Thursday, December 11, 2014

Encountering 'Write Failed: Broken Pipe" suring SSH connection on CentOS

I encountered this error Write Failed: Broken Pipe" during SSH connection. From what I know, it is caused by the Linux Server severing connections that have been idle too long ago.

To solve the issues, you can do the following

1. At your Linux Server Side, you can configure
# vim /etc/ssh/sshd_config

.....
ClientAliveInterval 60
.....


2. At your Client Side
# vim ~/.ssh/config 

.....
ServerAliveInterval 60
.....

Tuesday, December 9, 2014

LRZ HPC Cluster Storage Systems

I thought I pen down the LRZ HPC Cluster Storage Systems usage of NetApp and GPFS File System to support their computing needs.

Storage Systems
SuperMUC has a powerful I/O-Subsystem which helps to process large amounts of data generated by simulations.

Home file systems
Permanent storage for data and programs is provided by a 16-node NAS cluster from Netapp. This primary cluster has a capacity of 2 Petabytes and has demonstrated an aggregated throughput of more than 10 GB/s using NFSv3. Netapp's Ontap 8 "Cluster-mode" provides a single namespace for several hundred project volumes on the system. Users can access multiple snapshots of data in their home directories.

Data is regularly replicated to a separate 4-node Netapp cluster with another 2 PB of storage for recovery purposes. Replication uses Snapmirror-technology and runs with up to 2 GB/s in this setup.

Storage hardware consists of >3400 SATA-Disks with 2 TB each protected by double-parity RAID and integrated checksum


Work and Scratch areas
For highest-performance checkpoint I/O IBM's General Parallel File System (GPFS) with 10 PB of capacity and an aggregated throughput of 200 GB/s is available. Disk storage subsystems were built by DDN.


References:
  1.  SuperMUC Petascale System

Monday, December 8, 2014

Changing local and group ownership

I usually use the following commands to change ownership of a file or directory

# chown username.usergroups myfile.

But sometimes the users name contain a fullstop in the username. In that case, the following
# chown user.name:usergroups myfile

Thursday, December 4, 2014

Yum giving "Cannot retrieve metalink for repository: epel" Error for CentOS 6

When I was updating yum install or doing yum update on CentOS 6.4, I received an error "Cannot retrieve metalink for repository: epel"

The error is because of the scripts in the epel.repo under the mirrorlist pointing to https instead of http. If you amend it to http, the epel repo will work

 At /etc/yum/repos.d/epel.repo, change to

[epel]
.....
.....
mirrorlist=http://mirrors.fedoraproject.org/metalink?repo=epel-6&arch=$basearch

[epel-debuginfo]
.....
.....
mirrorlist=http://mirrors.fedoraproject.org/metalink?repo=epel-debug-6&arch=$basearch

References:
  1. CentOS 6.3 Instance Giving "Cannot retrieve metalink for repository: epel" Error