cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Marcus Eriksson (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (CASSANDRA-3569) Failure detector downs should not break streams
Date Tue, 20 May 2014 10:14:39 GMT

    [ https://issues.apache.org/jira/browse/CASSANDRA-3569?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14003040#comment-14003040
] 

Marcus Eriksson commented on CASSANDRA-3569:
--------------------------------------------

It works perfectly when the TCP connection actually comes back, a few problems when it doesn't;

On the sending side, I get a proper exception after keepalive_time + keepalive_probe*keepalive_intvl,
but the stream session is not cleared, nodetool netstats still says we are sending files,
but in the logs it says "Session ... is complete" and "Stream failed".

On the receiving side I get nothing (this might very well be me messing up the firewalling),
stream/repair is just stuck.

The firewall rules I use are;
{code}
iptables -A OUTPUT -d <othernodeip> -j DROP
iptables -A INPUT -s <othernodeip> -j DROP
{code}

> Failure detector downs should not break streams
> -----------------------------------------------
>
>                 Key: CASSANDRA-3569
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-3569
>             Project: Cassandra
>          Issue Type: New Feature
>            Reporter: Peter Schuller
>            Assignee: Joshua McKenzie
>             Fix For: 2.1.1
>
>         Attachments: 3569-2.0.txt, 3569_v1.txt
>
>
> CASSANDRA-2433 introduced this behavior just to get repairs to don't sit there waiting
forever. In my opinion the correct fix to that problem is to use TCP keep alive. Unfortunately
the TCP keep alive period is insanely high by default on a modern Linux, so just doing that
is not entirely good either.
> But using the failure detector seems non-sensicle to me. We have a communication method
which is the TCP transport, that we know is used for long-running processes that you don't
want to incorrectly be killed for no good reason, and we are using a failure detector tuned
to detecting when not to send real-time sensitive request to nodes in order to actively kill
a working connection.
> So, rather than add complexity with protocol based ping/pongs and such, I propose that
we simply just use TCP keep alive for streaming connections and instruct operators of production
clusters to tweak net.ipv4.tcp_keepalive_{probes,intvl} as appropriate (or whatever equivalent
on their OS).
> I can submit the patch. Awaiting opinions.



--
This message was sent by Atlassian JIRA
(v6.2#6252)

Mime
View raw message