From owner-freebsd-hackers@freebsd.org Mon Dec 2 10:38:00 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id A9E681CD163 for ; Mon, 2 Dec 2019 10:38:00 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: from puchar.net (puchar.net [194.1.144.90]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 47RM5L3PJPz4vtG for ; Mon, 2 Dec 2019 10:37:58 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: Received: from 127.0.0.1 (localhost [127.0.0.1]) by puchar.net (8.15.2/8.15.2) with ESMTPS id xB2AbsFn030190 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO) for ; Mon, 2 Dec 2019 11:37:54 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=puchar.net; s=default; t=1575283074; bh=iDCpVmVzYb4q5tP7rHVaCf59RUKIX0fmx605GInFPg8=; h=Date:From:To:Subject; b=W0VSATPrBj52F3UNvbwJkMiku6WjC4FXOrnBXQtaRy19VF4qalZV3ngYEpV/pGP4H g/vONN1JeYHjgB1eNllHinFIYXq5eORAyTEueWCM/8v/Iz+sHfT1Qlwa3KwDwOio1t z7ggxPsMzJObbUU7gfWH/1A46AKVsca1+gsOtAlw= Received: from localhost (puchar-wojtek@localhost) by puchar.net (8.15.2/8.15.2/Submit) with ESMTP id xB2Abs5E030184 for ; Mon, 2 Dec 2019 11:37:54 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) Date: Mon, 2 Dec 2019 11:37:54 +0100 (CET) From: Wojciech Puchar To: freebsd-hackers@freebsd.org Subject: bhyve+windows 7 multicore performance Message-ID: User-Agent: Alpine 2.20 (BSF 67 2015-01-07) MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset=US-ASCII X-Rspamd-Queue-Id: 47RM5L3PJPz4vtG X-Spamd-Bar: ---- Authentication-Results: mx1.freebsd.org; dkim=fail (rsa verify failed) header.d=puchar.net header.s=default header.b=W0VSATPr; dmarc=none; spf=pass (mx1.freebsd.org: domain of wojtek@puchar.net designates 194.1.144.90 as permitted sender) smtp.mailfrom=wojtek@puchar.net X-Spamd-Result: default: False [-4.61 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; FROM_HAS_DN(0.00)[]; R_SPF_ALLOW(-0.20)[+mx]; R_DKIM_REJECT(1.00)[puchar.net:s=default]; MIME_GOOD(-0.10)[text/plain]; PREVIOUSLY_DELIVERED(0.00)[freebsd-hackers@freebsd.org]; TO_DN_NONE(0.00)[]; RCPT_COUNT_ONE(0.00)[1]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; DMARC_NA(0.00)[puchar.net]; TO_MATCH_ENVRCPT_ALL(0.00)[]; DKIM_TRACE(0.00)[puchar.net:-]; RCVD_IN_DNSWL_NONE(0.00)[90.144.1.194.list.dnswl.org : 127.0.10.0]; IP_SCORE(-3.31)[ip: (-8.76), ipnet: 194.1.144.0/24(-4.38), asn: 43476(-3.50), country: PL(0.07)]; FROM_EQ_ENVFROM(0.00)[]; MIME_TRACE(0.00)[0:+]; RCVD_TLS_LAST(0.00)[]; ASN(0.00)[asn:43476, ipnet:194.1.144.0/24, country:PL]; MID_RHS_MATCH_FROM(0.00)[]; RCVD_COUNT_TWO(0.00)[2] X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 02 Dec 2019 10:38:00 -0000 i am already using bhyve to run windows 7 guests on one server, all are small guests with 1 or 2 cores allocated. Works fine with good performance. Recently i changed computer configuration in one of my client's office. Before: low end PC as unix server Dell T110-II with quad core Xeon E3 v1 running windows 7 natively After: New server with CPU: Intel(R) Xeon(R) E-2136 CPU @ 3.30GHz (6 cores*2 threads) as unix server with windows 7 moved to bhyve. i run bhyve VM like this: nice -n -20 /usr/sbin/bhyve -s 0,hostbridge -m 22528M \ -H -P -S -c cpus=11,sockets=1,cores=11,threads=1 \ -s 7,fbuf,rfb=10.2.3.4:5900,password=secret \ -s 3,ahci,hd:/dev/ada2p5.eli,hd:/dev/ada2p6.eli,hd:/dev/ada2p127.eli \ -s 5,virtio-net,tap0,mac=08:00:27:b7:ca:16 \ -s 30,virtio-rnd -s 31,lpc -U 0072c755-0e33-11ea-b92a-4c53821d28a6 \ -l bootrom,/usr/local/share/uefi-firmware/BHYVE_UEFI.fd -w windows And it runs properly with 11 threads available for windows. But windows feels quite slower that it was before. There is for sure no problem with I/O performance. It's about compute speed. What i do wrong? From owner-freebsd-hackers@freebsd.org Tue Dec 3 07:36:17 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id B517B1CB683 for ; Tue, 3 Dec 2019 07:36:17 +0000 (UTC) (envelope-from karnajitw@gmail.com) Received: from mail-vs1-xe30.google.com (mail-vs1-xe30.google.com [IPv6:2607:f8b0:4864:20::e30]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) server-signature RSA-PSS (4096 bits) client-signature RSA-PSS (2048 bits) client-digest SHA256) (Client CN "smtp.gmail.com", Issuer "GTS CA 1O1" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 47Rv1F00P6z41gC for ; Tue, 3 Dec 2019 07:36:16 +0000 (UTC) (envelope-from karnajitw@gmail.com) Received: by mail-vs1-xe30.google.com with SMTP id p6so1701724vsj.11 for ; Mon, 02 Dec 2019 23:36:16 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:from:date:message-id:subject:to; bh=FzyfIcOoVb5Q02ZdCO3LdcY6liqRTzzNGujCwTp8cK4=; b=spOI7EfRkxiHBF53+ODiJzeqdk6Hp6Ii15oJ4gMm1T9jLOxnropxh9LUGxLD9i7Q01 hKw8pOsyHpoTwk0SxfFFNMu07i+4NIUfcseOGZhgeRJp0QmBLn7xK3beDkr7EAYve17j OYnG0Uepoc1LvLh9aZXRlIVXWH3F/BlLDWwm/IFDyOoUzahxt6+XfS5X/AjZhIxhrmEj yklA0E9wafeMUE4sYmVvmMeje6Rp0NgZl3eIFqP891mQ56hOAmvt5B5yrRIptXG4b1GQ znMWeAcJJaOQ9CPCS/CERZgZTsTQnIOLEW58ErdztrkDmtm3Z4SD5xjg01c6+efN/09o d+/w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:from:date:message-id:subject:to; bh=FzyfIcOoVb5Q02ZdCO3LdcY6liqRTzzNGujCwTp8cK4=; b=k7OkNaPz38sVhlYZbScV4y7awzVioYITutGfwc0XxESXABm8P5ChCBtL0OflnYtCQr vRVZqGjy+hjbqcG+iuXQ+kwUPOAjJ1pkYRGg+gIAedloIEQI1q7p/b1M3OuTwu/01B2D 9VvrODePa16ig9snfRnxi6y1E/F9oyzPwp/8JkMsDut8BUG6tLMEc5mO+4JTZkUZHasf eyYhLGMT3CdUw9ZcTYQACUL20FrkD8S5ZNDNRX89nfra9YjCQLiLpG2yI7cUUU+JN8MC EJwdqE6mUU4EtgKOZaSKS8z2FsEi/idcXm1TqgE4a455YhGX+6iZCWEacbJnsi212jYo 7cVg== X-Gm-Message-State: APjAAAWVnZq4v+0cHeJ8A82fDJfBuIcWzAxZgymVfVzxsTalijDoQQjb PSZ+okd+YuMU+Nm5p6Jn59QwKHFE4bLfI3Gr+amquEQs X-Google-Smtp-Source: APXvYqweWBtJNoyOxW2pab4NkqNijsxwMr9rYqmj4PiqsUw2jYcNQMcXKOyvZ1G1kse+WkqNDSHFR9vA7hAbeHhMW6Y= X-Received: by 2002:a05:6102:a17:: with SMTP id t23mr1827739vsa.121.1575358575490; Mon, 02 Dec 2019 23:36:15 -0800 (PST) MIME-Version: 1.0 From: karnajit wangkhem Date: Tue, 3 Dec 2019 13:06:04 +0530 Message-ID: Subject: State of register edx on valgrind-freebsd after syscall To: freebsd-hackers@freebsd.org X-Rspamd-Queue-Id: 47Rv1F00P6z41gC X-Spamd-Bar: -- Authentication-Results: mx1.freebsd.org; dkim=pass header.d=gmail.com header.s=20161025 header.b=spOI7EfR; dmarc=pass (policy=none) header.from=gmail.com; spf=pass (mx1.freebsd.org: domain of karnajitw@gmail.com designates 2607:f8b0:4864:20::e30 as permitted sender) smtp.mailfrom=karnajitw@gmail.com X-Spamd-Result: default: False [-3.00 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; R_DKIM_ALLOW(-0.20)[gmail.com:s=20161025]; FROM_HAS_DN(0.00)[]; R_SPF_ALLOW(-0.20)[+ip6:2607:f8b0:4000::/36:c]; FREEMAIL_FROM(0.00)[gmail.com]; MIME_GOOD(-0.10)[multipart/alternative,text/plain]; PREVIOUSLY_DELIVERED(0.00)[freebsd-hackers@freebsd.org]; TO_DN_NONE(0.00)[]; IP_SCORE_FREEMAIL(0.00)[]; RCPT_COUNT_ONE(0.00)[1]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; IP_SCORE(0.00)[ip: (-9.63), ipnet: 2607:f8b0::/32(-2.24), asn: 15169(-1.94), country: US(-0.05)]; TO_MATCH_ENVRCPT_ALL(0.00)[]; DKIM_TRACE(0.00)[gmail.com:+]; DMARC_POLICY_ALLOW(-0.50)[gmail.com,none]; RCVD_IN_DNSWL_NONE(0.00)[0.3.e.0.0.0.0.0.0.0.0.0.0.0.0.0.0.2.0.0.4.6.8.4.0.b.8.f.7.0.6.2.list.dnswl.org : 127.0.5.0]; FROM_EQ_ENVFROM(0.00)[]; MIME_TRACE(0.00)[0:+,1:+,2:~]; FREEMAIL_ENVFROM(0.00)[gmail.com]; ASN(0.00)[asn:15169, ipnet:2607:f8b0::/32, country:US]; RCVD_COUNT_TWO(0.00)[2]; RCVD_TLS_ALL(0.00)[]; DWL_DNSWL_NONE(0.00)[gmail.com.dwl.dnswl.org : 127.0.5.0] Content-Type: text/plain; charset="UTF-8" X-Content-Filtered-By: Mailman/MimeDel 2.1.29 X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 03 Dec 2019 07:36:17 -0000 Hi All, Below is the valgrind-freebsd I used https://www.freshports.org/devel/valgrind https://bitbucket.org/stass/valgrind-freebsd/get/ce1acb28953f.tar.gz?dummy=/ $ ./valgrind --version valgrind-3.10.1 Please consider the following assembly ============================================================ .section .data .long 0 /* Valgrind segfaults without this dummy */ .section .text .global _start STR0: .ascii "Hello World\n" kernel: int $0x80 ret _start: mov $2, %ebx /* Store value 2, 3, 4 in reg ebx, ecx, edx */ mov $3, %ecx mov $4, %edx push $12 /* Push arguments on stack as per x86 freebsd convention */ push $STR0 push $1 mov $4, %eax /* write syscall no == 4 */ call kernel add %ebx, %eax /* Now lets add all the GP registers */ add %ecx, %eax add %edx, %eax push %eax /* We expect 4(edx) + 3(ecx) + 2(ebx) + 12(eax) == 21 */ mov $1, %eax /* Perform exit syscall */ call kernel ============================================================ compile: $ clang --target=i386-unknown-freebsd10.3 -nostdlib -nostdinc reg_minimal.s $ ./a.out Hello World $ echo $? 21 $ ./valgrind ./a.out ==69326== Memcheck, a memory error detector ==69326== Copyright (C) 2002-2013, and GNU GPL'd, by Julian Seward et al. ==69326== Using Valgrind-3.10.1 and LibVEX; rerun with -h for copyright info ==69326== Command: ./a.out ==69326== Hello World ==69326== ==69326== HEAP SUMMARY: ==69326== in use at exit: 0 bytes in 0 blocks ==69326== total heap usage: 0 allocs, 0 frees, 0 bytes allocated ==69326== ==69326== All heap blocks were freed -- no leaks are possible ==69326== ==69326== For counts of detected and suppressed errors, rerun with: -v ==69326== ERROR SUMMARY: 0 errors from 0 contexts (suppressed: 0 from 0) $ echo $? 177 <<<<<<<<<< This is wrong Now, if we modify the code slightly to return %edx instead, the return value will looks like this $ echo $? 160 So, the reason why eax + ebx + ecx + edx returned 177 instead of 21 was because register edx has been clobbered by valgrind instrumentation of syscall. In case of linux, the syscall calling convention is bit different and we need to pass the arguments in registers ebx, ecx, edx, but even after the syscall, these register value holds the same argument values (valgrind-linux valgrind-3.7.0). Could someone give a pointer to which part of the freebsd-valgrind code could be responsible for this bug? Or if possible where I can fix this? Regards, Karan From owner-freebsd-hackers@freebsd.org Tue Dec 3 08:12:47 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id 4F00E1CCE50 for ; Tue, 3 Dec 2019 08:12:47 +0000 (UTC) (envelope-from freebsd-rwg@gndrsh.dnsmgr.net) Received: from gndrsh.dnsmgr.net (br1.CN84in.dnsmgr.net [69.59.192.140]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 47RvqL2WH5z43dq for ; Tue, 3 Dec 2019 08:12:45 +0000 (UTC) (envelope-from freebsd-rwg@gndrsh.dnsmgr.net) Received: from gndrsh.dnsmgr.net (localhost [127.0.0.1]) by gndrsh.dnsmgr.net (8.13.3/8.13.3) with ESMTP id xB38Cic0033845; Tue, 3 Dec 2019 00:12:44 -0800 (PST) (envelope-from freebsd-rwg@gndrsh.dnsmgr.net) Received: (from freebsd-rwg@localhost) by gndrsh.dnsmgr.net (8.13.3/8.13.3/Submit) id xB38ChQ0033844; Tue, 3 Dec 2019 00:12:43 -0800 (PST) (envelope-from freebsd-rwg) From: "Rodney W. Grimes" Message-Id: <201912030812.xB38ChQ0033844@gndrsh.dnsmgr.net> Subject: Re: bhyve+windows 7 multicore performance In-Reply-To: To: Wojciech Puchar Date: Tue, 3 Dec 2019 00:12:43 -0800 (PST) CC: freebsd-hackers@freebsd.org X-Mailer: ELM [version 2.4ME+ PL121h (25)] MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII X-Rspamd-Queue-Id: 47RvqL2WH5z43dq X-Spamd-Bar: / Authentication-Results: mx1.freebsd.org; dkim=none; dmarc=none; spf=none (mx1.freebsd.org: domain of freebsd-rwg@gndrsh.dnsmgr.net has no SPF policy when checking 69.59.192.140) smtp.mailfrom=freebsd-rwg@gndrsh.dnsmgr.net X-Spamd-Result: default: False [-0.69 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-0.88)[-0.880,0]; FROM_HAS_DN(0.00)[]; TO_DN_SOME(0.00)[]; NEURAL_HAM_LONG(-0.75)[-0.751,0]; MIME_GOOD(-0.10)[text/plain]; RCVD_TLS_LAST(0.00)[]; DMARC_NA(0.00)[dnsmgr.net]; AUTH_NA(1.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; RCPT_COUNT_TWO(0.00)[2]; R_SPF_NA(0.00)[]; FROM_EQ_ENVFROM(0.00)[]; R_DKIM_NA(0.00)[]; MIME_TRACE(0.00)[0:+]; ASN(0.00)[asn:13868, ipnet:69.59.192.0/19, country:US]; MID_RHS_MATCH_FROM(0.00)[]; IP_SCORE(0.04)[ip: (0.14), ipnet: 69.59.192.0/19(0.07), asn: 13868(0.03), country: US(-0.05)]; RCVD_COUNT_TWO(0.00)[2] X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 03 Dec 2019 08:12:47 -0000 > i am already using bhyve to run windows 7 guests on one server, all are > small guests with 1 or 2 cores allocated. Works fine with good > performance. > > Recently i changed computer configuration in one of my client's office. > > Before: > low end PC as unix server > Dell T110-II with quad core Xeon E3 v1 running windows 7 natively > > After: > New server with CPU: Intel(R) Xeon(R) E-2136 CPU @ 3.30GHz > (6 cores*2 threads) > as unix server with windows 7 moved to bhyve. > > > i run bhyve VM like this: > nice -n -20 /usr/sbin/bhyve -s 0,hostbridge -m 22528M \ ^^^^^^^^^^^^ why? > -H -P -S -c cpus=11,sockets=1,cores=11,threads=1 \ > -s 7,fbuf,rfb=10.2.3.4:5900,password=secret \ > -s 3,ahci,hd:/dev/ada2p5.eli,hd:/dev/ada2p6.eli,hd:/dev/ada2p127.eli \ > -s 5,virtio-net,tap0,mac=08:00:27:b7:ca:16 \ > -s 30,virtio-rnd -s 31,lpc -U 0072c755-0e33-11ea-b92a-4c53821d28a6 \ > -l bootrom,/usr/local/share/uefi-firmware/BHYVE_UEFI.fd -w windows > > And it runs properly with 11 threads available for windows. I am not so sure about how well the SMP code in windows 7 deals with this odd core count, or for that matter more than 4 cores as at the time Windows 7 was released not many systems existed above 4 cores. > > But windows feels quite slower that it was before. There is for sure no > problem with I/O performance. It's about compute speed. How did you measure this? If it is just a "feel" then it could be almost anything, if you have some solid numbers to look at then perhaps some conclusions can be made. > What i do wrong? Try 4 cores, and drop the priority boost, you may be causeing an unintended side effect. Did you copy the windows 7 from the old server, or is this a new install to the VM. If you copied it there may be a HAL issue/missmatch. -- Rod Grimes rgrimes@freebsd.org From owner-freebsd-hackers@freebsd.org Tue Dec 3 09:58:11 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id 524FB1CFDCB for ; Tue, 3 Dec 2019 09:58:11 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: from puchar.net (puchar.net [194.1.144.90]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 47Ry8x2Xt7z4B6h for ; Tue, 3 Dec 2019 09:58:08 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: Received: from 127.0.0.1 (localhost [127.0.0.1]) by puchar.net (8.15.2/8.15.2) with ESMTPS id xB39w1ve065409 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO); Tue, 3 Dec 2019 10:58:01 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=puchar.net; s=default; t=1575367081; bh=o9TJyytu+NfoqV6uo1lpET2b1GCm430HRlVUeBECkdk=; h=Date:From:To:cc:Subject:In-Reply-To:References; b=EoxLjeibERDHdjL/gCbXj9QffxjrhTzCVZp2w6mYSu6LE/xEbdezXfy7+PLYNFETB OD8zC3pAWHTfURnqrh6lq7z5ulSYQl8XiaNyRrH/rf4N7gyX5mcFAwFPopSi0gIDft 1aKb1j94RDTbiyKOyLCcxyZF4NZvQ+rUCxdFJ93I= Received: from localhost (puchar-wojtek@localhost) by puchar.net (8.15.2/8.15.2/Submit) with ESMTP id xB39w0bK065406; Tue, 3 Dec 2019 10:58:00 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) Date: Tue, 3 Dec 2019 10:58:00 +0100 (CET) From: Wojciech Puchar To: "Rodney W. Grimes" cc: Wojciech Puchar , freebsd-hackers@freebsd.org Subject: Re: bhyve+windows 7 multicore performance In-Reply-To: <201912030812.xB38ChQ0033844@gndrsh.dnsmgr.net> Message-ID: References: <201912030812.xB38ChQ0033844@gndrsh.dnsmgr.net> User-Agent: Alpine 2.20 (BSF 67 2015-01-07) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII; format=flowed X-Rspamd-Queue-Id: 47Ry8x2Xt7z4B6h X-Spamd-Bar: ---- Authentication-Results: mx1.freebsd.org; dkim=fail (rsa verify failed) header.d=puchar.net header.s=default header.b=EoxLjeib; dmarc=none; spf=pass (mx1.freebsd.org: domain of wojtek@puchar.net designates 194.1.144.90 as permitted sender) smtp.mailfrom=wojtek@puchar.net X-Spamd-Result: default: False [-4.60 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; FROM_HAS_DN(0.00)[]; RCPT_COUNT_THREE(0.00)[3]; R_SPF_ALLOW(-0.20)[+mx]; R_DKIM_REJECT(1.00)[puchar.net:s=default]; MIME_GOOD(-0.10)[text/plain]; DMARC_NA(0.00)[puchar.net]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; TO_DN_SOME(0.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; DKIM_TRACE(0.00)[puchar.net:-]; RCVD_IN_DNSWL_NONE(0.00)[90.144.1.194.list.dnswl.org : 127.0.10.0]; IP_SCORE(-3.30)[ip: (-8.73), ipnet: 194.1.144.0/24(-4.36), asn: 43476(-3.49), country: PL(0.07)]; FROM_EQ_ENVFROM(0.00)[]; MIME_TRACE(0.00)[0:+]; RCVD_TLS_LAST(0.00)[]; ASN(0.00)[asn:43476, ipnet:194.1.144.0/24, country:PL]; MID_RHS_MATCH_FROM(0.00)[]; RCVD_COUNT_TWO(0.00)[2] X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 03 Dec 2019 09:58:11 -0000 >> >> >> i run bhyve VM like this: >> nice -n -20 /usr/sbin/bhyve -s 0,hostbridge -m 22528M \ > ^^^^^^^^^^^^ why? to make sure VM will not be slower down too much if i put other high load on host site. > >> >> But windows feels quite slower that it was before. There is for sure no >> problem with I/O performance. It's about compute speed. > > How did you measure this? If it is just a "feel" then it could > be almost anything, if you have some solid numbers to look at > then perhaps some conclusions can be made. > >> What i do wrong? > > Try 4 cores, and drop the priority boost, you may be causeing Well i need more cores than 4 for that VM. I will try even number (10) and no nice. > an unintended side effect. > > Did you copy the windows 7 from the old server, or is this > a new install to the VM. If you copied it there may be a > HAL issue/missmatch. Copied, and installed missing drivers. I didn't install windoze for over 5 years :) From owner-freebsd-hackers@freebsd.org Tue Dec 3 15:29:25 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id A65D61B29B0 for ; Tue, 3 Dec 2019 15:29:25 +0000 (UTC) (envelope-from freebsd-rwg@gndrsh.dnsmgr.net) Received: from gndrsh.dnsmgr.net (br1.CN84in.dnsmgr.net [69.59.192.140]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 47S5W86z7Wz4WCx for ; Tue, 3 Dec 2019 15:29:24 +0000 (UTC) (envelope-from freebsd-rwg@gndrsh.dnsmgr.net) Received: from gndrsh.dnsmgr.net (localhost [127.0.0.1]) by gndrsh.dnsmgr.net (8.13.3/8.13.3) with ESMTP id xB3FTM3M035615; Tue, 3 Dec 2019 07:29:22 -0800 (PST) (envelope-from freebsd-rwg@gndrsh.dnsmgr.net) Received: (from freebsd-rwg@localhost) by gndrsh.dnsmgr.net (8.13.3/8.13.3/Submit) id xB3FTMnY035614; Tue, 3 Dec 2019 07:29:22 -0800 (PST) (envelope-from freebsd-rwg) From: "Rodney W. Grimes" Message-Id: <201912031529.xB3FTMnY035614@gndrsh.dnsmgr.net> Subject: Re: bhyve+windows 7 multicore performance In-Reply-To: To: Wojciech Puchar Date: Tue, 3 Dec 2019 07:29:22 -0800 (PST) CC: "Rodney W. Grimes" , freebsd-hackers@freebsd.org X-Mailer: ELM [version 2.4ME+ PL121h (25)] MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII X-Rspamd-Queue-Id: 47S5W86z7Wz4WCx X-Spamd-Bar: / Authentication-Results: mx1.freebsd.org; dkim=none; dmarc=none; spf=none (mx1.freebsd.org: domain of freebsd-rwg@gndrsh.dnsmgr.net has no SPF policy when checking 69.59.192.140) smtp.mailfrom=freebsd-rwg@gndrsh.dnsmgr.net X-Spamd-Result: default: False [-0.61 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-0.78)[-0.779,0]; RCPT_COUNT_THREE(0.00)[3]; TO_DN_SOME(0.00)[]; FROM_HAS_DN(0.00)[]; MIME_GOOD(-0.10)[text/plain]; RCVD_TLS_LAST(0.00)[]; DMARC_NA(0.00)[dnsmgr.net]; AUTH_NA(1.00)[]; NEURAL_HAM_LONG(-0.77)[-0.768,0]; TO_MATCH_ENVRCPT_SOME(0.00)[]; R_SPF_NA(0.00)[]; FROM_EQ_ENVFROM(0.00)[]; R_DKIM_NA(0.00)[]; MIME_TRACE(0.00)[0:+]; ASN(0.00)[asn:13868, ipnet:69.59.192.0/19, country:US]; MID_RHS_MATCH_FROM(0.00)[]; IP_SCORE(0.04)[ip: (0.14), ipnet: 69.59.192.0/19(0.07), asn: 13868(0.03), country: US(-0.05)]; RCVD_COUNT_TWO(0.00)[2] X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 03 Dec 2019 15:29:25 -0000 > >> i run bhyve VM like this: > >> nice -n -20 /usr/sbin/bhyve -s 0,hostbridge -m 22528M \ > > ^^^^^^^^^^^^ why? > > to make sure VM will not be slower down too much if i put other high load > on host site. > > > > >> > >> But windows feels quite slower that it was before. There is for sure no > >> problem with I/O performance. It's about compute speed. > > > > How did you measure this? If it is just a "feel" then it could > > be almost anything, if you have some solid numbers to look at > > then perhaps some conclusions can be made. > > > >> What i do wrong? > > > > Try 4 cores, and drop the priority boost, you may be causeing > > Well i need more cores than 4 for that VM. > I will try even number (10) and no nice. If 4 cores performs better than 10 cores why would you want to intentionally slow it down? > > an unintended side effect. > > > > > > > > Did you copy the windows 7 from the old server, or is this > > a new install to the VM. If you copied it there may be a > > HAL issue/missmatch. > Copied, and installed missing drivers. > > I didn't install windoze for over 5 years :) Ok, this may mean there is a HAL missmatch. -- Rod Grimes rgrimes@freebsd.org From owner-freebsd-hackers@freebsd.org Wed Dec 4 16:21:52 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id 806F21CCD4A for ; Wed, 4 Dec 2019 16:21:52 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: from puchar.net (puchar.net [194.1.144.90]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 47SkdC22MRz42GJ for ; Wed, 4 Dec 2019 16:21:50 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: Received: from 127.0.0.1 (localhost [127.0.0.1]) by puchar.net (8.15.2/8.15.2) with ESMTPS id xB4GLikp006523 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO); Wed, 4 Dec 2019 17:21:44 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=puchar.net; s=default; t=1575476504; bh=dGbkBImLzBvgOvKkcsTWCREB8RCnSDOQLYKObgBPx5g=; h=Date:From:To:cc:Subject:In-Reply-To:References; b=laIhNb6RNEGCzHotGSopM9/S3dPMGDYq4XgRRLECsFPqp7jbTNVqA26jNNlPfdiBg wo2u6ptujxZCd5w0czPnIoTBXoyXu6Diau2PscqEUoNly9Og/8b9ByYyVlWbdPzM/9 KikNx4QPfrB9M4i0bFdAE0Hmgw+7OyudDoYZBZ0M= Received: from localhost (puchar-wojtek@localhost) by puchar.net (8.15.2/8.15.2/Submit) with ESMTP id xB4GLhFm006517; Wed, 4 Dec 2019 17:21:43 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) Date: Wed, 4 Dec 2019 17:21:43 +0100 (CET) From: Wojciech Puchar To: "Rodney W. Grimes" cc: Wojciech Puchar , freebsd-hackers@freebsd.org Subject: Re: bhyve+windows 7 multicore performance In-Reply-To: <201912031529.xB3FTMnY035614@gndrsh.dnsmgr.net> Message-ID: References: <201912031529.xB3FTMnY035614@gndrsh.dnsmgr.net> User-Agent: Alpine 2.20 (BSF 67 2015-01-07) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII; format=flowed X-Rspamd-Queue-Id: 47SkdC22MRz42GJ X-Spamd-Bar: ---- Authentication-Results: mx1.freebsd.org; dkim=fail (rsa verify failed) header.d=puchar.net header.s=default header.b=laIhNb6R; dmarc=none; spf=pass (mx1.freebsd.org: domain of wojtek@puchar.net designates 194.1.144.90 as permitted sender) smtp.mailfrom=wojtek@puchar.net X-Spamd-Result: default: False [-4.59 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; FROM_HAS_DN(0.00)[]; RCPT_COUNT_THREE(0.00)[3]; R_SPF_ALLOW(-0.20)[+mx]; R_DKIM_REJECT(1.00)[puchar.net:s=default]; MIME_GOOD(-0.10)[text/plain]; DMARC_NA(0.00)[puchar.net]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; TO_DN_SOME(0.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; DKIM_TRACE(0.00)[puchar.net:-]; RCVD_IN_DNSWL_NONE(0.00)[90.144.1.194.list.dnswl.org : 127.0.10.0]; IP_SCORE(-3.29)[ip: (-8.70), ipnet: 194.1.144.0/24(-4.35), asn: 43476(-3.48), country: PL(0.07)]; FROM_EQ_ENVFROM(0.00)[]; MIME_TRACE(0.00)[0:+]; RCVD_TLS_LAST(0.00)[]; ASN(0.00)[asn:43476, ipnet:194.1.144.0/24, country:PL]; MID_RHS_MATCH_FROM(0.00)[]; RCVD_COUNT_TWO(0.00)[2] X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 04 Dec 2019 16:21:52 -0000 >>> >>> Try 4 cores, and drop the priority boost, you may be causeing >> >> Well i need more cores than 4 for that VM. >> I will try even number (10) and no nice. > > If 4 cores performs better than 10 cores why would you want performs better per thread. Not as total. removing -P option improved performance a bit. Well - a large bit. From owner-freebsd-hackers@freebsd.org Wed Dec 4 17:56:36 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id D3D881AA066 for ; Wed, 4 Dec 2019 17:56:36 +0000 (UTC) (envelope-from dariusmihaim@gmail.com) Received: from mail-qv1-xf2f.google.com (mail-qv1-xf2f.google.com [IPv6:2607:f8b0:4864:20::f2f]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) server-signature RSA-PSS (4096 bits) client-signature RSA-PSS (2048 bits) client-digest SHA256) (Client CN "smtp.gmail.com", Issuer "GTS CA 1O1" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 47SmkW4MwVz494S for ; Wed, 4 Dec 2019 17:56:35 +0000 (UTC) (envelope-from dariusmihaim@gmail.com) Received: by mail-qv1-xf2f.google.com with SMTP id t5so199829qvs.5 for ; Wed, 04 Dec 2019 09:56:35 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=hGNgOaolvIr8K5XVML3jLe5E0MJoj+FU5sjRnYN1zyc=; b=YMbloR9flVyx6YcfB4vHgWJOAxnEoCv2T2fqV/GI0oBoQTb+D6uZvWv3vp+7PNgPud kA+I9+yjyq8bmodWhh/u5DNASH0qpkXyUJCRxskjn1qTYXW0IQgEIQwPIa0rwitkhDc2 6jiiXhLnV1gic4W7DHABe/YoIFurEbizDFWQRbH2Yoh9MY9VpsrpSejzza9+taRVFNvc JeTpGX8oOU4mYVfjPu5Zp5guMskz/KnG0kcrcJayBl6b3dS1czivp1AM5PatbVG4Puv/ dqkIZobmv1fTvBxTCk0iZ8nH43AjpihFPjMMjlJ5xoEr1AT+G3Xt37y7LZUtbyGxKUVS AgNg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=hGNgOaolvIr8K5XVML3jLe5E0MJoj+FU5sjRnYN1zyc=; b=X9+31TKaH8e8OF0dlvBAqSwEFfCJPdAW4H2KhiuhYA4LQYCK4/uO58dpLw8JCSrc0J W4LBgDEHvIdppEHJGPUDHjTAZmVcQwTCtLQyCxOK+6E6/J0dJ2dw+O5pr63N/wUgPsTZ gPlpO5/49Iq7vndHqbJpmJYlnxXR5XqDw8800LzQ+KAopxKOX8ylKWv0EnyWA/F6ASWu OOnRGdckA+95To23uOoSPwRJTteZecjNNt8c2lUgGkf7fqCf8ZmJKxYRE8w1YfCd3j5C fMtvYPfDmeCR/KWZX1RS2lJ5gkjE83sG/x5SXDa3L25/LxwL+hzSPEFNvpYrmGZzAaKY tSJg== X-Gm-Message-State: APjAAAWBdiV3vDvrdKXDrF6YgmGlxTJYQDmEmB9e0uGyEF07BFsAs0it ZMpYQz/MMz2HasKoikpom3HEVGh9/KGZW8QavS4= X-Google-Smtp-Source: APXvYqzyTRMNJMg0xjgeKmI3enMJl4KFXEo4n60IbTrtsf4lTftp26hVUYCHjif8v2C9lmpW5la0K6gFXaoiT43o5WI= X-Received: by 2002:ad4:5689:: with SMTP id bc9mr3732481qvb.132.1575482189046; Wed, 04 Dec 2019 09:56:29 -0800 (PST) MIME-Version: 1.0 References: <201912031529.xB3FTMnY035614@gndrsh.dnsmgr.net> In-Reply-To: From: Darius Mihai Date: Wed, 4 Dec 2019 19:56:18 +0200 Message-ID: Subject: Re: bhyve+windows 7 multicore performance To: Wojciech Puchar Cc: "Rodney W. Grimes" , freebsd-hackers@freebsd.org X-Rspamd-Queue-Id: 47SmkW4MwVz494S X-Spamd-Bar: -- Authentication-Results: mx1.freebsd.org; dkim=pass header.d=gmail.com header.s=20161025 header.b=YMbloR9f; dmarc=pass (policy=none) header.from=gmail.com; spf=pass (mx1.freebsd.org: domain of dariusmihaim@gmail.com designates 2607:f8b0:4864:20::f2f as permitted sender) smtp.mailfrom=dariusmihaim@gmail.com X-Spamd-Result: default: False [-3.00 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; R_DKIM_ALLOW(-0.20)[gmail.com:s=20161025]; FROM_HAS_DN(0.00)[]; RCPT_COUNT_THREE(0.00)[3]; R_SPF_ALLOW(-0.20)[+ip6:2607:f8b0:4000::/36]; FREEMAIL_FROM(0.00)[gmail.com]; MIME_GOOD(-0.10)[multipart/alternative,text/plain]; PREVIOUSLY_DELIVERED(0.00)[freebsd-hackers@freebsd.org]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; TO_DN_SOME(0.00)[]; IP_SCORE_FREEMAIL(0.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; DKIM_TRACE(0.00)[gmail.com:+]; DMARC_POLICY_ALLOW(-0.50)[gmail.com,none]; IP_SCORE(0.00)[ipnet: 2607:f8b0::/32(-2.23), asn: 15169(-1.93), country: US(-0.05)]; FROM_EQ_ENVFROM(0.00)[]; MIME_TRACE(0.00)[0:+,1:+,2:~]; FREEMAIL_ENVFROM(0.00)[gmail.com]; ASN(0.00)[asn:15169, ipnet:2607:f8b0::/32, country:US]; RCVD_COUNT_TWO(0.00)[2]; RCVD_TLS_ALL(0.00)[]; DWL_DNSWL_NONE(0.00)[gmail.com.dwl.dnswl.org : 127.0.5.0] Content-Type: text/plain; charset="UTF-8" X-Content-Filtered-By: Mailman/MimeDel 2.1.29 X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 04 Dec 2019 17:56:36 -0000 On Wed, Dec 4, 2019, 18:22 Wojciech Puchar wrote: > >>> > >>> Try 4 cores, and drop the priority boost, you may be causeing > >> > >> Well i need more cores than 4 for that VM. > >> I will try even number (10) and no nice. > > > > If 4 cores performs better than 10 cores why would you want > > performs better per thread. Not as total. > > > removing -P option improved performance a bit. Well - a large bit. > If I remember correctly, windows runs PAUSE very often when idling, so having many cores that stay idle may slow down the system since -P forces context switches when that instruction is executed. Darius From owner-freebsd-hackers@freebsd.org Thu Dec 5 09:44:45 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id 493871C3EF4 for ; Thu, 5 Dec 2019 09:44:45 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: from puchar.net (puchar.net [194.1.144.90]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 47T9mW6CHzz41h4 for ; Thu, 5 Dec 2019 09:44:43 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: Received: from 127.0.0.1 (localhost [127.0.0.1]) by puchar.net (8.15.2/8.15.2) with ESMTPS id xB59iajk084287 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO); Thu, 5 Dec 2019 10:44:36 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=puchar.net; s=default; t=1575539077; bh=xI3uTs2WlaJZqSQnRCmrkiUkMoJ2zJM6pcIFxXUVqIs=; h=Date:From:To:cc:Subject:In-Reply-To:References; b=KckWqSqq+4Ou2p9tiO9aSwqQ5pDKMoUzqUm78QPpcAEMNDW1McWhYQyXku3nAY2d/ udD1H956FE9uC6irI+Uw8hOdRuM65DL3lPRb3wBSQw1oLb32p+jZuN4FW/qHywqmzG A39LmYnPnxMk90Rl6YB8Rymder8Eq/ULIk3c+zoM= Received: from localhost (puchar-wojtek@localhost) by puchar.net (8.15.2/8.15.2/Submit) with ESMTP id xB59iaAP084284; Thu, 5 Dec 2019 10:44:36 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) Date: Thu, 5 Dec 2019 10:44:36 +0100 (CET) From: Wojciech Puchar To: Darius Mihai cc: Wojciech Puchar , "Rodney W. Grimes" , freebsd-hackers@freebsd.org Subject: Re: bhyve+windows 7 multicore performance In-Reply-To: Message-ID: References: <201912031529.xB3FTMnY035614@gndrsh.dnsmgr.net> User-Agent: Alpine 2.20 (BSF 67 2015-01-07) MIME-Version: 1.0 X-Rspamd-Queue-Id: 47T9mW6CHzz41h4 X-Spamd-Bar: --- Authentication-Results: mx1.freebsd.org; dkim=fail (rsa verify failed) header.d=puchar.net header.s=default header.b=KckWqSqq; dmarc=none; spf=pass (mx1.freebsd.org: domain of wojtek@puchar.net designates 194.1.144.90 as permitted sender) smtp.mailfrom=wojtek@puchar.net X-Spamd-Result: default: False [-3.58 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; FROM_HAS_DN(0.00)[]; RCPT_COUNT_THREE(0.00)[4]; R_SPF_ALLOW(-0.20)[+mx]; R_DKIM_REJECT(1.00)[puchar.net:s=default]; MIME_GOOD(-0.10)[multipart/mixed,text/plain]; DMARC_NA(0.00)[puchar.net]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; TO_DN_SOME(0.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; DKIM_TRACE(0.00)[puchar.net:-]; CTYPE_MIXED_BOGUS(1.00)[]; RCVD_IN_DNSWL_NONE(0.00)[90.144.1.194.list.dnswl.org : 127.0.10.0]; IP_SCORE(-3.28)[ip: (-8.66), ipnet: 194.1.144.0/24(-4.33), asn: 43476(-3.47), country: PL(0.07)]; FREEMAIL_TO(0.00)[gmail.com]; FROM_EQ_ENVFROM(0.00)[]; MIME_TRACE(0.00)[0:+,1:+]; RCVD_TLS_LAST(0.00)[]; ASN(0.00)[asn:43476, ipnet:194.1.144.0/24, country:PL]; MID_RHS_MATCH_FROM(0.00)[]; RCVD_COUNT_TWO(0.00)[2] Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8BIT X-Content-Filtered-By: Mailman/MimeDel 2.1.29 X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 05 Dec 2019 09:44:45 -0000 On Wed, 4 Dec 2019, Darius Mihai wrote: > > > On Wed, Dec 4, 2019, 18:22 Wojciech Puchar wrote: > >>> > >>> Try 4 cores, and drop the priority boost, you may be causeing > >> > >> Well i need more cores than 4 for that VM. > >> I will try even number (10) and no nice. > > > > If 4 cores performs better than 10 cores why would you want > > performs better per thread. Not as total. > > > removing -P option improved performance a bit. Well - a large bit. > > > If I remember correctly, windows runs PAUSE very often when idling, > so having many cores that stay idle may slow down the system > since -P forces context switches when that instruction is > executed.  > > Darius Possibly. But for sure - this made things faster a lot. Actually close to bare metal performance. From owner-freebsd-hackers@freebsd.org Thu Dec 5 19:25:01 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id DD7751A974C for ; Thu, 5 Dec 2019 19:25:01 +0000 (UTC) (envelope-from freebsd-rwg@gndrsh.dnsmgr.net) Received: from gndrsh.dnsmgr.net (br1.CN84in.dnsmgr.net [69.59.192.140]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 47TQf45ZfCz4YD0 for ; Thu, 5 Dec 2019 19:25:00 +0000 (UTC) (envelope-from freebsd-rwg@gndrsh.dnsmgr.net) Received: from gndrsh.dnsmgr.net (localhost [127.0.0.1]) by gndrsh.dnsmgr.net (8.13.3/8.13.3) with ESMTP id xB5JOw1B045422; Thu, 5 Dec 2019 11:24:58 -0800 (PST) (envelope-from freebsd-rwg@gndrsh.dnsmgr.net) Received: (from freebsd-rwg@localhost) by gndrsh.dnsmgr.net (8.13.3/8.13.3/Submit) id xB5JOw7V045421; Thu, 5 Dec 2019 11:24:58 -0800 (PST) (envelope-from freebsd-rwg) From: "Rodney W. Grimes" Message-Id: <201912051924.xB5JOw7V045421@gndrsh.dnsmgr.net> Subject: Re: bhyve+windows 7 multicore performance In-Reply-To: To: Wojciech Puchar Date: Thu, 5 Dec 2019 11:24:58 -0800 (PST) CC: Darius Mihai , "Rodney W. Grimes" , freebsd-hackers@freebsd.org X-Mailer: ELM [version 2.4ME+ PL121h (25)] MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=US-ASCII X-Rspamd-Queue-Id: 47TQf45ZfCz4YD0 X-Spamd-Bar: / Authentication-Results: mx1.freebsd.org; dkim=none; dmarc=none; spf=none (mx1.freebsd.org: domain of freebsd-rwg@gndrsh.dnsmgr.net has no SPF policy when checking 69.59.192.140) smtp.mailfrom=freebsd-rwg@gndrsh.dnsmgr.net X-Spamd-Result: default: False [-0.69 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-0.82)[-0.824,0]; FROM_HAS_DN(0.00)[]; RCPT_COUNT_THREE(0.00)[4]; TO_DN_SOME(0.00)[]; IP_SCORE(0.04)[ip: (0.14), ipnet: 69.59.192.0/19(0.07), asn: 13868(0.03), country: US(-0.05)]; MIME_GOOD(-0.10)[text/plain]; RCVD_TLS_LAST(0.00)[]; DMARC_NA(0.00)[dnsmgr.net]; AUTH_NA(1.00)[]; NEURAL_HAM_LONG(-0.80)[-0.803,0]; TO_MATCH_ENVRCPT_SOME(0.00)[]; R_SPF_NA(0.00)[]; FROM_EQ_ENVFROM(0.00)[]; R_DKIM_NA(0.00)[]; MIME_TRACE(0.00)[0:+]; ASN(0.00)[asn:13868, ipnet:69.59.192.0/19, country:US]; FREEMAIL_CC(0.00)[gmail.com]; MID_RHS_MATCH_FROM(0.00)[]; RCVD_COUNT_TWO(0.00)[2] X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 05 Dec 2019 19:25:01 -0000 > > On Wed, 4 Dec 2019, Darius Mihai wrote: > > > > > > > On Wed, Dec 4, 2019, 18:22 Wojciech Puchar wrote: > > >>> > > >>> Try 4 cores, and drop the priority boost, you may be causeing > > >> > > >> Well i need more cores than 4 for that VM. > > >> I will try even number (10) and no nice. > > > > > > If 4 cores performs better than 10 cores why would you want > > > > performs better per thread. Not as total. > > > > > > removing -P option improved performance a bit. Well - a large bit. > > > > > > If I remember correctly, windows runs PAUSE very often when idling, > > so having many cores that stay idle may slow down the system > > since -P forces context switches when that instruction is > > executed.? > > > > Darius > Possibly. But for sure - this made things faster a lot. Actually close to > bare metal performance. Does this close the issue of performance for you and I can remove this thread from my list of active investigation? THanks, -- Rod Grimes rgrimes@freebsd.org From owner-freebsd-hackers@freebsd.org Fri Dec 6 08:58:51 2019 Return-Path: Delivered-To: freebsd-hackers@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id F40821C5FF3 for ; Fri, 6 Dec 2019 08:58:50 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: from puchar.net (puchar.net [194.1.144.90]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 47Tmj54gMTz4Bnr for ; Fri, 6 Dec 2019 08:58:49 +0000 (UTC) (envelope-from wojtek@puchar.net) Received: Received: from 127.0.0.1 (localhost [127.0.0.1]) by puchar.net (8.15.2/8.15.2) with ESMTPS id xB68wg0w052997 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NO); Fri, 6 Dec 2019 09:58:42 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=puchar.net; s=default; t=1575622723; bh=f8VAN/5a3h2IgDxUOhx73cSckywR7lPaxMIibgku4tU=; h=Date:From:To:cc:Subject:In-Reply-To:References; b=sNsHkSfnordccZ/dl24J1/Ie9BLUYC8GhkcQCQLDIdmfJbszNinrZ7l8+W2Mrv6Yl 22gLgi6xp2+c1rX6IiXX7NguQkwtIfrZbiac/qT5H3HRJFj4M4FuURq2owAo3lxB/5 IowNPiHYCPqy+IDhNGDDm/3BYWirNxZloxzw2G/0= Received: from localhost (puchar-wojtek@localhost) by puchar.net (8.15.2/8.15.2/Submit) with ESMTP id xB68wg9N052994; Fri, 6 Dec 2019 09:58:42 +0100 (CET) (envelope-from puchar-wojtek@puchar.net) Date: Fri, 6 Dec 2019 09:58:42 +0100 (CET) From: Wojciech Puchar To: "Rodney W. Grimes" cc: Wojciech Puchar , Darius Mihai , freebsd-hackers@freebsd.org Subject: Re: bhyve+windows 7 multicore performance In-Reply-To: <201912051924.xB5JOw7V045421@gndrsh.dnsmgr.net> Message-ID: References: <201912051924.xB5JOw7V045421@gndrsh.dnsmgr.net> User-Agent: Alpine 2.20 (BSF 67 2015-01-07) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII; format=flowed X-Rspamd-Queue-Id: 47Tmj54gMTz4Bnr X-Spamd-Bar: ---- Authentication-Results: mx1.freebsd.org; dkim=fail (rsa verify failed) header.d=puchar.net header.s=default header.b=sNsHkSfn; dmarc=none; spf=pass (mx1.freebsd.org: domain of wojtek@puchar.net designates 194.1.144.90 as permitted sender) smtp.mailfrom=wojtek@puchar.net X-Spamd-Result: default: False [-4.57 / 15.00]; ARC_NA(0.00)[]; NEURAL_HAM_MEDIUM(-1.00)[-1.000,0]; FROM_HAS_DN(0.00)[]; RCPT_COUNT_THREE(0.00)[4]; R_SPF_ALLOW(-0.20)[+mx]; R_DKIM_REJECT(1.00)[puchar.net:s=default]; MIME_GOOD(-0.10)[text/plain]; DMARC_NA(0.00)[puchar.net]; NEURAL_HAM_LONG(-1.00)[-1.000,0]; TO_DN_SOME(0.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; DKIM_TRACE(0.00)[puchar.net:-]; RCVD_IN_DNSWL_NONE(0.00)[90.144.1.194.list.dnswl.org : 127.0.10.0]; IP_SCORE(-3.27)[ip: (-8.63), ipnet: 194.1.144.0/24(-4.32), asn: 43476(-3.45), country: PL(0.07)]; FROM_EQ_ENVFROM(0.00)[]; MIME_TRACE(0.00)[0:+]; RCVD_TLS_LAST(0.00)[]; ASN(0.00)[asn:43476, ipnet:194.1.144.0/24, country:PL]; MID_RHS_MATCH_FROM(0.00)[]; RCVD_COUNT_TWO(0.00)[2] X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 06 Dec 2019 08:58:51 -0000 >>> since -P forces context switches when that instruction is >>> executed.? >>> >>> Darius >> Possibly. But for sure - this made things faster a lot. Actually close to >> bare metal performance. > > Does this close the issue of performance for you and I can remove this > thread from my list of active investigation? yes. thank you. i used -P before but for VMs with one or 2 threads and the problem was just not visible. It just became visible on 12 thread VM.