Intel Software Network articles Feed http://software.intel.com/en-us/articles/intel-cluster-ready-kb/type/known-issues/ en-us The mflops_intel_mkl test module hangs during execution on Scyld Clusterware 5.4 Symptom

Intel® Cluster Checker hangs during the execution of the mflops_intel_mkl test module on clusters running Penguin Computing* Scyld Clusterware* 5.4. 

In addition, inactive or zombie processes named dgemm_mflops may be present on the nodes.  The dgemm_mflops binary is a DGEMM benchmark optimized with the Intel® Math Kernel library.  It is packaged with Intel® Cluster Checker.

Debug output provides no other information.

Cause

The root cause of this error is undetermined.  It appears to be an incompatibility between the binary version of dgemm_mflops included with Intel® Cluster Checker and Scyld ClusterWare 5.4.  It only occurs when executing over non-interactive SSH.

Resolution

Configure Intel® Cluster Checker to build dgemm_mflops from source rather than using the prebuilt binary. This is accomplished using the <build/> configuration tag.

The Intel Math Kernel Library must be in the linker path or the <mkl-path> option must also be set. The <mkl-path> option can also be set using the global configuration capability.  The GNU C Compiler (gcc) must also be present, so it is recommended to add the corresponding test module as a dependency.

The following is an example of the updated test module configuration to work around the issue:

<mflops_intel_mkl>
  <add_dependency>gcc</add_dependency>
  <build/>
  <mkl-path>/opt/intel/cmkl/10.1</mkl-path>
</mflops_intel_mkl>

]]> http://software.intel.com/en-us/articles/the-mflops_intel_mkl-test-module-hangs-during-execution-on-scyld-clusterware-54/ Wed, 03 Feb 2010 22:00:00 -0800 http://software.intel.com/en-us/articles/the-mflops_intel_mkl-test-module-hangs-during-execution-on-scyld-clusterware-54/#comments http://software.intel.com/en-us/articles/the-mflops_intel_mkl-test-module-hangs-during-execution-on-scyld-clusterware-54/ Intel® Cluster Checker Knowledge Base Intel® Cluster Ready Knowledge Base Troubleshooting the dmidecode check: Wake-up Type Symptom

The dmidecode module of Intel® Cluster Checker reports inconsistencies in the “Wake-Up Type” value. The error may appear similar to the following example:

SMBIOS/DMI Uniformity,(dmidecode).............................................FAILED
subtest 'System Information (0x0002): Wake-up Type' failed
- failing hosts node-1, node-2 returned: 'AC Power Restored'
- failing host node-0 returned: 'Power Switch'

Modifying the Power Restore Policy or Restore on AC Power Loss setting, using either the IPMI/BIOS configuration interface or the Save and Restore System Configuration utility (syscfg), has no effect on this error.

Cause

The “Wake-Up Type” value does not represent the current setting for power restore or power-on response. It describes how the system was powered-on after the last power off, regardless of restore settings. This value may change after each boot, depending on what method was used to power-on the individual node.

Resolution

This value stores dynamic data and compute nodes are not expected to have identical data for this value. It can be ignored for the purposes of Intel® Cluster Ready certification and verification.

Exclude the value by adding an exclude element to the dmidecode block in the Intel® Cluster Checker configuration file. For example:

<dmidecode>
  <exclude>System Information (0x0002): Wake-up Type</exclude>
</dmidecode>

In Intel® Cluster Checker 1.4, the exclude element has been enhanced to support regular expression matching. In this case, the following option is sufficient:

<dmidecode>
  <exclude>Wake-up Type</exclude>
</dmidecode>

For more information on troubleshooting the dmidecode check, see this article.  ]]> http://software.intel.com/en-us/articles/troubleshooting-the-dmidecode-check-wake-up-type/ Wed, 16 Dec 2009 22:00:00 -0800 http://software.intel.com/en-us/articles/troubleshooting-the-dmidecode-check-wake-up-type/#comments http://software.intel.com/en-us/articles/troubleshooting-the-dmidecode-check-wake-up-type/ Intel® Cluster Checker Knowledge Base Intel® Cluster Ready Knowledge Base How to Deal with file_tree issues in Intel® Cluster Checker 1.3 Note: this article describes behavior in Intel® Cluster Checker version 1.3 Update 2 or earlier.

The file_tree Intel® Cluster Checker test module verifies that a consistent set of files is present on all cluster nodes.  This consistency is a requirement of the Intel® Cluster Ready Specification.  However, some files are expected to contain data unique to each node, such as hostname and IP address.  While the file_tree test automatically excludes many common examples of such files from its consistency check, special cases exist that are not automatically handled (see the end of this article for a list). 

If the file_tree test identifies files that are not consistent across the cluster, you should manually determine whether the reported difference must be resolved by applying the following rules:

  • Does the reported file contain unique information to each node, such as a time stamp or network configuration?  If so, manually verify that other than than the node unique data, the file is identical on all nodes. 
  • Does the file name itself or the path to the file contain node unique information?  If so, are similar files present on all the nodes?
  • Is the file dynamically generated or modified, e.g., a log file, compiled from source on each node, or modified by the prelink utility, on each node?  If so, a time stamp or other node unique information may be embedded.

If you can determine why the file is different on each node and verify that the differences are not material, then you may ignore the reported errors.  If you are certifying a cluster design as Intel® Cluster Ready, you should include a brief description of why you believe the reported errors are immaterial with your submitted Intel® Cluster Checker output logs.  You should document the files you manually resolved with your cluster design so that other engineers and technicians at your company understand that they can ignore file_tree errors with these files, but should not ignore errors reported for other files. 

Forthcoming versions of Intel® Cluster Checker will have the capability to configure which files should be automatically excluded.

Files that are known to differ from node to node not automatically handled by Intel® Cluster Checker 1.3

  • /opt/mlnx-ofed/src/*
  • /opt/rocks/lib/graphviz/config
  • /opt/torque/lib64/xpbs*
  • /opt/torque/mom_logs/*
  • /usr/java/jdk1.6.0_14/jre/lib/servicetag/registration.xml
  • /usr/java/jdk1.6.0_14/register.html
  • /usr/java/jdk1.6.0_14/register_ja.html
  • /usr/java/jdk1.6.0_14/register_zh_CN.html
  • /usr/java/i386/jre1.6.0_12/lib/i386/client/classes.jsa
]]> http://software.intel.com/en-us/articles/how-to-deal-with-file_tree-issues-in-intel-cluster-checker-13/ Mon, 28 Sep 2009 22:00:00 -0700 http://software.intel.com/en-us/articles/how-to-deal-with-file_tree-issues-in-intel-cluster-checker-13/#comments http://software.intel.com/en-us/articles/how-to-deal-with-file_tree-issues-in-intel-cluster-checker-13/ Intel® Cluster Checker Knowledge Base Intel® Cluster Ready Knowledge Base Standard C++ Library (libstdc++) Version Requirements The Intel® Cluster Ready specification requires that the GCC* 3.4 or later runtime be present on all cluster nodes.  The Standard C++ Library, libstdc++.so.6, is part of the GCC* 3.4 runtime.  However, some software packages, such as the Intel compilers, may still depend on the GCC* 3.2 runtime and an earlier version of the Standard C++ Library, libstdc++.so.5. 

Currently, all of the leading Linux distributions install the GCC* 3.4 runtime and libstdc++.so.6 and do not install libstdc++.so.5 by default.

If the software package with the dependency on libstdc++.so.5 does not include the earlier version of the Standard C++ Library, you may need to install it yourself.  Many Linux distributions provide libstdc++.so.5 in an optional RPM package.  For example:

  • Red Hat* Enterprise Linux: compat-libstdc++-33
  • SUSE* Linux Enterprise Edition: compat-libstdc++-5.x.x
The Standard C++ Library is also available as source from the GNU Project.

Note: It is not sufficient to link libstdc++.so.5 to libstd++.so.6, as the libraries are not binary compatible.

More information on the Standard C++ Library requirements for the Intel compilers may be found at:
http://software.intel.com/en-us/articles/performance-tools-for-software-developers-intel-10x-compilers-dependency-on-usrliblibstdcso5/

]]> http://software.intel.com/en-us/articles/standard-c-library-libstdc-version-requirements/ Wed, 19 Aug 2009 22:00:00 -0700 http://software.intel.com/en-us/articles/standard-c-library-libstdc-version-requirements/#comments http://software.intel.com/en-us/articles/standard-c-library-libstdc-version-requirements/ Intel® Cluster Ready Knowledge Base