惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Blog — PlanetScale
Blog — PlanetScale
S
Security @ Cisco Blogs
博客园 - 三生石上(FineUI控件)
博客园 - 叶小钗
Last Week in AI
Last Week in AI
Jina AI
Jina AI
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
阮一峰的网络日志
阮一峰的网络日志
GbyAI
GbyAI
Microsoft Security Blog
Microsoft Security Blog
B
Blog
A
About on SuperTechFans
B
Blog RSS Feed
M
MIT News - Artificial intelligence
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
宝玉的分享
宝玉的分享
H
Hackread – Cybersecurity News, Data Breaches, AI and More
腾讯CDC
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
H
Help Net Security
博客园 - Franky
D
Darknet – Hacking Tools, Hacker News & Cyber Security
P
Palo Alto Networks Blog
罗磊的独立博客
S
Securelist
L
LINUX DO - 热门话题
T
Tor Project blog
人人都是产品经理
人人都是产品经理
Google DeepMind News
Google DeepMind News
T
Threatpost
Simon Willison's Weblog
Simon Willison's Weblog
P
Privacy International News Feed
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
Spread Privacy
Spread Privacy
WordPress大学
WordPress大学
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
MyScale Blog
MyScale Blog
T
The Blog of Author Tim Ferriss
爱范儿
爱范儿
Cyberwarzone
Cyberwarzone
NISL@THU
NISL@THU
Apple Machine Learning Research
Apple Machine Learning Research
S
SegmentFault 最新的问题
C
Cyber Attacks, Cyber Crime and Cyber Security
G
Google Developers Blog
The Hacker News
The Hacker News
Latest news
Latest news
A
Arctic Wolf
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
S
Schneier on Security

博客园 - 季石磊

jps 报process information unavailable解决办法 Jobtracker重启Job recovery过程分析 hadoop & hbase 上下线 Hbase性能优化 ldconfig几个需要注意的地方[转] [转]HBase性能优化方法总结 centos 查看版本 关于Hbase集群需要使用DNS域名解析的体会 修改Hadoop集群的备份数 [转载]ext4的noatime 指定HADOOP_HOME位置的三种方法 Windows下 Python 安装包的配置 django1.4测试环境 css样式,图片路径问题解决 Python用subprocess的Popen实现用户切换 CentOS 6安装JDK及系统配置 mapreduce程序运行避免手动删除output目录 HDFS配置设置 Hadoop运维操作 HDFS Permissions & Acls
Poor performance running Hadoop on RHEL 6.2 or later when transparent hugepage compaction is enabled
季石磊 · 2013-03-29 · via 博客园 - 季石磊

RHEL 6.2 and 6.3 include a feature called "transparent hugepage compaction" which interacts poorly with Hadoop workloads. This can cause a serious performance regression compared to other operating system versions on the same hardware.

Symptom: top and other system monitoring tools show a large percentage of the CPU usage classified as "system CPU". If system CPU usage is 30% or more of the total CPU usage, your system may be experiencing this issue.

Bug: https://bugzilla.redhat.com/show_bug.cgi?id=805593
Severity: Medium (up to 3x performance loss)
Anticipated Resolution: Currently working with Red Hat to resolve for a future RHEL update
Workaround: Add the following command to /etc/rc.local to disable transparent hugepage compaction:

解决方法:

echo always > /sys/kernel/mm/redhat_transparent_hugepage/enabled
echo never > /sys/kernel/mm/redhat_transparent_hugepage/defrag