Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Thu, 21 Feb 2019 10:12:17 +0100
From:   Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To:     Wei Yang <richardw.yang@linux.intel.com>
Cc:     "Huang, Ying" <ying.huang@intel.com>,
        kernel test robot <rong.a.chen@intel.com>,
        Stephen Rothwell <sfr@canb.auug.org.au>,
        "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>, lkp@01.org,
        LKML <linux-kernel@vger.kernel.org>
Subject: Re: [LKP] [driver core] 570d020012: will-it-scale.per_thread_ops
 -12.2% regression
Message-ID: <20190221091217.GA18701@kroah.com>
References: <20190218075442.GI29177@shao2-debian>
 <20190219005945.GA16734@richard>
 <20190219121904.GA24103@kroah.com>
 <20190221031049.GE28258@shao2-debian>
 <20190221071023.GA28637@kroah.com>
 <8736oh1uf5.fsf@yhuang-dev.intel.com>
 <20190221073510.GA17369@kroah.com>
 <87va1dzgpj.fsf@yhuang-dev.intel.com>
 <20190221083926.GA7834@richard>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20190221083926.GA7834@richard>
User-Agent: Mutt/1.11.3 (2019-02-01)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Thu, Feb 21, 2019 at 04:39:27PM +0800, Wei Yang wrote:
> >>> I don't think this is an issues of struct device.  As you said, struct
> >>> device isn't access much during test.  Struct device may share slab page
> >>> with some other data structures (signal related, or fd related (as in
> >>> some other test cases)), so that the alignment of these data structures
> >>> are affected, so caused the performance regression.
> >>
> >> But allocation of a structure should always be "properly" aligned, no
> >> matter what something else did in the system as that is what kmalloc
> >> ensures.  If not, then we have problems in our memory allocator :)
> >>
> >> So something is odd here, but I don't think that is it...
> >
> >If all these data structure are allocated with kmalloc() instead of
> >kmem_cache_alloc(), then my guessing above seems incorrect ...
> >
> 
> Seems we don't have special kmem_cache for device and device_private.

Nor do we need one :)

Remember, 'struct device' is included inside lots of other structures
already, it is not very often created "on its own."

thanks,

greg k-h