Commit Graph

231 Commits

Author SHA1 Message Date
David Youngworth d0391db862 Merge branch 'release-6.2' into release-6.3 2020-11-16 10:15:23 -08:00
Vishesh Yadav 1976f2c371 FlowTransport: Sample connect latencies 2020-11-10 12:12:01 -08:00
Vishesh Yadav 7bdcb01bdf FlowTransport: Count number of incoming/outgoing/failed connections with logging 2020-11-02 18:51:48 -08:00
Jingyu Zhou d7420bb8c7 Fix merging 6.3 caused test failure 2020-10-16 21:11:01 -07:00
Jingyu Zhou 8f17a1a5d6 Merge branch 'release-6.2' into release-6.3 2020-10-16 15:25:39 -07:00
Evan Tschannen 52828f9e03 Added bytesSent to the PingLatency logging; increasing the logging interval from 1 second to 3 seconds 2020-10-11 23:05:21 -07:00
Evan Tschannen f03a355c4e Merge branch 'release-6.2' into release-6.3
# Conflicts:
#	CMakeLists.txt
#	documentation/sphinx/source/downloads.rst
#	fdbrpc/FlowTransport.actor.cpp
#	fdbrpc/FlowTransport.h
#	flow/Arena.h
#	flow/Knobs.cpp
#	flow/Knobs.h
#	packaging/msi/FDBInstaller.wxs
2020-10-07 12:28:22 -07:00
Evan Tschannen e82bd2a6ff added a suppressFor just in case a warning is spammy 2020-10-06 18:27:19 -07:00
Evan Tschannen d59ee9cc30 add a sample when a ping times out 2020-10-06 17:22:33 -07:00
Evan Tschannen 1eccabc285 added logging for a scenario that should not happen 2020-10-06 17:19:02 -07:00
Evan Tschannen eddf8530d8 fix compile errors 2020-10-06 17:09:14 -07:00
Evan Tschannen 12d2f3a8f3 fixed includes 2020-10-06 17:01:13 -07:00
Evan Tschannen 2c97a7e160 added missing include 2020-10-06 16:56:52 -07:00
Evan Tschannen 822312b31d only track latencies to public network addresses; use a continousSample to get median and p90 latencies 2020-10-06 16:55:35 -07:00
Evan Tschannen 2166f9a3dd added logging about bytes received 2020-10-06 16:07:35 -07:00
Evan Tschannen 9efda1fec5 added logging for the ping latencies for all network connections 2020-10-06 13:58:05 -07:00
Evan Tschannen 1883f0d21f Merge branch 'release-6.2' into release-6.3 2020-08-31 10:40:52 -07:00
Evan Tschannen b4a1c269b8 lastConnectTime was not being set for incomingConnections 2020-08-31 09:10:30 -07:00
Evan Tschannen 29eec30183 Merge branch 'release-6.2' into release-6.3
# Conflicts:
#	CMakeLists.txt
#	build/Dockerfile
#	build/Dockerfile.devel
#	documentation/sphinx/source/downloads.rst
#	fdbserver/Knobs.cpp
#	fdbserver/LogSystem.h
#	fdbserver/MasterProxyServer.actor.cpp
#	fdbserver/TagPartitionedLogSystem.actor.cpp
#	fdbserver/WaitFailure.actor.cpp
#	fdbserver/fdbserver.vcxproj
#	fdbserver/fdbserver.vcxproj.filters
#	packaging/msi/FDBInstaller.wxs
2020-08-31 01:10:29 -07:00
Evan Tschannen c9ff450a36 do not reject a connection as redundant if our existing connection is more than 15 seconds old 2020-08-30 18:49:49 -07:00
Steve Atherton 38cade1146 Merged tag release-6.3.3 into tls-background-handshake. 2020-07-17 23:39:57 -07:00
Steve Atherton d375ee7939 Rolled back the knob and logic for doing multiple write() calls in write loops before yielding, because they are not necessary. The testing that suggested otherwise was in error. 2020-07-16 22:54:14 -07:00
Steve Atherton c4f3553826 TLS handshake limit changed to regular flow lock, added new knob for simultaneous handshakes limit and removed old knobs. Added knob to control how much data the FlowTransport connectionWriter() can write using multiple write() calls before yielding to other tasks, and updated p2p network test to use the same logic. Changed knob defaults for send limit on single writes and TLS handshake thread count. 2020-07-16 02:31:17 -07:00
A.J. Beamon b09dddc07e Merge branch 'release-6.2' into merge-release-6.2-into-release-6.3
# Conflicts:
#	cmake/ConfigureCompiler.cmake
#	documentation/sphinx/source/downloads.rst
#	fdbrpc/FlowTransport.actor.cpp
#	fdbrpc/fdbrpc.vcxproj
#	fdbserver/DataDistributionQueue.actor.cpp
#	fdbserver/Knobs.cpp
#	fdbserver/Knobs.h
#	fdbserver/LogSystemPeekCursor.actor.cpp
#	fdbserver/MasterProxyServer.actor.cpp
#	fdbserver/Status.actor.cpp
#	fdbserver/storageserver.actor.cpp
#	flow/flow.vcxproj
2020-07-10 15:06:34 -07:00
Evan Tschannen f6163d0a79 fix compile errors 2020-07-09 22:53:02 -07:00
Evan Tschannen 717242a0ee reset WAN network connections every 5 minutes is responses take more than 500ms 2020-07-09 22:50:47 -07:00
sfc-gh-tclinkenbeard dd5cd762a8 Removed dead code 2020-07-04 12:50:40 -07:00
Steve Atherton 0da4c91ad5 Performance improvements in socket use and buffering which results in TLS network connections using around 3.5x less CPU.
PacketBuffers are 16k minimum sizes, using FastAlloc.  All calling paths to PacketBuffer creation now pass a size hint if known.  P2PNetworkTest improved in many ways, errors go to TraceEvents instead of stdout, error counts are reported in stats, range min/max parameters are combined into "min:max" strings, new options to "stutter" connections by delaying randomly before socket read or write, message size to send is now configured separately for incoming vs outgoing sessions.
2020-06-25 20:44:43 -07:00
Evan Tschannen f1dca05cf3
Merge pull request #3194 from etschannen/feature-small-endpoint
Optimized failure monitor performance
2020-05-20 14:48:13 -07:00
Evan Tschannen 6a006c4c1f use the first RequestStream as the base endpoint 2020-05-20 13:52:22 -07:00
Evan Tschannen 459186dad0 revert previous change to bit shift 2020-05-20 12:32:50 -07:00
Evan Tschannen dfc152ebb3 shift the bits farther 2020-05-20 11:34:24 -07:00
Evan Tschannen c09a28b0db speed up comparison of endpoints 2020-05-19 20:41:56 -07:00
Evan Tschannen bf9f24beb5 fixed mismatch of Endpoint UIDs 2020-05-19 17:16:41 -07:00
Evan Tschannen 9313e490aa change the first part of the UID to make comparisons cheaper 2020-05-19 16:48:20 -07:00
Vishesh Yadav afe6bf19e2 Fix typos and whitespace 2020-05-11 12:53:19 -07:00
Vishesh Yadav 9dc65547ad Avoid setting failure status of local addresses in main thread 2020-05-11 11:24:19 -07:00
Evan Tschannen f0f52fb2be Merge branch 'master' into feature-small-endpoint
# Conflicts:
#	fdbclient/StorageServerInterface.h
2020-05-08 16:37:35 -07:00
Evan Tschannen 51d3aaf4ae fixed a few rare correctness bugs 2020-05-06 23:24:58 -07:00
tclinken bc19f70455 Move delayedHealthUpdateF declaration 2020-05-01 18:14:51 -07:00
Evan Tschannen c126422296 fix: firstFree was not reset after using all available space 2020-05-01 17:46:20 -07:00
Evan Tschannen fd0ee72293 Merge branch 'master' into feature-small-endpoint 2020-04-29 18:43:10 -07:00
Evan Tschannen 76fb345dd1 Merge branch 'master' into feature-tree-broadcast
# Conflicts:
#	fdbrpc/FailureMonitor.actor.cpp
2020-04-29 09:51:22 -07:00
Evan Tschannen 2b2e0b9f75
Merge pull request #2932 from vishesh/task/issue-1017-slow-machine-poisoning
FailureMonitoring: Mark unstable connections as failed [1/X]
2020-04-28 13:57:49 -07:00
Evan Tschannen b7f5f3be48 merge in master 2020-04-28 13:11:47 -07:00
Evan Tschannen c87aa33941 Merge branch 'release-6.2'
# Conflicts:
#	CMakeLists.txt
#	bindings/go/src/fdb/generated.go
#	documentation/sphinx/source/api-common.rst.inc
#	documentation/sphinx/source/api-ruby.rst
#	documentation/sphinx/source/release-notes.rst
#	fdbclient/FailureMonitorClient.actor.cpp
#	fdbclient/NativeAPI.actor.cpp
#	fdbclient/vexillographer/fdb.options
#	fdbrpc/FlowTransport.actor.cpp
#	fdbserver/OldTLogServer_6_0.actor.cpp
#	fdbserver/TLogServer.actor.cpp
#	fdbserver/fdbserver.actor.cpp
#	versions.target
2020-04-23 13:47:53 -07:00
Vishesh Yadav c30010f5b8 FlowTransport: Increase delay for connecting to failed connections 2020-04-23 09:44:30 -07:00
Evan Tschannen a835123680 exit fdbserver after a ReceiverError, because a packet which should be delivered will never be received 2020-04-22 23:38:46 -07:00
Evan Tschannen 810bba2067 cleanup calls to FlowTransport::isClient() 2020-04-22 23:36:40 -07:00
Vishesh Yadav 3a5315d10c FlowTransport: Don't immediately mark connections failed
In connectionKeeper(), when a connection is failed for
FAILURE_DETECTION_DELAY, then only mark connection as failed.

This is much closer to the original centralized behaviour, and also
adds more confidence on whether the connection is actually failed.
2020-04-22 19:46:04 -07:00