It is primarily staffed by college students – cheap labor – managed by senior engineers.
Protocol testing is it’s primary function. The IOL tests many protocols such as Ethernet, Fibre Channel, iSCSI, SAS, SATA, PCIe and more. As most protocol “standards” are festooned with options this isn’t as simple as it seems.
For example, NVMe (non-volatile memory express) testing. One of the options in the NVMe spec is reservations for storage resources – pinning a resource to a server or app.
As an option it may or may not be implemented. But if the vendor says it is implemented, then the IOL will test it for correctness.
IOL maintains integrators lists that show who has been tested, and when. But IOL doesn’t make their testing report – where they list features and results – public.
As the property of the vendor they aren’t available unless the vendor makes them public. Or released to you under NDA. To use them you’d still have to match up the tested features with whatever you want to interoperate with.
The StorageMojo take
The IOL is funded by industry – and UNH student labor – so the limited distribution of its results isn’t surprising, though it is sad. This reflects the fact that interoperability – or lack thereof – is a competitive weapon almost as much as it is a useful feature.
This was evident in Fibre Channel’s heyday, when frequent plug fests convinced buyers that FC was open and interoperable. But niggling details made multi-vendor FC networks rare in production.
Despite the limitations, the IOL is a useful tool for ensuring that protocol implementations meet the letter, if not the spirit, of industry standards.
Courteous comments welcome, of course.