Date: Wed, 19 Jul 2017 16:11:34 -0700
From: Davidlohr Bueso <dave@stgolabs.net>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>,
        Elena Reshetova <elena.reshetova@intel.com>,
        linux-kernel@vger.kernel.org, peterz@infradead.org,
        gregkh@linuxfoundation.org, mingo@redhat.com, adobriyan@gmail.com,
        serge@hallyn.com, arozansk@redhat.com, keescook@chromium.org,
        Hans Liljestrand <ishkamiel@gmail.com>,
        David Windsor <dwindsor@gmail.com>
Subject: Re: [PATCH 1/3] ipc: convert ipc_namespace.count from atomic_t to
 refcount_t
Message-ID: <20170719231134.GF14395@linux-80c1.suse>
References: <1499417992-3238-1-git-send-email-elena.reshetova@intel.com>
 <1499417992-3238-2-git-send-email-elena.reshetova@intel.com>
 <87bmottgo4.fsf@xmission.com>
 <20170719153546.37567fbf77861653172fa263@linux-foundation.org>
 <20170719225427.GD14395@linux-80c1.suse>
 <20170719155833.641a283467bf6b89a7d2e56b@linux-foundation.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Disposition: inline
In-Reply-To: <20170719155833.641a283467bf6b89a7d2e56b@linux-foundation.org>
User-Agent: Mutt/1.5.24 (2015-08-30)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1208
Lines: 36

On Wed, 19 Jul 2017, Andrew Morton wrote:

>On Wed, 19 Jul 2017 15:54:27 -0700 Davidlohr Bueso <dave@stgolabs.net> wrote:
>
>> On Wed, 19 Jul 2017, Andrew Morton wrote:
>>
>> >I do rather dislike these conversions from the point of view of
>> >performance overhead and general code bloat.  But I seem to have lost
>> >that struggle and I don't think any of these are fastpath(?).
>>
>> Well, since we now have fd25d19 (locking/refcount: Create unchecked atomic_t
>> implementation), performance is supposed to be ok.
>
>Sure, things are OK for people who disable the feature.
>
>But for people who want to enable the feature we really should minimize
>the cost by avoiding blindly converting sites which simply don't need
>it: simple, safe, old, well-tested code.  Why go and slow down such
>code?  Need to apply some common sense here...

Fair points.

>
>> It would be lovely to have
>> some actual numbers nonetheless.
>
>Very much so.

May I suggest using mmtests with the following config file:

https://github.com/gormanm/mmtests/blob/7e070a810bc0af92e592e5121d0ea75fada51aeb/configs/config-global-dhp__workload-ipc-scale-short

It will run two of Manfred's ipcscale sem benchmarks.

Thanks,
Davidlohr