From owner-freebsd-stable@freebsd.org Sun Jun 3 17:49:54 2018 Return-Path: Delivered-To: freebsd-stable@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id B02DFFE54CA for ; Sun, 3 Jun 2018 17:49:54 +0000 (UTC) (envelope-from mike@sentex.net) Received: from smarthost2.sentex.ca (smarthost2.sentex.ca [IPv6:2607:f3e0:80:80::2]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (Client CN "smarthost.sentex.ca", Issuer "smarthost.sentex.ca" (not verified)) by mx1.freebsd.org (Postfix) with ESMTPS id 06EEA7184A; Sun, 3 Jun 2018 17:49:53 +0000 (UTC) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (lava.sentex.ca [IPv6:2607:f3e0:0:5::11]) by smarthost2.sentex.ca (8.15.2/8.15.2) with ESMTPS id w53HnqP8028728 (version=TLSv1 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Sun, 3 Jun 2018 13:49:52 -0400 (EDT) (envelope-from mike@sentex.net) Received: from [192.168.43.26] (saphire3.sentex.net [192.168.43.26]) by lava.sentex.ca (8.15.2/8.15.2) with ESMTP id w53HnoOQ049687; Sun, 3 Jun 2018 13:49:50 -0400 (EDT) (envelope-from mike@sentex.net) Subject: Re: Ryzen issues on FreeBSD ? (with sort of workaround) To: Pete French , Don Lewis Cc: eric@vangyzen.net, freebsd-stable@freebsd.org, freebsd@hda3.com, avg@freebsd.org References: <0e8b197f-15b2-b865-b532-cee2a20f2b42@ingresso.co.uk> From: Mike Tancsa Openpgp: preference=signencrypt Autocrypt: addr=mike@sentex.net; prefer-encrypt=mutual; keydata= xsBNBEzcA24BCACpwI/iqOrs0GfQSfhA1v6Z8AcXVeGsRyKEKUpxoOYxXWc2z3vndbYlIP6E YJeifzKhS/9E+VjhhICaepLHfw865TDTUPr5D0Ed+edSsKjlnDtb6hfNJC00P7eoiuvi85TW F/gAxRY269A5d856bYrzLbkWp2lKUR3Bg6NnORtflGzx9ZWAltZbjYjjRqegPv0EQNYcHqWo eRpXilEo1ahT6nmOU8V7yEvT2j4wlLcQ6qg7w+N/vcBvyd/weiwHU+vTQ9mT61x5/wUrQhdw 2gJHeQXeDGMJV49RT2EEz+QVxaf477eyWsdQzPVjAKRMT3BVdK8WvpYAEfBAbXmkboOxABEB AAHNHG1pa2UgdGFuY3NhIDxtaWtlQHNlbnRleC5jYT7CwHgEEwECACIFAkzcA24CGwMGCwkI BwMCBhUIAgkKCwQWAgMBAh4BAheAAAoJEJXHwM2kc8rX+sMH/2V6pTBKsQ5mpWWLgs6wVP2k BC+6r/YKNXv9Rw/PrC6+9hTbgA+sSjJ+8gxsCbJsOQXZrxF0x3l9oYdYfuKcwdwXFX1/FS8p HfBeDkmlH+dI709xT9wgrR4dS5aMmKp0scPrXPIAKiYVOHjOlNItcLYTEEWEFBepheEVsgmk GrNbcrHwOx/u4igUQ8vcpyXPyUki+BsftPw8ZQvBU887igh0OxaCR8AurJppQ5UQd63r81cX E1ZjoFoWCaGK/SjPb/OhpYpu5swoZIhOxQbn7OtakYPsDd5t2A5KhvjI8BMTnd5Go+2xsCmr jlIEq8Bi29gCcfQUvNiClevi13ifmnnOwE0ETNwDbgEIALWGNJHRAhpd0A4vtd3G0oRqMBcM FGThQr3qORmEBTPPEomTdBaHcn+Xl+3YUvTBD/67/mutWBwgp2R5gQOSqcM7axvgMSHbKqBL 9sd1LsLw0UT2O5AYxv3EwzhG84pwRg3XcUqvWA4lA8tIj/1q4Jzi5qOkg1zxq4W9qr9oiYK5 bBR638JUvr3eHMaz/Nz+sDVFgwHmXZj3M6aE5Ce9reCGbvrae7H5D5PPvtT3r22X8SqfVAiO TFKedCf/6jbSOedPN931FJQYopj9P6b3m0nI3ZiCDVSqeyOAIBLzm+RBUIU3brzoxDhYR8pz CJc2sK8l6YjqivPakrD86bFDff8AEQEAAcLAXwQYAQIACQUCTNwDbgIbDAAKCRCVx8DNpHPK 1+iQB/99aqNtez9ZTBWELj269La8ntuRx6gCpzfPXfn6SDIfTItDxTh1hrdRVP5QNGGF5wus N4EMwXouskva1hbFX3Pv72csYSxxEJXjW16oV8WK4KjKXoskLg2RyRP4uXqL7Mp2ezNtVY5F 9nu3fj4ydpHCSaqKy5xd70A8D50PfZsFgkrsa5gdQhPiGGEdxhq/XSeAAnZ4uVLJKarH+mj5 MEhgZPEBWkGrbDZpezl9qbFcUem/uT9x8FYT/JIztMVh9qDcdP5tzANW5J7nvgXjska+VFGY ryZK4SPDczh74mn6GI/+RBi7OUzXXPgpPBrhS5FByjwCqjjsSpTjTds+NGIY Organization: Sentex Communications Message-ID: <2a54be25-f845-e493-37e7-403247383e9e@sentex.net> Date: Sun, 3 Jun 2018 13:49:51 -0400 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.8.0 MIME-Version: 1.0 In-Reply-To: <0e8b197f-15b2-b865-b532-cee2a20f2b42@ingresso.co.uk> Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 8bit X-Scanned-By: MIMEDefang 2.78 X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.26 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 03 Jun 2018 17:49:55 -0000 On 6/3/2018 1:10 PM, Pete French wrote: > >> The compile bug has been fixed for me.  However, last I checked I can >> still freeze a system by generating a lot of network traffic between VMs >> in either bhyve or virtbox.  Its been a while since I tested (couple of >> months) but I dont recall anything obviously committed that highlighted >> that issue.  Note this is on Epyc and Ryzen boxes > > Yes, it was your iperf3 tests which enable me to freeze the system with > SMP enabled. With SMP disabled it works fine, however. have you tried > that at all ? The only other settings I ahve are the global C-states > and cool-n-quiet being disabled. I dont really care about either so > havent tested re-enabling them. I have c-states disabled on the ryzen both for FreeBSD and Linux. To disable SMP on the Epyc doesnt seem to be possible. But then again kill off 31 cores is a heavy cost to pay for stability :( When I am back at the office, I will see if a recent checkout of HEAD still freezes the Epyc. ---Mike -- ------------------- Mike Tancsa, tel +1 519 651 3400 x203 Sentex Communications, mike@sentex.net Providing Internet services since 1994 www.sentex.net Cambridge, Ontario Canada