You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on May 3, 2024. It is now read-only.
This file contains 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
So as seen in the above sequence, problem is observed in motr client when we return the failure during iosm launch with partial fops send successfully but error is received while sending next fop. In such case ioo fini asserts as successfully sent fop are still outstanding for their completion
Design
Fix: When A problem is detected during rpc post of any fop request then error should not be immediately reported back instead the error is to be saved in nw xfr status. But network transfer completion handling for ioo will only be triggered when all the successfully sent fops post their completion along with failed fop (during rpc post). Its expected that completion for any fop for which rpc dispatch is failed (due to error returned from m0_rpc_post), should be triggered by bottom half handling triggered from m0_rpc_item_failed.
This would ensure graceful completion of nw xfr request associated with an IO with error being reported at later point of time when all the partial successfully sent fops as well as failed fop request bottom half completions are processed.
Coding
Checklist for Author
Coding conventions are followed and code is consistent
Testing
Checklist for Author
Unit and System Tests are added
Test Cases cover Happy Path, Non-Happy Path and Scalability
Testing was performed with RPM
Impact Analysis
Checklist for Author/Reviewer/GateKeeper
Interface change (if any) are documented
Side effects on other features (deployment/upgrade)
Dependencies on other component(s)
Review Checklist
Checklist for Author
JIRA number/GitHub Issue added to PR
PR is self reviewed
Jira and state/status is updated and JIRA is updated with PR link
Check if the description is clear and explained
Documentation
Checklist for Author
Changes done to WIKI / Confluence page / Quick Start Guide
discontinue sending next fops and wait for outstanding fop completion to happen
and avoid immediately returning the error to dispatch operation which then
would trigger the completion handling even if some fop processing may in
progress
Signed-off-by: Vidyadhar Pinglikar <vidyadhar.pinglikar@seagate.com>
Thanks for your contribution!
The CLA bot has flagged your contribution as not having a Contributor License Agreement
in place. Note that this is not needed in the overwhelming majority of instances and this warning will usually be ignored.
The code reviewers will make a determination and may ask you to sign a CLA or may choose to ignore this warning.
More information about this can be found here.
huanghua78
changed the title
Cortx-33909: Panic is receivedin Motr Client while performing nw_xfer_request_fini
Cortx-33909: Panic is received in Motr Client while performing nw_xfer_request_fini
Sep 6, 2022
Thanks for your contribution!
The CLA bot has flagged your contribution as not having a Contributor License Agreement
in place. Note that this is not needed in the overwhelming majority of instances and this warning will usually be ignored.
The code reviewers will make a determination and may ask you to sign a CLA or may choose to ignore this warning.
More information about this can be found here.
is not failed for the case of one or more rpc errors or if one or more
fops are successfully sent.
Signed-off-by: Vidyadhar Pinglikar <vidyadhar.pinglikar@seagate.com>
Thanks for your contribution!
The CLA bot has flagged your contribution as not having a Contributor License Agreement
in place. Note that this is not needed in the overwhelming majority of instances and this warning will usually be ignored.
The code reviewers will make a determination and may ask you to sign a CLA or may choose to ignore this warning.
More information about this can be found here.
Thanks for your contribution!
The CLA bot has flagged your contribution as not having a Contributor License Agreement
in place. Note that this is not needed in the overwhelming majority of instances and this warning will usually be ignored.
The code reviewers will make a determination and may ask you to sign a CLA or may choose to ignore this warning.
More information about this can be found here.
# for freeto subscribe to this conversation on GitHub.
Already have an account?
#.
Labels
None yet
8 participants
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.
vidyadhar-pinglikar
requested review from
mehjoshi,
madhavemuri,
nikitadanilov,
yeshpal-jain-seagate,
huanghua78,
andriytk,
siningwuseagate,
shashank-parulekar,
nkommuri,
sg-shankar,
yatin-mahajan and
rkothiya
as code owners
huanghua78
changed the title
Problem Statement
Its seen that outstanding io fops number is non zero during fini of nw xfr for an IO.
RCA:
Its seen that while dispatching the fop requests, data fops are successfully sent
But error is received for while sending cob create fop request
Subsequently, launch of io fails with rpc error reported while posting "cob create fop" request.
When Failure is reported in ioreq_iosm_handle_launch, it will immediately trigger completion of failed transfer;
and also will inform the upper layer of failed dispatch error status by invoking op fail callback
and subsequently panic is received as a part of this fini operation with outstanding data fops still being 4,
So as seen in the above sequence, problem is observed in motr client when we return the failure during iosm launch with partial fops send successfully but error is received while sending next fop. In such case ioo fini asserts as successfully sent fop are still outstanding for their completion
Design
This would ensure graceful completion of nw xfr request associated with an IO with error being reported at later point of time when all the partial successfully sent fops as well as failed fop request bottom half completions are processed.
Coding
Checklist for Author
Testing
Checklist for Author
Impact Analysis
Checklist for Author/Reviewer/GateKeeper
Review Checklist
Checklist for Author
Documentation
Checklist for Author