Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 1 to 10 from 24 (0.066s).
Loading phrases to help you
refine your search...
Re: Cluster design distribution and JBOD vs RAID - Kafka - [mail # user]
...Just curious, would losing one disk in a JBOD setup really mean you’d have to re-replicate 20TB of data?  If a single drive dies, wouldn’t you only lose the partitions that happen to be...
   Author: Andrew Otto, 2014-04-18, 14:36
Zookeeper reconnect failed due to 'state changed (Expired)' - Kafka - [mail # user]
...Hm, just saw something a little fishy.  (In the following logs, analytics1021 (id 21) and analytics1022 (id 22) are Brokers and analytics1023,analytics1024,analytics1025 are Zookeepers....
   Author: Andrew Otto, 2014-03-20, 22:27
Re: Using Kafka Metrics - Kafka - [mail # user]
...I’m using jmxtrans to do this for Ganglia, but it should work the same for Graphite:http://www.jmxtrans.org/Here’s an example Kafka jmxtrans json file.https://github.com/wikimedia/puppet-kaf...
   Author: Andrew Otto, 2014-03-20, 14:47
Re: Puppet module for deploying Kafka released - Kafka - [mail # user]
...Ah cool, missed that, thanks!  I’m equally envious of the Hiera support in yours :)On Feb 26, 2014, at 12:00 PM, Michael G. Noll  wrote: ...
   Author: Andrew Otto, 2014-02-26, 19:36
Re: Unexpected broker election - Kafka - [mail # user]
...Yeah, I can do that, but I’d prefer if the first broker didn’t drop out of the ISR in the first place.  Just trying to figure out why it did…On Feb 21, 2014, at 11:30 PM, Jun Rao  ...
   Author: Andrew Otto, 2014-02-22, 22:06
Re: Description of jmx exposed metrics? - Kafka - [mail # user]
...Although that is not all of them, just recommended ones to pay attention to :/On Feb 11, 2014, at 6:50 AM, Tomas Nunez  wrote: ...
   Author: Andrew Otto, 2014-02-11, 14:53
Re: Broker rejoin with big replica lag - Kafka - [mail # user]
...Totally worked, thanks all.On Feb 5, 2014, at 5:18 PM, Andrew Otto  wrote:>> - Increasing num.replica.fetchers (defaults is one)> Awesome!  I just tried this one, bumped i...
   Author: Andrew Otto, 2014-02-06, 19:15
Re: How to design a robust producer? - Kafka - [mail # user]
...Thibaud, I wouldn't say this is a 'robust' solution, but the Wikimedia Foundation uses a piece of software we wrote called udp2log.  We are in the process of replacing it with more robu...
   Author: Andrew Otto, 2014-01-30, 16:00
Re: Kafka Cluster Failover - Kafka - [mail # user]
...> by non-HA broker do you mean non-HA> by virtue of it being a single broker with no replication?  You would> still need to get it registered in a ZooKeeper cluster right?\Righ...
   Author: Andrew Otto, 2013-11-27, 20:38
Re: How to get monitoring stats - Kafka - [mail # user]
...For Kafka 0.8, you could use http://www.jmxtrans.org/ and a variation of this json file:https://github.com/wikimedia/puppet-kafka/blob/master/kafka-jmxtrans.json.mdJust change the ganglia ou...
   Author: Andrew Otto, 2013-11-20, 14:18
Kafka (24)
Flume (2)
Hadoop (1)
mail # user (22)
issue (1)
mail # dev (1)
last 7 days (1)
last 30 days (3)
last 90 days (8)
last 6 months (16)
last 9 months (24)
Jun Rao (857)
Neha Narkhede (577)
"Neha Narkhede (412)
Jay Kreps (303)
"Jun Rao (277)
Joe Stein (162)
Joel Koshy (146)
Guozhang Wang (124)
John Fung (95)
"Joe Stein (94)
"Jay Kreps (90)
"Guozhang Wang (89)
Jason Rosenberg (68)
Swapnil Ghike (62)
David Arthur (61)
Andrew Otto