IBM System Storage Ideas Portal


This portal is to open public enhancement requests against IBM System Storage products. To view all of your ideas submitted to IBM, create and manage groups of Ideas, or create an idea explicitly set to be either visible by all (public) or visible only to you and IBM (private), use the IBM Unified Ideas Portal (https://ideas.ibm.com).


Shape the future of IBM!

We invite you to shape the future of IBM, including product roadmaps, by submitting ideas that matter to you the most. Here's how it works:

Search existing ideas

Start by searching and reviewing ideas and requests to enhance a product or service. Take a look at ideas others have posted, and add a comment, vote, or subscribe to updates on them if they matter to you. If you can't find what you are looking for,

Post your ideas

  1. Post an idea.

  2. Get feedback from the IBM team and other customers to refine your idea.

  3. Follow the idea through the IBM Ideas process.


Specific links you will want to bookmark for future use

Welcome to the IBM Ideas Portal (https://www.ibm.com/ideas) - Use this site to find out additional information and details about the IBM Ideas process and statuses.

IBM Unified Ideas Portal (https://ideas.ibm.com) - Use this site to view all of your ideas, create new ideas for any IBM product, or search for ideas across all of IBM.

ideasibm@us.ibm.com - Use this email to suggest enhancements to the Ideas process or request help from IBM for submitting your Ideas.

Add a new idea Subscribe
Status Not under consideration
Workspace Storage Scale (formerly known as GPFS)
Created by Guest
Created on Feb 25, 2016

RELATED IDEAS

Implement end-to-end checksums for non GNR environments

Implement data block checksums in GPFS to protect against silent data corruption. This is particularly important in an FPO environment where there are no RAID controllers to protect against individual SATA drives returning bad data to the application. This RFE is suggesting that checksums be written on a per-block level and that GPFS handle a mismatched checksum in 3 ways:

1. None. Don't read or write checksum information.
2. Permissive/Report only. Only report the error in the mmfs logs but allow the operation to succeed.
3. Semi-permissive. Report the checksum error in the mmfs logs but attempt to retrieve the block from other NSDs if there are sufficient replicas. If no replicas return a correct checksum, still allow the read operation to continue.
4. Enforcing. Report the error in the mmfs logs, attempt to redirect the read to any available replicas of the block. If all replicas of the block fail to validate their checksum then return an I/O error.

The RFE is also requesting that this be a filesystem-level configurable parameter but that an application could override the behavior via fcntl/ioctl operations.

Idea priority High
  • Guest
    Reply
    |     Sep 30, 2020

    Due to processing by IBM, this request was reassigned to have the following updated attributes:
    Brand - Servers and Systems Software
    Product family - IBM Spectrum Scale
    Product - Spectrum Scale (formerly known as GPFS) - Public RFEs
    Component - Product functionality

    For recording keeping, the previous attributes were:
    Brand - Servers and Systems Software
    Product family - IBM Spectrum Scale
    Product - Spectrum Scale (formerly known as GPFS) - Public RFEs
    Component - Technical Foundation

  • Guest
    Reply
    |     Sep 28, 2016

    If GNR were open to all GPFS customers I think that would be a fine answer, but since it's not, I think it's problematic.

  • Guest
    Reply
    |     Aug 29, 2016

    Performing end-to-end data checksumming is a task of considerable complexity, and requires significant and impactful changes to many aspects of GPFS design and implementation. While the benefits of data checksumming are very clear, the implementation cost is prohibitively high. Given that this function is already available in GNR environments, the cost of another implementation could not be justified. After a prolonged discussion, a decision was reached that we won't go in this direction.

  • Guest
    Reply
    |     Apr 20, 2016

    I believe this is actually possible within GPFS now... it's just a setting that is not documented nor is it recommended with out strict direction from IBM Support. If you feel there is data corruption or other issues related to GPFS or the subsystems it relies upon (e.g. networking in particular) then open a PMR and ask for this kind of checksum analysis/debugging.

  • Guest
    Reply
    |     Feb 26, 2016

    Creating a new RFE based on Community RFE #84523 in product Spectrum Scale (formerly known as GPFS) - Public RFEs.

By clicking the "Post Comment" or "Submit Idea" button, you are agreeing to the IBM Ideas Portal Terms of Use.
Do not place IBM confidential, company confidential, or personal information into any field.