ignite-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Loredana Radulescu Ivanoff <lradu...@tibco.com>
Subject Re: Re: Partition-exchanger blocked after upgrade to 2.7
Date Thu, 20 Dec 2018 18:40:57 GMT

We've been witnessing a similar set of logs from Apache Ignite after
upgrading to 2.7 (from 2.6) in a couple of different environments, one of
which had only one Ignite node. Very frequently, ignite will log the
message "Blocked system-critical thread has been detected. This can lead to
cluster-wide undefined behaviour [threadName=partition-exchanger,
blockedFor=13s]" and write a full thread dump. An examination of the thread
dump does not seem to indicate any specific threads that are actually
blocked or delayed. We do not appear to have any cluster wide issues
despite the logging.
In our understanding the sysWorkerBlockedTimeout property defaults to
DFLT_FAILURE_DETECTION_TIMEOUT. We have the failure detection timeout
configured to 10s.
We do not have a solution for it so far.

On Thu, Dec 20, 2018 at 7:34 AM ilya.kasnacheev <ilya.kasnacheev@gmail.com>

> Hello!
> Do you have any non-standard settings for failureDetectionTimeout or
> networkTimeout?
> Do you have any observable issues besides occasional extra logging?
> Regards,
> --
> Sent from: http://apache-ignite-users.70518.x6.nabble.com/

View raw message