[
https://issues.apache.org/jira/browse/TS-242?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13093137#comment-13093137
]
Alan M. Carroll commented on TS-242:
------------------------------------
I need to fix this for other reasons. Looking at some debugging output what
happens is that the timeout is set correctly but then overridden by the connect
timeout. I have not yet determined where exactly in the code this occurs.
> Connect timeout doesn't reset until first byte is received from server
> ----------------------------------------------------------------------
>
> Key: TS-242
> URL: https://issues.apache.org/jira/browse/TS-242
> Project: Traffic Server
> Issue Type: Bug
> Components: Core
> Reporter: Steve Jiang
> Assignee: Alan M. Carroll
> Priority: Minor
> Fix For: 3.1.1
>
>
> proxy.config.http.connect_attempts_timeout
> proxy.config.http.parent_proxy.connect_attempts_timeout
> proxy.config.http.post_connect_attempts_timeout
> These timeouts are implemented with inactivity timeout on the netvc and don't
> behave as expected.
> If the connect succeeds (the remote server successfully accepted) but the
> remote server does not respond with any bytes within the timeout period, TS
> still treats it as a connect timeout. If retries are enabled and the origin
> server is slow to start sending responses (but not down), it will keep
> sending requests and closing the connection after getting no response within
> the connect timeout.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira