From nobody Sat Sep 24 05:58:39 2022 X-Original-To: questions@mlmmj.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mlmmj.nyi.freebsd.org (Postfix) with ESMTP id 4MZJHX0YHwz4cV6D for ; Sat, 24 Sep 2022 05:59:04 +0000 (UTC) (envelope-from kob6558@gmail.com) Received: from mail-io1-xd2f.google.com (mail-io1-xd2f.google.com [IPv6:2607:f8b0:4864:20::d2f]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256 client-signature RSA-PSS (2048 bits) client-digest SHA256) (Client CN "smtp.gmail.com", Issuer "GTS CA 1D4" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 4MZJHV6PDjz3R8l for ; Sat, 24 Sep 2022 05:59:02 +0000 (UTC) (envelope-from kob6558@gmail.com) Received: by mail-io1-xd2f.google.com with SMTP id b23so1489476iof.2 for ; Fri, 23 Sep 2022 22:59:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date; bh=etFtuZbqjBn8baaEwumYtXAB4CSnHqMFoyM+2uVuvK8=; b=dNQwI9cy4AJVVqi9UDV8GYvka63MjSMOgNR/KIm5WLrLWgD7uZ3HaVugITX6mLcw+c FmLh7bcmL2VDdG8STNTBJwK336GqEvjfE6F0jZBYqkaY0oDMWIe1tuQxe0pMr8xyJcYo UjUWMCne+SU7xGwM2mHynjDYHT5O/20USRq7x9rlMpWQk5WNYkKrNZ8gqx8tFqPhRufu I7NozYqqQ9tGpXYJCCkZxhnnvyXY1vt3b6l0ieNJK1F0Q56AwJi7h7GVTy0WkGIJcE9R 3R3azuNfSA3xrdYuJd3LrQUwAYruGxJX7IkeCQD+dzEt3c3iHT1QCumRK36N/zM/QzbX l/Tg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date; bh=etFtuZbqjBn8baaEwumYtXAB4CSnHqMFoyM+2uVuvK8=; b=o018fNz1qHLiES8llHnQDo6/1jHWacKXt6y7EcLT6W3rUYbUOtv8v23cALWq7rW5J8 e1ZDuv7PqHsxmXBRBvFscb9Lzt6ksrZK5BfKHcezI14yVSAfIwAZcKF6F8ra6zwCLL9i ySH9yhJT37XJokpEB/frHosBa8uadPa6c8CIZ6g/lH9X8C1qpQDmSGsoQyfHDMdAoRbA hXo7eTRBK0Z0Qo6BW0lYD+LihRL4kvwYdBb0YkAnxMKUqSJxgH0r4GliIL3BYzKJBjQ/ 0GzlLQ01thWTp9E1gLTmdQ4Jc3+rh5BvBIuOVry2TDVOQKSUTmX/biHuEJEL7fqe2Hxc Z/fQ== X-Gm-Message-State: ACrzQf33jkEllIn50mHR5LwSGaIYgnVuuLcuiVFy3jqvtPQ3oNjCOiG6 v+cyoKtJ1VCDhVCPj+bRrqcS2EY/6UxiD19g3ZdJREW7 X-Google-Smtp-Source: AMsMyM6ANjxhuu80F1tMRJgUwi8YcV+uxLinS9Zqzulhip/sRinkGsb51cgzRbD3qij9fKMu7z3xdvwfuhBFvLXmmas= X-Received: by 2002:a05:6602:1509:b0:69b:35ba:4720 with SMTP id g9-20020a056602150900b0069b35ba4720mr5520347iow.155.1663999142010; Fri, 23 Sep 2022 22:59:02 -0700 (PDT) List-Id: User questions List-Archive: https://lists.freebsd.org/archives/freebsd-questions List-Help: List-Post: List-Subscribe: List-Unsubscribe: Sender: owner-freebsd-questions@freebsd.org X-BeenThere: freebsd-questions@freebsd.org MIME-Version: 1.0 References: <20220922180626.GB79310@darkbeer.org> In-Reply-To: <20220922180626.GB79310@darkbeer.org> From: Kevin Oberman Date: Fri, 23 Sep 2022 22:58:39 -0700 Message-ID: Subject: Re: Disabling CPUs To: Amar Takhar Cc: questions@freebsd.org Content-Type: multipart/alternative; boundary="000000000000c4256905e965fd2f" X-Rspamd-Queue-Id: 4MZJHV6PDjz3R8l X-Spamd-Bar: --- Authentication-Results: mx1.freebsd.org; dkim=pass header.d=gmail.com header.s=20210112 header.b=dNQwI9cy; dmarc=pass (policy=none) header.from=gmail.com; spf=pass (mx1.freebsd.org: domain of kob6558@gmail.com designates 2607:f8b0:4864:20::d2f as permitted sender) smtp.mailfrom=kob6558@gmail.com X-Spamd-Result: default: False [-3.66 / 15.00]; NEURAL_HAM_MEDIUM(-1.00)[-0.999]; NEURAL_HAM_LONG(-0.99)[-0.994]; NEURAL_HAM_SHORT(-0.97)[-0.969]; DMARC_POLICY_ALLOW(-0.50)[gmail.com,none]; FORGED_SENDER(0.30)[rkoberman@gmail.com,kob6558@gmail.com]; R_DKIM_ALLOW(-0.20)[gmail.com:s=20210112]; R_SPF_ALLOW(-0.20)[+ip6:2607:f8b0:4000::/36:c]; MIME_GOOD(-0.10)[multipart/alternative,text/plain]; FROM_HAS_DN(0.00)[]; TO_DN_SOME(0.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; PREVIOUSLY_DELIVERED(0.00)[questions@freebsd.org]; MLMMJ_DEST(0.00)[questions@freebsd.org]; RCVD_IN_DNSWL_NONE(0.00)[2607:f8b0:4864:20::d2f:from]; ARC_NA(0.00)[]; FROM_NEQ_ENVFROM(0.00)[rkoberman@gmail.com,kob6558@gmail.com]; RCVD_COUNT_TWO(0.00)[2]; DKIM_TRACE(0.00)[gmail.com:+]; MID_RHS_MATCH_FROMTLD(0.00)[]; FREEMAIL_FROM(0.00)[gmail.com]; DWL_DNSWL_NONE(0.00)[gmail.com:dkim]; RCPT_COUNT_TWO(0.00)[2]; FREEMAIL_ENVFROM(0.00)[gmail.com]; MIME_TRACE(0.00)[0:+,1:+,2:~]; ASN(0.00)[asn:15169, ipnet:2607:f8b0::/32, country:US]; RCVD_TLS_LAST(0.00)[] X-ThisMailContainsUnwantedMimeParts: N --000000000000c4256905e965fd2f Content-Type: text/plain; charset="UTF-8" Thanks, Amar! I'll give this a try tomorrow. Have you compared performance using only P cores vs. only E cores? My testing (using only cpuset) compiles C faster with 8 E cores than 2 P cores (4 "CPUs"). By any chance have you run a VirtualBox VM? I have found that a Windows 10 VM loads, but the system panics as soon as the VM starts running. I have a couple of things to try that could be triggering the problem. Notably, I have 3D HW acceleration enabled and, since it is not available with scfb, it's a possible cause. I'm getting tired of trailblazing! My current laptop did not have a working Wii interface until iwlwifi. I had een almost no comments on CURRENT, soi I had no idea how much trouble I was gettig into. On Thu, Sep 22, 2022 at 11:06 AM Amar Takhar wrote: > On 2022-09-21 19:05 -0700, Kevin Oberman wrote: > > I am looking to disable all 8 E-cores on my Alder Lake system to prevent > > repeated crashes. The man page has an example of this: > > Modify the cpuset all threads are in by default to contain only the > first 4 > > CPUs, leaving the rest idle: > > cpuset -l 0-3 -s 1 > > I did this, but in subsequent port build, all 12 "CPUs" were running at > 100%. > > Am I missing something? Maybe use -p 1" instead of "-s 1". > > > > I also found suggestions to use "hint.lapic.N.disabled", but teh lines > that > > were supposed to be in dmesg and the messages log were not present. I am > > baffled, but really need to do something to stop the crashes currently > > impacting Alder Lake systems. > > You need to do it in BIOS it's the only way. Unfortunately even if you do > it > within FreeBSD it still sees those cores just doesn't schedule them it > causes an > issue somewhere regardless I did try to not schedule anything to them. > > If you don't see any specific option to disable E-cores you'll need to > disable > them individually. As far as I know the E-cores are always the last cores > in > the list. > > Any Alder Lake BIOS should have the setting. > > > Amar. > > -- Kevin Oberman, Part time kid herder and retired Network Engineer E-mail: rkoberman@gmail.com PGP Fingerprint: D03FB98AFA78E3B78C1694B318AB39EF1B055683 --000000000000c4256905e965fd2f Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Thanks, Amar! I'll give this a try tomorrow.=

Have you compared performance using onl= y P cores vs. only E cores? My testing (using only cpuset) compiles C faste= r with 8 E cores than 2 P cores (4 "CPUs").
=
By any chance have you run a VirtualBox VM? I have foun= d that a Windows 10 VM loads, but the system panics as soon as the VM start= s running. I have a couple of things to try that could be triggering the pr= oblem. Notably, I have 3D HW acceleration enabled and, since it is not avai= lable with scfb, it's a possible cause.

I'm getting tired of trailblazing! My current laptop did not have a= working Wii interface until iwlwifi. I had een almost no comments on CURRE= NT, soi I had no idea how much trouble I was gettig into.
On Thu, = Sep 22, 2022 at 11:06 AM Amar Takhar <verm@darkbeer.org> wrote:
On 2022-09-21 19:05 -0700, Kevin Oberman wrote:
> I am looking to disable all 8 E-cores on my Alder Lake system to preve= nt
> repeated crashes. The man page has an example of this:
> Modify the cpuset all threads are in by default to contain only the fi= rst 4
> CPUs, leaving the rest idle:
> =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0cpuset -l 0-3 -s 1
> I did this, but in subsequent port build, all 12 "CPUs" were= running at 100%.
> Am I missing something? Maybe use -p 1" instead of "-s 1&quo= t;.
>
> I also found suggestions to use "hint.lapic.N.disabled", but= teh lines that
> were supposed to be in dmesg and the messages log were not present. I = am
> baffled, but really need to do something to stop the crashes currently=
> impacting Alder Lake systems.

You need to do it in BIOS it's the only way.=C2=A0 Unfortunately even i= f you do it
within FreeBSD it still sees those cores just doesn't schedule them it = causes an
issue somewhere regardless I did try to not schedule anything to them.

If you don't see any specific option to disable E-cores you'll need= to disable
them individually.=C2=A0 As far as I know the E-cores are always the last c= ores in
the list.

Any Alder Lake BIOS should have the setting.


Amar.



--
Kevin Oberman, Part time kid herder and retired Net= work Engineer
E-mail: rkoberman@gmail.com
PGP Fingerprint: D03FB98AFA78E= 3B78C1694B318AB39EF1B055683
--000000000000c4256905e965fd2f--