Re: deadNodes in DFSInputStream

Why the status of HDFS-4273 is still "Unresolved"? HDFS-5540 is fixed now. On Wed, Jan 1, 2014 at 6:12 AM, Colin McCabe wrote: > Take a look at HDFS-4273, which fixes some issues with the read retry > logic. > > cheers, > Colin > > On Tue, Dec 31

[jira] [Created] (HDFS-5710) FSDirectory#getFullPathName should check for inodes against null

Ted Yu created HDFS-5710: Summary: FSDirectory#getFullPathName should check for inodes against null Key: HDFS-5710 URL: https://issues.apache.org/jira/browse/HDFS-5710 Project: Hadoop HDFS Issue Typ

[jira] [Created] (HDFS-5709) Improve upgrade with existing files and directories named ".snapshot"

Andrew Wang created HDFS-5709: - Summary: Improve upgrade with existing files and directories named ".snapshot" Key: HDFS-5709 URL: https://issues.apache.org/jira/browse/HDFS-5709 Project: Hadoop HDFS

Re: deadNodes in DFSInputStream

Take a look at HDFS-4273, which fixes some issues with the read retry logic. cheers, Colin On Tue, Dec 31, 2013 at 1:25 AM, lei liu wrote: > I use Hbase-0.94 and CDH-4.3.1 > When RegionServer read data from loca datanode, if local datanode is dead, > the local datanode is add to deadNodes, and R

Re: ByteBuffer-based read API for pread

It's true that HDFS (and Hadoop generally) doesn't currently have a ByteBuffer-based pread API. There is a JIRA open for this issue, HDFS-3246. I do not know if implementing a ByteBuffer API for pread would be as big of a performance gain as implementing it for regular read. One issue is that wh

Jenkins build is back to normal : Hadoop-Hdfs-trunk #1630

See

Hadoop-Hdfs-0.23-Build - Build # 837 - Still Failing

See https://builds.apache.org/job/Hadoop-Hdfs-0.23-Build/837/ ### ## LAST 60 LINES OF THE CONSOLE ### [...truncated 7894 lines...] [ERROR] location: class com.google.pro

Build failed in Jenkins: Hadoop-Hdfs-0.23-Build #837

See -- [...truncated 7701 lines...] [ERROR] symbol : class Parser [ERROR] location: package com.google.protobuf [ERROR]

deadNodes in DFSInputStream

I use Hbase-0.94 and CDH-4.3.1 When RegionServer read data from loca datanode, if local datanode is dead, the local datanode is add to deadNodes, and RegionServer read data from remote datanode. But when local datanode is become live, RegionServer still read data from remote datanode, that reduces

ByteBuffer-based read API for pread

There is ByteBuffer read API for sequential read in CDH4.3.1, example:public synchronized int read(final ByteBuffer buf) throws IOException API. But there is not ByteBuffe read API for pread. Why don't support ByteBuffer read API for pread in CDH4.3.1? Thanks, LiuLei