Re: [Xen-devel] xentrace, xenalyze

[Paul Sujkov <psujkov@xxxxxxxxx>]

> Have a look at this series:
>Âhttp://lists.xenproject.org/archives/html/xen-devel/2016-02/msg02233.html

Thanks a lot! Looking through it at the moment, looks very promising.

> And I've got another one that I'll send out asap (and I can Cc you).

Thanks in advance :)

> I usually enable a subset of them (one or more "classes") and try to
> figure out if I see the problem in the resulting trace. If yes, I try
> with a narrower subset. If not, I try with either a broader or a
> different one.

Well, I have doubts on how to interpret the very basic info xenalyze is supporting me with. E.g. how can I measure intra-vm latencies, both global (how much PCPU time did hypervisor itself spent during all the testing time) or local (doing the same for specific interrupts)? Why domainÂ32767 (default domain for cases when it's not clear what domain traces are about - according to documentation) is getting quite a lot of PCPU time (does this mean traces are incorrect or there is some significant problem in setup)? What'sÂconcurrency_hazard,Âpartial contention,Âfull_contention, etc (these are from xenalyze summary)? How can I get number of context switches (overall or average)?

Adding some subtle questions, like, e.g. I have domain summary looking like this:

|-- Domain 2 --|

ÂRunstates:

 Âblocked:   273 Â0.35s  7908 { Â2093| Â9561| 47811}

 partial run:  Â2284 Â1.27s  3420 { Â6183| Â6197| Â6382}

 full run:  Â1322 Â0.10s  Â479 {  Â95| Â3772| Â6164}

 partial contention:   907 Â1.73s Â11713 { 30655| 34266| 34305}

 concurrency_hazard:  Â2474 Â0.18s  Â435 {  Â48| Â5681| Â6206}

 full_contention:   381 Â0.02s  Â383 {  Â56| 36601| 36601}
...

-- v0 --

ÂRunstates:

 Ârunning:  Â1981 Â1.36s  4217 { Â6193| Â6215| Â6242}

 runnable:   737 Â1.74s Â14472 {  271| 36780| 38705}

    wake:   430 Â0.04s  Â632 {  Â67| 26049| 35549}

  Âpreempt:   307 Â1.69s Â33856 {  108| 36650| 39345}

 Âblocked:   430 Â0.56s  7974 { Â1189| 21758| 60893}

Âcpu affinity: Â Â 336 Â66914 { Â3456| 52202|243760}

 Â[0]:   167 Â66156 { Â3650| 57926|216477}

 Â[1]:   169 Â67663 { Â3205| 44754|245733}

-- v1 --

ÂRunstates:

 Ârunning:  Â2773 Â0.29s  Â649 {  Â54| Â6382| Â6382}

 runnable:   874 Â0.22s  1520 { Â5995| 36669| 36710}

    wake:   845 Â0.09s  Â640 {  452| 25366| 26313}

  Âpreempt:   Â29 Â0.13s Â27152 { 34413| 36708| 36710}

 Âblocked:   845 Â3.14s Â22856 { Â2477| 61224| 61422}

Âcpu affinity: Â Â 391 Â57508 { Â2788| 58686|128810}

 Â[0]:   196 Â59685 { Â2834| 58664|128810}

 Â[1]:   195 Â55319 { Â2770| 60622|130371}

It looks like Domain 2 had 0.10s of full run and 1.27s of partial run, but it's VCPU v0 was running 1.36s and VCPU v1 was running 0.29s. How does these numbers relate, what exactly is partial run, can I get some insight fromÂconcurrency_hazard orÂfull_contention numbers?

I am trying to build up some understanding using xenalyze sources mostly because documentation does not go into any details whatsoever, but it goes pretty slow.

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel