Repository navigation
vmm: disable GPU sanitize_on_attach by default - #1455
Merged
Merged
Conversation
On an 8x H200 PPCIe host, one GPU started failing SPDM session setup (_kgspEstablishSpdmSession timeout, RmInitAdapter 0x62:0x65) on every boot after an attach-time hot reset that followed a clean guest shutdown. Further SBRs, including manual ones, do not recover it. It is not yet clear whether the per-GPU SBR caused this, but it does not recover the state and resets GPUs individually without the NVSwitches. Make it opt-in until it is validated on PPCIe systems. Signed-off-by: Kevin Wang <wy721@qq.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Flip the default of
[cvm.gpu] sanitize_on_attachtofalse.On an 8x H200 PPCIe host, one GPU began failing SPDM session setup on every boot (
Timeout waiting for SPDM,RmInitAdapter failed (0x62:0x65)) right after an attach-time hot reset that followed a clean guest shutdown. Further SBRs (VMM and manual) did not recover it. Root cause is still unknown, but the per-GPU SBR (without resetting the NVSwitches) is a suspect and does not help here, so make it opt-in until validated on PPCIe systems.Deployments that want it can set
sanitize_on_attach = trueexplicitly.