pmc: enable the new pmc commands
AcceptedPublic
Actions

Authored by ali_mashtizadeh.com on Tue, Jun 23, 4:27 PM.

Details

Reviewers

imp
jhb
mhorne
adrian

Group Reviewers

pmc

Summary

This change hooks everything up to the pmc command and improves the
usage to document all functions. There are a couple older commands that
are currently broken that I have hidden from the usage, but left in the
code for those using it. I won't remove those until we have our
replacements upstreamed that depend on the AMD PMC multiplexing patches.

Diff Detail

Repository

rG FreeBSD src repository

Lint

Lint Skipped

Unit

Tests Skipped

Build Status

Buildable 74158
Build 71041: arc lint + arc unit

Event Timeline

ali_mashtizadeh.com requested review of this revision.Tue, Jun 23, 4:27 PM

ali_mashtizadeh.com created this revision.

Harbormaster completed remote builds in B74158: Diff 180404.Tue, Jun 23, 4:27 PM

ali_mashtizadeh.com added a parent revision: D57779: pmc: pmc frontend stall analysis based on IBS.Tue, Jun 23, 4:27 PM

mhorne added reviewers: pmc, adrian.Tue, Jun 30, 3:05 PM

Hi, commenting here. From a high-level perspective this seems like a good move; this pmc(8) utility is open to improvements and seems like it never got past a beta phase.
It is good to be thoughtful about the old commands, but as you note they are broken and the tool as a whole is undocumented. So I do not think we are burdened with supporting them indefinitely.

I will be AFK for, probably the next two weeks. Also my C++ knowledge is pretty basic; I am not going to be much help for thorough review on this series.

A separate question: does this series depend on the group/multiplex additions recently added for review by @raghavendra.kt_amd.com? Or are they unrelated?

adrian accepted this revision.Tue, Jun 30, 5:49 PM

This revision is now accepted and ready to land.Tue, Jun 30, 5:49 PM

In D57780#1328923, @mhorne wrote:

Hi, commenting here. From a high-level perspective this seems like a good move; this pmc(8) utility is open to improvements and seems like it never got past a beta phase.
It is good to be thoughtful about the old commands, but as you note they are broken and the tool as a whole is undocumented. So I do not think we are burdened with supporting them indefinitely.

I'm glad your okay with that will do after I land my replacement to the stat interface.

I will be AFK for, probably the next two weeks. Also my C++ knowledge is pretty basic; I am not going to be much help for thorough review on this series.

A separate question: does this series depend on the group/multiplex additions recently added for review by @raghavendra.kt_amd.com? Or are they unrelated?

No it's unrelated for now this is all sampling based most of the commands will depend on IBS, but obviously not all. @raghavendra.kt_amd.com 's diffs are for counter mode, and I have a plan for that but its about half done. Will worry about it after landing everything I outlined in the first diff.