> How does this work? Is there an Intel IFS blob v1.17 that is expected > to be *the* blob for a given CPU until an update happens? This is the model. Although internally the blob is divided into chunks that can be run separately, folks outside Intel have no visibility into which chunk tests which circuits (even *inside* ... I don't know what each chunk does :-) ) How often will updates occur? No idea. Since this is new, I'd expect that there might be some improvements when there is feedback from large CSPs running on many more systems than we have. > Or is the > expectation that several different blobs might all useful on the same > system and operators might want to run different blobs under different > circumstances? One of our early implementations included extra sysfs hooks to only test specific chunks ... but we dropped that complexity as there's no way for end users to decide which chunks to run. So the posted series just iterates all chunks for a core. -Tony
