Questions tagged [cluster]
discussion related to cluster mechanisms.
213
questions
1
vote
1
answer
23
views
Can I fully utilize HDR Infiniband network throughput between servers and NFS volume?
I'm working on a project building a CPU cluster, and those servers and NFS storage (not a parallel file system) are going to be connected through HDR InfiniBand cables. In this architecture, can I get ...
- 25
1
vote
1
answer
28
views
Unable to run linpack on head node of cluster
I recently set up my own home cluster - 4 units of raspberry pi. But I am having problems trying to benchmark all 4 units using Linpack
One node is the head node called rpislave1, it connects to the ...
- 21
0
votes
0
answers
152
views
configure: error: libcurl >= 7.28.0 library and headers are required with support for https at HPC
I met an issue when I tried to configure for R installation in HPC. I'm trying to install R-4.1.0 and 4.3.0; both show similar issue.
configure: error: libcurl >= 7.28.0 library and headers are ...
0
votes
0
answers
39
views
Trying to find the Solaris/Unix Veritas VCS Single Cluster Manager (Java Console)
I have an old install of VCSHA installed on my Sparc kit (Solaris 11 with VCS V5), and would like to try and get the VCS Single Cluster Manager (Java Console) installed.
When i attempt to run it, i ...
- 141
2
votes
1
answer
41
views
How to set up a bunch of linux servers with shared file system without using job scheduler?
I am managing multiple GPU servers in our lab, which are mainly used for deep learning tasks. We would like these machines to share the same file system, so it is easier to switch between them.
...
- 23
0
votes
0
answers
52
views
Proper way to design filesystems structure for a cluster of diskless nodes
I'm trying to learn the basics of Linux clustering so I started designing a really humble cluster:
6 worker nodes (Libre Computer La Frite | Cortex-A53 @ 1.2 GHz | 1GB RAM)
1 master node (Raspberry ...
- 1
0
votes
1
answer
88
views
Remove internet access without losing LAN
I have a small cluster (all nodes run Debian 10) and need to remove the internet connections of all slave nodes. The internet cable connection connects to a computer that acts as a firewall, then, ...
1
vote
1
answer
97
views
Transferring very large dataset from cluster to a storage server
We have to move a set of very large data (in petabytes) from HPC cluster to a storage server. We have a high capacity communication link between the devices. However, the bottleneck seems to be a fast ...
- 111
-1
votes
1
answer
195
views
IBM AIX - Method to identify Cluster or HA services
I am keen to learn if existing IBM AIX servers from different location have Clustering/HA features. Kindly let me know the steps to check. Thanks.
- 49
1
vote
1
answer
794
views
Running multiple SLURM jobs on the same GPU
So, I am by no means a sysadmin but I need to use an existing SLURM installation to launch a sizable amount of jobs (around 5000).
The cluster is composed of 1 node with 10 GPUs (with 8GB of memory ...
- 113
0
votes
1
answer
121
views
How to tell if a VG is clustered?
I have a CentOS 7 Pacemaker cluster with GFS2 Filesystrems mounted. I'm fairly certain that vgchange -cy vg_name was NOT run during setup. I tried running vgchange --test -cy vg_name and it tells me ...
0
votes
0
answers
31
views
NFS shared file system that uses all PCs hard drive
I'm building a small cluster with desktop computers that run on Debian 11.
I want a shared /home directory where all user's files are located. I know that the ideal way to do this is to have a master ...
0
votes
0
answers
117
views
How to update computing nodes in a cluster?
I am in the process of small computing cluster assembly. It will run Ubuntu/Slurm for job scheduling. Only the head node will be connected to the Internet, all others will be accessible from the local ...
- 11
1
vote
0
answers
37
views
Will execution of many parallel instances of an application from NFS drive affect performance?
I am assembling a simple computing cluster under Ubuntu 20.04 and Slurm as a job scheduler.
The cluster will be primarily used for quantum-chemical calculations, so, as a rule, each job will run its ...
- 11
0
votes
1
answer
107
views
Does the size of a file system cluster have to be even bytes?
Basically, could we have a file system with odd byte size clusters? Why is everything even? Thanks
- 1,346
0
votes
0
answers
726
views
What is "quorum-manager" under Designation in GPFS Cluster Information?
I get this block of information under my GPFS cluster information when I execute /usr/lpp/mmfs/bin/mmlscluster and I can't find documentation on what the Designation actually means. Does quorum-...
- 121
0
votes
0
answers
269
views
Sharing ssh keys between cluster nodes
I have a cluster with several login nodes and many compute nodes (call it the cluster). Then I have another server with a large shared storage (call it the storage). I need to be able to rsync (i.e. ...
- 135
-1
votes
1
answer
29
views
Sync sudo anthority to all nodes
I want to submit a task that is interpreted by /bin/csh, which only exists in master node. And I have no root permission but only sudo, which is limited in master node. So I can't use sudo apt install ...
- 1
1
vote
0
answers
67
views
Jetson Nano Picocluster not accessible from network
I recently received a Picocluster with five Jetson Nano boards running MicroK8S. The cluster has a built in switch, which I know works as I can route my own network traffic through it just fine. All ...
1
vote
0
answers
90
views
Is it possible to mount an ATA over Ethernet (AOE) block device on multiple clients, if so how?
I have a lab consisting of 3 machines connected with 2 10gbe links on 2 segregated networks. Each device has 100tb in block storage connected to it. I want to use ATA over Ethernet to create a storage ...
- 111
0
votes
1
answer
661
views
How to create a ocfs2 filesystem in ubuntu?
Can someone please walk me through the step-by-step process of configuring a ocfs2 filesystem right from splitting an existing partition? When I tried, I am seeing the below error:
mount.ocfs2: ...
0
votes
0
answers
27
views
Why non-root python installation can work across the whole cluster?
I recently installed anaconda (which includes a python3) locally in my account folder on a cluster with a dozen of nodes (each node with several cores). I use it to install some package P that is used ...
- 111
1
vote
1
answer
816
views
Debian 10 Pacemaker-Cluster: GFS2 Mount fails because of "Global lock failed: check that global lockspace is started."
I'm trying to setup a new Debian 10 cluster with three instances. My stack is based on pacemaker, corosync, dlm, and lvmlockd with a GFS2 volume. All servers have access to the GFS2 volume but I can't ...
- 11
0
votes
1
answer
2k
views
Error: #error This file requires compiler and library support for the ISO C++ 2011 standard
I am running a c++ code with TAU (analyzing and profiling tool) on Ubuntu 20.04 LTS using some cluster. The command I am running looks like this:
tau_cxx.sh -I$FFTW3_INC wrappingScript.cpp ...
- 111
1
vote
1
answer
1k
views
How can I submit multiple R job at once?
I have a R-script which runs multiple files say file=1 to 50.
I usually submit repeated jobs say 5 times with 10 files each time by changing the number in R-script.
So, how can I submit the 5-job at ...
- 21
0
votes
1
answer
17
views
What are the existing open source tools to develop on-premise organizational app store on linux?
We have a Linux cluster in our organization and my data science team is developing a number of ML projects to be utilized by teams across the organization. To enable the teams to access the ML models, ...
- 101
0
votes
1
answer
226
views
Where are libvirt's VM definitions "originals" stored, and how to sync them across multiple nodes?
Migrating from Xen's xm to Xen's xl under control of libvirt, I wonder:
Where does libvirt store the "originals" of VM configurations?
I found that my PVM configurations are stored in /etc/...
- 1,104
2
votes
1
answer
656
views
Python error only when I run script on Linux cluster: _tkinter.TclError: no display name and no $DISPLAY environment variable
My question is related to a python error, but I suspect that it is more a Linux question than a python one. Thus I post it first here.
I am running a python script which does a calculation and then ...
- 165
0
votes
0
answers
2k
views
How can I cancel all waiting jobs with qsub?
I am running a lot of jobs with qsub: some are running, some are waiting. Is there a way to cancel all the jobs for a given user which are queued/waiting without giving the individual job IDs?
- 133
2
votes
1
answer
1k
views
how to set passwordless authentication in a cluster where users /home directory from headnode is mounted to all machines /home of the cluster
First of all thank you in advance for your help.
I hope the title makes sense. Basically, on the headnode the users' home directory (i.e: headnode:/home/eric) are NFS shared and mounted to all the ...
- 33
0
votes
1
answer
1k
views
Pacemaker apache resource is Failed to access httpd status page after change to HTTPS
I get this error from pacemaker after i change apache from http to https.
now my ocf::heartbeat:apache resource is not find status page.
I generate SSL certificate separately for 3 servers.
Everything ...
2
votes
1
answer
1k
views
Simple cp command not working (inside shell script and submitted using sbatch on a cluster)
I am working on a cluster running RHEL and I submit jobs using the following command.
sbatch MyScript.sh
The content of the MyScript.sh are as below.
#!/bin/sh
# ....
# Other SBATCH related commands ...
- 123
1
vote
1
answer
207
views
compiling HPL-2.0_FERMIv15
when i compile xhpl i always get the error message:
./xhpl: error while loading shared libraries: libdgemm.so.1: cannot open shared object file: No such file or directory
when i type ldd xhpl:
linux-...
- 11
1
vote
0
answers
477
views
Cannot seem to start pcs cluster (NFS Cluster) disk_fencing trouble
For the life of me, I can't find a clear answer on how to start my NFS active / passive cluster. I have two nodes, node1 and node2 and followed the guide here: https://www.linuxtechi.com/configure-nfs-...
- 11
0
votes
1
answer
3k
views
DRBD: "Couldn't mount device [/dev/drbd0] as /mydata" when failing over or rebooting node
I'm creating a cluster system using two ESXi hosts, with a CentOS 7 server on each.
Going through I created the filesystem, and it mounts on node1.
When I perform a standby or reboot from node01 to ...
- 133
0
votes
2
answers
3k
views
How to Remove caavg_private Properly on AIX?
I am trying to cleanup a server which had a PowerHA configuration. I have stopped cluster (smitty clstop) and removed resource groups. How do I remove the caavg_private properly?
hdisk5 ...
0
votes
1
answer
64
views
RHEL 6.9 HA clustering issue with one node completely down
I have two node servers with SAN storage.
Each node have RHEL 6.9 with HA and the partition are mapped from the storage using fiber cables with clustered resources.
The thing is when the two nodes ...
0
votes
1
answer
230
views
Trying to Create an AFM relationship by using GPFS protocol. Having error in cache side cluster
I am trying to create an AFM relationship by using GPFS protocol. Having error in cache side cluster.
Steps of Home cluster :
1) Create a home cluster (cluster name - gpfs01).
2) Create a file ...
1
vote
0
answers
289
views
OpenLDAP Cluster
Trying to implement an OpenLDAP cluster, I already managed to set up the two backend LDAP servers in mirroring mode.
The application (iRedMail) using the LDAP service is running on the same systems ...
- 11
0
votes
0
answers
662
views
How does htop calculate times? (Impossible times shown)
I was running what was supposed to be a small make job on a small node in our cluster, but a sorting process seemed to be overwhelming the allocated RAM, so I killed it after 20 hours (same jobs on ...
- 101
0
votes
1
answer
80
views
how to move fs resource in service group in ccs cluster
I have a ccs cluster running on RHEL 6.4 where there is no luci service, i have added a filesystem resource to the cluster with the below command but i need to move the resource inside a service group....
0
votes
1
answer
420
views
How to setup a compute cluster in local network on top of linux
I have 3 machines in my local network running manjaro. I am running python scripts using dask, pandas, etc which max out the cpu on the first machine and I usually need to wait more than 30 min until ...
- 123
0
votes
2
answers
174
views
Why worker nodes are not fault-tolerant?
A swarm manager nodes handles cluster management tasks such as:
1) Maintaining cluster state
2) Scheduling services
3) Serving swarm mode HTTP API endpoints
You may execute any of the - docker ...
- 1,486
1
vote
1
answer
674
views
what is the purpose of overlay network driver?
Below is the command run on ubuntu to create overlay network driver for swarm cluster instead of using bridge network driver
$ docker network create -d overlay xyz
$ docker network ls ...
- 1,486
0
votes
1
answer
457
views
Performing maintenance on GFS2 inside pacemaker cluster
I will need to perform a maintenance on one of storage servers that provides GFS2 volume to a three node pacemaker cluster.
Same cluster has an addition of 2 GFS2 volumes as well.
Would it be safe to ...
- 367
1
vote
1
answer
155
views
Run a shell script within an already running shell script
I have a small SLURM cluster, which I am using to run jobs. I run a script and while that script is running, I want to enter a specific key command "t + enter". I believe I should do it by submitting ...
- 111
2
votes
1
answer
1k
views
Slurm on desktop computers, how to prioritize the owner
In short: On a Slurm cluster, I need some computers to be available and responsive to their respective owners during work hours.
Problem: I manage a small (but growing) heterogeneous cluster with ...
- 151
2
votes
1
answer
3k
views
PCS Stonith (fencing) will kill two node cluster if first is down
I have configured a two node physical server cluster (HP ProLiant DL560 Gen8) using pcs (corosync/pacemaker/pcsd). I have also configured fencing on them using fence_ilo4.
The weird thing will happen ...
- 367
1
vote
1
answer
609
views
Pacemaker: stopping pacemaker doesn't always move resources to other node
I have created a 2 node cluster on sles12. Following is the configuration -
msnode1:~ # crm --version
crm 3.0.0
msnode1:~ # corosync -v
Corosync Cluster Engine, version '2.3.6'
...
- 11
1
vote
0
answers
42
views
OpenLDAP cluster: deletion of an entry is not replicated
We have an OpenLDAP 2.4 cluster of three nodes configured in multi-master and accessed through a VIP in round-robin. The three machines run RHEL7.
We noticed that deletion of an entry (done from a ...
- 28.8k