Hardware Management/Hardware Fault Management: Difference between revisions

From OpenCompute
Jump to navigation Jump to search
 
(36 intermediate revisions by 4 users not shown)
Line 17: Line 17:


Activities of the sub-project include:
Activities of the sub-project include:
  - Develop running list of pain-points related to HW fault handling in the fleet(Facebook): [https://drive.google.com/file/d/1zrML07aKGBALBFzClBaM3pZMRZ_K-65r/view?usp=sharing OCP-PainpointList]
  - Develop running list of pain-points related to HW fault handling in the fleet  
  - Develop hardware fault management solution best practices to address the above pain-points(Facebook): [https://drive.google.com/file/d/1SquZ9DS-BtJ7PnPfth1JtbvMUagNeozF/view?usp=sharing OCP-BestPractice]
  - Develop hardware fault management solution best practices to address the above pain-points
  - Hardware Error reporting format Standardization(Microsoft): [https://docs.google.com/document/d/1JuxxsrUb5K4JkTxOLTk04fHF1IX_Lauy/edit HW error reporting format]
  - Hardware Error reporting format Standardization
  - Define hardware error classification(HPE): [https://docs.google.com/document/d/1xQzeYlesh6SV57EA_yxKI30w8H-6Je7B/edit HW Error Classification]
  - Define hardware error classification
  - OCP Fault Management Infrastructure Proposal(Google): [https://docs.google.com/document/d/1LOaVJb8oD1AzjCOhlen0rFsRi63rRoX7kyU01SKlblI/edit OCP Fault Management Infrastructure Proposal]
  - OCP Fault Management Infrastructure Proposal
  - Standardizing system behavior under hardware failures (future topic)
  - Standardizing system behavior under hardware failures (future topic)
  - Provide reference and guidance on system hardware failure management (future topic)
  - Provide reference and guidance on system hardware failure management (future topic)


==Sub-Project Leadership==
==Sub-Project Leadership==


:- [mailto:zhengyuyang@fb.com Zhengyu Yang] (Facebook), [mailto:anilagrawal@fb.com Anil Agrawal] (Facebook), [mailto:ramab@microsoft.com Rama Bhimanadhuni] (Microsoft), & [mailto:yogesh.varma@ocproject.net Yogesh Varma] (Intel)
 
:- [mailto:ramab@microsoft.com Rama Bhimanadhuni] (Microsoft), [mailto:zhengyuyang@fb.com Zhengyu Yang] (Meta), [mailto:yogesh.varma@ocproject.net Yogesh Varma] (Intel)


==Get Involved==
==Get Involved==


:Participate in the discussion, mailing list: OCP-HWFaultMgt@OCP-All.groups.io [https://ocp-all.groups.io/g/OCP-HWFaultMgt/ Mailing List Info]
:Participate in HW Fault Management sub-project meetings
: - [http://opencompute.org/projects/projects-calendar/ OCP Calendar]
: - [https://global.gotomeeting.com/join/865768677 Call Link]


: - Regular meetings are held every other Friday from 2-3pm PT.
:  - You can also dial in using your phone.
:  - United States (Toll Free): 1 877 309 2073
:  - United States: +1 (646) 749-3129
:  - (Access Code: 865-768-677)


:Provide feedback and comments to working documents


==Agendas and Minutes==
===Subproject Meets every Friday from 2-3pm PT ===
: - [https://global.gotomeeting.com/join/865768677 Link to the Meeting]
:  - You can also dial in using your phone : US (Toll Free): 1 877 309 2073 / US: +1 (646) 749-3129 - (Access Code: 865-768-677)


===Mailing List ===
Participate in the discussion, mailing list: OCP-HWFaultMgt@OCP-All.groups.io [https://ocp-all.groups.io/g/OCP-HWFaultMgt/ Mailing List Info]


=== Review and provide Feedback ===
:Provide feedback and comments to working documents - [https://drive.google.com/drive/folders/1tOtsUfol8g6DKpWOhKyyT_wdKlaE6XH_?usp=sharing Link to In-progress Documents Folder]


=== Meeting Date 07/22/21 ===
==Links to Documents==


Participant: Anil (FB), Drew (Google), Mark (HPE), Rama (MS), Yogesh (Intel), Antonio (Intel)
===[https://drive.google.com/drive/folders/1tOtsUfol8g6DKpWOhKyyT_wdKlaE6XH_?usp=sharing Work_in_Progress_Documents Folder]:===


Proposed Agenda:


1. OCP global summit planning (Anil)
- Running list of pain-points related to HW fault handling: [https://drive.google.com/file/d/1zrML07aKGBALBFzClBaM3pZMRZ_K-65r/view?usp=sharing OCP-PainpointList]


2. Logistics of core meetings (Antonio/Yogesh)
- Hardware fault management solution best practices to address the above pain-points: [https://drive.google.com/file/d/1SquZ9DS-BtJ7PnPfth1JtbvMUagNeozF/view?usp=sharing OCP-BestPractice]
        a. Meeting time and duration change
        b. Update pain-point spreadsheet


3. EDAC-extensions proposal (Anil)
- Hardware Error reporting format Standardization: [https://docs.google.com/document/d/1JuxxsrUb5K4JkTxOLTk04fHF1IX_Lauy/edit HW error reporting format]


Meeting Notes:
- Hardware error classification: [https://docs.google.com/document/d/1xQzeYlesh6SV57EA_yxKI30w8H-6Je7B/edit HW Error Classification]


1. The following proposals were submitted for OCP Global Summit:
- OCP Fault Management Infrastructure Proposal : [https://drive.google.com/file/d/1A9Qc7hB3THw0wiEK_dbXYj85_NOJWrb5/view?usp=sharing OCP Fault Management Infrastructure Proposal]
        a. A study of 'Host-based Hardware Corrected Fault Reporting' methods in a compute platform for large-scale cloud infrastructure
        b. Study of memory corrected error profile in cloud infrastructure
        c. Mark: Error classification standardization
2. Proposals getting ready to submit:
        a. Rama/Antonio/Jeff Autor: Error formatting standardization proposal (plan to submit)
          i.  Antonio to take lead for getting requirements published at the OCP portal
          ii. Rama took the lead in submitting the proposal and presenting.
        b. Drew: Error reporting architecture for cloud infrastructure
        c. Yogesh: Status of HW fault management sub-project


3. Logistics of core meetings (Antonio/Yogesh)
===[https://drive.google.com/drive/folders/1Lw7IuM0HHD7F_xAUBZ33GuK0PHW2wMeG?usp=sharing Completed Versions of WIP Documents Folder]===
        a. Meeting time is agreed by the core team. Yogesh/Michael sent the revised meeting invitation. Alternate Fridays 2-3 PM PST
===[https://drive.google.com/drive/folders/1RLewtetXMHJTPyYCFvoECftaPX0-v-q7?usp=sharing  Published Documents Folder]===
        b. Pending Task - review the updates in pain-point spreadsheet
4. EDAC-extensions proposal (Anil)
        - Reviewed briefly. Need to discuss further in the following meeting.


==Working Documents==


- Running list of pain-points related to HW fault handling: [https://drive.google.com/file/d/1zrML07aKGBALBFzClBaM3pZMRZ_K-65r/view?usp=sharing OCP-PainpointList]


- Hardware fault management solution best practices to address the above pain-points: [https://drive.google.com/file/d/1SquZ9DS-BtJ7PnPfth1JtbvMUagNeozF/view?usp=sharing OCP-BestPractice]


- Hardware Error reporting format Standardization: [https://docs.google.com/document/d/1JuxxsrUb5K4JkTxOLTk04fHF1IX_Lauy/edit HW error reporting format]
===Presentations & Other Documents===
 
OCP Presentation Template - please contact [mailto:michael@opencompute.org Michael Schill] or [mailto:archna@opencompute.org Archna Haylock] for a copy
- Hardware error classification: [https://docs.google.com/document/d/1xQzeYlesh6SV57EA_yxKI30w8H-6Je7B/edit HW Error Classification]


- OCP Fault Management Infrastructure Proposal : [https://docs.google.com/document/d/1LOaVJb8oD1AzjCOhlen0rFsRi63rRoX7kyU01SKlblI/edit OCP Fault Management Infrastructure Proposal]
1. OCP2021 Global Summit: [https://www.youtube.com/watch?v=15yhpo2r7u8 OCP HW Fault Management Sub-project Status Update]
 
==Presentations & Other Documents==
1. OCP Presentation Template - please contact [mailto:michael@opencompute.org Michael Schill] or [mailto:archna@opencompute.org Archna Haylock] for a copy


2. OCP2020 Tech Week - Lighting Talk: [https://2020ocptechweek.fnvirtual.app/a/event/863 OCP HW Fault Management Sub-project Update]
2. OCP2020 Tech Week - Lighting Talk: [https://2020ocptechweek.fnvirtual.app/a/event/863 OCP HW Fault Management Sub-project Update]
Line 104: Line 80:
5. OCP2019 Global Summit: [http://www.youtube.com/watch?v=hSHiN4XEJxc Minimizing the performance penalty associated with SMM based hardware error handling solution]
5. OCP2019 Global Summit: [http://www.youtube.com/watch?v=hSHiN4XEJxc Minimizing the performance penalty associated with SMM based hardware error handling solution]


==Past Calls - Recordings==
6. DMTF/Redfish Hardware Error Reporting Standardization Proposal : [https://docs.google.com/presentation/d/1QTWlN1xTJ2sPFMkizPF_P3PNDxqj1Smm/edit?usp=sharing&ouid=105588765119189812335&rtpof=true&sd=true Hardware Error Reporting Standardization for cloud-scale and Edge Infrastructure presented at OCP2021]
 
==Past Meeting Recordings==
 
:- January 6, 2023 - No Recording
:- December 23, 2022 - No Recording
:- [https://www.youtube.com/watch?v=DHJUpGXCtWI December 16th, 2022]
:- [https://www.youtube.com/watch?v=jf8HBsof36k December 9th, 2022]
:- [https://www.youtube.com/watch?v=LVcjJ5EgEys December 2nd, 2022]
:- [https://www.youtube.com/watch?v=iit_wasD2XA November 18th, 2022]
:- [https://www.youtube.com/watch?v=YeNfpVgZyTc November 4th, 2022]
:- [https://www.youtube.com/watch?v=MPbY9-Gtbik October 14th, 2022]
:- [https://www.youtube.com/watch?v=oX3fnQaSYtg October 7th, 2022]
:- [https://www.youtube.com/watch?v=eQPX8nBkvdw September 30th, 2022]
:- [https://www.youtube.com/watch?v=_SGCfWPuNsg September 23rd, 2022]
:- [https://www.youtube.com/watch?v=KscSFkjNrHo August 26th, 2022]
:- [https://www.youtube.com/watch?v=kBnWEgasnKI August 19th, 2022]
:- [https://www.youtube.com/watch?v=kBnWEgasnKI August 12th, 2022]
:- [https://www.youtube.com/watch?v=clJs-cIexhU August 5th, 2022]
:- [https://www.youtube.com/watch?v=iZAaFMvY-gc July 29th, 2022]
:- [https://www.youtube.com/watch?v=wWtehCCwdF0 July 15th, 2022]
:- [https://www.youtube.com/watch?v=7B2ZGhVcN4M June 24th, 2022]
:- [https://www.youtube.com/watch?v=MP_36y-Ji_Y June 10th, 2022]
:- [https://www.youtube.com/watch?v=Hw5VCb7g2xU May 6th, 2022]
:- [https://transcripts.gotomeeting.com/#/s/fd568c5cee9ae5bd82ae1873feeeb7f23e147f918dd7e31ff2b8c108ce6abe6e April 22nd, 2022]
:- [https://www.youtube.com/watch?v=p3Xhep90DW4 April 8th, 2022]
:- [https://www.youtube.com/watch?v=shwr97O7hTc February 18th, 2022]
:- [https://www.youtube.com/watch?v=OHPzb5Fr93E February 11th, 2022]
:- [https://www.youtube.com/watch?v=gnBY7MUgpYA February 4th, 2022]
:- [https://www.youtube.com/watch?v=iFbm0kAhyLk January 28th, 2022]
:- [https://www.youtube.com/watch?v=B55zh36OQYI January 21st, 2022]
:- [https://www.youtube.com/watch?v=AXH4isTtfh8 October 8th, 2021]
:- [https://www.youtube.com/watch?v=bx8aaVy1VPk September 17th, 2021]
:- [https://www.youtube.com/watch?v=7pBzZKf7Nds August 20th, 2021]
:- [https://www.youtube.com/watch?v=7pBzZKf7Nds August 20th, 2021]
:- [https://www.youtube.com/watch?v=dku8mIa7Quc August 13th, 2021]
:- [https://www.youtube.com/watch?v=dku8mIa7Quc August 13th, 2021]
Line 117: Line 125:
:- [https://www.youtube.com/watch?v=kKpOoNkod4k July 31st, 2020]
:- [https://www.youtube.com/watch?v=kKpOoNkod4k July 31st, 2020]
:- [https://www.youtube.com/watch?v=R4QnBKAgiZg June 26th, 2020]
:- [https://www.youtube.com/watch?v=R4QnBKAgiZg June 26th, 2020]
== Calendar ==
:Participate in HW Fault Management sub-project meetings - [https://calendar.google.com/calendar/embed?src=opencompute.org_0bjgh9s81nj0ph2utsr61j0lbg%40group.calendar.google.com&ctz=America%2FChicago OCP Hardware Management Calendar]

Latest revision as of 08:30, 10 January 2023

OCP-Open-compute-hardware-fault-management-icon-3x-v1-1a.png

Welcome[edit]

Welcome to the OCP Hardware Fault Management Sub-project. This is a sub-project of the OCP Hardware Management Project
This Project is open to the public and we welcome all those who would like to be involved.
Disclaimer: Please do not submit any confidential information to the Project Community. All presentation materials, proposals, meeting minutes and/or supporting documents are published by OCP and are open to the public in accordance to OCP's Bylaws and IP Policy. This can be found on the OCP OCP Policies page. If you have any questions please contact OCP.

Project Overview[edit]

The Hardware Fault Management subproject’s goal is to address the Large scale data center pain-points in managing hardware faults effectively. Objective of the subproject: to define hardware fault management solution such that it

- Minimizes performance degradation
- Reduces No Trouble Found (NTF) in RMA
- Scales the solution across heterogeneous fleet

Activities of the sub-project include:

- Develop running list of pain-points related to HW fault handling in the fleet 
- Develop hardware fault management solution best practices to address the above pain-points
- Hardware Error reporting format Standardization
- Define hardware error classification
- OCP Fault Management Infrastructure Proposal
- Standardizing system behavior under hardware failures (future topic)
- Provide reference and guidance on system hardware failure management (future topic)


Sub-Project Leadership[edit]

- Rama Bhimanadhuni (Microsoft), Zhengyu Yang (Meta), Yogesh Varma (Intel)

Get Involved[edit]

Subproject Meets every Friday from 2-3pm PT[edit]

- Link to the Meeting
- You can also dial in using your phone : US (Toll Free): 1 877 309 2073 / US: +1 (646) 749-3129 - (Access Code: 865-768-677)

Mailing List[edit]

Participate in the discussion, mailing list: OCP-HWFaultMgt@OCP-All.groups.io Mailing List Info

Review and provide Feedback[edit]

Provide feedback and comments to working documents - Link to In-progress Documents Folder

Links to Documents[edit]

Work_in_Progress_Documents Folder:[edit]

- Running list of pain-points related to HW fault handling: OCP-PainpointList

- Hardware fault management solution best practices to address the above pain-points: OCP-BestPractice

- Hardware Error reporting format Standardization: HW error reporting format

- Hardware error classification: HW Error Classification

- OCP Fault Management Infrastructure Proposal : OCP Fault Management Infrastructure Proposal

Completed Versions of WIP Documents Folder[edit]

Published Documents Folder[edit]

Presentations & Other Documents[edit]

OCP Presentation Template - please contact Michael Schill or Archna Haylock for a copy

1. OCP2021 Global Summit: OCP HW Fault Management Sub-project Status Update

2. OCP2020 Tech Week - Lighting Talk: OCP HW Fault Management Sub-project Update

3. OCP2020 Global Virtual Summit presentation: Overview of HW Fault Management Sub-project

4. OCP2019 Regional Summit: Platform Hardware Error Handling Requirements for Large Scale Data Center

5. OCP2019 Global Summit: Minimizing the performance penalty associated with SMM based hardware error handling solution

6. DMTF/Redfish Hardware Error Reporting Standardization Proposal : Hardware Error Reporting Standardization for cloud-scale and Edge Infrastructure presented at OCP2021

Past Meeting Recordings[edit]

- January 6, 2023 - No Recording
- December 23, 2022 - No Recording
- December 16th, 2022
- December 9th, 2022
- December 2nd, 2022
- November 18th, 2022
- November 4th, 2022
- October 14th, 2022
- October 7th, 2022
- September 30th, 2022
- September 23rd, 2022
- August 26th, 2022
- August 19th, 2022
- August 12th, 2022
- August 5th, 2022
- July 29th, 2022
- July 15th, 2022
- June 24th, 2022
- June 10th, 2022
- May 6th, 2022
- April 22nd, 2022
- April 8th, 2022
- February 18th, 2022
- February 11th, 2022
- February 4th, 2022
- January 28th, 2022
- January 21st, 2022
- October 8th, 2021
- September 17th, 2021
- August 20th, 2021
- August 13th, 2021
- July 30th, 2021
- June 25th, 2021
- April 30th, 2021
- March 26th, 2021
- February 26th, 2021
- January 29th, 2021
- September 25th, 2020
- August 28th, 2020
- July 31st, 2020
- June 26th, 2020

Calendar[edit]

Participate in HW Fault Management sub-project meetings - OCP Hardware Management Calendar