[patch 3/3] OCFS2 Configurable timeouts - Protocol changes

Modify the OCFS2 handshake to ensure essential timeouts are configured
identically on all nodes.

Only allow changes when there are no connected peers

Improves the logic in o2net_advance_rx() which broke now that
sizeof(struct o2net_handshake) is greater than sizeof(struct o2net_msg)

Included is the field for userspace-heartbeat timeout to avoid the need for
further protocol changes.

Uses a global spinlock to ensure the decisions to update configfs entries
are made on the correct value.  The region covered by the spinlock when
incrementing the counter is much larger as this is the more critical case.

Small cleanup contributed by Adrian Bunk <bunk@stusta.de>

Signed-off-by: Andrew Beekhof <abeekhof@suse.de>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>

1 files changed, 24 insertions, 6 deletions

diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index 234f83f2897f..357f1d551771 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -573,12 +573,21 @@ static ssize_t o2nm_cluster_attr_idle_timeout_ms_write(
         ret =  o2nm_cluster_attr_write(page, count, &val);
 
         if (ret > 0) {
-                if (val <= cluster->cl_keepalive_delay_ms) {
+                if (cluster->cl_idle_timeout_ms != val
+                        && o2net_num_connected_peers()) {
+                        mlog(ML_NOTICE,
+                             "o2net: cannot change idle timeout after "
+                             "the first peer has agreed to it."
+                             "  %d connected peers\n",
+                             o2net_num_connected_peers());
+                        ret = -EINVAL;
+                } else if (val <= cluster->cl_keepalive_delay_ms) {
                         mlog(ML_NOTICE, "o2net: idle timeout must be larger "
                              "than keepalive delay\n");
-                        return -EINVAL;
+                        ret = -EINVAL;
+                } else {
+                        cluster->cl_idle_timeout_ms = val;
                 }
-                cluster->cl_idle_timeout_ms = val;
         }
 
         return ret;
@@ -599,12 +608,21 @@ static ssize_t o2nm_cluster_attr_keepalive_delay_ms_write(
         ret =  o2nm_cluster_attr_write(page, count, &val);
 
         if (ret > 0) {
-                if (val >= cluster->cl_idle_timeout_ms) {
+                if (cluster->cl_keepalive_delay_ms != val
+                    && o2net_num_connected_peers()) {
+                        mlog(ML_NOTICE,
+                             "o2net: cannot change keepalive delay after"
+                             " the first peer has agreed to it."
+                             "  %d connected peers\n",
+                             o2net_num_connected_peers());
+                        ret = -EINVAL;
+                } else if (val >= cluster->cl_idle_timeout_ms) {
                         mlog(ML_NOTICE, "o2net: keepalive delay must be "
                              "smaller than idle timeout\n");
-                        return -EINVAL;
+                        ret = -EINVAL;
+                } else {
+                        cluster->cl_keepalive_delay_ms = val;
                 }
-                cluster->cl_keepalive_delay_ms = val;
         }
 
         return ret;