From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (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 E2A8436EAB2 for ; Tue, 14 Jul 2026 02:05:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1783994718; cv=none; b=hG8vrQwPOFI5iYEk/Fezk4ZozjBhbn8ED0KUG7tPauUzSBLiQBXSoAhxB3fpa9YbwoXDSjGoSpx25LyZ4a/EWJCjpLdiCuyZba48KpGRCc7TWAOlGWxbEMnoT96gg6NVNxWFhullCV3KcY19mBXe9DUK4qU+bEus6VbkzJlBkTE= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1783994718; c=relaxed/simple; bh=w72F5jsz33slsXtl34AhaD4E3pAfBGUR7UPWDC4z8r4=; h=Date:From:To:Cc:Subject:Message-Id:In-Reply-To:References: Mime-Version:Content-Type; b=QFXYWYcBYE7gWI5svjzeatHGkZFWQNxrJD7hYtYMkHlk8d4qnILwV7CcA86yDMtwDM2cAGMEklpIN3DeAViVCFOPKZxV8RRhjgPRRei3Eo8LLzPjocn/3Nt6nLDe6Y2ddNkCn0AONv8F+eagqGvDbD3Md+OfZyHwNDdvNrX1HBM= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b=CuDkh283; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b="CuDkh283" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 9E0DA1F000E9; Tue, 14 Jul 2026 02:05:16 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux-foundation.org; s=korg; t=1783994717; bh=ZbJ5LwUhuXRY/Z1ZqpnZgDpdVeIUjnlTCRKxmq8/Z5A=; h=Date:From:To:Cc:Subject:In-Reply-To:References; b=CuDkh283igfk/RoVjv23OF3m85eAWtwTif8W9ydD5h/jT+KADP/avJipKzjv51Pq4 jQi6k64QdnaWj+cNQglY7nm/RSDIAJ5HMqW2k/ruRNtkf2A+NPgR63OPHWYtapSQC6 YHl2w70jw8BAoUFFmifKvtE2Gh9KvAj2Um672PqE= Date: Mon, 13 Jul 2026 19:05:16 -0700 From: Andrew Morton To: Shivank Garg Cc: David Hildenbrand , Lorenzo Stoakes , Rik van Riel , "Liam R. Howlett" , Vlastimil Babka , Harry Yoo , Jann Horn , Lance Yang , Mike Rapoport , Suren Baghdasaryan , Michal Hocko , Zi Yan , Matthew Brost , Joshua Hahn , Rakie Kim , Byungchul Park , Gregory Price , Ying Huang , "Alistair Popple" , Karim Manaouil , Frank van der Linden , Kinsey Ho , Wei Xu , Bharata B Rao , David Rientjes , Dev Jain , , Subject: Re: [PATCH 0/6] mm: batch rmap walks during large folio migration Message-Id: <20260713190516.0c669b5207667c893a9c0938@linux-foundation.org> In-Reply-To: <20260712-migrate-rmap-batch-v1-0-872a734431d1@amd.com> References: <20260712-migrate-rmap-batch-v1-0-872a734431d1@amd.com> X-Mailer: Sylpheed 3.8.0beta1 (GTK+ 2.24.33; x86_64-pc-linux-gnu) Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On Sun, 12 Jul 2026 07:38:46 +0000 Shivank Garg wrote: > Performance: >=20 > AMD EPYC ZEN 3, 2-socket system (1 node per socket). > move_pages() migrating 1 GB from node 0 -> node 1, throughput > in GB/s: > batch- batch-restore + > folio vanilla restore unmap restore% restore+= unmap% > 4K 2.98=B10.09 2.95=B10.07 3.06=B10.05 -1.0% += 2.6% > 64K 6.16=B10.09 6.24=B10.08 7.80=B10.08 +1.3% +2= 6.6% > 256K 6.85=B10.06 6.85=B10.09 9.54=B10.19 +0.0% +3= 9.3% > 1M 7.06=B10.09 7.17=B10.09 9.89=B10.06 +1.5% +4= 0.1% > 2M 10.97=B10.17 10.67=B10.13 10.69=B10.15 -2.7% -= 2.6% >=20 > In plain migration, the folio copy itself dominate the cost, so these rma= p walk > savings are only partly visible end-to-end. > When the folio copy is batched-copy and offloaded to DMA engine [1], the = copy is > no longer the bottlneck and rmap-walk batching translates into much large= r gains: >=20 > This series + [1], DMA Offload on PTDMA (DCBM), 16 channels: >=20 > batch-copy > folio vanilla -offload(dcbm) dcbm+restore dcbm+restore+unmap > 4K 3.36 =B1 0.10 4.16 =B1 0.18 4.10 =B1 0.14 4.12 =B1 0.13 > 64K 6.16 =B1 0.47 9.63 =B1 0.23 10.00 =B1 0.33 14.63 =B1 0.14 > 256K 6.70 =B1 0.09 12.98 =B1 0.18 13.52 =B1 0.15 32.30 =B1 0.65 = (2.38x) > 1M 6.99 =B1 0.02 14.32 =B1 0.67 14.84 =B1 0.17 38.97 =B1 1.03 = (2.62x) > 2M 10.74 =B1 0.29 64.25 =B1 1.48 65.36 =B1 1.00 64.97 =B1 1.75 Well dang. Thanks. I'll await reviewer input on this series. Sashiko said things: https://sashiko.dev/#/patchset/20260712-migrate-rmap-batch-v1-0-872a734431= d1@amd.com