Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 1 to 10 from 744 (0.245s).
Loading phrases to help you
refine your search...
[KAFKA-911] Bug in controlled shutdown logic in controller leads to controller not sending out some state change request - Kafka - [issue]
...The controlled shutdown logic in the controller first tries to move the leaders from the broker being shutdown. Then it tries to remove the broker from the isr list. During that operation, i...
http://issues.apache.org/jira/browse/KAFKA-911    Author: Neha Narkhede, 2013-05-22, 18:21
Re: orders of launching kafka servers and zookeepers - Kafka - [mail # user]
...First launch the zookeeper cluster completely followed by the kafkacluster.Thanks,NehaOn May 22, 2013 8:43 AM, "Yu, Libo"  wrote:> Hi,>> I want to launch kafka on three machine...
   Author: Neha Narkhede, 2013-05-22, 16:11
Re: Producer can't initialize if zk host down (0.7.2) - Kafka - [mail # user]
...Right. Zookeeper has added the feature to allow dynamically reconfiguringzookeeper clusters, but it is part of zookeeper 3.5.0.Thanks,NehaOn Tue, May 21, 2013 at 3:05 PM, Jason Rosenberg &nb...
   Author: Neha Narkhede, 2013-05-21, 22:38
Re: Producer can't initialize if zk host down (0.7.2) - Kafka - [mail # user]
...According to zookeeper code, when you try to create a client handle tozookeeper, it resolves each of the hosts in the zookeeper connectionstring. If any of these fail, it throws an exception...
   Author: Neha Narkhede, 2013-05-21, 21:20
Re: produce request wire format question - Kafka - [mail # dev]
...Dave,Colin described the producer behavior of picking the partition for amessage before it is sent to Kafka broker correctly. However, I'minterested in knowing your use case a little before ...
   Author: Neha Narkhede, 2013-05-21, 19:31
[KAFKA-901] Kafka server can become unavailable if clients send several metadata requests - Kafka - [issue]
...Currently, if a broker is bounced without controlled shutdown and there are several clients talking to the Kafka cluster, each of the clients realize the unavailability of leaders for some p...
http://issues.apache.org/jira/browse/KAFKA-901    Author: Neha Narkhede, 2013-05-21, 18:07
Re: About Kafka Users Group around Hadoop Summit - Kafka - [mail # user]
...It will be great to have a user group meeting around Hadoop Summit. Iprefer Thursday.Thanks,NehaOn Tue, May 21, 2013 at 10:54 AM, Vaibhav Puranik wrote:> Any day will work for me. I am wa...
   Author: Neha Narkhede, 2013-05-21, 17:56
Re: produce request wire format question - Kafka - [mail # dev]
...No. In 0.8, if you don't specify a key for a message, it is sent to any ofthe available partitions. In other words, the partition id is selected onthe partition and the server doesn't get -1...
   Author: Neha Narkhede, 2013-05-21, 17:47
Re: Closing socket connections during extended message delivery - Kafka - [mail # user]
...Yes. This was added to get around the VIP hard killing connections that areidle. If your producer doesn't use a VIP you can set this high enough so itrarely reconnects.Thanks,NehaOn May 21, ...
   Author: Neha Narkhede, 2013-05-21, 15:44
RE: only-once consumer groups - Kafka - [mail # user]
...Rob,A consumer rebalances whenever a consumer process dies or a new consumerprocess joins the group. The details of the algorithm can be found herehttp://kafka.apache.org/07/design.htmlThank...
   Author: Neha Narkhede, 2013-05-21, 02:00
Sort:
project
Kafka (744)
Zookeeper (29)
HBase (1)
type
mail # user (415)
issue (167)
mail # dev (162)
date
last 7 days (36)
last 30 days (77)
last 90 days (233)
last 6 months (336)
last 9 months (744)
author
Jun Rao (1167)
Neha Narkhede (744)
Jay Kreps (489)
"Neha Narkhede (251)
Joe Stein (183)
Chris Burroughs (171)
"Jun Rao (155)
Joel Koshy (153)
Alan D. Cabrera (141)
David Arthur (120)
Jason Rosenberg (115)
Taylor Gautier (98)
S Ahmed (92)
John Fung (91)
Chris Curtin (67)