From d893fb5b00ba03e9718b08950b40b9af4a91b3e6 Mon Sep 17 00:00:00 2001 From: Rohit Yadav Date: Wed, 16 May 2018 15:35:00 +0530 Subject: [PATCH] agent: Fixes #2633 don't wait for pending tasks on reconnection (#2638) When agent loses connection with management server, the reconnection logic waits for any pending tasks to finish. However, when such tasks do finish they fail to send an `Answer` back to managements server. Therefore from a management server's perspective such pending operations are stuck in a FSM state and need manual removal or fixing. This is by design where management server's side cmd-answer request pattern is code/execution dependent, therefore even if the answer were to be sent when management server came back up (reconnects) the management server will fail to acknowledge and process the answer due to missing listeners or being in the exact state to handle answers. Historically, the Agent would wait to reconnect until the internal tasks complete but I found no reason why it should wait for reconnection at all. Signed-off-by: Rohit Yadav --- agent/src/com/cloud/agent/Agent.java | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/agent/src/com/cloud/agent/Agent.java b/agent/src/com/cloud/agent/Agent.java index 90e37909434..8a6c24b8ed4 100644 --- a/agent/src/com/cloud/agent/Agent.java +++ b/agent/src/com/cloud/agent/Agent.java @@ -495,19 +495,7 @@ public class Agent implements HandlerFactory, IAgentControl { _resource.disconnected(); - final String lastConnectedHost = _shell.getConnectedHost(); - - int inProgress = 0; - do { - _shell.getBackoffAlgorithm().waitBeforeRetry(); - - s_logger.info("Lost connection to host: " + lastConnectedHost + ". Dealing with the remaining commands..."); - - inProgress = _inProgress.get(); - if (inProgress > 0) { - s_logger.info("Cannot connect because we still have " + inProgress + " commands in progress."); - } - } while (inProgress > 0); + s_logger.info("Lost connection to host: " + _shell.getConnectedHost() + ". Attempting reconnection while we still have " + _inProgress.get() + " commands in progress."); _connection.stop();