From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <osandov@osandov.com>
Return-Path: <osandov@osandov.com>
Date: Wed, 7 Jun 2017 15:04:11 -0700
From: Omar Sandoval <osandov@osandov.com>
To: Christoph Hellwig <hch@lst.de>
Cc: Thomas Gleixner <tglx@linutronix.de>, Jens Axboe <axboe@kernel.dk>,
	Keith Busch <keith.busch@intel.com>, linux-nvme@lists.infradead.org,
	linux-block@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 7/8] blk-mq: create hctx for each present CPU
Message-ID: <20170607220411.GF7481@vader.DHCP.thefacebook.com>
References: <20170603140403.27379-1-hch@lst.de>
 <20170603140403.27379-8-hch@lst.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
In-Reply-To: <20170603140403.27379-8-hch@lst.de>
List-ID: <linux-block@vger.kernel.org>

On Sat, Jun 03, 2017 at 04:04:02PM +0200, Christoph Hellwig wrote:
> Currently we only create hctx for online CPUs, which can lead to a lot
> of churn due to frequent soft offline / online operations.  Instead
> allocate one for each present CPU to avoid this and dramatically simplify
> the code.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>

Oh man, this cleanup is great. Did you run blktests on this? block/008
does a bunch of hotplugging while I/O is running.