[LU-7470] Extend TBF policy with NID/JobID expressions

• Status: Resolved
• Project: Lustre
• Fix Version/s: Lustre 2.10.0
• Type: New Feature
• Priority: Minor
• Reporter: Li Xi (Inactive)
• Assignee: Emoly Liu
• Resolution: Fixed
• Labels: cea, patch

Description

In NRS TBF policy, RPCs need to be classified according to user-defined rules to meet with different requirements. Existing rules can only based on NID or JobID according to the type of TBF. However, these kind of rules might not enough for some use cases, for example, when we want to limit NID rates as well as JobID rates at the same time.

So, we extend the existing TBF policy so that following kind of rules can be used:

JOBID={dd.500}&NID={192.168.1.1@tcp},JOBID={dd.0}&NID={192.168.1.*@tcp} 10000

The expression of the rule is combined by two sub-expression, JOBID={dd.500}&NID={192.168.1.1@tcp and JOBID={dd.0}&NID={192.168.1.*@tcp. The expression's value is the disjunction of all the sub-expressions, which mean, the expression will be true if at least one of the sub-expressions is true.

And sub-expression JOBID={dd.500}&NID={192.168.1.1@tcp is combined by JOBID={dd.500 and NID={192.168.1.1@tcp. The value of sub-expression is the conjunction of both minimum-expressions (i.e. JOBID={dd.500 and NID={192.168.1.1@tcp), which means the sub-expression will be true if both of the minimum-expressions are ture.

By using this kind of expression, we can define as complex rules as we wish.

Issue Links

• is related to: LUDOC-328 documentation updates for complex TBF...
• is related to: LU-8008 Can't enable or add rules to TBF
• is related to: LU-9535 Interop 2.9<->master sanityn test_77j...
• is related to: LU-3558 NRS TBF policy for QoS purposes
• is related to: LU-8006 Specify ordering of TBF policy rules

Comments

[Gerrit Updater]

Li Xi ([e-mail]) uploaded a new patch: http://review.whamcloud.com/17345
Subject: LU-7470 nrs: extend TBF with NID/JobID expression
Project: fs/lustre-release
Branch: master
Current Patch Set: 1
Commit: b266613c4751f3633b26308504e5fc68b0399e6b

[Richard Henwood (Inactive)]

Very interesting work!

Please ensure the relevant section of the Lustre Operations Manual is updated to include this new feature:

https://build.hpdd.intel.com/job/lustre-manual/lastSuccessfulBuild/artifact/lustre_manual.xhtml#idp3359544

to make a change to the manual source.
https://wiki.hpdd.intel.com/display/PUB/Making+changes+to+the+Lustre+Manual+source

[Li Xi (Inactive)]

I am checking the possibility of combining this work with LU-8674 (general policy engine) for more general expression.

[Emoly Liu]

Thanks, LiXi !

[Gerrit Updater]

Oleg Drokin ([e-mail]) merged in patch https://review.whamcloud.com/17345/
Subject: LU-7470 nrs: extend TBF with NID/JobID/OPCode expression
Project: fs/lustre-release
Branch: master
Current Patch Set:
Commit: 949bc00ad1ec0786940bd00ba53479d88c23ea14

[Peter Jones]

Landed for 2.10