Home | About | Sematext search-lucene.com search-hadoop.com
clear query|facets|time Search criteria: .   Results from 81 to 90 from 123 (0.093s).
Loading phrases to help you
refine your search...
Re: adding/removing a zookeeper server - Zookeeper - [mail # user]
...Hi Mohammad,  Support for adding/removing servers as well as dynamic changes to other parameters will be added as part of ZOOKEEPER-107, hopefully in the 3.5.0 release.  Thanks, Al...
   Author: Alexander Shraer, 2012-04-30, 06:32
Re: Please vote for ZOOKEEPER-107 to be presented in the Hadoop Summit - Zookeeper - [mail # dev]
...Thanks everyone for voting! With > 200 votes this project won the popularity contest in its track and will presented it in the Hadoop Summit!!   Alex   On Mon, Mar 12, 2012 at 3...
   Author: Alexander Shraer, 2012-04-04, 05:50
Re: Sequential znode creation and sync - Zookeeper - [mail # user]
...Hi Luca,  The whole tree -- when an update (such as create) returns the local server's tree reflects all the updates scheduled before the create.  Alex  On Sun, Mar 18, 2012 a...
   Author: Alexander Shraer, 2012-03-19, 05:33
Re: Zookeeper on short lived VMs and ZOOKEEPER-107 - Zookeeper - [mail # user]
...I think this is why when you're doing rolling restarts / reconfiguration you should never have two different servers that have any chance of being up at the same time with the same id. With ...
   Author: Alexander Shraer, 2012-03-16, 18:37
Re: Zookeeper on short lived VMs and ZOOKEEPER-107 - Zookeeper - [mail # user]
...Actually its still not clear to me how you would enforce the 2x+1. In Zookee per we can guarantee liveness (progress) only when x+1 are connected and up,  however safety (correctness) i...
   Author: Alexander Shraer, 2012-03-16, 03:43
Re: Zookeeper on short lived VMs and ZOOKEEPER-107 - Zookeeper - [mail # user]
...I think the concern is that the old VM can recover and try to reconnect. Theoretically you could even go back and forth between new and old VM. For example, suppose that you have servers A, ...
   Author: Alexander Shraer, 2012-03-15, 22:54
Re: Zookeeper on short lived VMs and ZOOKEEPER-107 - Zookeeper - [mail # user]
...yes, by replacing x at a time from 2x+1 you have quorum intersection.  i have one more question - zookeeper itself doesn't assume perfect failure detection, which your scheme requires. ...
   Author: Alexander Shraer, 2012-03-15, 15:33
Re: Zookeeper on short lived VMs and ZOOKEEPER-107 - Zookeeper - [mail # user]
...Hi Christian,  ZK-107 would indeed allow you to add/remove servers and change their addresses.  zookeeper servers with a fixed set of host names.  You should probably also ens...
   Author: Alexander Shraer, 2012-03-15, 06:46
Please vote for ZOOKEEPER-107 to be presented in the Hadoop Summit - Zookeeper - [mail # dev]
...Dear All,   If you like Zookeeper-107, 1355, 1411, etc  (Dynamic reconfiguration of Zookeeper)  please vote for it to be presented at the Hadoop summit:    https://h...
   Author: Alexander Shraer, 2012-03-12, 22:03
RE: Rolling upgrades - Zookeeper - [mail # user]
...I don't think they must be an odd number, but it does make sense to have an  odd number because with majority quorums the fault tolerance you get with 3 servers is  the same as the...
   Author: Alexander Shraer, 2012-03-09, 00:15
Sort:
project
Zookeeper (123)
type
mail # user (61)
mail # dev (43)
issue (18)
wiki (1)
date
last 7 days (2)
last 30 days (9)
last 90 days (26)
last 6 months (45)
last 9 months (123)
author
Patrick Hunt (752)
Ted Dunning (454)
Mahadev Konar (306)
Jordan Zimmerman (271)
Camille Fournier (198)
Benjamin Reed (194)
Flavio Junqueira (140)
Alexander Shraer (123)
Michi Mutsuzaki (90)
Thomas Koch (69)
Fournier, Camille F. (67)
Marshall McMullen (57)
Ted Yu (50)
Vishal Kher (50)
Henry Robinson (47)