Date: Fri, 20 Mar 2015 15:38:23 +0300 From: Slawa Olhovchenkov <slw@zxy.spb.ru> To: John Baldwin <jhb@freebsd.org> Cc: Harrison Grundy <harrison.grundy@astrodoggroup.com>, freebsd-arch@freebsd.org Subject: Re: RFC: Simplfying hyperthreading distinctions Message-ID: <20150320123823.GA49621@zxy.spb.ru> In-Reply-To: <1526311.uylCbgv5VB@ralph.baldwin.cx> References: <1640664.8z9mx3EOQs@ralph.baldwin.cx> <54FA1180.3080605@astrodoggroup.com> <1526311.uylCbgv5VB@ralph.baldwin.cx>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Mar 06, 2015 at 04:17:37PM -0500, John Baldwin wrote:
> On Friday, March 06, 2015 12:43:44 PM Harrison Grundy wrote:
> > On 03/06/15 12:44, John Baldwin wrote:
> > > Currently we go out of our way a bit to distinguish Pentium4-era
> > > hyperthreading from more recent ("modern") hyperthreading. I
> > > suspect that this distinction probably results in confusion more
> > > than anything else. Intel's documentation does not make near as
> > > broad a distinction as far as I can tell. Both types of SMT are
> > > called hyperthreading in the SDM for example. However, we have the
> > > astonishing behavior that 'machdep.hyperthreading_allowed' only
> > > affects "old" hyperthreads, but not "new" ones. We also try to be
> > > overly cute in our dmesg output by using HTT for "old"
> > > hyperthreading, and SMT for "new" hyperthreading. I propose the
> > > following changes to simplify things a bit:
> > >
> > > 1) Call both "old" and "new" hyperthreading HTT in dmesg.
> > >
> > > 2) Change machdep.hyperthreading_allowed to apply to both new and
> > > old HTT. However, doing this means a POLA violation in that we
> > > would now disable modern HTT by default. Balanced against
> > > re-enabling "old" HTT by default on an increasingly-shrinking pool
> > > of old hardware, I think the better approach here would be to also
> > > change the default to allow HTT.
> > >
> > > 3) Possibly add a different knob (or change the behavior of
> > > machdep.hyperthreading_allowed) to still bring up hyperthreads, but
> > > leave them out of the default cpuset (set 1). This would allow
> > > those threads to be re-enabled dynamically at runtime by adjusting
> > > the mask on set 1. The original htt settings back when
> > > 'hyperthreading_allowed' was introduced actually permitted this via
> > > by adjusting 'machdep.hlt_cpus' at runtime.
> > >
> > > What do people think?
> >
> > I'm not sure of how interrupt handling works as it relates to HTT, but
> > wouldn't using cpuset potentially leave them active for interrupt
> > handling?
> >
> > Other than that question, this all makes sense to me.
>
> Interrupt handling works differently. Per my commit a few minutes ago, we do
> not send interrupts to hyperthreads by default (either old or new). However,
> ithreads that are not explicitly bound to a specific CPU will "float" among
> all the CPUs in set 1 so 3) would affect that. Eventually I want to use a
> separate cpuset for interrupts that ithreads inherit from (rather than
> belonging to set 1).
Can you explain interrupt handling some more?
How routing real interrupt? Can be real interrupt routing to specific
core?
Is real interrupt and `cpuset -x irq` is same (I see interrup from
chelsio on cpu other then pinned)?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20150320123823.GA49621>