etcd/rafthttp
Gyuho Lee b6d11019e0 rafthttp: probe all raft transports
This PR adds another probing routine to monitor the connection
for Raft message transports. Previously, we only monitored
snapshot transports.

In our production cluster, we found one TCP connection had >8-sec
latencies to a remote peer, but "etcd_network_peer_round_trip_time_seconds"
metrics shows <1-sec latency distribution, which means etcd server
was not sampling enough while such latency spikes happen
outside of snapshot pipeline connection.

Signed-off-by: Gyuho Lee <leegyuho@amazon.com>
2018-10-09 18:17:16 -07:00
..
coder.go rafthttp: use pointers to avoid extra copies upon message encoding 2016-06-29 21:17:18 +05:00
doc.go rafthttp: update LICENSE header 2016-05-12 20:49:28 -07:00
fake_roundtripper_test.go rafthttp: use http.Request.WithContext instead of Cancel 2017-02-02 02:30:36 +05:30
functional_test.go *: fix go tool vet -all -shadow errors 2017-06-06 09:47:06 -07:00
http.go etcdserver/api/rafthttp: add v3 snapshot send/receive metrics 2018-08-29 14:51:31 -07:00
http_test.go rafthttp: add Transport.Cut/MendPeer 2016-08-10 17:09:35 -07:00
metrics.go etcdserver/api/rafthttp: add v3 snapshot send/receive metrics 2018-08-29 14:51:31 -07:00
msg_codec.go rafthttp: permit very large v2 snapshots 2017-06-09 10:49:51 -07:00
msg_codec_test.go rafthttp: fix misprint in readBytesLimit value 2016-09-05 11:06:08 +05:00
msgappv2_codec.go rafthttp: use pointers to avoid extra copies upon message encoding 2016-06-29 21:17:18 +05:00
msgappv2_codec_test.go rafthttp: use pointers to avoid extra copies upon message encoding 2016-06-29 21:17:18 +05:00
peer.go rafthttp: add missing "peer_sent_failures_total" metrics call 2018-03-28 10:09:50 -07:00
peer_status.go rafthttp: clarify "became inactive" warning 2018-08-29 14:33:46 -07:00
peer_test.go rafthttp: update LICENSE header 2016-05-12 20:49:28 -07:00
pipeline.go rafthttp: use http.Request.WithContext instead of Cancel 2017-02-02 02:30:36 +05:30
pipeline_test.go rafthttp: bump up timeout in pipeline test 2016-12-30 09:46:16 -08:00
probing_status.go rafthttp: probe all raft transports 2018-10-09 18:17:16 -07:00
remote.go rafthttp: add missing "peer_sent_failures_total" metrics call 2018-03-28 10:09:50 -07:00
snapshot_sender.go etcdserver/api/rafthttp: add v3 snapshot send/receive metrics 2018-08-29 14:51:31 -07:00
snapshot_test.go rafthttp: snapshot tests 2016-06-06 11:38:11 -07:00
stream.go rafthttp: use 'transport.IsClosedConnError' 2017-04-13 11:55:22 -07:00
stream_test.go rafthttp: fix race in TestStreamWriterAttachOutgoingConn 2016-08-19 19:59:16 -07:00
transport.go rafthttp: probe all raft transports 2018-10-09 18:17:16 -07:00
transport_bench_test.go rafthttp: update LICENSE header 2016-05-12 20:49:28 -07:00
transport_test.go rafthttp: probe all raft transports 2018-10-09 18:17:16 -07:00
urlpick.go rafthttp: update LICENSE header 2016-05-12 20:49:28 -07:00
urlpick_test.go rafthttp: fix gofmt issues with go tip 2016-10-20 16:32:56 -07:00
util.go *: deny incoming peer certs with wrong IP SAN 2017-04-12 13:41:33 -07:00
util_test.go rafthttp: move test-only functions to '_test.go' 2017-04-10 16:07:31 -07:00