Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Wed, 2 Sep 2020 15:44:35 +0200
From:   Christoph Hellwig <hch@lst.de>
To:     Ming Lei <ming.lei@redhat.com>
Cc:     linux-kernel@vger.kernel.org, linux-block@vger.kernel.org,
        Sagi Grimberg <sagi@grimberg.me>, Tejun Heo <tj@kernel.org>,
        Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
        Bart Van Assche <bvanassche@acm.org>
Subject: Re: [PATCH V2 1/2] percpu_ref: reduce memory footprint of
 percpu_ref in fast path
Message-ID: <20200902134435.GA32502@lst.de>
References: <20200902122643.634143-1-ming.lei@redhat.com> <20200902122643.634143-2-ming.lei@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20200902122643.634143-2-ming.lei@redhat.com>
User-Agent: Mutt/1.5.17 (2007-11-01)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Wed, Sep 02, 2020 at 08:26:42PM +0800, Ming Lei wrote:
> 'struct percpu_ref' is often embedded into one user structure, and the
> instance is usually referenced in fast path, however actually only
> 'percpu_count_ptr' is needed in fast path.
> 
> So move other fields into one new structure of 'percpu_ref_data', and
> allocate it dynamically via kzalloc(), then memory footprint of
> 'percpu_ref' in fast path is reduced a lot and becomes suitable to put
> into hot cacheline of user structure.

This looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>