From nobody Sat Dec 23 23:27:59 2023 X-Original-To: freebsd-arm@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 4SyL284rddz558WL for ; Sat, 23 Dec 2023 23:28:16 +0000 (UTC) (envelope-from marklmi@yahoo.com) Received: from sonic301-22.consmr.mail.gq1.yahoo.com (sonic301-22.consmr.mail.gq1.yahoo.com [98.137.64.148]) (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 did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 4SyL274dDhz3CbT for ; Sat, 23 Dec 2023 23:28:15 +0000 (UTC) (envelope-from marklmi@yahoo.com) Authentication-Results: mx1.freebsd.org; dkim=pass header.d=yahoo.com header.s=s2048 header.b=SOUwfCl9; spf=pass (mx1.freebsd.org: domain of marklmi@yahoo.com designates 98.137.64.148 as permitted sender) smtp.mailfrom=marklmi@yahoo.com; dmarc=pass (policy=reject) header.from=yahoo.com DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s2048; t=1703374093; bh=VI2JFgjxZpzWgeuuLZFLAZDRD24fNHoRG4rvwyFAuBY=; h=Subject:From:In-Reply-To:Date:Cc:References:To:From:Subject:Reply-To; b=SOUwfCl9+K8NIoigc4v5nAE9lAKNsEhOhS0MuygHTJfySCvIAUYmVfla1FrZBRi1MFCjAHxhog84o9m5Tfp9b0jSKSWmZe+1GGTaBXeDFXsLPXUvFMosjuLNG9A+ZEo847osCJXcyGOwlAzmtUeynVsO9VRLztdLhvZdbaBGDIEx9gsB48Z0CpiqaUxGz+Fi/oMiJcqmNQOVFQXyy3aqMe1R7WJgzua7Yvf6tIk0cGXP9myFqwWiBiWSoZmsfKwPPYy4wD+Li0RqZp5cEB4Uxpcqrb2/F+FiptQK4E8aRmmfEeqDN92xQhQ9ABNzzQR7pp5+xJKfLYmMIodyfuzfCA== X-SONIC-DKIM-SIGN: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s2048; t=1703374093; bh=SsJKK3xUs7cz4pKMIjypl/2qHQiBRRgRNQIlqJ33l9b=; h=X-Sonic-MF:Subject:From:Date:To:From:Subject; b=cSz9w/oHjnDQ89O36AvfBRAIKu4QeQtj/Tf+Yv3AJUbj4BR0H6SebNzjLmWBvzaxh26QoJczHzugXjRacar5Do/s9ZZGTPlqdMSExXaPRMFNMp1FZFrhASSqbbjd54heTuCsmuKfg854xEq8Y9rHoAgVsmr3xANK4PqzlUcICzFr6sNkRrkSCS+bNyW3XIZ24TQ9/ep4fR6okh65ItGxEC9vmzotWJBgYMDHHiEtD2lg41DtLbJbEnJPV+TmTf+IT+5m/5itsgIvp7V6UtpHi8Ax2+0PpI9qUHpMaKLhg7NTEOm+up+B3x5UDzx1h1R2QULGMh2sY8CRQAl2e+3fGA== X-YMail-OSG: 093yTdsVM1kOhcRVDqpyx5nr2cka4uvDqgUFV_epbrvU7EEhI9F2Xmc_vJnXhIj B.vO.G7k6EdlYVNd1LDp9avuXWHXIY9QsbTl26f5fOR8hRUSjKlyAnZmnA3Ow_b91ykax8L9EK1G 14sW_wYMHKfNKZsBuPR_VMrd_mD.qEY52ow.E0Rfal2nZ5c1TRES_ydwnHDmTC9lFpBnI_vuhFCE ZAGbNjgJen7qOJ9Pj01P72vOX52alD8r8wcc5bPkiny0xl.aMl7V7Nw96bpmHrNSdC3OGbp6iBck c3nSD03ggSRBZv930uKuXJIJ9XJNaluJha1Ayevce7Op8A7WEo9DJLK2uSByu1HLnRzWUbVrdx7N BctI9Nfrf0E_sqdsSaY_KdseFeav5TkudjgO0EeuCQwZEiP7iNwSTZBsA1NDeTDq1A6Rmx_FmN52 qZ4KnmgY2yGRwKo2jJENyGw6.D.Xobd1XxD8XQHF5r7lPu.K1f2yVf7O5PJ_M1osF8TkozqQCLKS JHk0KrE35V96UVb_AkyL0UuTpJ.7ljQhL3d9HzVMBazgjgWynVHLEicl1Mgymmt.m15sFUwqOqhR _t8cJRNrTFZhyPzW56NRx.cUaJ5jYPufE9Wk5VPN89gb3LtxS5SNvUHqgJZmINoCptZS1b2oHzqA a8jEDRLMJeBRvi89LeBUIKWPReHY8IXYMgdtb2XR06bJ8kobOgh2DfGkpKqTcCs4jE4Mk7JZjhgR dyhSMo5JQfXY9UGVCsM.AYfbwTtcZl04vTQaMuGet7QNYWVAiVMkUchBPKs5gcmRQPmWeF_yrtPx wCokASJO2JzOnWVuV3XlkypIJ4Jb_c5w3pR7Kh9dVRRjpU5sXuevPtT4EUXMaH1DQ_Dnn37V1Dco p.NXQ9aXee9YZv4evxaDRJk7dUg.6kVbFa39r6i7D0wIgwnq6suGXyhPK3qDwUQvHjLEuHtsGJ2M j_asVVCWGsK3eiJXhkP2w7e99LucuodBckzDHRcYvOuM8o6i3Az0LKBFsUXFltUOeS.4gCOP3mrW 9EvLAc60ssJZP2zuJNSiOSgZKhuHBrI9n5t41Fp5KZSbesLYjcrGc20LXiFzl97gtraZPNfEUUeH wtx1PMJZfsf985uREEaYRfX_5rNbeFum_cj6yAqSeM696iFscEjJEDO4xrnSJpDmbqRIYRSUKIHE h5_R7Lea9WJsA3UcEnVcSF9fWDYscJF4hXHN5U4uV8M8umyPgb97iY97bXg49jwLWuFyY0DP6P4d P3pXVTfjCqhoTOk4d.x6xkSfqwgOqxu0vyqmYygqdXrC22zISXz1unBSzFWZlZzQCMxa9UhAciaY A6kYrxH0n0dhLZen4MrWs4kD5dFv6ub2uMC.pJcXct1JYBdt_0A7p9r81fjR2GSHamuNCfZgGI2R jwsyfgEfDQrs1uxtyw7T4EIn3QNrjurqQWBV_LGdZUCqkpL.D3RFenaliJnTY92X7H7QRCpEICRI MlYSzYpMOZE1R_I16IaULbPt1QD9CgblOt2SWMz123wVoceW5hUNxdG91ODAfIE3JZRb4JpQy2zy M8VkWqRK0VAO.hRzz9m.LIaeB_iuxHiUdKbKwnmdDGWo_ehxfhUpyMtBsQNrCte2QMFMFBTdfpxB X9jzj3fXWPj9m_gdwHlDSxIchgQw2WRGwWUJTSzjN5mE1p5y0v6iVeDP_nHNTj_ro3hXDP6cgqiN 8tdUW5VkG.wDjZXuQ.W0RDCS1KdNwjwnsY3LWu.q4WE8XIlqIzdwB14mLs2.DcSOLby_o9ehevxx Kt6_KCwPmOudgGGXfmcXJtpxFOwFFsiNq_IAjckI1LoUyYkM3ndwpb4BkaT8oycwE8JWsb4RpCCy TX_zTw0AdR0UAz6qpJD9IucVOZ9isgHPg.SE8fwS7deTOOL2w8FY0ljbZ52KfN8KvzjUWA7H8KfB DUtHPka9HN0dwVNk21TBIDENLKnML99jiq4gelq_.F8vcxgDHEobS5q3k1c7N.94w3LF_g0Ys8GI .p3hw4B0w9.oky38fjTH_xcTi0WMmVRw6UWBeYERGOhXHez4Hbs6_bPGOQwbFH.STaYp.dHzVhTx 3QNI7IXdWx01wD34DOUNqqavkm18bqu6TtirR72bEXmK.YffzMnMSmURQHc1ohVfnDyVFL8t1Qgm 8uFfPpmOIxe2jhS6Rl_iFYEcuyHt7MpIDSuzCpb9k3uEWzX5Oir804I4SKc_I2L3guulhxoCnMk0 mbhtmQaFKI0c_yn9a4.X9aDzjd12UGhvcXY1oaUso_q8W3XHPxNmA6.s5O.Dll9usvsZtXQqsnlS 5 X-Sonic-MF: X-Sonic-ID: 36a94a90-67d1-4fd3-b9d4-15df5213e230 Received: from sonic.gate.mail.ne1.yahoo.com by sonic301.consmr.mail.gq1.yahoo.com with HTTP; Sat, 23 Dec 2023 23:28:13 +0000 Received: by hermes--production-gq1-6949d6d8f9-7dnvp (Yahoo Inc. Hermes SMTP Server) with ESMTPA ID eff594264e6ab2729fc70351e78985eb; Sat, 23 Dec 2023 23:28:11 +0000 (UTC) Content-Type: text/plain; charset=us-ascii List-Id: Porting FreeBSD to ARM processors List-Archive: https://lists.freebsd.org/archives/freebsd-arm List-Help: List-Post: List-Subscribe: List-Unsubscribe: Sender: owner-freebsd-arm@freebsd.org Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3774.300.61.1.2\)) Subject: Re: FreeBSD 14.0-RELEASE and Raspberry Pi CM4 4GB From: Mark Millard In-Reply-To: Date: Sat, 23 Dec 2023 15:27:59 -0800 Cc: Steve Bernacki , "freebsd-arm@freebsd.org" Content-Transfer-Encoding: quoted-printable Message-Id: <8CBB5E92-942E-43FA-B188-8288480B8D95@yahoo.com> References: <445940f7-e8f1-4dbc-87be-99bfd705141d@copacetic.net> <2E1B887B-EB3C-4F47-A6EE-8256149F7C84@karels.net> To: Mike Karels X-Mailer: Apple Mail (2.3774.300.61.1.2) X-Spamd-Result: default: False [-3.50 / 15.00]; NEURAL_HAM_LONG(-1.00)[-1.000]; NEURAL_HAM_MEDIUM(-1.00)[-1.000]; NEURAL_HAM_SHORT(-1.00)[-0.999]; MV_CASE(0.50)[]; DMARC_POLICY_ALLOW(-0.50)[yahoo.com,reject]; R_SPF_ALLOW(-0.20)[+ptr:yahoo.com]; R_DKIM_ALLOW(-0.20)[yahoo.com:s=s2048]; MIME_GOOD(-0.10)[text/plain]; RCPT_COUNT_THREE(0.00)[3]; FROM_HAS_DN(0.00)[]; TO_DN_EQ_ADDR_SOME(0.00)[]; TO_MATCH_ENVRCPT_SOME(0.00)[]; ARC_NA(0.00)[]; MLMMJ_DEST(0.00)[freebsd-arm@FreeBSD.org]; RCVD_IN_DNSWL_NONE(0.00)[98.137.64.148:from]; DWL_DNSWL_NONE(0.00)[yahoo.com:dkim]; ASN(0.00)[asn:36647, ipnet:98.137.64.0/20, country:US]; RWL_MAILSPIKE_POSSIBLE(0.00)[98.137.64.148:from]; FREEMAIL_FROM(0.00)[yahoo.com]; TO_DN_SOME(0.00)[]; RCVD_VIA_SMTP_AUTH(0.00)[]; MID_RHS_MATCH_FROM(0.00)[]; DKIM_TRACE(0.00)[yahoo.com:+]; RCVD_TLS_LAST(0.00)[]; FROM_EQ_ENVFROM(0.00)[]; FREEMAIL_ENVFROM(0.00)[yahoo.com]; MIME_TRACE(0.00)[0:+]; RCVD_COUNT_TWO(0.00)[2] X-Rspamd-Queue-Id: 4SyL274dDhz3CbT X-Spamd-Bar: --- On Dec 22, 2023, at 17:28, Mark Millard wrote: > On Dec 22, 2023, at 14:48, Mike Karels wrote: >=20 > On 22 Dec 2023, at 16:14, Steve Bernacki wrote: >>=20 >>> Hi Mike, >>>=20 >>> Indeed, I'm getting a lot of retransmits: >>>=20 >>> [ 5] local 172.16.200.2 port 55551 connected to 172.16.200.182 port = 5201 >>> [ ID] Interval Transfer Bitrate Retr Cwnd >>> [ 5] 0.00-1.00 sec 36.2 MBytes 304 Mbits/sec 60 9.98 = KBytes >>> [ 5] 1.00-2.00 sec 35.7 MBytes 300 Mbits/sec 143 111 = KBytes >>> [ 5] 2.00-3.00 sec 34.9 MBytes 293 Mbits/sec 141 7.13 = KBytes >>> [ 5] 3.00-4.00 sec 33.9 MBytes 284 Mbits/sec 198 99.5 = KBytes >>> [ 5] 4.00-5.00 sec 34.9 MBytes 292 Mbits/sec 167 1.43 = KBytes >>> [ 5] 5.00-6.00 sec 34.2 MBytes 287 Mbits/sec 221 2.85 = KBytes >>> [ 5] 6.00-7.00 sec 34.1 MBytes 286 Mbits/sec 169 100 = KBytes >>> [ 5] 7.00-8.00 sec 35.2 MBytes 295 Mbits/sec 159 7.13 = KBytes >>> [ 5] 8.00-9.00 sec 34.3 MBytes 287 Mbits/sec 138 4.28 = KBytes >>> [ 5] 9.00-10.00 sec 33.3 MBytes 279 Mbits/sec 182 2.85 = KBytes >>> - - - - - - - - - - - - - - - - - - - - - - - - - >>> [ ID] Interval Transfer Bitrate Retr >>> [ 5] 0.00-10.00 sec 347 MBytes 291 Mbits/sec 1578 = sender >>> [ 5] 0.00-10.00 sec 346 MBytes 291 Mbits/sec = receiver >>>=20 >>> Thanks, >>> Steve >>=20 >> One other question: are you running powerd? I booted without it, and = my >> throughput dropped to 600-640 Mb/s. Repeating the test, = retransmissions >> went down but throughput was about the same. Note, the RPi 4, and = probably >> the CM 4, boots at a lower clock frequency by default, and powerd = raises it >> under load. I'm running powerd with -M 1800, overclocking a little. >=20 > I explore here fixed frequencies: 2000 MHz, 600 MHz, 1500 MHz, 1800 = MHz > (no powerd use) Well, my later assumption about the likes of the = hw.cpufreq.sdram_freq_min being due to RPi* firmware looks to be wrong. The RPi* documentation changed from 400 MHz to 3200 MHz for RPi4B sdram_freq_min at: Before (400), Jun 8, 2021: = https://github.com/raspberrypi/documentation/blob/974995fabb184a2435a98e68= c1e728b346112f89/configuration/config-txt/overclocking.md After (3200), Jun 9, 2021: = https://github.com/raspberrypi/documentation/blob/920ff905995541f7ef1c6048= 2924a392143e9192/configuration/config-txt/overclocking.md The RPi* firmware should be setting things up to have 3200 MHz. Since that is not what FreeBSD ends up with in modern snapshots with the FreeBSD supplied config.txt , Likely FreeBSD has taken control of such. This might just be one example parameter that is overridden. FYI: the 2023-Dec-16 stable/14 snapshot that I'm using has: # strings /boot/efi/start4.elf | grep VC_BUILD_ID_ VC_BUILD_ID_USER: dom VC_BUILD_ID_TIME: 10:50:39 VC_BUILD_ID_VARIANT: start VC_BUILD_ID_TIME: Mar 17 2023 VC_BUILD_ID_BRANCH: bcm2711_2 VC_BUILD_ID_HOSTNAME: buildbot VC_BUILD_ID_PLATFORM: raspberrypi_linux VC_BUILD_ID_VERSION: 82f3750a65fadae9a38077e3c2e217ad158c8d54 (clean) Far more recent than 2021. > Based on: >=20 > # uname -apKU > FreeBSD generic 14.0-STABLE FreeBSD 14.0-STABLE #0 = stable/14-n266002-2ef9079ece5a: Sat Dec 16 08:49:23 UTC 2023 = root@releng1.nyi.freebsd.org:/usr/obj/usr/src/arm64.aarch64/sys/GENERIC = arm64 aarch6 >=20 > # more /boot/efi/config.txt=20 > [all] > arm_64bit=3D1 > dtparam=3Daudio=3Don,i2c_arm=3Don,spi=3Don > dtoverlay=3Dmmc > dtoverlay=3Ddisable-bt > device_tree_address=3D0x4000 > kernel=3Du-boot.bin >=20 > [pi4] > hdmi_safe=3D1 > armstub=3Darmstub8-gic.bin > # > over_voltage=3D6 > sdram_freq_min=3D3200 > arm_freq_min=3D2000 > force_turbo=3D1 >=20 > # sysctl dev.bcm2835_cpufreq.0.freq_settings dev.cpu.0.freq_levels = dev.cpu.0.freq > dev.bcm2835_cpufreq.0.freq_settings: 2000/-1 > dev.cpu.0.freq_levels: 2000/-1 > dev.cpu.0.freq: 2000 >=20 >=20 > # iperf3 -c 192.168.1.157 > Connecting to host 192.168.1.157, port 5201 > [ 5] local 192.168.1.159 port 52424 connected to 192.168.1.157 port = 5201 > [ ID] Interval Transfer Bitrate Retr Cwnd > [ 5] 0.00-1.00 sec 113 MBytes 948 Mbits/sec 243 328 = KBytes > [ 5] 1.00-2.00 sec 112 MBytes 941 Mbits/sec 150 18.5 = KBytes > [ 5] 2.00-3.00 sec 112 MBytes 942 Mbits/sec 149 173 = KBytes > [ 5] 3.00-4.00 sec 112 MBytes 942 Mbits/sec 150 456 = KBytes > [ 5] 4.00-5.00 sec 112 MBytes 941 Mbits/sec 159 456 = KBytes > [ 5] 5.00-6.00 sec 112 MBytes 941 Mbits/sec 160 538 = KBytes > [ 5] 6.00-7.00 sec 112 MBytes 941 Mbits/sec 143 1.43 = KBytes > [ 5] 7.00-8.00 sec 112 MBytes 942 Mbits/sec 215 167 = KBytes > [ 5] 8.00-9.00 sec 112 MBytes 941 Mbits/sec 194 580 = KBytes > [ 5] 9.00-10.00 sec 112 MBytes 941 Mbits/sec 157 552 = KBytes > - - - - - - - - - - - - - - - - - - - - - - - - - > [ ID] Interval Transfer Bitrate Retr > [ 5] 0.00-10.00 sec 1.10 GBytes 942 Mbits/sec 1720 = sender > [ 5] 0.00-10.01 sec 1.10 GBytes 941 Mbits/sec = receiver >=20 > iperf Done. >=20 >=20 > Note: The amd64 system running main [so: 15] and the RPi4B are > on the same ethernet switch. >=20 >=20 > With the 4 overclocking lines in config.txt commented out : >=20 > # sysctl dev.bcm2835_cpufreq.0.freq_settings dev.cpu.0.freq_levels = dev.cpu.0.freq > dev.bcm2835_cpufreq.0.freq_settings: 1500/-1 600/-1 > dev.cpu.0.freq_levels: 1500/-1 600/-1 > dev.cpu.0.freq: 600 >=20 > Note: the default context lacks 1800 (based on the RPi* firmware = vintage > in the snapshot). Later I show having 1800 instead of 1500. >=20 > # iperf3 -c 192.168.1.157 > Connecting to host 192.168.1.157, port 5201 > [ 5] local 192.168.1.159 port 42060 connected to 192.168.1.157 port = 5201 > [ ID] Interval Transfer Bitrate Retr Cwnd > [ 5] 0.00-1.00 sec 70.8 MBytes 594 Mbits/sec 18 195 = KBytes =20 > [ 5] 1.00-2.00 sec 73.8 MBytes 619 Mbits/sec 8 293 = KBytes =20 > [ 5] 2.00-3.00 sec 73.6 MBytes 618 Mbits/sec 19 250 = KBytes =20 > [ 5] 3.00-4.00 sec 73.6 MBytes 618 Mbits/sec 9 366 = KBytes =20 > [ 5] 4.00-5.00 sec 73.3 MBytes 615 Mbits/sec 9 447 = KBytes =20 > [ 5] 5.00-6.00 sec 73.3 MBytes 615 Mbits/sec 16 303 = KBytes =20 > [ 5] 6.00-7.00 sec 73.2 MBytes 614 Mbits/sec 0 455 = KBytes =20 > [ 5] 7.00-8.00 sec 73.6 MBytes 618 Mbits/sec 1 328 = KBytes =20 > [ 5] 8.00-9.00 sec 73.5 MBytes 616 Mbits/sec 16 246 = KBytes =20 > [ 5] 9.00-10.00 sec 73.3 MBytes 615 Mbits/sec 0 435 = KBytes =20 > - - - - - - - - - - - - - - - - - - - - - - - - - > [ ID] Interval Transfer Bitrate Retr > [ 5] 0.00-10.00 sec 732 MBytes 614 Mbits/sec 96 = sender > [ 5] 0.00-10.01 sec 732 MBytes 613 Mbits/sec = receiver >=20 > iperf Done. >=20 > Assigning 1500: >=20 > # sysctl dev.cpu.0.freq=3D1500 > dev.cpu.0.freq: 600 -> 1500 >=20 > # sysctl dev.cpu.0.freq=3D1500 > dev.cpu.0.freq: 600 -> 1500 > root@generic:~ # iperf3 -c 192.168.1.157 > Connecting to host 192.168.1.157, port 5201 > [ 5] local 192.168.1.159 port 28904 connected to 192.168.1.157 port = 5201 > [ ID] Interval Transfer Bitrate Retr Cwnd > [ 5] 0.00-1.00 sec 113 MBytes 949 Mbits/sec 4 472 = KBytes =20 > [ 5] 1.00-2.00 sec 112 MBytes 941 Mbits/sec 6 464 = KBytes =20 > [ 5] 2.00-3.00 sec 112 MBytes 941 Mbits/sec 5 452 = KBytes =20 > [ 5] 3.00-4.00 sec 112 MBytes 941 Mbits/sec 3 443 = KBytes =20 > [ 5] 4.00-5.00 sec 112 MBytes 941 Mbits/sec 4 421 = KBytes =20 > [ 5] 5.00-6.00 sec 112 MBytes 941 Mbits/sec 4 397 = KBytes =20 > [ 5] 6.00-7.00 sec 112 MBytes 942 Mbits/sec 3 378 = KBytes =20 > [ 5] 7.00-8.00 sec 112 MBytes 941 Mbits/sec 5 355 = KBytes =20 > [ 5] 8.00-9.00 sec 112 MBytes 941 Mbits/sec 2 476 = KBytes =20 > [ 5] 9.00-10.00 sec 112 MBytes 941 Mbits/sec 5 446 = KBytes =20 > - - - - - - - - - - - - - - - - - - - - - - - - - > [ ID] Interval Transfer Bitrate Retr > [ 5] 0.00-10.00 sec 1.10 GBytes 942 Mbits/sec 41 = sender > [ 5] 0.00-10.00 sec 1.10 GBytes 941 Mbits/sec = receiver >=20 >=20 >=20 > Adding arm_boost=3D1 to config.txt in order to have 1800 instead of = 1500 > (needed due to the RPi* firmware vintage in FreeBSD snapshots): >=20 > # sysctl dev.bcm2835_cpufreq.0.freq_settings dev.cpu.0.freq_levels = dev.cpu.0.freq > dev.bcm2835_cpufreq.0.freq_settings: 1800/-1 600/-1 > dev.cpu.0.freq_levels: 1800/-1 600/-1 > dev.cpu.0.freq: 600 >=20 > # sysctl dev.cpu.0.freq=3D1800 > dev.cpu.0.freq: 600 -> 1800 >=20 > # iperf3 -c 192.168.1.157 > Connecting to host 192.168.1.157, port 5201 > [ 5] local 192.168.1.159 port 27499 connected to 192.168.1.157 port = 5201 > [ ID] Interval Transfer Bitrate Retr Cwnd > [ 5] 0.00-1.00 sec 114 MBytes 952 Mbits/sec 169 104 = KBytes =20 > [ 5] 1.00-2.00 sec 112 MBytes 941 Mbits/sec 150 320 = KBytes =20 > [ 5] 2.00-3.00 sec 112 MBytes 942 Mbits/sec 157 52.8 = KBytes =20 > [ 5] 3.00-4.00 sec 112 MBytes 941 Mbits/sec 143 87.0 = KBytes =20 > [ 5] 4.00-5.00 sec 112 MBytes 941 Mbits/sec 143 121 = KBytes =20 > [ 5] 5.00-6.00 sec 112 MBytes 941 Mbits/sec 159 104 = KBytes =20 > [ 5] 6.00-7.00 sec 112 MBytes 941 Mbits/sec 138 238 = KBytes =20 > [ 5] 7.00-8.00 sec 112 MBytes 941 Mbits/sec 152 276 = KBytes =20 > [ 5] 8.00-9.00 sec 112 MBytes 941 Mbits/sec 145 115 = KBytes =20 > [ 5] 9.00-10.00 sec 112 MBytes 941 Mbits/sec 162 283 = KBytes =20 > - - - - - - - - - - - - - - - - - - - - - - - - - > [ ID] Interval Transfer Bitrate Retr > [ 5] 0.00-10.00 sec 1.10 GBytes 943 Mbits/sec 1518 = sender > [ 5] 0.00-10.00 sec 1.10 GBytes 941 Mbits/sec = receiver >=20 > iperf Done. >=20 >=20 >=20 > =46rom this it appears that the Retr counts do not seem to make > much of a difference to the Bitrate's achieved. But the arm > frequency does if 600 is involved. >=20 >=20 > My understanding is that arm_boost=3D1 was later made the default > in later vintages of the rpi* firmware. arm_boots only causes > 1800 for Rev 1.4+ . Pi 400's have 1800 available by default, at > least for modern enough RPi* firmware. >=20 > https://www.raspberrypi.com/documentation/computers/config_txt.html > is not necessarily accurate for the older RPi* firmware that FreeBSD > uses in its snapshots/releases. >=20 >> IIRC >> the standard clock is 1500 for the RPi 4. But the throughput is = about the >> same using the standard clock with powerd. >>=20 >> Mike >>=20 >>> On 12/22/2023 9:23 AM, Mike Karels wrote: >>>> On 22 Dec 2023, at 6:20, Steve Bernacki wrote: >>>>=20 >>>>> I recently purchased a RPI CM4 with 4GB and 32GB eMMC to replace = my aging FreeBSD firewall. I managed to install FreeBSD 14.0-RELEASE-p3 = on it, and both Ethernet devices (genet0 and ue0) were properly = identified. However, network throughput on my gigabit network is pretty = bad; iperf3 reports a maximum transfer speed of 291 Mbits/sec. Flashing = OpenWRT on the same hardware using the same ethernet port, I'm able to = achieve 923 Mbits/sec. >>>>>=20 >>>>> Does anyone have any suggestions on how to improve throughput = under FreeBSD? >>>>>=20 >>>>> Thank you >>>>> Steve >>>> I just tested with an RPi4 (4 GB) and 14.0 using iperf3. It looks = like I'm getting >>>> a rather variable number of retransmissions. On my first run = (client on RPi 4), >>>> I got 460 Mb/s with a lot of retransmissions, but the next couple = of runs, including >>>> one receiving, I got about 940 Mb even with some retransmissions. = The peers were >>>> fairly fast FreeBSD 13.2 and 15-current systems. Are you seeing = retransmissions? >>>>=20 >>>> I'll try to look into this, but I'm not sure when I'll get to it. >>>>=20 >>>> Mike =3D=3D=3D Mark Millard marklmi at yahoo.com