- FAQ Home
- General
- Support And Documentation
- Installing BCM
- Cluster Management
- Configuring
- Power Management
- Node Provisioning
- Cloudbursting
- User Management
- Workload Management
- Software Management
- Cluster Monitoring
- Day-to-day Administration
- Third Party Software
- High Availability
- Burn
- Initialize And Finalize Scripts
- Security
- Development
- OpenStack
- Big Data
- Containers
- NVIDIA DGX
Advanced search
215 search results
Page 1 out of 5 Pages
- Configuring: How do I install the user portal on a login node from 8.0 onward? Answer: How to install the user portal on a login node from 8.0 onward The following procedure describes how to install and serve the user portal on ...
- Configuring: How do I add a login node? Answer: How do I add a login node? Table of contents Why have a login node?What do we need to consider for login nodes?1. Make a login image ...
- Cluster Management: Why can I login to the node as root, but not as a regular user? Answer: Two likely possibilities: 1. Maybe because /home is not mounted. Or 2. Maybe because users have been configured by Bright Cluster Manager to prevent ssh access. So check these ...
- NVIDIA DGX: How do I add NVIDIA DGX nodes to a Bright cluster using the official Ubuntu Answer: How do I add NVIDIA DGX nodes to a Bright cluster using the official Ubuntu DGX software stack? Bright provides a software image for the official ...
- Installing BCM: How do I install my head node using a PXE server? Answer: In certain situations it may be desirable to install a Bright head node by booting it off of a PXE server. There are a few ...
- Configuring: How do I make regular nodes return an FQDN using 'hostname -f'? Or resolve the Answer: How do I make regular nodes return an FQDN using 'hostname -f'? Or resolve the hostnames to IPs on the external network? There are two ways ...
- Third Party Software: How can I login to cmgui with a one-time password? Answer: How can I authenticate to cmgui with a one-time password? Introduction: One time password (OTP) authentication overcomes replay attacks. It allows an administrator to login to a ...
- Configuring: What is cm-register-node, and how can I use it? Answer: What is cm-register-node, and how can I use it? (was: How can I add an SGI UV node to an existing Bright Cluster?) Written in catechismic ...
- High Availability: How do I rename my head nodes? Answer: I've got a failover setup. How do I rename my head nodes? The following works even if you are exchanging names: Eg: head 1 is a white ...
- Configuring: How do I configure a generic node as an external DNS entry on the head Answer: How do I configure a generic node as an external DNS entry on the head node?A non-managed bright node is a generic device that is ...
- General: The node-installer fails to detect the bridge interfaces after upgrading to RHEL/CentOS 7.3 Answer: In recent (december 2016) versions of RHEL/CentOS 7.3, the bridge kernel module has been split into two components: the bridge and br_netfilter kernel modules. By ...
- Node Provisioning: How do I set up a storage node? Answer: Setting up a Storage Node Aside from the following points, setting up a storage node is no different from setting up any other compute node: ...
- Cluster Monitoring: How do I run a health check only for a specific set of nodes? Answer: With Bright 8.x this can be done using nodeexecutionfilters. Example: Modifying the megaraid health check to only be run on a specific set of nodes rather than ...
- Cluster Management: How can I reduce the size of cmdaemon and node installer logs? Answer: By default, cmdaemon, node installer and some other Bright Cluster Manager logs are handled with logrotate. The options for these can be set in:/etc/logrotate.d/cmdaemonThe logrotate ...
- Workload Management: How do I call Slurm utilities from nodes that run no slurmdbd? Answer: On a node, some Slurm utilities such as sacct need to connect to the slurmdbd daemon. slurmdbd in turn talks to mysql. If the node ...
- Node Provisioning: How can I flash update all my nodes (from DOS)? Answer: How can I flash update all my nodes (from DOS)? (For update via Linux, see http://kb.brightcomputing.com/faq/index.php?action=artikel&cat=11&id=105 ) The problem:I have to perform some maintenance on the nodes ...
- Installing BCM: How do I upgrade my cluster if I have a storage node that is being Answer: How do I update a cluster with a storage node that is shared? Upgrading with a Storage Node Special considerations must be made when upgrading Bright versions ...
- Workload Management: How can a PBSPro Server installed externally get recognized by a head node? Answer: An externally installed PBS Pro server is not visible to Bright Cluster Manager, by default. But this can be made possible, with a few tricks, as ...
- Configuring: How do I use Samba to share folders on a Bright Head Node? Answer: How do I share folders using Samba on a Bright Head Node? Basically: /etc/samba/smb.conf needs to be modified to add the required share, and shorewall rules ...
- Software Management: Why has my software suite has vanished from the bunch of nodes I installed it Answer: Most likely you installed the software directly onto those nodes instead of on the "software image". Then, after a reboot of the nodes, whatever you ...
- Configuring: How do I stop nodes from accessing the internet? Answer: How do I stop nodes from accessing the Internet? By default all compute nodes use the head node as its default gateway, and the head node ...
- Node Provisioning: How do I automatically plug in new nodes and assign it an identity in Bright? Answer: How do I automatically plug in new nodes and assign it an identity in Bright? The following technique can save labor, when you are adding a ...
- Node Provisioning: My regular nodes aren't booting up after an update, why? What now? Answer: Some updates in the software image require recreating the initrd. Bright Cluster Manager is not aware of such updates. As result, when regular nodes are rebooted, ...
- Cluster Management: When does a node need to be restarted? Answer: When does a node need to be restarted? Why does a node need to be restarted? Can I ignore it? How do I clear that ...
- Installing BCM: How can I mass-produce Bright head node installations using PXE? Answer: An already-installed (or primary) Bright head node can be used to create a head node PXE image. Machines that are booted using PXE, from the ...
- Node Provisioning: How can Windows Server 2008 R2 be provisioned to a node with Bright? Answer: How can Windows Server 2008 R2 be provisioned to a node, using Bright? This guide walks through configuring Bright Cluster Manager 7.1/RHEL7 to deploy Windows Server ...
- Cloudbursting: How do I use EBS volume snapshots to boot my cloud nodes? Answer: Why should I use snapshots? Because it reduces the provisioning times of your cloud nodes. Some more background details By default, all newly-created cloud nodes, and their associated ...
- Node Provisioning: How do I (re)install an operating system on a compute node disk, without losing data Answer: How do I (re)install an operating system on a regular node (compute node) disk, without losing data on the other disks of that node? Sometimes an ...
- General: How to retrieve my product key from my head node? Answer: Starting from Bright 7.3, CMDaemon revision 35506 or later, a script is provided to retrieve the product key from the CSR file on the head node. ...
- Software Management: How do I enable a graphical (X11) login after installation? Answer: Why Is The SLES Graphical Console Disabled After Installation? After the Bright head node installation for SLES, the Graphical console option is disabled. This is because ...
- OpenStack: How do I extend an OpenStack cluster with extra controller/network nodes? Answer: How do I extend an OpenStack cluster with extra controller/network nodes? Scenario: You have installed OpenStack with one controller. Now you want to add two more controllers ...
- High Availability: How to Install Lustre with ZFS and HA for OSS and MDS Nodes Answer: Prerequisites: 2 OSS nodes connected via SAS over multiple paths to their own JBOD shared storage (minimum eight drives) 2 MDS nodes connected via SAS over multiple ...
- Configuring: Can I dual-boot my nodes between Linux and Windows? Answer: There are a number of ways to set up nodes that dual-boot between Linux and Windows. Bright Cluster Manager cannot provision Windows images to compute ...
- Installing BCM: How do I put a custom disk layout in the head node installer? Answer: How do I put a custom disk layout in the head node installer? The head node installer stages are described in the chapter Installing Bright Cluster ...
- NVIDIA DGX: Can I run a DGX node using Ubuntu 16.04? Answer: Bright only provides a DGX software images based on the official DGX software stack for Ubuntu 18.04. If you want to run a DGX node ...
- Configuring: How do I install LUKS/NBDE onto Bright nodes? Answer: How do I use LUKS + NBDE "Network-Bound Disk Encryption" to encrypt data on regular Bright nodes? Introduction: This FAQ describes how to use Network-Bound Disk Encryption ...
- Node Provisioning: How can I flash update all my nodes (from Linux)? Answer: How can I flash update all my nodes (from Linux)? (For update via DOS, see http://kb.brightcomputing.com/faq/index.php?action=artikel&cat=20&id=94 ) Some manufacturers like Dell provide a flash BIOS upgrade utility ...
- High Availability: Why are my filesystems no longer exported from my head node after setting up HA? Answer: Why are my filesystems no longer exported from my head node after setting up HA? Short answer: It is done by Bright to protect the filesystems ...
- Initialize And Finalize Scripts: How do I use the finalize script to transfer certificates to the nodes? Answer: How do I use the finalize script to transfer certificates to the nodes? In many cases, it might be desired to use node-specific certificates for certain ...
- Cloudbursting: How can I attach an EBS snapshot volume to a new node in Amazon EC2? Answer: Advanced customization of Amazon EC2 instances — attaching snapshots In some cases there is a need to automatically attach an EBS volume created from a snapshot ...
- Security: How to keep my port scanning tool from crashing my head node? Answer: If you find that using a port scanning tool like Nessus or nmap causes your head node to crash or temporarily become unresponsive, then make ...
- NVIDIA DGX: Can I run a DGX as a Bright head node? Answer: We recommend that you do not run a DGX head node. In order to be able to scale up, it is beneficial to run a ...
- Cluster Monitoring: How to have Bright 8.x email me when a node goes down? Answer: You can add the following trigger using cmsh on your active head node: # cmsh % monitoring trigger % add node_down % ...
- High Availability: How do I switch the identity of the primary head node to the secondary head Answer: This can be useful if you want to switch the active headnode to the passive headnode. For example, for the purposes of swapping hardware. (NOTE: ...
- User Management: How do I enable multi-level kerberos and LDAP authentication in cmgui? Answer: How do I enable both kerberos and LDAP authentication for cmgui? For Red Hat-based system such as RHEL, CentOS or Scientific Linux: Configure The Head Node Configure your ...
- Configuring: How do I update behind a proxy? Answer: How do I update Bright if it is connected to the network behind a web proxy server? If you are sitting behind a network proxy server ...
- User Management: How do I integrate Bright with AD Using SSSD 's LDAP provider and Simple BIND? Answer: How do I integrate a Bright cluster into an Active Directory domain with SSSD 's LDAP provider? (The method in "How do I authenticate against Active ...
- Installing BCM: How do I install Bright on Virtual Box? Answer: How do I install Bright on Virtual Box? Prerequisite: In order to use PXE booting, the VirtualBox Extension Pack should be installed. Create a Virtual Machine (VM) for ...
- Big Data: How can I patch Apache HBase 1.2.x for the Kerberos TGT renewal issue? Answer: How can I patch Apache HBase 1.2.x for the Kerberos TGT renewal issue?The Problem HBase stops working after 24 hours. Restarting all HBase services will fix ...
- Power Management: Setup up custom power scripts for ProfitBricks Answer: Custom Power Scripts for controlling ProfitBricks Instances Prerequisites To use dynamic scaling of clusters on ProfitBricks’ IaaS platform you have to install a head node in a ...