IBM Elastic Storage Server vs. StorPool

Reliable data storage and access is a big challenge in AI applications and IBM ESS is a service you need to solve the problem. If you are building an AI service and you already use the IBM ecosystem for AI compute requirements, ESS can serve as an excellent software based storage solution. Integration with other platforms such as EMR/Databricks is still a challenge and should be improved.

Incentivized

Independently Invited by TrustRadius

A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info

Storpool performs well on block level (and that is what we use it for). It is not yet supporting a kind of distributed filesystem or object storage - a filesystem layer needs to be built on top of it.

• Powerful processing power, literally support unlimited scale out storage capabilities
• well integrated and supported with multi flavor environment and file systems.
• Huge capacity with in a very reduced form factor of disks/enclosures

• Distributed Storage array with very high throughput in terms of reading & write operations.
• Horizontal scaling without much complexity of management.
• Easily integrate with OpenStack cloud.
• Doesn't depend on proprietary hardware, integrates with commodity hardware.

• Integration and configuration need a bit more technical expertise which is I guess expected.
• There can be some improvement in integration with Legacy applications.

Incentivized

Independently Invited by TrustRadius

A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info

• Graphical interface is for monitoring and stats, but not for operations.

IBM ESS is optimized for AI and Big Data usecases while S3 is a general purpose storage solutions. EMR and Databricks have lakehouse/data warehousing solutions for distributed computing but are more optimized for just the big data pipelining solutions and not essentially for AI usecases, especially for inference, when you need to load model artifacts really quickly.

Incentivized

Independently Invited by TrustRadius

A de minimis incentive was given to thank the reviewer for their time. The incentive was not used to bias or drive a particular response, nor was the incentive contingent on a positive endorsement. More Info

We made a very careful selection of our storage vendor and solution. After researching the newest technologies, our team decided to deploy a software-defined storage solution from StorPool.

• When the cost and price dynamics comes into account, we have replaced age old traditional arrays with almost negligible cost with ESS
• able to extend the capabilities of global teams to work and share their experiences and knowledge with other teams.

• We have not calculated precise ROI. We focused on getting the best solution at a reasonable price, based on market research. Initially, we didn’t need a lot of capacity, so we invested in servers and network, which could handle several times more capacity, but bought smaller drives to keep the investment low. We achieved a starting price of $3.2/GB usable and $1.4/GB logical. Later we expanded the capacity by adding more drives to the system. Currently, the system has a price of approximately $2.3/GB usable and $0.99/GB logical and a price of $0.09/IOPS.