From: Jens Axboe Subject: Re: improve the bio allocation interface Date: Wed, 19 Jan 2022 06:27:04 -0700 Message-ID: <2b9aedb6-4531-91fe-3493-133470ebee80@kernel.dk> References: <20220118071952.1243143-1-hch@lst.de> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel-dk.20210112.gappssmtp.com; s=20210112; h=subject:to:cc:references:from:message-id:date:user-agent :mime-version:in-reply-to:content-language:content-transfer-encoding; bh=bOtjTSupMPdLeWMiVKrD7jaORGYKT+sk6BwRJT6YH5k=; b=7BEfqJqRzXAE088B+2bHOpvIL0UUVYOZUvHjaUycgtIQCZS6qJSTGhtIwa1Xa6EPfk oV2YXPGcxgiVF5LaQHluLKvgATLLAeZKgM3nn6DNYQRh6ifI6cdJPU7ZNOAzZ5g1fFkO MWYcErn30fkxjWY45t9Yboy2jcExTsCrzys7xQCWMUAHOZ2PvIOKEUon3RlzTMdRHOFW W8Ams8MdRsSgkRcx2W8R30267oa8zRJAWTCRB6MNRYIPNawBrTjM+yr6IoXc6oDoeZjs ao5paPXCdk//Rx9HxN4miEoGhchTg9VDu7RK7HyILmak+tgC3BqPCX5DU7MxKWRj66d8 cjpA== In-Reply-To: <20220118071952.1243143-1-hch-jcswGhMUV9g@public.gmane.org> Content-Language: en-US List-ID: Content-Type: text/plain; charset="us-ascii" To: Christoph Hellwig Cc: Pavel Begunkov , Mike Snitzer , Ryusuke Konishi , Konstantin Komarov , Andrew Morton , "Md . Haris Iqbal" , Jack Wang , =?UTF-8?Q?Roger_Pau_Monn=c3=a9?= , Philipp Reisner , Lars Ellenberg , linux-block-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org, linux-fsdevel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-nfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-nilfs-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, ntfs3-cunTk1MwBs/YUNznpcFYbw@public.gmane.org, xen-devel-GuqFBffKawtpuQazS67q72D2FQJk+8+b@public.gmane.org, drbd-dev-cunTk1MwBs8qoQakbn7OcQ@public.gmane.org On 1/18/22 12:19 AM, Christoph Hellwig wrote: > Hi Jens, > > this series is posted early because it has wide-ranging changes and > could use some early ACKs before -rc1. > > It changes the interface to the bio allocators to always pass a > block_device and the operation, which is information needed for every > bio submitted through bio_submit. This means the fields can be > directly initialized in bio_init instead of first being zeroed and > thus should help to micro-optimize even better than the __bio_set_dev > that Pavel proposed while also cleaning up code. Looks pretty straight forward from the block core point of view. Didn't look too closely at the fs/driver changes yet. -- Jens Axboe