Snapshots are huge. In some cases we could receive several outdated
append replies from the remote server. This could happen in high
scale cases if the remote server is overloaded and not able to process
all the raft requests in time. As an action to each outdated append
reply we're sending full database snapshot. While remote server is
already overloaded those snapshots will stuck in jsonrpc backlog for
a long time making it grow up to few GB. Since remote server wasn't
able to timely process incoming messages it will likely not able to
process snapshots leading to the same situation with low chances to
recover. Remote server will likely stuck in 'candidate' state, other
servers will grow their memory consumption due to growing jsonrpc
backlogs:
jsonrpc|INFO|excessive sending backlog, jsonrpc: ssl:192.16.0.3:6644,
num of msgs: 3795, backlog: 8838994624.
This patch is trying to avoid that situation by avoiding sending of
equal snapshot install requests. This helps maintain reasonable memory
consumption and allows the cluster to recover on a larger scale.
Signed-off-by: Ilya Maximets <i.maxim...@ovn.org>
---
I'm not an expert in this code, so there might be better way to track
equal snapshot installation requests. Suggestions are welcome.
ovsdb/raft-private.c | 1 +
ovsdb/raft-private.h | 4 ++++
ovsdb/raft.c | 39 ++++++++++++++++++++++++++++++++++++++-
3 files changed, 43 insertions(+), 1 deletion(-)
diff --git a/ovsdb/raft-private.c b/ovsdb/raft-private.c
index 26d39a087..9468fdaf4 100644
--- a/ovsdb/raft-private.c
+++ b/ovsdb/raft-private.c
@@ -137,6 +137,7 @@ raft_server_destroy(struct raft_server *s)
if (s) {
free(s->address);
free(s->nickname);
+ free(s->last_install_snapshot_request);
free(s);
}
}
diff --git a/ovsdb/raft-private.h b/ovsdb/raft-private.h
index ac8656d42..1f366b4ab 100644
--- a/ovsdb/raft-private.h
+++ b/ovsdb/raft-private.h
@@ -27,6 +27,7 @@
struct ds;
struct ovsdb_parser;
+struct raft_install_snapshot_request;
/* Formatting server IDs and cluster IDs for use in human-readable logs. Do
* not use these in cases where the whole server or cluster ID is needed; use
@@ -83,6 +84,9 @@ struct raft_server {
bool replied; /* Reply to append_request was received from this
node during current election_timeout interval.
*/
+ /* Copy of the last install_snapshot_request sent to this server. */
+ struct raft_install_snapshot_request *last_install_snapshot_request;
+
/* For use in adding and removing servers: */
struct uuid requester_sid; /* Nonzero if requested via RPC. */
struct unixctl_conn *requester_conn; /* Only if requested via unixctl. */
diff --git a/ovsdb/raft.c b/ovsdb/raft.c
index 515eadab3..708b0624c 100644
--- a/ovsdb/raft.c
+++ b/ovsdb/raft.c
@@ -1421,8 +1421,20 @@ raft_conn_run(struct raft *raft, struct raft_conn *conn)
jsonrpc_session_run(conn->js);
unsigned int new_seqno = jsonrpc_session_get_seqno(conn->js);
- bool just_connected = (new_seqno != conn->js_seqno
+ bool reconnected = new_seqno != conn->js_seqno;
+ bool just_connected = (reconnected
&& jsonrpc_session_is_connected(conn->js));
+
+ if (reconnected) {
+ /* Clear 'last_install_snapshot_request' since it might not reach the
+ * destination or server was restarted. */
+ struct raft_server *server = raft_find_server(raft, &conn->sid);
+ if (server) {
+ free(server->last_install_snapshot_request);
+ server->last_install_snapshot_request = NULL;
+ }
+ }
+
conn->js_seqno = new_seqno;
if (just_connected) {
if (raft->joining) {
@@ -3296,6 +3308,31 @@ raft_send_install_snapshot_request(struct raft *raft,
.election_timer = raft->election_timer, /* use latest value */
}
};
+
+ if (s->last_install_snapshot_request) {
+ struct raft_install_snapshot_request *old, *new;
+
+ old = s->last_install_snapshot_request;
+ new = &rpc.install_snapshot_request;
+ if ( old->term == new->term
+ && old->last_index == new->last_index
+ && old->last_term == new->last_term
+ && old->last_servers == new->last_servers
+ && old->data == new->data
+ && old->election_timer == new->election_timer
+ && uuid_equals(&old->last_eid, &new->last_eid)) {
+ static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 5);
+
+ VLOG_WARN_RL(&rl, "not sending exact same install_snapshot_request"
+ " to server %s again", s->nickname);
+ return;
+ }
+ }
+ free(s->last_install_snapshot_request);
+ CONST_CAST(struct raft_server *, s)->last_install_snapshot_request
+ = xmemdup(&rpc.install_snapshot_request,
+ sizeof rpc.install_snapshot_request);
+
raft_send(raft, &rpc);
}
--
2.25.4
_______________________________________________
dev mailing list
d...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-dev
