From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B9B4317E; Sun, 26 Jan 2025 12:23:32 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1737894212; cv=none; b=I0xfxA712a9D/DD5QYM6ZyqfpW3Z7jCuvcZn+Enczz0ylFy0Vg++SPc+CKgr8K+oMCcOM0xvj0TRcpdc3o19Merv8MfJ0ndrunQy3tJH1JWyK+BXvw/IWzMtSxUY6xkH4BE9277dcxPEdeFfT0DY9PNdbWYmaqw1OZ0uOdRsXOk= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1737894212; c=relaxed/simple; bh=eU0HT97H5SLajS01N1UuGCqrqWAEWv5s6UU8e0CMB88=; h=Message-ID:Subject:From:To:Cc:Date:In-Reply-To:References: Content-Type:MIME-Version; b=BP5mx0zbcWLRu/ZGWKH9IyRwWk/OzFujGVEr78WP/zikpR7DPAAJxHZuPeNans5essxJpmpEWcsWfRzicBsS1svrfoxOI/kRG8Oibyc651xxOmH5gg4iSUnoyxmUi2CS7dO5PzZ8+hFUwpluT0AYfqcdRfBjPp0AW+sSRX3piD8= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=MdKYPyBf; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="MdKYPyBf" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 83802C4CED3; Sun, 26 Jan 2025 12:23:31 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1737894212; bh=eU0HT97H5SLajS01N1UuGCqrqWAEWv5s6UU8e0CMB88=; h=Subject:From:To:Cc:Date:In-Reply-To:References:From; b=MdKYPyBfrcReYDYV0CuzWBFYJfTBbJvpVtvmr7z1USxdxxr7iBoLtYOmp/qVXAHN5 oSCXa4aj0vVjgMb9P665rtKiPjILPtPFRQCVqtchYTgiOu8zwyhye42rqGPNdGDxyh IY551aRgGq+bIUX2lASBGjo7pZeJahy7fja/1s0tCqig9lKAVj9TbQ2onQ553G8AVu nXMSnOQhAVHM0lzAtnUOZX4et1+UrTqUYalNAM/nW3B5rDG/GPxyCY/bjVD1MF9DBp 6zry6GpRzDFUD4O2NjtbZ0pymNHOqxffLDPa1gbgtPNQAYtPyCtNVPrb87X9JcggcS 3wjBWEuWFM4bQ== Message-ID: Subject: Re: [linus:master] [timekeeping] ee3283c608: will-it-scale.per_process_ops 4.8% regression From: Jeff Layton To: kernel test robot Cc: oe-lkp@lists.linux.dev, lkp@intel.com, linux-kernel@vger.kernel.org, Christian Brauner , Thomas Gleixner , John Stultz Date: Sun, 26 Jan 2025 07:23:30 -0500 In-Reply-To: <202501261527.c3bf4764-lkp@intel.com> References: <202501261527.c3bf4764-lkp@intel.com> Autocrypt: addr=jlayton@kernel.org; prefer-encrypt=mutual; keydata=mQINBE6V0TwBEADXhJg7s8wFDwBMEvn0qyhAnzFLTOCHooMZyx7XO7dAiIhDSi7G1NPxw n8jdFUQMCR/GlpozMFlSFiZXiObE7sef9rTtM68ukUyZM4pJ9l0KjQNgDJ6Fr342Htkjxu/kFV1Wv egyjnSsFt7EGoDjdKqr1TS9syJYFjagYtvWk/UfHlW09X+jOh4vYtfX7iYSx/NfqV3W1D7EDi0PqV T2h6v8i8YqsATFPwO4nuiTmL6I40ZofxVd+9wdRI4Db8yUNA4ZSP2nqLcLtFjClYRBoJvRWvsv4lm 0OX6MYPtv76hka8lW4mnRmZqqx3UtfHX/hF/zH24Gj7A6sYKYLCU3YrI2Ogiu7/ksKcl7goQjpvtV YrOOI5VGLHge0awt7bhMCTM9KAfPc+xL/ZxAMVWd3NCk5SamL2cE99UWgtvNOIYU8m6EjTLhsj8sn VluJH0/RcxEeFbnSaswVChNSGa7mXJrTR22lRL6ZPjdMgS2Km90haWPRc8Wolcz07Y2se0xpGVLEQ cDEsvv5IMmeMe1/qLZ6NaVkNuL3WOXvxaVT9USW1+/SGipO2IpKJjeDZfehlB/kpfF24+RrK+seQf CBYyUE8QJpvTZyfUHNYldXlrjO6n5MdOempLqWpfOmcGkwnyNRBR46g/jf8KnPRwXs509yAqDB6sE LZH+yWr9LQZEwARAQABtCVKZWZmIExheXRvbiA8amxheXRvbkBwb29jaGllcmVkcy5uZXQ+iQI7BB MBAgAlAhsDBgsJCAcDAgYVCAIJCgsEFgIDAQIeAQIXgAUCTpXWPAIZAQAKCRAADmhBGVaCFc65D/4 gBLNMHopQYgG/9RIM3kgFCCQV0pLv0hcg1cjr+bPI5f1PzJoOVi9s0wBDHwp8+vtHgYhM54yt43uI 7Htij0RHFL5eFqoVT4TSfAg2qlvNemJEOY0e4daljjmZM7UtmpGs9NN0r9r50W82eb5Kw5bc/r0km R/arUS2st+ecRsCnwAOj6HiURwIgfDMHGPtSkoPpu3DDp/cjcYUg3HaOJuTjtGHFH963B+f+hyQ2B rQZBBE76ErgTDJ2Db9Ey0kw7VEZ4I2nnVUY9B5dE2pJFVO5HJBMp30fUGKvwaKqYCU2iAKxdmJXRI ONb7dSde8LqZahuunPDMZyMA5+mkQl7kpIpR6kVDIiqmxzRuPeiMP7O2FCUlS2DnJnRVrHmCljLkZ Wf7ZUA22wJpepBligemtSRSbqCyZ3B48zJ8g5B8xLEntPo/NknSJaYRvfEQqGxgk5kkNWMIMDkfQO lDSXZvoxqU9wFH/9jTv1/6p8dHeGM0BsbBLMqQaqnWiVt5mG92E1zkOW69LnoozE6Le+12DsNW7Rj iR5K+27MObjXEYIW7FIvNN/TQ6U1EOsdxwB8o//Yfc3p2QqPr5uS93SDDan5ehH59BnHpguTc27Xi QQZ9EGiieCUx6Zh2ze3X2UW9YNzE15uKwkkuEIj60NvQRmEDfweYfOfPVOueC+iFifbQgSmVmZiBM YXl0b24gPGpsYXl0b25AcmVkaGF0LmNvbT6JAjgEEwECACIFAk6V0q0CGwMGCwkIBwMCBhUIAgkKC wQWAgMBAh4BAheAAAoJEAAOaEEZVoIViKUQALpvsacTMWWOd7SlPFzIYy2/fjvKlfB/Xs4YdNcf9q LqF+lk2RBUHdR/dGwZpvw/OLmnZ8TryDo2zXVJNWEEUFNc7wQpl3i78r6UU/GUY/RQmOgPhs3epQC 3PMJj4xFx+VuVcf/MXgDDdBUHaCTT793hyBeDbQuciARDJAW24Q1RCmjcwWIV/pgrlFa4lAXsmhoa c8UPc82Ijrs6ivlTweFf16VBc4nSLX5FB3ls7S5noRhm5/Zsd4PGPgIHgCZcPgkAnU1S/A/rSqf3F LpU+CbVBDvlVAnOq9gfNF+QiTlOHdZVIe4gEYAU3CUjbleywQqV02BKxPVM0C5/oVjMVx3bri75n1 TkBYGmqAXy9usCkHIsG5CBHmphv9MHmqMZQVsxvCzfnI5IO1+7MoloeeW/lxuyd0pU88dZsV/riHw 87i2GJUJtVlMl5IGBNFpqoNUoqmvRfEMeXhy/kUX4Xc03I1coZIgmwLmCSXwx9MaCPFzV/dOOrju2 xjO+2sYyB5BNtxRqUEyXglpujFZqJxxau7E0eXoYgoY9gtFGsspzFkVNntamVXEWVVgzJJr/EWW0y +jNd54MfPRqH+eCGuqlnNLktSAVz1MvVRY1dxUltSlDZT7P2bUoMorIPu8p7ZCg9dyX1+9T6Muc5d Hxf/BBP/ir+3e8JTFQBFOiLNdFtB9KZWZmIExheXRvbiA8amxheXRvbkBzYW1iYS5vcmc+iQI4BBM BAgAiBQJOldK9AhsDBgsJCAcDAgYVCAIJCgsEFgIDAQIeAQIXgAAKCRAADmhBGVaCFWgWD/0ZRi4h N9FK2BdQs9RwNnFZUr7JidAWfCrs37XrA/56olQl3ojn0fQtrP4DbTmCuh0SfMijB24psy1GnkPep naQ6VRf7Dxg/Y8muZELSOtsv2CKt3/02J1BBitrkkqmHyni5fLLYYg6fub0T/8Kwo1qGPdu1hx2BQ RERYtQ/S5d/T0cACdlzi6w8rs5f09hU9Tu4qV1JLKmBTgUWKN969HPRkxiojLQziHVyM/weR5Reu6 FZVNuVBGqBD+sfk/c98VJHjsQhYJijcsmgMb1NohAzwrBKcSGKOWJToGEO/1RkIN8tqGnYNp2G+aR 685D0chgTl1WzPRM6mFG1+n2b2RR95DxumKVpwBwdLPoCkI24JkeDJ7lXSe3uFWISstFGt0HL8Eew P8RuGC8s5h7Ct91HMNQTbjgA+Vi1foWUVXpEintAKgoywaIDlJfTZIl6Ew8ETN/7DLy8bXYgq0Xzh aKg3CnOUuGQV5/nl4OAX/3jocT5Cz/OtAiNYj5mLPeL5z2ZszjoCAH6caqsF2oLyAnLqRgDgR+wTQ T6gMhr2IRsl+cp8gPHBwQ4uZMb+X00c/Amm9VfviT+BI7B66cnC7Zv6Gvmtu2rEjWDGWPqUgccB7h dMKnKDthkA227/82tYoFiFMb/NwtgGrn5n2vwJyKN6SEoygGrNt0SI84y6hEVbQlSmVmZiBMYXl0b 24gPGpsYXl0b25AcHJpbWFyeWRhdGEuY29tPokCOQQTAQIAIwUCU4xmKQIbAwcLCQgHAwIBBhUIAg kKCwQWAgMBAh4BAheAAAoJEAAOaEEZVoIV1H0P/j4OUTwFd7BBbpoSp695qb6HqCzWMuExsp8nZjr uymMaeZbGr3OWMNEXRI1FWNHMtcMHWLP/RaDqCJil28proO+PQ/yPhsr2QqJcW4nr91tBrv/MqItu AXLYlsgXqp4BxLP67bzRJ1Bd2x0bWXurpEXY//VBOLnODqThGEcL7jouwjmnRh9FTKZfBDpFRaEfD FOXIfAkMKBa/c9TQwRpx2DPsl3eFWVCNuNGKeGsirLqCxUg5kWTxEorROppz9oU4HPicL6rRH22Ce 6nOAON2vHvhkUuO3GbffhrcsPD4DaYup4ic+DxWm+DaSSRJ+e1yJvwi6NmQ9P9UAuLG93S2MdNNbo sZ9P8k2mTOVKMc+GooI9Ve/vH8unwitwo7ORMVXhJeU6Q0X7zf3SjwDq2lBhn1DSuTsn2DbsNTiDv qrAaCvbsTsw+SZRwF85eG67eAwouYk+dnKmp1q57LDKMyzysij2oDKbcBlwB/TeX16p8+LxECv51a sjS9TInnipssssUDrHIvoTTXWcz7Y5wIngxDFwT8rPY3EggzLGfK5Zx2Q5S/N0FfmADmKknG/D8qG IcJE574D956tiUDKN4I+/g125ORR1v7bP+OIaayAvq17RP+qcAqkxc0x8iCYVCYDouDyNvWPGRhbL UO7mlBpjW9jK9e2fvZY9iw3QzIPGKtClKZWZmIExheXRvbiA8amVmZi5sYXl0b25AcHJpbWFyeWRh dGEuY29tPokCOQQTAQIAIwUCU4xmUAIbAwcLCQgHAwIBBhUIAgkKCwQWAgMBAh4BAheAAAoJEAAOa EEZVoIVzJoQALFCS6n/FHQS+hIzHIb56JbokhK0AFqoLVzLKzrnaeXhE5isWcVg0eoV2oTScIwUSU apy94if69tnUo4Q7YNt8/6yFM6hwZAxFjOXR0ciGE3Q+Z1zi49Ox51yjGMQGxlakV9ep4sV/d5a50 M+LFTmYSAFp6HY23JN9PkjVJC4PUv5DYRbOZ6Y1+TfXKBAewMVqtwT1Y+LPlfmI8dbbbuUX/kKZ5d dhV2736fgyfpslvJKYl0YifUOVy4D1G/oSycyHkJG78OvX4JKcf2kKzVvg7/Rnv+AueCfFQ6nGwPn 0P91I7TEOC4XfZ6a1K3uTp4fPPs1Wn75X7K8lzJP/p8lme40uqwAyBjk+IA5VGd+CVRiyJTpGZwA0 jwSYLyXboX+Dqm9pSYzmC9+/AE7lIgpWj+3iNisp1SWtHc4pdtQ5EU2SEz8yKvDbD0lNDbv4ljI7e flPsvN6vOrxz24mCliEco5DwhpaaSnzWnbAPXhQDWb/lUgs/JNk8dtwmvWnqCwRqElMLVisAbJmC0 BhZ/Ab4sph3EaiZfdXKhiQqSGdK4La3OTJOJYZphPdGgnkvDV9Pl1QZ0ijXQrVIy3zd6VCNaKYq7B AKidn5g/2Q8oio9Tf4XfdZ9dtwcB+bwDJFgvvDYaZ5bI3ln4V3EyW5i2NfXazz/GA/I/ZtbsigCFc 8ftCBKZWZmIExheXRvbiA8amxheXRvbkBrZXJuZWwub3JnPokCOAQTAQIAIgUCWe8u6AIbAwYLCQg HAwIGFQgCCQoLBBYCAwECHgECF4AACgkQAA5oQRlWghUuCg/+Lb/xGxZD2Q1oJVAE37uW308UpVSD 2tAMJUvFTdDbfe3zKlPDTuVsyNsALBGclPLagJ5ZTP+Vp2irAN9uwBuacBOTtmOdz4ZN2tdvNgozz uxp4CHBDVzAslUi2idy+xpsp47DWPxYFIRP3M8QG/aNW052LaPc0cedYxp8+9eiVUNpxF4SiU4i9J DfX/sn9XcfoVZIxMpCRE750zvJvcCUz9HojsrMQ1NFc7MFT1z3MOW2/RlzPcog7xvR5ENPH19ojRD CHqumUHRry+RF0lH00clzX/W8OrQJZtoBPXv9ahka/Vp7kEulcBJr1cH5Wz/WprhsIM7U9pse1f1g Yy9YbXtWctUz8uvDR7shsQxAhX3qO7DilMtuGo1v97I/Kx4gXQ52syh/w6EBny71CZrOgD6kJwPVV AaM1LRC28muq91WCFhs/nzHozpbzcheyGtMUI2Ao4K6mnY+3zIuXPygZMFr9KXE6fF7HzKxKuZMJO aEZCiDOq0anx6FmOzs5E6Jqdpo/mtI8beK+BE7Va6ni7YrQlnT0i3vaTVMTiCThbqsB20VrbMjlhp f8lfK1XVNbRq/R7GZ9zHESlsa35ha60yd/j3pu5hT2xyy8krV8vGhHvnJ1XRMJBAB/UYb6FyC7S+m QZIQXVeAA+smfTT0tDrisj1U5x6ZB9b3nBg65kc= Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable User-Agent: Evolution 3.54.3 (3.54.3-1.fc41) Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 On Sun, 2025-01-26 at 16:25 +0800, kernel test robot wrote: > hi, Jeff Layton, >=20 >=20 > we make out below report just FYI since the results is stable in our test= s. > we don't have enough knowledge if this regression is due to align. >=20 > +static __cacheline_aligned_in_smp atomic64_t mg_floor; >=20 > if low value, please just ignore. thanks a lot. >=20 I think this is more or less the same regression we measured with the pipe1 test during the rc phase: https://lore.kernel.org/linux-fsdevel/202410091041.6f5d221e-oliver.sang= @intel.com/ This test just testing how fast it can do writes into a file in /tmp without doing anything else in between. I don't think there is much we can do to mitigate the perf hit here, as there is a basic cost to fetching and handling the floor and ctime consistently. >=20 > Hello, >=20 > kernel test robot noticed a 4.8% regression of will-it-scale.per_process_= ops on: >=20 >=20 > commit: ee3283c608dfa21251b0821d7bb198c7ae3189f6 ("timekeeping: Add inter= faces for handling timestamps with a floor value") That patch just adds two new interfaces, but the first caller of them wasn't added until a later patch. Are you sure that bisect landed in the right place? > https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git master >=20 > [test failed on linus/master bc8198dc7ebc492ec3e9fa1617dcdfbe98e73b1= 7] > [test failed on linux-next/master 5ffa57f6eecefababb8cbe327222ef171943b18= 3] >=20 > testcase: will-it-scale > config: x86_64-rhel-9.4 > compiler: gcc-12 > test machine: 104 threads 2 sockets (Skylake) with 192G memory > parameters: >=20 > nr_task: 100% > mode: process > test: pwrite1 > cpufreq_governor: performance >=20 >=20 > If you fix the issue in a separate patch/commit (i.e. not just a new vers= ion of > the same patch/commit), kindly add following tags > > Reported-by: kernel test robot > > Closes: https://lore.kernel.org/oe-lkp/202501261527.c3bf4764-lkp@intel.= com >=20 >=20 > Details are as below: > -------------------------------------------------------------------------= -------------------------> >=20 >=20 > The kernel config and materials to reproduce are available at: > https://download.01.org/0day-ci/archive/20250126/202501261527.c3bf4764-lk= p@intel.com >=20 > =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D > compiler/cpufreq_governor/kconfig/mode/nr_task/rootfs/tbox_group/test/tes= tcase: > gcc-12/performance/x86_64-rhel-9.4/process/100%/debian-12-x86_64-202402= 06.cgz/lkp-skl-fpga01/pwrite1/will-it-scale >=20 > commit:=20 > v6.12-rc2 > ee3283c608 ("timekeeping: Add interfaces for handling timestamps with a= floor value") >=20 > v6.12-rc2 ee3283c608dfa21251b0821d7bb=20 > ---------------- ---------------------------=20 > %stddev %change %stddev > \ | \ =20 > 57550068 -4.8% 54794800 will-it-scale.104.processes > 553365 -4.8% 526872 will-it-scale.per_process_o= ps > 57550068 -4.8% 54794800 will-it-scale.workload > 43.00 =C2=B1 27% -60.0% 17.20 =C2=B1 27% perf-c2c.DRAM.loc= al > 251.20 =C2=B1 23% -57.5% 106.80 =C2=B1 16% perf-c2c.DRAM.rem= ote > 520.00 =C2=B1 33% -70.3% 154.20 =C2=B1 13% perf-c2c.HITM.loc= al > 218.50 =C2=B1 25% -55.2% 97.80 =C2=B1 18% perf-c2c.HITM.rem= ote > 0.03 =C2=B1 14% +48.4% 0.04 =C2=B1 9% perf-sched.sch_de= lay.avg.ms.worker_thread.kthread.ret_from_fork.ret_from_fork_asm > 4.18 =C2=B1 4% +21.5% 5.08 perf-sched.sch_delay.m= ax.ms.worker_thread.kthread.ret_from_fork.ret_from_fork_asm > 653.70 =C2=B1 5% +50.5% 983.70 =C2=B1 7% perf-sched.wait_a= nd_delay.count.__cond_resched.generic_perform_write.shmem_file_write_iter.v= fs_write.__x64_sys_pwrite64 > 913.40 =C2=B1 6% -24.8% 686.80 =C2=B1 7% perf-sched.wait_a= nd_delay.count.__cond_resched.shmem_get_folio_gfp.shmem_write_begin.generic= _perform_write.shmem_file_write_iter > 1.29 =C2=B1 81% +42618.3% 552.09 =C2=B1 74% perf-sched.wait_t= ime.avg.ms.devkmsg_read.vfs_read.ksys_read.do_syscall_64 > 2.58 =C2=B1 81% +65403.1% 1692 =C2=B1 72% perf-sched.wait_t= ime.max.ms.devkmsg_read.vfs_read.ksys_read.do_syscall_64 > 1.721e+10 -4.8% 1.639e+10 perf-stat.i.branch-instruct= ions > 1.66 +0.1 1.72 perf-stat.i.branch-miss-rat= e% > 2.852e+08 -1.2% 2.818e+08 perf-stat.i.branch-misses > 3.29 +4.9% 3.45 perf-stat.i.cpi > 8.743e+10 -4.8% 8.327e+10 perf-stat.i.instructions > 0.30 -4.7% 0.29 perf-stat.i.ipc > 1.66 +0.1 1.72 perf-stat.overall.branch-mi= ss-rate% > 3.29 +4.9% 3.45 perf-stat.overall.cpi > 0.30 -4.7% 0.29 perf-stat.overall.ipc > 1.715e+10 -4.8% 1.634e+10 perf-stat.ps.branch-instruc= tions > 2.842e+08 -1.2% 2.809e+08 perf-stat.ps.branch-misses > 8.714e+10 -4.8% 8.3e+10 perf-stat.ps.instructions > 2.632e+13 -4.7% 2.508e+13 perf-stat.total.instruction= s > 10.62 -4.8 5.81 perf-profile.calltrace.cycl= es-pp.shmem_write_begin.generic_perform_write.shmem_file_write_iter.vfs_wri= te.__x64_sys_pwrite64 > 8.89 =C2=B1 2% -4.6 4.25 perf-profile.calltrace= .cycles-pp.shmem_get_folio_gfp.shmem_write_begin.generic_perform_write.shme= m_file_write_iter.vfs_write > 5.98 =C2=B1 3% -4.2 1.79 =C2=B1 2% perf-profile.call= trace.cycles-pp.filemap_get_entry.shmem_get_folio_gfp.shmem_write_begin.gen= eric_perform_write.shmem_file_write_iter > 13.24 -1.4 11.88 perf-profile.calltrace.cycl= es-pp.entry_SYSRETQ_unsafe_stack.__libc_pwrite > 16.62 -1.2 15.42 perf-profile.calltrace.cycl= es-pp.syscall_return_via_sysret.__libc_pwrite > 2.90 -1.2 1.74 perf-profile.calltrace.cycl= es-pp.file_update_time.shmem_file_write_iter.vfs_write.__x64_sys_pwrite64.d= o_syscall_64 > 2.38 =C2=B1 2% -0.9 1.44 perf-profile.calltrace= .cycles-pp.inode_needs_update_time.file_update_time.shmem_file_write_iter.v= fs_write.__x64_sys_pwrite64 > 1.68 =C2=B1 2% -0.9 0.79 perf-profile.calltrace= .cycles-pp.folio_unlock.shmem_write_end.generic_perform_write.shmem_file_wr= ite_iter.vfs_write > 1.42 =C2=B1 13% -0.8 0.64 =C2=B1 3% perf-profile.call= trace.cycles-pp.file_remove_privs_flags.shmem_file_write_iter.vfs_write.__x= 64_sys_pwrite64.do_syscall_64 > 5.69 -0.7 4.99 =C2=B1 2% perf-profile.calltrace= .cycles-pp.shmem_write_end.generic_perform_write.shmem_file_write_iter.vfs_= write.__x64_sys_pwrite64 > 6.91 -0.4 6.53 perf-profile.calltrace.cycl= es-pp.entry_SYSCALL_64.__libc_pwrite > 1.23 =C2=B1 2% -0.2 1.01 perf-profile.calltrace= .cycles-pp.fdget.__x64_sys_pwrite64.do_syscall_64.entry_SYSCALL_64_after_hw= frame.__libc_pwrite > 1.41 -0.2 1.26 perf-profile.calltrace.cycl= es-pp.syscall_exit_to_user_mode.do_syscall_64.entry_SYSCALL_64_after_hwfram= e.__libc_pwrite > 0.87 -0.1 0.79 =C2=B1 2% perf-profile.calltrace= .cycles-pp.up_write.shmem_file_write_iter.vfs_write.__x64_sys_pwrite64.do_s= yscall_64 > 0.79 =C2=B1 2% -0.1 0.74 perf-profile.calltrace= .cycles-pp.noop_dirty_folio.shmem_write_end.generic_perform_write.shmem_fil= e_write_iter.vfs_write > 1.15 =C2=B1 2% +0.1 1.26 =C2=B1 2% perf-profile.call= trace.cycles-pp.down_write.shmem_file_write_iter.vfs_write.__x64_sys_pwrite= 64.do_syscall_64 > 0.54 +0.2 0.73 perf-profile.calltrace.cycl= es-pp.folio_mark_accessed.shmem_get_folio_gfp.shmem_write_begin.generic_per= form_write.shmem_file_write_iter > 0.82 =C2=B1 2% +0.4 1.26 =C2=B1 5% perf-profile.call= trace.cycles-pp.folio_mark_dirty.shmem_write_end.generic_perform_write.shme= m_file_write_iter.vfs_write > 0.00 +0.7 0.67 perf-profile.calltrace.cycl= es-pp.balance_dirty_pages_ratelimited_flags.generic_perform_write.shmem_fil= e_write_iter.vfs_write.__x64_sys_pwrite64 > 2.10 +1.2 3.35 perf-profile.calltrace.cycl= es-pp.fault_in_readable.fault_in_iov_iter_readable.generic_perform_write.sh= mem_file_write_iter.vfs_write > 2.36 +1.3 3.69 perf-profile.calltrace.cycl= es-pp.fault_in_iov_iter_readable.generic_perform_write.shmem_file_write_ite= r.vfs_write.__x64_sys_pwrite64 > 46.08 +2.8 48.91 perf-profile.calltrace.cycl= es-pp.__x64_sys_pwrite64.do_syscall_64.entry_SYSCALL_64_after_hwframe.__lib= c_pwrite > 43.76 +3.3 47.02 perf-profile.calltrace.cycl= es-pp.vfs_write.__x64_sys_pwrite64.do_syscall_64.entry_SYSCALL_64_after_hwf= rame.__libc_pwrite > 58.89 +3.4 62.32 perf-profile.calltrace.cycl= es-pp.entry_SYSCALL_64_after_hwframe.__libc_pwrite > 38.55 +3.5 42.07 perf-profile.calltrace.cycl= es-pp.shmem_file_write_iter.vfs_write.__x64_sys_pwrite64.do_syscall_64.entr= y_SYSCALL_64_after_hwframe > 49.37 +3.7 53.09 perf-profile.calltrace.cycl= es-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__libc_pwrite > 29.41 +5.6 34.99 perf-profile.calltrace.cycl= es-pp.generic_perform_write.shmem_file_write_iter.vfs_write.__x64_sys_pwrit= e64.do_syscall_64 > 4.60 +7.7 12.30 perf-profile.calltrace.cycl= es-pp.rep_movs_alternative.copy_page_from_iter_atomic.generic_perform_write= .shmem_file_write_iter.vfs_write > 6.68 +10.3 16.96 perf-profile.calltrace.cycl= es-pp.copy_page_from_iter_atomic.generic_perform_write.shmem_file_write_ite= r.vfs_write.__x64_sys_pwrite64 > 10.69 -4.8 5.86 perf-profile.children.cycle= s-pp.shmem_write_begin > 8.99 =C2=B1 2% -4.6 4.35 perf-profile.children.= cycles-pp.shmem_get_folio_gfp > 6.00 =C2=B1 3% -4.2 1.81 =C2=B1 2% perf-profile.chil= dren.cycles-pp.filemap_get_entry > 14.20 -1.4 12.77 perf-profile.children.cycle= s-pp.entry_SYSRETQ_unsafe_stack > 1.62 =C2=B1 9% -1.3 0.37 =C2=B1 5% perf-profile.chil= dren.cycles-pp.xas_load > 16.76 -1.2 15.54 perf-profile.children.cycle= s-pp.syscall_return_via_sysret > 2.96 -1.2 1.79 perf-profile.children.cycle= s-pp.file_update_time > 2.47 =C2=B1 2% -1.0 1.51 perf-profile.children.= cycles-pp.inode_needs_update_time > 1.69 =C2=B1 2% -0.9 0.79 perf-profile.children.= cycles-pp.folio_unlock > 1.44 =C2=B1 13% -0.8 0.65 =C2=B1 3% perf-profile.chil= dren.cycles-pp.file_remove_privs_flags > 5.94 -0.7 5.24 =C2=B1 2% perf-profile.children.= cycles-pp.shmem_write_end > 7.17 -0.5 6.67 perf-profile.children.cycle= s-pp.entry_SYSCALL_64 > 1.77 -0.4 1.42 perf-profile.children.cycle= s-pp.__cond_resched > 0.67 =C2=B1 3% -0.3 0.41 perf-profile.children.= cycles-pp.ktime_get_coarse_real_ts64 > 1.68 =C2=B1 9% -0.2 1.42 =C2=B1 4% perf-profile.chil= dren.cycles-pp.generic_write_checks > 1.25 -0.2 1.03 perf-profile.children.cycle= s-pp.fdget > 1.44 -0.2 1.28 perf-profile.children.cycle= s-pp.syscall_exit_to_user_mode > 0.38 =C2=B1 3% -0.1 0.27 =C2=B1 2% perf-profile.chil= dren.cycles-pp.timestamp_truncate > 0.37 =C2=B1 4% -0.1 0.26 perf-profile.children.= cycles-pp.rw_verify_area > 0.69 =C2=B1 3% -0.1 0.60 perf-profile.children.= cycles-pp.rcu_all_qs > 0.90 -0.1 0.82 =C2=B1 2% perf-profile.children.= cycles-pp.up_write > 0.23 =C2=B1 5% -0.1 0.16 =C2=B1 2% perf-profile.chil= dren.cycles-pp.xas_start > 0.85 -0.1 0.80 perf-profile.children.cycle= s-pp.noop_dirty_folio > 0.23 =C2=B1 4% -0.0 0.20 =C2=B1 3% perf-profile.chil= dren.cycles-pp.x64_sys_call > 0.15 =C2=B1 5% -0.0 0.11 =C2=B1 4% perf-profile.chil= dren.cycles-pp.security_file_permission > 0.28 =C2=B1 2% -0.0 0.26 perf-profile.children.= cycles-pp.syscall_exit_to_user_mode_prepare > 0.17 =C2=B1 5% +0.0 0.19 =C2=B1 3% perf-profile.chil= dren.cycles-pp.sched_tick > 1.18 +0.1 1.28 =C2=B1 2% perf-profile.children.= cycles-pp.down_write > 0.35 =C2=B1 3% +0.1 0.48 =C2=B1 6% perf-profile.chil= dren.cycles-pp.folio_mapping > 0.50 =C2=B1 2% +0.2 0.69 perf-profile.children.= cycles-pp.balance_dirty_pages_ratelimited_flags > 0.55 =C2=B1 2% +0.2 0.75 perf-profile.children.= cycles-pp.folio_mark_accessed > 1.75 =C2=B1 2% +0.4 2.10 =C2=B1 2% perf-profile.chil= dren.cycles-pp.entry_SYSCALL_64_safe_stack > 0.90 +0.5 1.36 =C2=B1 5% perf-profile.children.= cycles-pp.folio_mark_dirty > 2.17 +1.2 3.41 perf-profile.children.cycle= s-pp.fault_in_readable > 2.40 +1.4 3.75 perf-profile.children.cycle= s-pp.fault_in_iov_iter_readable > 46.10 +2.8 48.93 perf-profile.children.cycle= s-pp.__x64_sys_pwrite64 > 43.86 +3.2 47.10 perf-profile.children.cycle= s-pp.vfs_write > 39.00 +3.4 42.41 perf-profile.children.cycle= s-pp.shmem_file_write_iter > 59.15 +3.4 62.56 perf-profile.children.cycle= s-pp.entry_SYSCALL_64_after_hwframe > 49.50 +3.7 53.21 perf-profile.children.cycle= s-pp.do_syscall_64 > 29.56 +5.6 35.14 perf-profile.children.cycle= s-pp.generic_perform_write > 4.74 +8.3 13.02 perf-profile.children.cycle= s-pp.rep_movs_alternative > 6.85 +9.6 16.44 perf-profile.children.cycle= s-pp.copy_page_from_iter_atomic > 4.34 =C2=B1 2% -2.9 1.43 =C2=B1 2% perf-profile.self= .cycles-pp.filemap_get_entry > 14.06 -1.4 12.65 perf-profile.self.cycles-pp= .entry_SYSRETQ_unsafe_stack > 16.74 -1.2 15.53 perf-profile.self.cycles-pp= .syscall_return_via_sysret > 1.39 =C2=B1 10% -1.2 0.21 =C2=B1 8% perf-profile.self= .cycles-pp.xas_load > 1.49 =C2=B1 3% -0.9 0.58 perf-profile.self.cycl= es-pp.folio_unlock > 2.72 =C2=B1 2% -0.9 1.83 perf-profile.self.cycl= es-pp.__libc_pwrite > 1.42 =C2=B1 13% -0.8 0.61 =C2=B1 3% perf-profile.self= .cycles-pp.file_remove_privs_flags > 1.42 -0.6 0.83 perf-profile.self.cycles-pp= .inode_needs_update_time > 1.92 =C2=B1 5% -0.5 1.44 perf-profile.self.cycl= es-pp.shmem_get_folio_gfp > 6.24 -0.4 5.81 perf-profile.self.cycles-pp= .entry_SYSCALL_64 > 9.82 -0.3 9.50 perf-profile.self.cycles-pp= .entry_SYSCALL_64_after_hwframe > 0.64 =C2=B1 3% -0.3 0.38 perf-profile.self.cycl= es-pp.ktime_get_coarse_real_ts64 > 1.06 =C2=B1 2% -0.3 0.79 perf-profile.self.cycl= es-pp.__cond_resched > 1.74 =C2=B1 5% -0.2 1.52 =C2=B1 2% perf-profile.self= .cycles-pp.shmem_write_begin > 1.24 =C2=B1 2% -0.2 1.03 perf-profile.self.cycl= es-pp.fdget > 0.45 =C2=B1 3% -0.2 0.25 perf-profile.self.cycl= es-pp.file_update_time > 0.98 =C2=B1 2% -0.2 0.79 =C2=B1 2% perf-profile.self= .cycles-pp.__x64_sys_pwrite64 > 2.73 =C2=B1 2% -0.2 2.54 =C2=B1 2% perf-profile.self= .cycles-pp.shmem_write_end > 0.72 =C2=B1 5% -0.1 0.58 =C2=B1 4% perf-profile.self= .cycles-pp.generic_write_checks > 1.14 -0.1 1.02 perf-profile.self.cycles-pp= .syscall_exit_to_user_mode > 0.36 =C2=B1 3% -0.1 0.25 =C2=B1 2% perf-profile.self= .cycles-pp.timestamp_truncate > 0.23 =C2=B1 4% -0.1 0.15 =C2=B1 2% perf-profile.self= .cycles-pp.rw_verify_area > 0.60 =C2=B1 3% -0.1 0.53 perf-profile.self.cycl= es-pp.rcu_all_qs > 0.81 -0.1 0.74 perf-profile.self.cycles-pp= .noop_dirty_folio > 0.20 =C2=B1 4% -0.1 0.14 =C2=B1 2% perf-profile.self= .cycles-pp.xas_start > 0.81 -0.1 0.75 =C2=B1 2% perf-profile.self.cycl= es-pp.up_write > 0.21 =C2=B1 3% -0.0 0.18 =C2=B1 3% perf-profile.self= .cycles-pp.x64_sys_call > 0.26 =C2=B1 2% -0.0 0.23 =C2=B1 2% perf-profile.self= .cycles-pp.syscall_exit_to_user_mode_prepare > 0.12 =C2=B1 6% -0.0 0.09 =C2=B1 4% perf-profile.self= .cycles-pp.security_file_permission > 0.21 =C2=B1 4% +0.0 0.24 perf-profile.self.cycl= es-pp.testcase > 0.77 =C2=B1 2% +0.0 0.82 =C2=B1 3% perf-profile.self= .cycles-pp.down_write > 0.24 =C2=B1 3% +0.1 0.36 perf-profile.self.cycl= es-pp.fault_in_iov_iter_readable > 0.30 =C2=B1 3% +0.1 0.43 =C2=B1 6% perf-profile.self= .cycles-pp.folio_mapping > 0.35 =C2=B1 2% +0.2 0.54 perf-profile.self.cycl= es-pp.balance_dirty_pages_ratelimited_flags > 2.74 +0.2 2.93 =C2=B1 2% perf-profile.self.cycl= es-pp.generic_perform_write > 0.52 +0.2 0.72 perf-profile.self.cycles-pp= .folio_mark_accessed > 0.55 =C2=B1 2% +0.3 0.87 =C2=B1 5% perf-profile.self= .cycles-pp.folio_mark_dirty > 0.56 +0.5 1.10 =C2=B1 4% perf-profile.self.cycl= es-pp.entry_SYSCALL_64_safe_stack > 1.48 =C2=B1 2% +1.1 2.55 =C2=B1 4% perf-profile.self= .cycles-pp.do_syscall_64 > 2.14 +1.2 3.35 perf-profile.self.cycles-pp= .fault_in_readable > 2.20 +1.3 3.51 =C2=B1 2% perf-profile.self.cycl= es-pp.copy_page_from_iter_atomic > 4.59 +8.2 12.80 perf-profile.self.cycles-pp= .rep_movs_alternative >=20 >=20 >=20 >=20 > Disclaimer: > Results have been estimated based on internal Intel analysis and are prov= ided > for informational purposes only. Any difference in system hardware or sof= tware > design or configuration may affect actual performance. >=20 >=20 --=20 Jeff Layton