From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-2.2 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_SANE_1 autolearn=no autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2F048C43141 for ; Fri, 15 Nov 2019 07:29:41 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 11DB12073A for ; Fri, 15 Nov 2019 07:29:41 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1727257AbfKOH3k (ORCPT ); Fri, 15 Nov 2019 02:29:40 -0500 Received: from mx2.suse.de ([195.135.220.15]:51820 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726444AbfKOH3j (ORCPT ); Fri, 15 Nov 2019 02:29:39 -0500 X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (unknown [195.135.220.254]) by mx1.suse.de (Postfix) with ESMTP id C6613AD05; Fri, 15 Nov 2019 07:29:36 +0000 (UTC) Subject: Re: [PATCH RFC 3/5] blk-mq: Facilitate a shared tags per tagset To: Bart Van Assche , John Garry , "axboe@kernel.dk" , "jejb@linux.ibm.com" , "martin.petersen@oracle.com" Cc: "linux-block@vger.kernel.org" , "linux-kernel@vger.kernel.org" , "linux-scsi@vger.kernel.org" , "ming.lei@redhat.com" , "hare@suse.com" , "chenxiang (M)" References: <1573652209-163505-1-git-send-email-john.garry@huawei.com> <1573652209-163505-4-git-send-email-john.garry@huawei.com> <32880159-86e8-5c48-1532-181fdea0df96@suse.de> <2cbf591c-8284-8499-7804-e7078cf274d2@huawei.com> <02056612-a958-7b05-3c54-bb2fa69bc493@suse.de> <42b0bcd9-f147-76eb-dfce-270f77bca818@suse.de> <89cd1985-39c7-2965-d25b-2ee2c183d057@huawei.com> From: Hannes Reinecke Openpgp: preference=signencrypt Autocrypt: addr=hare@suse.de; prefer-encrypt=mutual; keydata= mQINBE6KyREBEACwRN6XKClPtxPiABx5GW+Yr1snfhjzExxkTYaINHsWHlsLg13kiemsS6o7 qrc+XP8FmhcnCOts9e2jxZxtmpB652lxRB9jZE40mcSLvYLM7S6aH0WXKn8bOqpqOGJiY2bc 6qz6rJuqkOx3YNuUgiAxjuoYauEl8dg4bzex3KGkGRuxzRlC8APjHlwmsr+ETxOLBfUoRNuE b4nUtaseMPkNDwM4L9+n9cxpGbdwX0XwKFhlQMbG3rWA3YqQYWj1erKIPpgpfM64hwsdk9zZ QO1krgfULH4poPQFpl2+yVeEMXtsSou915jn/51rBelXeLq+cjuK5+B/JZUXPnNDoxOG3j3V VSZxkxLJ8RO1YamqZZbVP6jhDQ/bLcAI3EfjVbxhw9KWrh8MxTcmyJPn3QMMEp3wpVX9nSOQ tzG72Up/Py67VQe0x8fqmu7R4MmddSbyqgHrab/Nu+ak6g2RRn3QHXAQ7PQUq55BDtj85hd9 W2iBiROhkZ/R+Q14cJkWhzaThN1sZ1zsfBNW0Im8OVn/J8bQUaS0a/NhpXJWv6J1ttkX3S0c QUratRfX4D1viAwNgoS0Joq7xIQD+CfJTax7pPn9rT////hSqJYUoMXkEz5IcO+hptCH1HF3 qz77aA5njEBQrDRlslUBkCZ5P+QvZgJDy0C3xRGdg6ZVXEXJOQARAQABtCpIYW5uZXMgUmVp bmVja2UgKFN1U0UgTGFicykgPGhhcmVAc3VzZS5kZT6JAkEEEwECACsCGwMFCRLMAwAGCwkI BwMCBhUIAgkKCwQWAgMBAh4BAheABQJOisquAhkBAAoJEGz4yi9OyKjPOHoQAJLeLvr6JNHx GPcHXaJLHQiinz2QP0/wtsT8+hE26dLzxb7hgxLafj9XlAXOG3FhGd+ySlQ5wSbbjdxNjgsq FIjqQ88/Lk1NfnqG5aUTPmhEF+PzkPogEV7Pm5Q17ap22VK623MPaltEba+ly6/pGOODbKBH ak3gqa7Gro5YCQzNU0QVtMpWyeGF7xQK76DY/atvAtuVPBJHER+RPIF7iv5J3/GFIfdrM+wS BubFVDOibgM7UBnpa7aohZ9RgPkzJpzECsbmbttxYaiv8+EOwark4VjvOne8dRaj50qeyJH6 HLpBXZDJH5ZcYJPMgunghSqghgfuUsd5fHmjFr3hDb5EoqAfgiRMSDom7wLZ9TGtT6viDldv hfWaIOD5UhpNYxfNgH6Y102gtMmN4o2P6g3UbZK1diH13s9DA5vI2mO2krGz2c5BOBmcctE5 iS+JWiCizOqia5Op+B/tUNye/YIXSC4oMR++Fgt30OEafB8twxydMAE3HmY+foawCpGq06yM vAguLzvm7f6wAPesDAO9vxRNC5y7JeN4Kytl561ciTICmBR80Pdgs/Obj2DwM6dvHquQbQrU Op4XtD3eGUW4qgD99DrMXqCcSXX/uay9kOG+fQBfK39jkPKZEuEV2QdpE4Pry36SUGfohSNq xXW+bMc6P+irTT39VWFUJMcSuQINBE6KyREBEACvEJggkGC42huFAqJcOcLqnjK83t4TVwEn JRisbY/VdeZIHTGtcGLqsALDzk+bEAcZapguzfp7cySzvuR6Hyq7hKEjEHAZmI/3IDc9nbdh EgdCiFatah0XZ/p4vp7KAelYqbv8YF/ORLylAdLh9rzLR6yHFqVaR4WL4pl4kEWwFhNSHLxe 55G56/dxBuoj4RrFoX3ynerXfbp4dH2KArPc0NfoamqebuGNfEQmDbtnCGE5zKcR0zvmXsRp qU7+caufueZyLwjTU+y5p34U4PlOO2Q7/bdaPEdXfpgvSpWk1o3H36LvkPV/PGGDCLzaNn04 BdiiiPEHwoIjCXOAcR+4+eqM4TSwVpTn6SNgbHLjAhCwCDyggK+3qEGJph+WNtNU7uFfscSP k4jqlxc8P+hn9IqaMWaeX9nBEaiKffR7OKjMdtFFnBRSXiW/kOKuuRdeDjL5gWJjY+IpdafP KhjvUFtfSwGdrDUh3SvB5knSixE3qbxbhbNxmqDVzyzMwunFANujyyVizS31DnWC6tKzANkC k15CyeFC6sFFu+WpRxvC6fzQTLI5CRGAB6FAxz8Hu5rpNNZHsbYs9Vfr/BJuSUfRI/12eOCL IvxRPpmMOlcI4WDW3EDkzqNAXn5Onx/b0rFGFpM4GmSPriEJdBb4M4pSD6fN6Y/Jrng/Bdwk SQARAQABiQIlBBgBAgAPBQJOiskRAhsMBQkSzAMAAAoJEGz4yi9OyKjPgEwQAIP/gy/Xqc1q OpzfFScswk3CEoZWSqHxn/fZasa4IzkwhTUmukuIvRew+BzwvrTxhHcz9qQ8hX7iDPTZBcUt ovWPxz+3XfbGqE+q0JunlIsP4N+K/I10nyoGdoFpMFMfDnAiMUiUatHRf9Wsif/nT6oRiPNJ T0EbbeSyIYe+ZOMFfZBVGPqBCbe8YMI+JiZeez8L9JtegxQ6O3EMQ//1eoPJ5mv5lWXLFQfx f4rAcKseM8DE6xs1+1AIsSIG6H+EE3tVm+GdCkBaVAZo2VMVapx9k8RMSlW7vlGEQsHtI0FT c1XNOCGjaP4ITYUiOpfkh+N0nUZVRTxWnJqVPGZ2Nt7xCk7eoJWTSMWmodFlsKSgfblXVfdM 9qoNScM3u0b9iYYuw/ijZ7VtYXFuQdh0XMM/V6zFrLnnhNmg0pnK6hO1LUgZlrxHwLZk5X8F uD/0MCbPmsYUMHPuJd5dSLUFTlejVXIbKTSAMd0tDSP5Ms8Ds84z5eHreiy1ijatqRFWFJRp ZtWlhGRERnDH17PUXDglsOA08HCls0PHx8itYsjYCAyETlxlLApXWdVl9YVwbQpQ+i693t/Y PGu8jotn0++P19d3JwXW8t6TVvBIQ1dRZHx1IxGLMn+CkDJMOmHAUMWTAXX2rf5tUjas8/v2 azzYF4VRJsdl+d0MCaSy8mUh Message-ID: <3cda2c0a-1b09-afd3-e0d2-28f7587a085c@suse.de> Date: Fri, 15 Nov 2019 08:29:36 +0100 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101 Thunderbird/60.7.2 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 11/15/19 6:30 AM, Bart Van Assche wrote: > On 11/14/19 1:41 AM, John Garry wrote: >> On 13/11/2019 18:38, Hannes Reinecke wrote: >>>> Hi Hannes, >>>> >>>>> Oh, my. Indeed, that's correct. >>>> >>>> The tags could be kept in sync like this: >>>> >>>> shared_tag = blk_mq_get_tag(shared_tagset); >>>> if (shared_tag != -1) >>>>      sbitmap_set(hctx->tags, shared_tag); >>>> >>>> But that's obviously not ideal. >>>> >>> Actually, I _do_ prefer keeping both in sync. >>> We might want to check if the 'normal' tag is set (typically it would not, but then, who knows ...) >>> The beauty here is that both 'shared' and 'normal' tag are in sync, so if a driver would be wanting to use the tag as index into a command array it can do so without any surprises. >>> >>> Why do you think it's not ideal? >> >> A few points: >> - Getting a bit from one tagset and then setting it in another tagset is a bit clunky. >> - There may be an atomicity of the getting the shared tag bit and setting the hctx tag bit - I don't think that there is. >> - Consider that sometimes we may want to check if there is space on a hw queue - checking the hctx tags is not really proper any longer, as typically there would always be space on hctx, but not always the shared tags. We did delete blk_mq_can_queue() yesterday, which >> would be an example of that. Need to check if there are others. >> >> Having said all that, the obvious advantage is performance gain, can still use request.tag and so maybe less intrusive changes. >> >> I'll have a look at the implementation. The devil is mostly in the detail... > > Wouldn't that approach trigger a deadlock if it is attempted to allocate the last > tag from two different hardware queues? How about sharing tag sets across hardware > queues, e.g. like in the (totally untested) patch below? > Why should it? The shared tag map determines which tag should be allocated in the per-hctx map, and as the former is a strict superset of all hctx maps the bit _has_ to be free in the hctx map. Cheers, Hannes -- Dr. Hannes Reinecke Teamlead Storage & Networking hare@suse.de +49 911 74053 688 SUSE Software Solutions Germany GmbH, Maxfeldstr. 5, 90409 Nürnberg HRB 247165 (AG München), GF: Felix Imendörffer