[LU-4460] Using multiple NIDs for the same failnode or mgsnode is STILL broken for Lustre 2.4

• Status: Resolved
• Project: Lustre
• Affects Version/s: Lustre 2.4.1
• Fix Version/s: Lustre 2.6.0, Lustre 2.5.1
• Type: Bug
• Priority: Minor
• Reporter: Aurelien Degremont (Inactive)
• Assignee: Jian Yu
• Resolution: Fixed
• Labels: mn4
• Severity: 3

Description

It seems to me this bug is still there for 2 reasons:
This is a follow-up of LU-3445.
This ticket was supposed to fix this problem. However, it seems to me this bug is still there for 2 reasons:

-the patch only take care of mkfs/tunefs and so there is still an upgrade issue if mountdata contains something like failover.node=10.3.0.228@o2ib,192.168.50.128@tcp
The way to workaround this looks to be a writeconf, which has side effect. Is there some UPGRADE notes somewhere relative to this?

-the patch seems to modify this kind of string

--failnode=10.3.0.228@o2ib,192.168.50.128@tcp

into

--failnode=10.3.0.228@o2ib --failnode=10.3.0.228@o2ib

Which is not the same. The first example refers to 1 failnode, with 2 NIDS to reach it. The second one refers to 2 different failnodes with 1 NID each

Comments

[Jian Yu]

I'll look into these issues and figure out whether I should fix the original issue in lmd_parse().

[Jian Yu]

I created a patch to fix lmd_parse(). After it passes testing locally, I'll upload the patch to Gerrit for review.

[Jian Yu]

Patch for master branch is in http://review.whamcloud.com/8918.

[Jian Yu]

Patch for Lustre b2_5 branch is in http://review.whamcloud.com/9029.

[Peter Jones]

Landed for 2.5.1 and 2.6