search for: nd_num

...ons(+), 2 deletions(-) diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index aa75ca3..7e4e451 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1796,9 +1796,9 @@ static int o2net_accept_one(struct socket *sock) goto out; } - if (o2nm_this_node() > node->nd_num) { + if (o2nm_this_node() >= node->nd_num) { mlog(ML_NOTICE, "unexpected connect attempted from a lower " - "numbered node '%s' at " "%pI4:%d with num %u\n", + "or same numbered node '%s' at " "%pI4:%d with num %u\n&q...

This fix modifies o2net layer behavior which seems to trigger some DLM race issues during umount/evictions that needs to be fixed as well. I am working on the dlm issues but meanwhile please review this patch. Thanks, --Srini

...num); - /* ensure an immediate connect attempt */ nn->nn_last_connect_attempt = jiffies - (msecs_to_jiffies(O2NET_RECONNECT_DELAY_MS) + 1); @@ -1739,7 +1730,7 @@ int o2net_start_listening(struct o2nm_no destroy_workqueue(o2net_wq); o2net_wq = NULL; } else - o2quo_conn_up(node->nd_num); + o2hb_notify(O2HB_CONN_UP_CB, node, node->nd_num); return ret; } @@ -1776,7 +1767,7 @@ void o2net_stop_listening(struct o2nm_no sock_release(o2net_listen_sock); o2net_listen_sock = NULL; - o2quo_conn_err(node->nd_num); + o2hb_notify(O2HB_CONN_DOWN_CB, node, node->nd_num); }...

...#39;t try reconnecting. - * the only way to start connecting again is to down - * heartbeat and bring it back up. */ cancel_delayed_work(&nn->nn_connect_expired); printk(KERN_INFO "o2net: %s " SC_NODEF_FMT "\n", o2nm_this_node() > sc->sc_node->nd_num ? @@ -457,6 +450,8 @@ static void o2net_set_nn_state(struct o2 delay = 0; mlog(ML_CONN, "queueing conn attempt in %lu jiffies\n", delay); queue_delayed_work(o2net_wq, &nn->nn_connect_work, delay); + queue_delayed_work(o2net_wq, &nn->nn_connect_expired, + delay +...

...930,19 +927,22 @@ static int o2net_send_tcp_msg(struct socket *sock, struct kvec *vec, } static void o2net_sendpage(struct o2net_sock_container *sc, - void *kmalloced_virt, - size_t size) + void *virt, size_t size) { struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num); + struct msghdr msg = {}; + struct bio_vec bv; ssize_t ret; + bvec_set_virt(&bv, virt, size); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, size); + while (1) { + msg.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES; mutex_lock(&sc->sc_send_lock); - ret = sc->sc_...

...930,19 +927,22 @@ static int o2net_send_tcp_msg(struct socket *sock, struct kvec *vec, } static void o2net_sendpage(struct o2net_sock_container *sc, - void *kmalloced_virt, - size_t size) + void *virt, size_t size) { struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num); + struct msghdr msg = {}; + struct bio_vec bv; ssize_t ret; + bvec_set_virt(&bv, virt, size); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, size); + while (1) { + msg.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES; mutex_lock(&sc->sc_send_lock); - ret = sc->sc_...

...930,19 +927,22 @@ static int o2net_send_tcp_msg(struct socket *sock, struct kvec *vec, } static void o2net_sendpage(struct o2net_sock_container *sc, - void *kmalloced_virt, - size_t size) + void *virt, size_t size) { struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num); + struct msghdr msg = {}; + struct bio_vec bv; ssize_t ret; + bvec_set_virt(&bv, virt, size); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, size); + while (1) { + msg.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES; mutex_lock(&sc->sc_send_lock); - ret = sc->sc_...

...930,19 +927,22 @@ static int o2net_send_tcp_msg(struct socket *sock, struct kvec *vec, } static void o2net_sendpage(struct o2net_sock_container *sc, - void *kmalloced_virt, - size_t size) + void *virt, size_t size) { struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num); + struct msghdr msg = {}; + struct bio_vec bv; ssize_t ret; + bvec_set_virt(&bv, virt, size); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, size); + while (1) { + msg.msg_flags = MSG_DONTWAIT | MSG_SPLICE_PAGES; mutex_lock(&sc->sc_send_lock); - ret = sc->sc_...

...#39;t try reconnecting. - * the only way to start connecting again is to down - * heartbeat and bring it back up. */ cancel_delayed_work(&nn->nn_connect_expired); printk(KERN_INFO "o2net: %s " SC_NODEF_FMT "\n", o2nm_this_node() > sc->sc_node->nd_num ? @@ -457,6 +450,18 @@ static void o2net_set_nn_state(struct o2 delay = 0; mlog(ML_CONN, "queueing conn attempt in %lu jiffies\n", delay); queue_delayed_work(o2net_wq, &nn->nn_connect_work, delay); + + /* + * Delay the expired work after idle timeout. + * + * We mi...

All, This is hopefully the final drop of the patches for adding global heartbeat to the o2cb stack. The diff from the previous set is here: http://oss.oracle.com/~smushran/global-hb-diff-2010-10-07 Implemented most of the suggestions provided by Joel and Wengang. The most important one was to activate the feature only at the end, Also, got mostly a clean run with checkpatch.pl. Sunil

The following series of patches comprises the bulk of our outstanding changes for Ocfs2. Aside from the usual set of cleanups and fixes that were inappropriate for 2.6.25, there are a few highlights: The '/sys/o2cb' directory has been moved to '/sys/fs/o2cb'. The new location meshes better with modern sysfs layout. A symbolic link has been placed in the old location so as to