NameNode as a single point of failure

Hello, HDFS Developers. I know that NN is a single point of failure of an entire HDFS cluster. If it fails, the cluster will be unavailable no matter how many DN there. I know that there is an initiative whic

[jira] [Created] (HDFS-8709) Clarify automatic sync in FSEditLog#logEdit

Andrew Wang created HDFS-8709: - Summary: Clarify automatic sync in FSEditLog#logEdit Key: HDFS-8709 URL: https://issues.apache.org/jira/browse/HDFS-8709 Project: Hadoop HDFS Issue Type: Improveme

Re: [VOTE] Release Apache Hadoop 2.7.1 RC0

Vinod, thanks for putting together this release. +1 (binding) - Verified signatures - Installed binary release on Centos 6 pseudo cluster * Copied files in and out of HDFS using the shell * Mounted HDFS via NFS and copied a 10GB file in and out over NFS * Ran example MapReduce job

Re: [DISCUSS] Create branch for HDFS-8707

+1. It will be great to have a high performance async client in c++ in HDFS. There are many use cases that will benefit from this work. From: Owen O'Malley Sent: Wednesday, July 01, 2015 2:38 PM To: hdfs-dev@hadoop.apache.org Subject: [DISCUSS] Create bran

[DISCUSS] Create branch for HDFS-8707

All, Haohui and I would like to pull code for an async io c++ hdfs client from https://github.com/haohui/libhdfspp as a new development branch. The motivation is to get a high performance asynchronous c++ hdfs client and the driving need is to support reading ORC files from HDFS without a jvm in

Re: [VOTE] Release Apache Hadoop 2.7.1 RC0

+1 (binding) - Verified signatures and digests - Successfully performed a native build from source- Deployed a single-node cluster- Ran sample MapReduce jobs Jason From: Vinod Kumar Vavilapalli To: common-...@hadoop.apache.org; hdfs-dev@hadoop.apache.org; yarn-...@hadoop.apache.org; mapr

[jira] [Created] (HDFS-8707) Implement an async pure c++ HDFS client

Owen O'Malley created HDFS-8707: --- Summary: Implement an async pure c++ HDFS client Key: HDFS-8707 URL: https://issues.apache.org/jira/browse/HDFS-8707 Project: Hadoop HDFS Issue Type: New Featu

Re: Planning Hadoop 2.6.1 release

Any update on a release plan for 2.6.1? On Wed, Jun 10, 2015 at 1:25 AM, Brahma Reddy Battula < brahmareddy.batt...@huawei.com> wrote: > HI vinod > > any update on this..? are we planning to give 2.6.1 Or can we make 2.7.1 > as stable give..? > > > Thanks & Regards > Brahma Reddy Battula > > ___

Re: Move blocks between Nodes

Hi Bing, I would recommend that you add your 50 new nodes to the cluster and the decommission the 50 nodes you want to get rid of. You can do the decommission in one operation (albeit a lengthy operation) by adding the nodes you want to decommission to your HDFS exclude file and running `hdfs

Hadoop-Hdfs-trunk-Java8 - Build # 233 - Still Failing

See https://builds.apache.org/job/Hadoop-Hdfs-trunk-Java8/233/ ### ## LAST 60 LINES OF THE CONSOLE ### [...truncated 7955 lines...] [INFO] --

Hadoop-Hdfs-trunk - Build # 2172 - Still Failing

See https://builds.apache.org/job/Hadoop-Hdfs-trunk/2172/ ### ## LAST 60 LINES OF THE CONSOLE ### [...truncated 7347 lines...] [INFO] ---

[jira] [Created] (HDFS-8706) Correct the datanode startup option #HDFSCommands.html

Brahma Reddy Battula created HDFS-8706: -- Summary: Correct the datanode startup option #HDFSCommands.html Key: HDFS-8706 URL: https://issues.apache.org/jira/browse/HDFS-8706 Project: Hadoop HDFS

[jira] [Created] (HDFS-8705) BlockStoragePolicySuite uses equalsIgnoreCase for name lookup, won't work in all locales

Steve Loughran created HDFS-8705: Summary: BlockStoragePolicySuite uses equalsIgnoreCase for name lookup, won't work in all locales Key: HDFS-8705 URL: https://issues.apache.org/jira/browse/HDFS-8705

[jira] [Created] (HDFS-8704) Erasure Coding: client fails to write large file when one datanode fails

Li Bo created HDFS-8704: --- Summary: Erasure Coding: client fails to write large file when one datanode fails Key: HDFS-8704 URL: https://issues.apache.org/jira/browse/HDFS-8704 Project: Hadoop HDFS Iss

RE: [VOTE] Release Apache Hadoop 2.7.1 RC0

+1 (non-binding) Build from source deployed in 4 nodes cluster for Secure Mode and Non-Secure Mode. Tested with applications spark and MapReduce for RM HA, RM workPreservingRestat, NM work preserving restart. - Rohith Sharma K S -Original Message- From: Mit Desai [mailto: