Gilbreth
Purdue University · DDN Gilbreth · Undefined
System Purpose
Question asked
Please describe the purpose and general usage of the submitted system. This would include the types of typical applications it supports (e.g., defense applications, molecular dynamics, benchmarking, system test, systems research), and the general use and purpose of the data generated by the applications running on it.
Gilbreth is a Community Cluster optimized for communities running GPU intensive applications such as machine learning. Gilbreth consists of Dell compute nodes with Intel Xeon and Epyc processors, and the GPUs are Nvidia A10, A30, and A100.
Gilbreth is named in honor of Lillian Moller Gilbreth, Purdue's first female engineering professor. Gilbreth is a general purpose cluster that support a variety of disciplines within the university.
Availability
Question asked
Please provide the deployment timeframe of the submitted system, or for on-demand cloud systems, the general period over which it is deployed and destroyed.
Please describe the availability of the system to users and who are its set of most regular users.
Gilbreth went into production in the year 2018 and is loosely planned to retire in 2027 as its successor is being built. It serves Purdue University's faculty and research groups from every School.
Storage System Software
Question asked
How is this storage software available? (e.g., commercially, open-source, not publicly available) Note that if the storage software is not open-source or commercially available, then a general description would be requested, but this would limit the submission’s reproducibility score.
Can anyone download/purchase this software?
List either product webpage or open-source repo of the exact software used in IO500.
Give any and all additional details of this specific storage deployment: (e.g., type of storage server product such IBM ESS or DDN SFA400X2, use of Ext4 or some other file system on each storage node, dual connected storage media to storage servers).
Gilbreth has one SFA400NVX2E storage appliance and four SS9024 disk enclosures.
It runs four VM servers on the SFA that host and present the lustre filesystem.
The total capacity is 3.2PB, 24 14TiB NVME and 329 16 TiB SAS drives.
It runs DDN Exascaler 6.3.7.
Runtime Environment
Question asked
State here that you provided all scripts/documentation that would allow someone else to reproduce your environment and attempt to achieve a similar IO500 score as the submitted system.
NOTE: provide all files/documentation/scripts that would enable a user to build your environment and deploy the custom scripts, software, or config files once they have obtained the appropriate storage system hardware and software. These may be included into the io500.tgz or into the extraCodes upload on the submission form.
Several examples include:
- Commands used to set striping information (either for the entire system or for particular directories)
- File system config and tuning information (or a reason why this is not available due to lack of root access, etc) on each node type (e.g., non-default config parameters on all three types of Lustre nodes: MDS, OSS, and client)
- Any additional scripts utilized that impact IO500 execution beyond the io500 config file. For example, with IBM Spectrum Scale, the output of mmlsconfig, mmlscluster, mmlsfs, and mmlsfileset commands (and possibly even a dump of the configuration if possible). Each file system probably has similar type of config/tuning information that would need to be shared for a user to fully reproduce the environment.
All commands used to reproduce this test have been provided. all stripe commands are available in the provided slurm scripts
Fault Tolerance Mechanisms
Question asked
Does your system have a single point of failure as defined by “Definition 7” of a Production System? Please describe all mechanisms that provide fault tolerance for the submitted storage system. Be specific to your submission, not general storage system capabilities.
- Power (For example, can power failure of a node or rack bring down the storage system?)
- Networking (For example, can failure of a single NIC bring down the storage system? Remember that any networking failure that brings down multiple nodes is acceptable)
- Inter storage data and metadata server (For example, what type of data protection mechanism does the storage system use to keep operating during node failures, e.g., active-active servers, client-directed RAID, declustered RAID, erasure-coding, 3-way replication)
- Intra storage data and metadata server storage media (For example, how does the storage eysstem protect against fiailure of a single storage device within a node, e.g., raid5)
Please list any additional information needed to determine whether this system has a single point of failure.
All systems are redundant from the power having split PDUs and being on separate power feeds. The storage uses distributed RAID provided be DDN SFA OS to protect against disk failure. The whole group can lose several disks overtime without data loss due to built-in spare capacity.
DDN Exascaler provides failover resiliency for individual server components to ensure metadata and data services remain online
Execution
Question asked
Please provide a description of how the IO500 benchmark was executed, e.g., via system scheduler (e.g., SLURM) to run a job on the compute cluster, which initially ran a setup process to configure the client and file system, and then started the full benchmark.
During the IO500 benchmark execution was the system entirely dedicated to running the benchmark or were there other jobs running in the same cluster and storage system?
The io500 test was submitted via the SLURM scheduler via a slurm script that would call the commands to set the stripes for the appropriate directories. The system was in use by other user jobs during this benchmarking process.
Caching
Question asked
Please describe all caching mechanisms in client/server that were utilized during the IO500 run. This could include caching in any storage medium (e.g., SSD, RAM).
A few examples would include:
- Client data/metadata caching (in Linux page cache or in other memory cache)
- Client side NVMe read-only data cache
- Storage server metadata/data caching in RAM
- Storage controller caching
- RAID card caching
The tests used regular POSIX I/O, so Linux page cache could be used for those. Please see the config.ini file for verification.
There is no caching storage on the clients
The storage servers have a write-back cache and battery backed cache at the SFA OS layer
Data Source
Question asked
Is the submitted system a stand-alone storage system or an acceleration layer in front of another storage system that is the source of truth for all application data? This question relates to whether the submitted system is a burst buffer layered on primary storage or primary storage itself.
The system is a stand-alone storage system. It is not a burst buffer layered on primary storage. All clients mount the storage as Lustre via nfs.
Trust
Question asked
Please describe any steps taken to ensure that the results are trustworthy.
- Did you run the benchmark multiple times and get similar scores?
- Did you validate the score is below the physical capabilities of the deployed hardware?
- How did you validate that the storage system follows the IO500 rules regarding persistence, which states, "All data must be written to persistent storage within the measured time for the individual benchmark, e.g. if a file system caches data, it must ensure that data is persistently stored before acknowledging the close"?
The benchmark was run many times over 2 weeks with little variation in score.
The vendor provided guidance to the maximum throughput capabilities of the system, and we validated the score was below these figures, as expected. In monitoring, I could see the throughput capability could be reached, but not exceeded.
The storage system is a POSIX-compliant, cache-coherent parallel filesystem with global lock management and flock enabled. I did not verify persistence personally, but the Lustre filesystem is known to comply with io500 rules regarding persistence.