From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=18.9.28.11 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1795188082; b=LmGP0GlzaDdpADZXT7skD17Q9twzEis5sF7lNUpS/JmKSJyAA97jDQGDyOLddJZgEqsj OheINObx6d8k+B5tFLdJedRY/nao/7zrgwFhMj9UB30CBOFfftrgQ5F7W0OsWy+xT4lD6 hxewyGkUDCMF5O/ZdjemUo6c3rvqFmXosi+7Y3Y9UEvI2IlXyS7Wi/d9ZVwakf+Vyzy1G zr9OyGOxA8EFoj9Qkb91F8xxNwZa4LsTpNfWIxB89PwPnBYaJLpvpirTNt9U1eVCc7RA9 8IuU3nnstAoaLvMjfKrNKlRgMgReUdkQgkywyz/FBnaAFdTDngmj4pp7Oq91FrMIPIw== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1795188082; h=DMARC-Filter:Received:DKIM-Signature:Received:Date:From:To:Subject: Message-ID:MIME-Version:Content-Type:Content-Disposition; bh=3h+ClZ2tT+UpcGVTNUCNAoAlK43AS0JSLWnhS6ZNLE8=; b=3Nsbsr4a8Fqcw/2VCQN1nUpvo4R7rMwOIRSijMkTVhh+Imza9hk5oS4DKPobBfZ+elLW X2Fx2yWHO4UKTa75m/ZQKOIREm8vHq9YCt4LuDv+IwTY5JgvU7W/t9PBSsmgepXSS2tXK 9zo0bX2PNFizxHtmoYG9nRyiHAxTmLQA1Z7dhaYC3qaSDcb7BEpdsTK0FvTFkCdkvnpSR gqOj2/SV+EZ+Bw7T3Nc4s4ZjA7B6mTSZK9rnDm6Sy+B+7ItKZMv2Vxjy26KbXPWPfU+bS sYydZreEw1ggNOIoZJmwwQJbLL4Ghbv0RtAGegH1xFrrMVHMXHeWshVqSMkrMvoY3zQ== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=mit.edu; spf=pass smtp.mailfrom=mit.edu; dkim=pass header.d=mit.edu header.i=@mit.edu header.a=rsa-sha256 header.s=outgoing header.b=XWu3fLwX; arc=none smtp.remote-ip=18.9.28.11 Received: from outgoing.mit.edu (outgoing-auth-1.mit.edu [18.9.28.11]) (using TLSv1.2 with cipher ECDHE-ECDSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 12C63606A320 for ; Fri, 20 Nov 2026 15:21:21 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 12C63606A320 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=mit.edu Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=mit.edu Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key, unprotected) header.d=mit.edu header.i=@mit.edu header.a=rsa-sha256 header.s=outgoing header.b=XWu3fLwX Received: from macsyma.thunk.org (c-73-9-28-129.hsd1.il.comcast.net [73.9.28.129]) (authenticated bits=0) (User authenticated as tytso@ATHENA.MIT.EDU) by outgoing.mit.edu (8.14.7/8.12.4) with ESMTP id 6AKFLBvk022687 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Fri, 20 Nov 2026 10:21:12 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=mit.edu; s=outgoing; t=1795188073; bh=3h+ClZ2tT+UpcGVTNUCNAoAlK43AS0JSLWnhS6ZNLE8=; h=Date:From:Subject:Message-ID:MIME-Version:Content-Type; b=XWu3fLwX4JIk1BcYF9eUjyZA67yBKv2DdTOJitvuzoBYAnvaVERH8cb2PdD+8pUsg ggwlMAHzMwuYExvQrFq68RloNHK5EZ8ZTIwAxTjN7iokeQJRtaI/zc/q7wI7toMykz kKuZ6RTMOlzI9ZStLrgn4ZDGAes9HrGO/LmeMQWkOliTN7imYKuu3orVXG5b3yNxBQ eMw5/rh0vcguslaz57r1zooEywMdKp9U0ZAWqAUvA7MPpS7sp0dpb2sAu3P8pnZ5Ts bcLjE5Lf2ph4MTahr9E6dyOwZdQ5kuXuTGYYiIKqtNrTD89lkaDK+WPzGOxQE0XnzN nnbg0kwjONq8w== Received: by macsyma.thunk.org (Postfix, from userid 15806) id 39014288DCDD; Fri, 20 Nov 2026 10:21:11 -0500 (EST) Date: Fri, 20 Nov 2026 10:21:11 -0500 From: "Theodore Tso" To: Ext4 Developers List Subject: Implementation plan for a dedicated block cache for ext4 Message-ID: X-Mailing-List: linux-ext4@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline As I had discussed on the ext4 conference call, I've been toying with the idea of creating a dedicated block cache for ext4. With the help of AI --- I won't say AI Overlords; I'm conficed the AI Intern, or perhaps AI PFY is more appropriate :-) --- I've come up with a high-level design and implementation doc: https://github.com/tytso/ext4-artifacts/blob/main/jbuf/implementation-plan.md I'd appreciate comments. I'd suggest reading sections 1 (Goals), 3 (Architectural Decisions and Hazards), and 7 (Block-Device Superblock Coherency) first. Nothing here is locked down. One of the things that I am still unsure about is how nasty including support for data=journal mode is going to be, and whether we will want to drop support before proceeding. I expect we'll be doing several rounds of design reviews before I ask the AI to create the patch series. For people who prefer to look at code first, feel free to wait until later. But I do think this is one place where debating things at the detail level of the implementation plan is more efficient than having reading throguh 37 iterations of a 20 patch series. :-) - Ted