pcp
[Top] [All Lists]

Re: [RFC PATCH] Metric to get the maximum memory bandwidth per node on x

To: Hemant Kumar <hemant@xxxxxxxxxxxxxxxxxx>
Subject: Re: [RFC PATCH] Metric to get the maximum memory bandwidth per node on x86
From: Nathan Scott <nathans@xxxxxxxxxx>
Date: Thu, 28 Jan 2016 16:25:56 -0500 (EST)
Cc: hemant kumar shaw <hkshaw.lk@xxxxxxxxx>, pcp@xxxxxxxxxxx, naveen n rao <naveen.n.rao@xxxxxxxxxxxxxxxxxx>
Delivered-to: pcp@xxxxxxxxxxx
In-reply-to: <56A9BA25.3000103@xxxxxxxxxxxxxxxxxx>
References: <1453693319-534-1-git-send-email-hemant@xxxxxxxxxxxxxxxxxx> <160893831.15176664.1453931473531.JavaMail.zimbra@xxxxxxxxxx> <56A9BA25.3000103@xxxxxxxxxxxxxxxxxx>
Reply-to: Nathan Scott <nathans@xxxxxxxxxx>
Thread-index: 5y/J5CPJtJeF4+MIvOKKdTolldkUxw==
Thread-topic: Metric to get the maximum memory bandwidth per node on x86

----- Original Message -----
> [...]
> > Another approach might be to run some code to attempt to saturate memory
> > bandwidth for a short time (perhaps using set_mempolicy(2) and cycling
> > through each node), then measure/export the max observed bandwidth?  (or
> > at least, use that to set initial per-node values in the config file).
> 
> Hmm, its a good idea, we can use "stream" to do that.
> But again, the theoretical max bandwidth will be something which
> will be difficult to saturate, even for the benchmark tools (like
> "stream"). Also, depending on the no. of nodes, it will take time to
> cycle, saturate and collect the observed max bandwidth.

*nod* - definitely not something to run all the time, and under relatively
controlled circumstances when it is run.

> > Either way, this is a fairly specialized domain so I guess it may be more
> > suited to a specialized PMDA rather than pmdalinux itself.  The ./Install
> > script might prove a good place to run the memory test and populate those
> > initial config file values?
> 
> Agreed. Will add a more specific pmda to find the max memory
> bandwidth metric.
> Can we put a check for the user if they want to proceed with the
> memory test (for the initialization of the config file) inside the Install
> script? That way, the user will have the choice to either populate
> the config file by themselves or by running some saturation tool
> (and hence, the user is aware of the risks).

Yes definitely - one can also ask for parameters interactively, if needed.
An example in PCP git that does similar things is src/pmdas/shping/Install

cheers.

--
Nathan

<Prev in Thread] Current Thread [Next in Thread>