From d052e94b451621b2957ab24e7886fb9dc1c966b1 Mon Sep 17 00:00:00 2001
From: Simon Murray <spjmurray@yahoo.co.uk>
Date: Mon, 14 Aug 2017 16:20:45 +0100
Subject: [PATCH] Fix TLS Race Connecting to InfluxDB

Rather than leaving stale connections about we tried to poll for data coming in
from InfluxDB and timeout if it didn't repond in a timely manner.  This introduced
a race where the timeout triggers, a context switch occurs where data is actually
available and the TlsStream spins trying to asynchronously notify that data is
available, but which never gets read.  Not only does this use up 100% of a core,
but it also slowly starves the system of handler threads at which point metrics
stop being delivered.

This basically removes the poll and timeout, any TLS socket erros should be
detected by TCP keep-alives.

Fixes #5460 #5469

refs #5504
---
 doc/09-object-types.md          |  1 -
 lib/perfdata/influxdbwriter.cpp | 15 +++------------
 lib/perfdata/influxdbwriter.hpp |  2 +-
 lib/perfdata/influxdbwriter.ti  |  3 ---
 4 files changed, 4 insertions(+), 17 deletions(-)

diff --git a/doc/09-object-types.md b/doc/09-object-types.md
index 78b59192c..cceed0bb7 100644
--- a/doc/09-object-types.md
+++ b/doc/09-object-types.md
@@ -926,7 +926,6 @@ Configuration Attributes:
   enable_send_metadata   | **Optional.** Whether to send check metadata e.g. states, execution time, latency etc.
   flush_interval         | **Optional.** How long to buffer data points before transfering to InfluxDB. Defaults to `10s`.
   flush_threshold        | **Optional.** How many data points to buffer before forcing a transfer to InfluxDB.  Defaults to `1024`.
-  socket_timeout         | **Optional.** How long to wait for InfluxDB to respond.  Defaults to `5s`.
 
 Note: If `flush_threshold` is set too low, this will always force the feature to flush all data
 to InfluxDB. Experiment with the setting, if you are processing more than 1024 metrics per second
diff --git a/lib/perfdata/influxdbwriter.cpp b/lib/perfdata/influxdbwriter.cpp
index c6fa2c2c3..0a7f506fd 100644
--- a/lib/perfdata/influxdbwriter.cpp
+++ b/lib/perfdata/influxdbwriter.cpp
@@ -134,9 +134,9 @@ void InfluxdbWriter::ExceptionHandler(boost::exception_ptr exp)
 	//TODO: Close the connection, if we keep it open.
 }
 
-Stream::Ptr InfluxdbWriter::Connect(TcpSocket::Ptr& socket)
+Stream::Ptr InfluxdbWriter::Connect()
 {
-	socket = new TcpSocket();
+	TcpSocket::Ptr socket = new TcpSocket();
 
 	Log(LogNotice, "InfluxdbWriter")
 	    << "Reconnecting to InfluxDB on host '" << GetHost() << "' port '" << GetPort() << "'.";
@@ -423,8 +423,7 @@ void InfluxdbWriter::Flush(void)
 	String body = boost::algorithm::join(m_DataBuffer, "\n");
 	m_DataBuffer.clear();
 
-	TcpSocket::Ptr socket;
-	Stream::Ptr stream = Connect(socket);
+	Stream::Ptr stream = Connect();
 
 	if (!stream)
 		return;
@@ -462,14 +461,6 @@ void InfluxdbWriter::Flush(void)
 	HttpResponse resp(stream, req);
 	StreamReadContext context;
 
-	struct timeval timeout = { GetSocketTimeout(), 0 };
-
-	if (!socket->Poll(true, false, &timeout)) {
-		Log(LogWarning, "InfluxdbWriter")
-		    << "Response timeout of TCP socket from host '" << GetHost() << "' port '" << GetPort() << "'.";
-		return;
-	}
-
 	try {
 		resp.Parse(context, true);
 	} catch (const std::exception& ex) {
diff --git a/lib/perfdata/influxdbwriter.hpp b/lib/perfdata/influxdbwriter.hpp
index dba570c45..e0a149c3a 100644
--- a/lib/perfdata/influxdbwriter.hpp
+++ b/lib/perfdata/influxdbwriter.hpp
@@ -74,7 +74,7 @@ private:
 	static String EscapeKey(const String& str);
 	static String EscapeField(const String& str);
 
-	Stream::Ptr Connect(TcpSocket::Ptr& socket);
+	Stream::Ptr Connect();
 
 	void AssertOnWorkQueue(void);
 
diff --git a/lib/perfdata/influxdbwriter.ti b/lib/perfdata/influxdbwriter.ti
index 94188471f..a2bf19248 100644
--- a/lib/perfdata/influxdbwriter.ti
+++ b/lib/perfdata/influxdbwriter.ti
@@ -90,9 +90,6 @@ class InfluxdbWriter : ConfigObject
 	[config] int flush_threshold {
 		default {{{ return 1024; }}}
 	};
-	[config] int socket_timeout {
-		default {{{ return 5; }}}
-	};
 };
 
 validator InfluxdbWriter {