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 Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id BFC9DC433FE for ; Fri, 18 Nov 2022 11:29:58 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235245AbiKRL35 (ORCPT ); Fri, 18 Nov 2022 06:29:57 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:32838 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230004AbiKRL34 (ORCPT ); Fri, 18 Nov 2022 06:29:56 -0500 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 64E1D657D5 for ; Fri, 18 Nov 2022 03:29:02 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1668770941; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: in-reply-to:in-reply-to:references:references; bh=5a+yrIkbIMgxgMgsl7YwCu05OPMIM0lA2aPkKKcR6U0=; b=MSHmtQ5RpA7Khmdp3XkuJSEL4eWusMGa+1SKVcH9LSLGV3sgIluR+O21KuA75meOd6bgHf oemHOz1h4x7ZMsdi0GRTctrk20ooxtoF1inw5l0oDqTifstmK8nz6+EYLp2CIb1uK2eaXE KcboyflfwFLlJiZdGPjOu6RGIMrSnQI= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-317-XM24GRmOMziOHxHrdzXQ6g-1; Fri, 18 Nov 2022 06:28:58 -0500 X-MC-Unique: XM24GRmOMziOHxHrdzXQ6g-1 Received: from smtp.corp.redhat.com (int-mx08.intmail.prod.int.rdu2.redhat.com [10.11.54.8]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id CE25138041C3; Fri, 18 Nov 2022 11:28:57 +0000 (UTC) Received: from T590 (ovpn-8-16.pek2.redhat.com [10.72.8.16]) by smtp.corp.redhat.com (Postfix) with ESMTPS id 35C9AC15BA5; Fri, 18 Nov 2022 11:28:53 +0000 (UTC) Date: Fri, 18 Nov 2022 19:28:48 +0800 From: Ming Lei To: Andreas Hindborg Cc: Damien Le Moal , Jens Axboe , linux-block@vger.kernel.org, ming.lei@redhat.com Subject: Re: Reordering of ublk IO requests Message-ID: References: <87o7t67zzv.fsf@wdc.com> <87k03u7x3r.fsf@wdc.com> <87fseh92aa.fsf@wdc.com> <2f86eb58-148b-03ac-d2bf-d67c5756a7a6@opensource.wdc.com> <8735ag8ueg.fsf@wdc.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <8735ag8ueg.fsf@wdc.com> X-Scanned-By: MIMEDefang 3.1 on 10.11.54.8 Precedence: bulk List-ID: X-Mailing-List: linux-block@vger.kernel.org On Fri, Nov 18, 2022 at 10:41:31AM +0100, Andreas Hindborg wrote: > > Ming Lei writes: > > > CAUTION: This email originated from outside of Western Digital. Do not click on > > links or open attachments unless you recognize the sender and know that the > > content is safe. > > > > > > On Fri, Nov 18, 2022 at 01:35:29PM +0900, Damien Le Moal wrote: > >> On 11/18/22 13:12, Ming Lei wrote: > >> [...] > >> >>> You can only assign it to zoned write request, but you still have to check > >> >>> the sequence inside each zone, right? Then why not just check LBAs in > >> >>> each zone simply? > >> >> > >> >> We would need to know the zone map, which is not otherwise required. > >> >> Then we would need to track the write pointer for each open zone for > >> >> each queue, so that we can stall writes that are not issued at the write > >> >> pointer. This is in effect all zones, because we cannot track when zones > >> >> are implicitly closed. Then, if different queues are issuing writes to > >> > > >> > Can you explain "implicitly closed" state a bit? > >> > > >> > From https://zonedstorage.io/docs/introduction/zoned-storage, only the > >> > following words are mentioned about closed state: > >> > > >> > ```Conversely, implicitly or explicitly opened zoned can be transitioned to the > >> > closed state using the CLOSE ZONE command.``` > >> > >> When a write is issued to an empty or closed zone, the drive will > >> automatically transition the zone into the implicit open state. This is > >> called implicit open because the host did not (explicitly) issue an open > >> zone command. > >> > >> When there are too many implicitly open zones, the drive may choose to > >> close one of the implicitly opened zone to implicitly open the zone that > >> is a target for a write command. > >> > >> Simple in a nutshell. This is done so that the drive can work with a > >> limited set of resources needed to handle open zones, that is, zones that > >> are being written. There are some more nasty details to all this with > >> limits on the number of open zones and active zones that a zoned drive may > >> have. > > > > OK, thanks for the clarification about implicitly closed, but I > > understand this close can't change the zone's write pointer. > > You are right, it does not matter if the zone is implicitly closed, I > was mistaken. But we still have to track the write pointer of every zone > in open or active state, otherwise we cannot know if a write that arrive > to a zone with no outstanding IO is actually at the write pointer, or > whether we need to hold it. > > > > >> > >> > > >> > zone info can be cached in the mapping(hash table)(zone sector is the key, and zone > >> > info is the value), which can be implemented as one LRU style. If any zone > >> > info isn't hit in the mapping table, ioctl(BLKREPORTZONE) can be called for > >> > obtaining the zone info. > >> > > >> >> the same zone, we need to sync across queues. Userspace may have > >> >> synchronization in place to issue writes with multiple threads while > >> >> still hitting the write pointer. > >> > > >> > You can trust mq-dealine, which guaranteed that write IO is sent to ->queue_rq() > >> > in order, no matter MQ or SQ. > >> > > >> > Yes, it could be issue from multiple queues for ublksrv, which doesn't sync > >> > among multiple queues. > >> > > >> > But per-zone re-order still can solve the issue, just need one lock > >> > for each zone to cover the MQ re-order. > >> > >> That lock is already there and using it, mq-deadline will never dispatch > >> more than one write per zone at any time. This is to avoid write > >> reordering. So multi queue or not, for any zone, there is no possibility > >> of having writes reordered. > > > > oops, I miss the single queue depth point per zone, so ublk won't break > > zoned write at all, and I agree order of batch IOs is one problem, but > > not hard to solve. > > The current implementation _does_ break zoned write because it reverses > batched writes. But if it is an easy fix, that is cool :) Please look at Damien's comment: >> That lock is already there and using it, mq-deadline will never dispatch >> more than one write per zone at any time. This is to avoid write >> reordering. So multi queue or not, for any zone, there is no possibility >> of having writes reordered. For zoned write, mq-deadline is used to limit at most one inflight write for each zone. So can you explain a bit how the current implementation breaks zoned write? Thanks, Ming