Nexus/CBCB: Difference between revisions

From UMIACS
Jump to navigation Jump to search
No edit summary
 
(24 intermediate revisions by the same user not shown)
Line 2: Line 2:


= Submission Nodes =
= Submission Nodes =
There are two submission nodes for Nexus exclusively available for CBCB users.
You can [[SSH]] to <code>nexuscbcb.umiacs.umd.edu</code> to log in to a submission host.


If you store something in a local directory (/tmp, /scratch0) on one of the two submission hosts, you will need to connect to that same submission host to access it later. The actual submission hosts are:
* <code>nexuscbcb00.umiacs.umd.edu</code>
* <code>nexuscbcb00.umiacs.umd.edu</code>
* <code>nexuscbcb01.umiacs.umd.edu</code>
* <code>nexuscbcb01.umiacs.umd.edu</code>


= Resources =  
= Nodes =  
The new CBCB partition has 22 new nodes with 32 [https://www.amd.com/en/products/cpu/amd-epyc-7313 AMD EPYC-7313] cores and 2000GB of memory each.  CBCB users can also submit jobs and access resources such as GPUs in other partitions in [[Nexus]].
All nodes in CBCB-owned partitions (see below section) owned by CBCB faculty are named in the format <code>cbcb##</code>. The sets of nodes are:
* 22 nodes that were purchased in October 2022 with center-wide funding.  They are cbcb[00-21].
* 4 nodes from the previous standalone CBCB cluster that moved in as of Summer 2023.  They are cbcb[22-25].
* A few additional nodes purchased by Dr. Heng Huang since then.  They are all remaining 'cbcb' named nodes.


Some of the newer nodes from the [https://wiki.umiacs.umd.edu/cbcb-private/index.php/Slurm standalone CBCB cluster] (albeit still several years old) have also moved into this partition as of Summer 2023. There have also been a few other nodes brought in as of Fall 2023.
{| class="wikitable sortable"
! Nodenames
! Quantity
! CPU cores per node (CPUs)
! Memory per node (type)
! Local storage per node (type/location)
! GPUs per node (type)
|-
|cbcb[00-21]
|22
|32 (Dual [https://www.amd.com/en/products/processors/server/epyc/7003-series/amd-epyc-7313.html AMD EPYC 7313])
|~2TB (DDR4 3200MHz)
|~350GB (SATA SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch0]]), ~2TB (NVMe SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch1]])
|0
|-
|cbcb22
|1
|28 (Dual [https://ark.intel.com/content/www/us/en/ark/products/91754/intel-xeon-processor-e5-2680-v4-35m-cache-2-40-ghz.html Intel Xeon E5-2680 v4])
|~768GB (DDR4 2400MHz)
|~650GB (SATA SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch0]])
|0
|-
|cbcb[23-24]
|2
|24 (Dual [https://www.intel.com/content/www/us/en/products/sku/91767/intel-xeon-processor-e52650-v4-30m-cache-2-20-ghz/specifications.html Intel Xeon E5-2650 v4])
|~256GB (DDR4 2400MHz)
|~800GB (SATA SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch0]])
|0
|-
|cbcb25
|1
|24 (Dual [https://www.intel.com/content/www/us/en/products/sku/91767/intel-xeon-processor-e52650-v4-30m-cache-2-20-ghz/specifications.html Intel Xeon E5-2650 v4])
|~256GB (DDR4 2400MHz)
|~1.4TB (SATA SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch0]])
|2 (1x [https://www.nvidia.com/en-gb/geforce/graphics-cards/geforce-gtx-1080-ti/specifications/ NVIDIA GeForce GTX 1080 Ti], 1x [https://www.nvidia.com/en-us/geforce/graphics-cards/compare/?section=compare-20 NVIDIA GeForce RTX 2080 Ti])
|-
|cbcb26
|1
|128 (Dual [https://www.amd.com/en/products/processors/server/epyc/7003-series/amd-epyc-7763.html AMD EPYC 7763])
|~512GB (DDR4 3200MHz)
|~3.4TB (NVMe SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch0]]), ~14TB (NVMe SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch1]])
|8 ([https://www.nvidia.com/en-us/design-visualization/rtx-a5000 NVIDIA RTX A5000])
|-
|cbcb27
|1
|64 (Dual [https://www.amd.com/en/products/processors/server/epyc/7003-series/amd-epyc-7513.html AMD EPYC 7513])
|~256GB (DDR4 3200MHz)
|~3.4TB (SATA SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch0]]), ~3.5TB (NVMe SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch1]])
|8 ([https://www.nvidia.com/en-us/design-visualization/rtx-a6000 NVIDIA RTX A6000])
|-
|cbcb[28-29]
|2
|32 (Dual [https://www.amd.com/en/products/processors/server/epyc/4th-generation-9004-and-8004-series/amd-epyc-9124.html AMD EPYC 9124])
|~768GB (DDR5 4800MHz)
|~350GB (SATA SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch0]]), ~7TB (NVMe SSD [[LocalDataStorage#UNIX_Local_Storage | /scratch1]])
|8 ([https://www.nvidia.com/en-us/design-visualization/rtx-6000 NVIDIA RTX 6000 Ada Generation])
|- class="sortbottom"
!Total
|30
|1060 (various)
|~49TB (various)
|~94TB (various)
|34 (various)
|}
 
Here is the listing of nodes as shown by the Slurm alias <code>show_nodes</code> (again, all nodes are named in the format <code>cbcb##</code>):
<pre>
[root@nexusctl00 ~]# show_nodes | grep cbcb
NODELIST            CPUS      MEMORY    AVAIL_FEATURES                GRES                            STATE
cbcb00              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb01              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb02              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb03              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb04              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb05              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb06              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb07              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb08              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb09              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb10              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb11              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb12              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb13              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb14              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb15              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb16              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb17              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb18              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb19              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb20              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb21              32        2061175    rhel8,Zen,EPYC-7313            (null)                          idle
cbcb22              28        771245    rhel8,Xeon,E5-2680            (null)                          idle
cbcb23              24        255150    rhel8,Xeon,E5-2650            (null)                          idle
cbcb24              24        255150    rhel8,Xeon,E5-2650            (null)                          idle
cbcb25              24        255278    rhel8,Xeon,E5-2650,Pascal,Turi gpu:rtx2080ti:1,gpu:gtx1080ti:1  idle
cbcb26              128        513243    rhel8,Zen,EPYC-7763,Ampere    gpu:rtxa5000:8                  idle
cbcb27              64        255167    rhel8,Zen,EPYC-7513,Ampere    gpu:rtxa6000:8                  idle
cbcb28              32        771166    rhel8,Zen,EPYC-9124,Ada        gpu:rtx6000ada:8                idle
cbcb29              32        771166    rhel8,Zen,EPYC-9124,Ada        gpu:rtx6000ada:8                idle
</pre>


= Partitions =
= Partitions =
Line 19: Line 122:
There is one additional partition available solely to Dr. Heng Huang's sponsored accounts.
There is one additional partition available solely to Dr. Heng Huang's sponsored accounts.


* '''cbcb-heng''' - This partition is for exclusive priority access to Dr. Huang's purchased A5000 and A6000 nodes. Job allocations are guaranteed.
* '''cbcb-heng''' - This partition is for exclusive priority access to Dr. Huang's purchased GPU nodes. Job allocations are guaranteed.


= QoS =  
= QoS =  
Line 31: Line 134:


= Jobs =
= Jobs =
You will need to specify <code>--partition=cbcb</code>, <code>--account=cbcb</code>, and a specific <code>--qos</code> to be able to submit jobs to the CBCB partition.  
You will need to specify <code>--partition=cbcb</code> and <code>--account=cbcb</code> to be able to submit jobs to the CBCB partition.  


<pre>
<pre>
Line 65: Line 168:


= Storage =
= Storage =
CBCB still has its current [https://wiki.umiacs.umd.edu/cbcb-private/index.php/Storage storage] allocation in place.  All data filesystems that are available in the standalone CBCB cluster are also available in Nexus.  Please note about the change in your home directory in the migration section below.
CBCB still has its current [https://wiki.umiacs.umd.edu/cbcb-private/index.php/Storage storage] allocation in place.  All data filesystems that were available in the standalone CBCB cluster are also available in Nexus.  Please note about the change in your home directory in the migration section below.


CBCB users can also request [[Nexus#Project_Allocations | Nexus project allocations]].
CBCB users can also request [[Nexus#Project_Allocations | Nexus project allocations]].
Line 72: Line 175:


== Home Directories ==
== Home Directories ==
The [[Nexus]] uses [[NFShomes]] home directories and not <code>/cbcbhomes/$USERNAME</code>.  As part of the process of migrating into Nexus, you may want (or need) to copy any shell customization from your existing <code>/cbcbhomes</code> to your <code>/nfshomes</code>.  To make this transition easier, <code>/cbcbhomes</code> is available to the Nexus CBCB submission nodes.
The [[Nexus]] uses [[NFShomes]] home directories and not <code>/cbcbhomes/<USERNAME></code>.  As part of the process of migrating into Nexus, you may want (or need) to copy any shell customization from your existing <code>/cbcbhomes</code> to your <code>/nfshomes</code>.  To make this transition easier, <code>/cbcbhomes</code> is available to the Nexus CBCB submission nodes.


== Operating System / Software ==
== Operating System / Software ==
CBCB's standalone cluster submission and compute nodes are running RHEL7.  [[Nexus]] is exclusively running RHEL8, so any software you may have compiled may need to be re-compiled to work correctly in this new environment.  The [https://wiki.umiacs.umd.edu/cbcb/index.php/CBCB_Software_Modules CBCB module tree] for RHEL8 may not yet be fully populated with RHEL8 software.  If you do not see the modules you need, please reach out to the [https://wiki.umiacs.umd.edu/cbcb/index.php/CBCB_Software_Modules#Contact CBCB software maintainers].
CBCB's standalone cluster submission and compute nodes were running RHEL7.  [[Nexus]] is exclusively running RHEL8, so any software you may have compiled may need to be re-compiled to work correctly in this new environment.  The [https://wiki.umiacs.umd.edu/cbcb/index.php/CBCB_Software_Modules CBCB module tree] for RHEL8 may not yet be fully populated with RHEL8 software.  If you do not see the modules you need, please reach out to the [https://wiki.umiacs.umd.edu/cbcb/index.php/CBCB_Software_Modules#Contact CBCB software maintainers].

Latest revision as of 16:36, 12 June 2024

The Nexus scheduler houses CBCB's new computational partition. Only CBCB lab members are able to run non-interruptible jobs on these nodes.

Submission Nodes

You can SSH to nexuscbcb.umiacs.umd.edu to log in to a submission host.

If you store something in a local directory (/tmp, /scratch0) on one of the two submission hosts, you will need to connect to that same submission host to access it later. The actual submission hosts are:

  • nexuscbcb00.umiacs.umd.edu
  • nexuscbcb01.umiacs.umd.edu

Nodes

All nodes in CBCB-owned partitions (see below section) owned by CBCB faculty are named in the format cbcb##. The sets of nodes are:

  • 22 nodes that were purchased in October 2022 with center-wide funding. They are cbcb[00-21].
  • 4 nodes from the previous standalone CBCB cluster that moved in as of Summer 2023. They are cbcb[22-25].
  • A few additional nodes purchased by Dr. Heng Huang since then. They are all remaining 'cbcb' named nodes.
Nodenames Quantity CPU cores per node (CPUs) Memory per node (type) Local storage per node (type/location) GPUs per node (type)
cbcb[00-21] 22 32 (Dual AMD EPYC 7313) ~2TB (DDR4 3200MHz) ~350GB (SATA SSD /scratch0), ~2TB (NVMe SSD /scratch1) 0
cbcb22 1 28 (Dual Intel Xeon E5-2680 v4) ~768GB (DDR4 2400MHz) ~650GB (SATA SSD /scratch0) 0
cbcb[23-24] 2 24 (Dual Intel Xeon E5-2650 v4) ~256GB (DDR4 2400MHz) ~800GB (SATA SSD /scratch0) 0
cbcb25 1 24 (Dual Intel Xeon E5-2650 v4) ~256GB (DDR4 2400MHz) ~1.4TB (SATA SSD /scratch0) 2 (1x NVIDIA GeForce GTX 1080 Ti, 1x NVIDIA GeForce RTX 2080 Ti)
cbcb26 1 128 (Dual AMD EPYC 7763) ~512GB (DDR4 3200MHz) ~3.4TB (NVMe SSD /scratch0), ~14TB (NVMe SSD /scratch1) 8 (NVIDIA RTX A5000)
cbcb27 1 64 (Dual AMD EPYC 7513) ~256GB (DDR4 3200MHz) ~3.4TB (SATA SSD /scratch0), ~3.5TB (NVMe SSD /scratch1) 8 (NVIDIA RTX A6000)
cbcb[28-29] 2 32 (Dual AMD EPYC 9124) ~768GB (DDR5 4800MHz) ~350GB (SATA SSD /scratch0), ~7TB (NVMe SSD /scratch1) 8 (NVIDIA RTX 6000 Ada Generation)
Total 30 1060 (various) ~49TB (various) ~94TB (various) 34 (various)

Here is the listing of nodes as shown by the Slurm alias show_nodes (again, all nodes are named in the format cbcb##): 

[root@nexusctl00 ~]# show_nodes | grep cbcb
NODELIST             CPUS       MEMORY     AVAIL_FEATURES                 GRES                             STATE
cbcb00               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb01               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb02               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb03               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb04               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb05               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb06               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb07               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb08               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb09               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb10               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb11               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb12               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb13               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb14               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb15               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb16               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb17               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb18               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb19               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb20               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb21               32         2061175    rhel8,Zen,EPYC-7313            (null)                           idle
cbcb22               28         771245     rhel8,Xeon,E5-2680             (null)                           idle
cbcb23               24         255150     rhel8,Xeon,E5-2650             (null)                           idle
cbcb24               24         255150     rhel8,Xeon,E5-2650             (null)                           idle
cbcb25               24         255278     rhel8,Xeon,E5-2650,Pascal,Turi gpu:rtx2080ti:1,gpu:gtx1080ti:1  idle
cbcb26               128        513243     rhel8,Zen,EPYC-7763,Ampere     gpu:rtxa5000:8                   idle
cbcb27               64         255167     rhel8,Zen,EPYC-7513,Ampere     gpu:rtxa6000:8                   idle
cbcb28               32         771166     rhel8,Zen,EPYC-9124,Ada        gpu:rtx6000ada:8                 idle
cbcb29               32         771166     rhel8,Zen,EPYC-9124,Ada        gpu:rtx6000ada:8                 idle

Partitions

There is only one partition available to general CBCB SLURM users. You must specify this partition when submitting your job.

  • cbcb - This is the default partition. Job allocations on all nodes except those also in the below-mentioned partition are guaranteed.

There is one additional partition available solely to Dr. Heng Huang's sponsored accounts.

  • cbcb-heng - This partition is for exclusive priority access to Dr. Huang's purchased GPU nodes. Job allocations are guaranteed.

QoS

CBCB users have access to all of the standard job QoSes in the cbcb partition using the cbcb account.

The additional job QoSes for the CBCB partition specifically are:

  • highmem: Allows for significantly increased memory to be allocated.
  • huge-long: Allows for longer jobs using higher overall resources.

Please note that the partition has a GrpTRES limit of 100% of the available cores/RAM on the partition-specific nodes in aggregate plus 50% of the available cores/RAM on legacy## nodes in aggregate, so your job may need to wait if all available cores/RAM (or GPUs) are in use.

Jobs

You will need to specify --partition=cbcb and --account=cbcb to be able to submit jobs to the CBCB partition. 

[username@nexuscbcb00:~ ] $ srun --pty --ntasks=16 --mem=2000G --qos=highmem --partition=cbcb --account=cbcb --time 1-00:00:00 bash
srun: job 218874 queued and waiting for resources
srun: job 218874 has been allocated resources
[username@cbcb00:~ ] $ scontrol show job 218874
JobId=218874 JobName=bash
   UserId=username(1000) GroupId=username(21000) MCS_label=N/A
   Priority=897 Nice=0 Account=cbcb QOS=highmem
   JobState=RUNNING Reason=None Dependency=(null)
   Requeue=1 Restarts=0 BatchFlag=0 Reboot=0 ExitCode=0:0
   RunTime=00:00:06 TimeLimit=1-00:00:00 TimeMin=N/A
   SubmitTime=2022-11-18T11:13:56 EligibleTime=2022-11-18T11:13:56
   AccrueTime=2022-11-18T11:13:56
   StartTime=2022-11-18T11:13:56 EndTime=2022-11-19T11:13:56 Deadline=N/A
   PreemptEligibleTime=2022-11-18T11:13:56 PreemptTime=None
   SuspendTime=None SecsPreSuspend=0 LastSchedEval=2022-11-18T11:13:56 Scheduler=Main
   Partition=cbcb AllocNode:Sid=nexuscbcb00:25443
   ReqNodeList=(null) ExcNodeList=(null)
   NodeList=cbcb00
   BatchHost=cbcb00
   NumNodes=1 NumCPUs=16 NumTasks=16 CPUs/Task=1 ReqB:S:C:T=0:0:*:*
   TRES=cpu=16,mem=2000G,node=1,billing=2266
   Socks/Node=* NtasksPerN:B:S:C=0:0:*:* CoreSpec=*
   MinCPUsNode=1 MinMemoryNode=2000G MinTmpDiskNode=0
   Features=(null) DelayBoot=00:00:00
   OverSubscribe=OK Contiguous=0 Licenses=(null) Network=(null)
   Command=bash
   WorkDir=/nfshomes/username
   Power=

Storage

CBCB still has its current storage allocation in place. All data filesystems that were available in the standalone CBCB cluster are also available in Nexus. Please note about the change in your home directory in the migration section below.

CBCB users can also request Nexus project allocations.

Migration

Home Directories

The Nexus uses NFShomes home directories and not /cbcbhomes/<USERNAME>. As part of the process of migrating into Nexus, you may want (or need) to copy any shell customization from your existing /cbcbhomes to your /nfshomes. To make this transition easier, /cbcbhomes is available to the Nexus CBCB submission nodes.

Operating System / Software

CBCB's standalone cluster submission and compute nodes were running RHEL7. Nexus is exclusively running RHEL8, so any software you may have compiled may need to be re-compiled to work correctly in this new environment. The CBCB module tree for RHEL8 may not yet be fully populated with RHEL8 software. If you do not see the modules you need, please reach out to the CBCB software maintainers.

Retrieved from "https://wiki.umiacs.umd.edu/umiacs/index.php?title=Nexus/CBCB&oldid=11899"