https://www.limulus-computing.com/Limulus-Manual/ 2026-04-30T18:47:53+00:00 https://www.limulus-computing.com/Limulus-Manual/ https://www.limulus-computing.com/Limulus-Manual/lib/tpl/dokuwiki/images/favicon.ico text/html 2021-04-29T15:58:41+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=adding_users&rev=1619711921&do=diff Adding and Deleting Users Adding users can be done using two convenience scripts. (See below for deleting users.) AddUser DelUser Both of these scripts can operate in either text or graphical mode. In text mode, they must be started in a terminal window as the text/html 2021-05-19T16:16:12+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=becoming_the_administrative_user&rev=1621440972&do=diff Becoming The Administrative User If you have been approved as an administrator, you should be able to run the following command from a terminal on the administrative node. (Assume USERNAME is your username on the cluster.) $ sudo -i [sudo] password for USERNAME: # text/html 2025-09-15T16:40:10+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=desk-side_case&rev=1757954410&do=diff Please see System Images for pictures and a description of the case. text/html 2020-07-28T16:05:56+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=essential_quick_start&rev=1595952356&do=diff Limulus HPC Systems Quick Start The following is basic information about your Limulus system. Please consult the other sections in this manual for further details. The Case: The case has two doors on both sides and a removable front bezel. The front bezel can be text/html 2021-05-19T16:03:25+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=essential_quick_start_data_analytics_systems&rev=1621440205&do=diff Limulus Data Analytics (Hadoop/Spark/Kafka) Systems Quick Start The following is basic information about your Limulus system. Please consult the other sections in this manual for further details. A general description of the systems can be found by consulting the text/html 2021-04-30T15:17:28+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=essential_quick_start_hpc_systems&rev=1619795848&do=diff Limulus HPC Systems Quick Start The following is basic information about your Limulus system. Please consult the other sections in this manual for further details. A general description of the systems can be found by consulting the Functional Diagram. Adding Users: text/html 2025-10-15T19:19:52+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=fan_control&rev=1760555992&do=diff Limulus Fan Control There are two fans that pull air from under the case. The fans are directly under the blades and ensure there is adequate airflow to the blade CPUs. The fans are connected to a single main motherboard auxiliary fan connector using a text/html 2021-05-03T14:47:49+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=functional_diagram&rev=1620053269&do=diff Functional Diagram The figure illustrates the functional parts that are packaged in a standard Limulus system (either desk-side or rack-mount). The “double-wide” Limulus diagram is forthcoming. It is similar and has eight total motherboards (one main motherboard), two 1-GbE switches, two USB Power Relay boards, and an additional 25-GbE NIC to facilitate the 25-GbE switchless network. text/html 2025-10-23T20:20:07+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=general_questions&rev=1761250807&do=diff General Limulus Systems Questions The following topics about Limulus personal HPC and Data Analytics Systems are discussed as a series of questions and answers. * Audience and Market * Hardware * Power Heat Noise * Software * Support Audience and Market Is this a real cluster? Yes, it is a real cluster. The basic system has four motherboards which are cluster nodes in a standard off-the-shelf case with a single power supply. The main motherboard is always powered on and functions … text/html 2021-04-28T14:15:56+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=getting_help&rev=1619619356&do=diff Getting Support For customers who have Limulus Computing Support you may submit questions to our Question and Answer Page. You must register with a valid Machine ID that can be found by running dmidecode -s system-uuid. A long hexadecimal string will be printed, similar to e.g. e5b27ff5-49c4-eeb0-2caa-3c7c3f81d9d7 text/html 2021-06-18T18:30:56+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=hadoop_distributed_file_system&rev=1624041056&do=diff HDFS Management text/html 2021-06-18T18:34:23+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=hdfs_management&rev=1624041263&do=diff HDFS Management coming soon text/html 2021-05-20T16:53:28+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=hpc_logs_and_log_management&rev=1621529608&do=diff HPC Logs and Log Management What Logs Should I Check? The logs have been configured so that all important information can be found on the headnode. There should not be a need to log in to nodes and check log files. The following is some general guidance when looking for problems. text/html 2025-09-15T14:59:58+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=limulus_compute_blades&rev=1757948398&do=diff Limulus Compute Blades Introduction The Limulus 2.0 Micro-ATX (μATX) blade represents a new generation of local, low-cost, and high-performance computing (e.g. for an office, lab, classroom, factory, a.k.a. edge computing). The modular design allows virtually any standard μATX motherboard to be combined into a dense high-performance computing resource using Limulus desk-side and rack-mount enclosures. The blade design provides an economic and flexible platform on which to build high performanc… text/html 2021-05-03T14:24:25+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=limulus_design_philosophy&rev=1620051865&do=diff Limulus Design Philosophy The Limulus design is based on several concepts. Many of these concepts, including commodity hardware and open software, were born during the early days of the Beowulf Cluster revolution. While conventional cluster designs rightfully grew to support more users and bigger problem sizes, the Limulus approach is designed to leverage quality low-cost hardware and open software to build high-performance text/html 2020-06-09T15:31:13+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=logging_in&rev=1591716673&do=diff Console Login (GUI) Remote Terminal Login text/html 2021-04-30T15:33:31+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=monitoring_system_resources&rev=1619796811&do=diff HPC Cluster Monitoring Ganglia On HPC systems the popular Ganglia monitoring tool is available. To bring up the Ganglia interface simply enter: http://localhost/ganglia/ In Firefox (or any other browser that is installed on the system). The default screen is shown below. text/html 2021-06-18T18:33:52+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=node_power_control&rev=1624041232&do=diff Node Power Control Each of the three worker nodes (seven nodes on the double-wide Limulus) can be powered up or down from the login node. This feature is generally not used in the Data Analytics systems because most of the daemons must be constantly running. In particular, the text/html 2020-07-01T17:04:29+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=open_hpc_components&rev=1593623069&do=diff OpenHPC Components slurm-slurmd-ohpc-18.08.8-4.1.ohpc.1.3.8.1.x86_64 slurm-example-configs-ohpc-18.08.8-4.1.ohpc.1.3.8.1.x86_64 warewulf-provision-ohpc-3.8.1-56.1.ohpc.1.3.9.x86_64 mrsh-rsh-compat-ohpc-2.12-19.1.x86_64 ohpc-ganglia-1.3.8-3.1.ohpc.1.3.8.x86_64 lua-posix-ohpc-33.2.1-4.1.x86_64 warewulf-cluster-ohpc-3.8.1-10.5.ohpc.1.3.6.x86_64 pdsh-mod-slurm-ohpc-2.33-97.1.ohpc.1.3.7.x86_64 munge-ohpc-0.5.13-7.1.ohpc.1.3.7.x86_64 lua-filesystem-ohpc-1.6.3-4.1.x86_64 slurm-ohpc-18.08.8-4.1.ohpc.1… text/html 2025-09-08T14:36:59+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=powering_up_down_nodes&rev=1757342219&do=diff Powering Nodes Up and Down Each Limulus system consists of one login-node and three or seven worker nodes. As shipped, the login-node has the alias name headnode (or limulus) and the worker node names are “n0, n1, and n2” and “n0, n1, n2, n3, n4, n5, and n6 text/html 2020-06-27T20:48:13+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=provision_listing&rev=1593290893&do=diff # wwsh provision print #### n0 ####################################################################### n0: BOOTSTRAP = 5.4.1-1.el7.elrepo.x86_64 n0: VNFS = co7_base n0: FILES = Limulus-node-startup.sh,gmond.conf,group,idmapd.conf,munge.key,passwd,report-ganglia-temp,resolv.conf,slurm.conf n0: PRESHELL = FALSE n0: POSTSHELL = FALSE n0: CONSOLE = UNDEF n0… text/html 2020-06-09T17:52:09+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=rack-mount_case&rev=1591725129&do=diff To be completed, contact Limulus Computing for more information text/html 2020-08-13T15:38:44+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=software_management&rev=1597333124&do=diff Software Management Installing, Updating, and Removing Packages Using Yum Using RPM Creating Module Files (lmod package) lmod documentation text/html 2025-09-15T16:27:04+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=start&rev=1757953624&do=diff Welcome to the Limulus Systems Manual Limulus Cluster Computing systems are available in either four- or eight-node desk-side cases or in a 4-node rack-mount unit. Multiple systems can be connected together to work as a larger cluster. There are two software stacks available: High Performance Computing (HPC) or scalable data analytics (Hadoop, Spark, Kafka, etc.). text/html 2021-04-28T14:51:38+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=submitting_jobs_to_the_slurm_workload_manager&rev=1619621498&do=diff Submitting Jobs to the Slurm Workload Manager All Limulus HPC systems use a workflow (user job) scheduler called Slurm. The purpose of the workflow scheduler is to distribute user programs across the cluster based on the amount of resources needed by each job, since the amount of user programs may exceed the amount of resources. For example, if each program needs one core and the cluster has 32 cores, then running more than 32 programs will oversubscribe the cluster resources. To manage a possi… text/html 2021-05-19T14:59:20+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=system-wide_administration_commands_pdsh&rev=1621436360&do=diff System Wide Commands using pdsh All Limulus systems have a a mechanism for executing commands on all worker nodes at the same time. The pdsh command allows the same command to be run on any combination of Limulus nodes. By default, and without any arguments, the text/html 2025-09-15T14:48:55+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=system_images&rev=1757947735&do=diff System Component Views and Identification The Limulus Cluster Workstation is a desk-side high performance machine. Views of the case are pictured below. Design detail are available on the Functional Diagram page. The case has two side doors,a removable front panel, and is on castors for easy movement. The power button (for the main motherboard), indicator lights, and USB ports are across the top. Immediately below, there is a removable SSD drive cage. text/html 2025-09-09T17:48:57+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=unpacking_and_startup&rev=1757440137&do=diff Unpacking The System The Limulus system may arrive in a double cardboard shipping box or on a mini-pallet. It is best to have two people unpack the system. It weighs approximately 60 pounds (27 kilograms). Once the system is unpacked and standing upright on the castors, text/html 2020-06-09T15:29:35+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=user_software&rev=1591716575&do=diff HPC Software Data Analytics Software text/html 2021-04-28T14:36:22+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=using_software_modules&rev=1619620582&do=diff Using Software Modules Many HPC systems support multiple libraries and library versions. For instance, by default, HPC Limulus systems support both Open MPI (Message Passing Interface) and MPICH. Each of these packages provides the MPI API for programmers and applications. These libraries are supplied as RPM packages as part of the text/html 2021-05-19T16:35:21+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=using_the_apache_ambari_cluster_manager&rev=1621442121&do=diff Introduction The Ambari web-based tool can be started opening a browser on the head node and entering "http://localhost:8080" . After login (password is provided by Limulus Computing), the Ambari Dash Board (control panel) similar to the image below will be displayed. The left side menu allows the values, services and nodes of the cluster to be viewed. An example of the the HDFS (Hadoop Distributed File System) is shown in the following figure: text/html 2025-10-15T19:21:31+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=using_the_zeppelin_web_notebook&rev=1760556091&do=diff TBC text/html 2021-05-20T17:18:21+00:00 Anonymous (anonymous@undisclosed.example.com) https://www.limulus-computing.com/Limulus-Manual/doku.php?id=warewulf_worker_node_images&rev=1621531101&do=diff Warewulf Worker Node Images All Limulus HPC systems use the Warewulf Toolkit to manage worker node images. The Warewulf toolkit allows worker nodes to boot “disk-less” using a RAM disk. The RAM disk and bootable kernel are managed by Warewulf. The following is a description of how Warewulf is configured and run on Limulus systems. Consult the Warewulf site for more detailed information.