Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <e46db33f-84a6-6d23-9be2-7429fec71046@kernel.dk>
Date:   Tue, 29 Mar 2022 08:35:29 -0600
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux aarch64; rv:91.0) Gecko/20100101
 Thunderbird/91.7.0
Subject: Re: [PATCH -next RFC 2/6] block: refactor to split bio thoroughly
Content-Language: en-US
To:     Christoph Hellwig <hch@infradead.org>, Yu Kuai <yukuai3@huawei.com>
Cc:     andriy.shevchenko@linux.intel.com, john.garry@huawei.com,
        ming.lei@redhat.com, linux-block@vger.kernel.org,
        linux-kernel@vger.kernel.org, yi.zhang@huawei.com
References: <20220329094048.2107094-1-yukuai3@huawei.com>
 <20220329094048.2107094-3-yukuai3@huawei.com>
 <YkMKgwsZ3K8dRVbX@infradead.org>
From:   Jens Axboe <axboe@kernel.dk>
In-Reply-To: <YkMKgwsZ3K8dRVbX@infradead.org>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 3/29/22 7:32 AM, Christoph Hellwig wrote:
> On Tue, Mar 29, 2022 at 05:40:44PM +0800, Yu Kuai wrote:
>> Currently, the splited bio is handled first, and then continue to split
>> the original bio. This patch tries to split the original bio thoroughly,
>> so that it can be known in advance how many tags will be needed.
> 
> How do you avoid the deadlock risk with all the split bios being
> submitted together?

That too

> But more importantly why does your use case even have splits that get
> submitted together?  Is this a case of Linus' stupidly low default
> max_sectors when the hardware supports more, or is the hardware limited
> to a low number of sectors per request?  Or do we hit another reason
> for the split?

See the posted use case, it's running 512kb ios on a 128kb device.

-- 
Jens Axboe