[ https://issues.apache.org/jira/browse/CASSANDRA-4375?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13401522#comment-13401522 ]
Brandon Williams commented on CASSANDRA-4375: --------------------------------------------- bq. since you're only gossiping to 1-2 random hosts You're always gossiping to a seed, though I suppose with enough seeds that too isn't reliable. I'd be fine with setting it to something static like 10s to match the default rpc timeout, we just need some kind of reasonable bound to prevent CASSANDRA-3273. > FD incorrectly using RPC timeout to ignore gossip heartbeats > ------------------------------------------------------------ > > Key: CASSANDRA-4375 > URL: https://issues.apache.org/jira/browse/CASSANDRA-4375 > Project: Cassandra > Issue Type: Bug > Components: Core > Reporter: Peter Schuller > > Short version: You can't run a cluster with short RPC timeouts because nodes > just constantly flap up/down. > Long version: > CASSANDRA-3273 tried to fix a problem resulting from the way the failure > detector works, but did so by introducing a much more sever bug: With low RPC > timeouts, that are lower than the typical gossip propagation time, a cluster > will just constantly have all nodes flapping other nodes up and down. > The cause is this: > {code} > + // in the event of a long partition, never record an interval longer > than the rpc timeout, > + // since if a host is regularly experiencing connectivity problems > lasting this long we'd > + // rather mark it down quickly instead of adapting > + private final double MAX_INTERVAL_IN_MS = > DatabaseDescriptor.getRpcTimeout(); > {code} > And then: > {code} > - tLast_ = value; > - arrivalIntervals_.add(interArrivalTime); > + if (interArrivalTime <= MAX_INTERVAL_IN_MS) > + arrivalIntervals_.add(interArrivalTime); > + else > + logger_.debug("Ignoring interval time of {}", interArrivalTime); > {code} > Using the RPC timeout to ignore unreasonably long intervals is not correct, > as the RPC timeout is completely orthogonal to gossip propagation delay (see > CASSANDRA-3927 for a quick description of how the FD works). > In practice, the propagation delay ends up being in the 0-3 second range on a > cluster with good local latency. With a low RPC timeout of say 200 ms, very > few heartbeat updates come in fast enough that it doesn't get ignored by the > failure detector. This in turn means that the FD records a completely skewed > average heartbeat interval, which in turn means that nodes almost always get > flapped on interpret() unless they happen to *just* have had their heartbeat > updated. Then they flap back up whenever the next heartbeat comes in (since > it gets brought up immediately). > In our build, we are replacing the FD with an implementation that simply uses > a fixed {{N}} second time to convict, because this is just one of many ways > in which the current FD hurts, while we still haven't found a way it actually > helps relative to the trivial fixed-second conviction policy. > For upstream, assuming people won't agree on changing it to a fixed timeout, > I suggest, at minimum, never using a value lower than something like 10 > seconds or something, when determining whether to ignore. Slightly better is > to make it a config option. > (I should note that if propagation delays are significantly off from the > expected level, other things than the FD already breaks - such as the whole > concept of {{RING_DELAY}}, which assumes the propagation time is roughly > constant with e.g. cluster size.) -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira