Google Cloud Managed Lustre Now Generally Available
Google and DDN have announced the general availability of Google Cloud Managed Lustre, a managed, high-performance parallel file system service, powered by DDN’s EXAScaler technology.
According to the announcement, Google Cloud Managed Lustre “delivers industry-leading performance of up to 1 TB/s read throughput with <1ms latency and can scale seamlessly from 18 TiB to 8 PiB+.”
Google says Managed Lustre provides “a POSIX-compliant, parallel file system that delivers consistently high throughput and low latency,” which is essential for:
- High-throughput inference
- Large-scale model training
- Checkpointing and restarting large models
- Data preprocessing and feature engineering
- Scientific simulations and research
Learn more at Google.
Related content
-
Working with the Lustre Filesystem
The Lustre open source distributed, parallel filesystem scales to high-performance computing environments.
-
Lustre HPC distributed filesystem
The Lustre open source distributed, parallel filesystem scales to high-performance computing environments. - Introducing Lustre 2.4
-
Databases in the Google Cloud
The Google Cloud Platform offers a wide range of different databases for various purposes. -
Moving HPC to the Cloud
HPC has a unique set of requirements that might not fit into standard clouds. However, plenty of commercial options, including cloud-like services, provide the advantages of real HPC without the capital expense of buying hardware.