linux-kernel - Re: [PATCH v3] x86,sched: allow topologies where NUMA nodes share an LLC

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20180329145544.GE4043@hirez.programming.kicks-ass.net>
Date:   Thu, 29 Mar 2018 16:55:44 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Dave Hansen <dave.hansen@...ux.intel.com>
Cc:     Thomas Gleixner <tglx@...utronix.de>,
        Alison Schofield <alison.schofield@...el.com>,
        Ingo Molnar <mingo@...nel.org>,
        Tony Luck <tony.luck@...el.com>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        "H. Peter Anvin" <hpa@...ux.intel.com>,
        Borislav Petkov <bp@...en8.de>,
        David Rientjes <rientjes@...gle.com>,
        Igor Mammedov <imammedo@...hat.com>,
        Prarit Bhargava <prarit@...hat.com>, brice.goglin@...il.com,
        x86@...nel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3] x86,sched: allow topologies where NUMA nodes share an
 LLC

On Thu, Mar 29, 2018 at 07:37:29AM -0700, Dave Hansen wrote:
> On 03/29/2018 06:47 AM, Peter Zijlstra wrote:
> > Further I think Dave argued that we should not change the llc-size,
> > because while SNC presents a subset of the cache to local CPUs, for
> > remote data the whole cache is still available, again something some
> > applications might rely on.
> 
> BTW, I may have argued this in the past, but I don't think it's the best
> thing to do.
> 
> If anything, we should optimize for the _users_ of this information: the
> performance-sensitive ones who are digging up the cache topology.  They
> are also likely to be the most NUMA-affinitized and stay node-local with
> much of their memory traffic.  That would seem to point us in the
> direction of enumerating two separate, half-sized LLCs "shared" only by
> the slice when SNC mode is on.
> 
> That's what I've argued to the hardware folks lately, at least.

Fair enough; then we need change the reported cache-size and mention all
this in (preferably) both comment and Changelog.