bio);
+ struct drbd_request *req, *tmp;
+ list_for_each_entry_safe(req, tmp, incoming, tl_requests) {
+ const int rw = bio_data_dir(req->master_bio);
- if (rw == WRITE && req->private_bio && req->i.size
- && !test_bit(AL_SUSPENDED, &mdev->flags)) {
- drbd_al_begin_io(mdev, &req->i, false);
- req->rq_state |= RQ_IN_ACT_LOG;
+ if (rw == WRITE /* rw != WRITE should not even end up here! */
+ && req->private_bio && req->i.size
+ && !test_bit(AL_SUSPENDED, &mdev->flags)) {
+ if (!drbd_al_begin_io_fastpath(mdev, &req->i))
+ continue;
+
+ req->rq_state |= RQ_IN_ACT_LOG;
+ }
+
+ list_del_init(&req->tl_requests);
+ drbd_send_and_submit(mdev, req);
}
- drbd_send_and_submit(mdev, req);
}
+static bool prepare_al_transaction_nonblock(struct drbd_conf *mdev,
+ struct list_head *incoming,
+ struct list_head *pending)
+{
+ struct drbd_request *req, *tmp;
+ int wake = 0;
+ int err;
+
+ spin_lock_irq(&mdev->al_lock);
+ list_for_each_entry_safe(req, tmp, incoming, tl_requests) {
+ err = drbd_al_begin_io_nonblock(mdev, &req->i);
+ if (err == -EBUSY)
+ wake = 1;
+ if (err)
+ continue;
+ req->rq_state |= RQ_IN_ACT_LOG;
+ list_move_tail(&req->tl_requests, pending);
+ }
+ spin_unlock_irq(&mdev->al_lock);
+ if (wake)
+ wake_up(&mdev->al_wait);
+
+ return !list_empty(pending);
+}
void do_submit(struct work_struct *ws)
{
struct drbd_conf *mdev = container_of(ws, struct drbd_conf, submit.worker);
- LIST_HEAD(writes);
+ LIST_HEAD(incoming);
+ LIST_HEAD(pending);
struct drbd_request *req, *tmp;
- spin_lock(&mdev->submit.lock);
- list_splice_init(&mdev->submit.writes, &writes);
- spin_unlock(&mdev->submit.lock);
+ for (;;) {
+ spin_lock(&mdev->submit.lock);
+ list_splice_tail_init(&mdev->submit.writes, &incoming);
+ spin_unlock(&mdev->submit.lock);
- list_for_each_entry_safe(req, tmp, &writes, tl_requests) {
- list_del_init(&req->tl_requests);
- __drbd_make_request_from_worker(mdev, req);
+ submit_fast_path(mdev, &incoming);
+ if (list_empty(&incoming))
+ break;
+
+ wait_event(mdev->al_wait, prepare_al_transaction_nonblock(mdev, &incoming, &pending));
+ /* Maybe more was queued, while we prepared the transaction?
+ * Try to stuff them into this transaction as well.
+ * Be strictly non-blocking here, no wait_event, we already
+ * have something to commit.
+ * Stop if we don't make any more progres.
+ */
+ for (;;) {
+ LIST_HEAD(more_pending);
+ LIST_HEAD(more_incoming);
+ bool made_progress;
+
+ /* It is ok to look outside the lock,
+ * it's only an optimization anyways */
+ if (list_empty(&mdev->submit.writes))
+ break;
+
+ spin_lock(&mdev->submit.lock);
+ list_splice_tail_init(&mdev->submit.writes, &more_incoming);
+ spin_unlock(&mdev->submit.lock);
+
+ if (list_empty(&more_incoming))
+ break;
+
+ made_progress = prepare_al_transaction_nonblock(mdev, &more_incoming, &more_pending);
+
+ list_splice_tail_init(&more_pending, &pending);
+ list_splice_tail_init(&more_incoming, &incoming);
+
+ if (!made_progress)
+ break;
+ }
+ drbd_al_begin_io_commit(mdev, false);
+
+ list_for_each_entry_safe(req, tmp, &pending, tl_requests) {
+ list_del_init(&req->tl_requests);
+ drbd_send_and_submit(mdev, req);
+ }
}
}