From mboxrd@z Thu Jan  1 00:00:00 1970
From: Stephen Hemminger <stephen@networkplumber.org>
Subject: Re: [PATCH RFC net-next 4/4] bridge: add ability to turn off fdb
 used updates
Date: Fri, 3 Feb 2017 14:24:03 -0800
Message-ID: <20170203142403.52eca52f@xeon-e3>
References: <1485876718-18091-1-git-send-email-nikolay@cumulusnetworks.com>
        <1485876718-18091-5-git-send-email-nikolay@cumulusnetworks.com>
        <20170202.214737.1978812863222769540.davem@davemloft.net>
        <45f588fd-bece-647c-5b1e-2c64975e640d@cumulusnetworks.com>
        <20170203102825.363907ae@xeon-e3>
        <08ba3317-6ec0-1a4e-bdb5-68f5bb91495b@cumulusnetworks.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Cc: David Miller <davem@davemloft.net>, netdev@vger.kernel.org,
        roopa@cumulusnetworks.com
To: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Return-path: <netdev-owner@vger.kernel.org>
Received: from mail-pg0-f44.google.com ([74.125.83.44]:35766 "EHLO
        mail-pg0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1752356AbdBCWYG (ORCPT
        <rfc822;netdev@vger.kernel.org>); Fri, 3 Feb 2017 17:24:06 -0500
Received: by mail-pg0-f44.google.com with SMTP id 194so9937361pgd.2
        for <netdev@vger.kernel.org>; Fri, 03 Feb 2017 14:24:05 -0800 (PST)
In-Reply-To: <08ba3317-6ec0-1a4e-bdb5-68f5bb91495b@cumulusnetworks.com>
Sender: netdev-owner@vger.kernel.org
List-ID: <netdev.vger.kernel.org>

On Fri, 3 Feb 2017 19:34:19 +0100
Nikolay Aleksandrov <nikolay@cumulusnetworks.com> wrote:

> On 03/02/17 19:28, Stephen Hemminger wrote:
> > On Fri, 3 Feb 2017 09:30:37 +0100
> > Nikolay Aleksandrov <nikolay@cumulusnetworks.com> wrote:
> >   
> >> On 03/02/17 03:47, David Miller wrote:  
> >>> From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
> >>> Date: Tue, 31 Jan 2017 16:31:58 +0100
> >>>     
> >>>> @@ -197,7 +197,8 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
> >>>>  		if (dst->is_local)
> >>>>  			return br_pass_frame_up(skb);
> >>>>  
> >>>> -		dst->used = jiffies;
> >>>> +		if (br->used_enabled)
> >>>> +			dst->used = jiffies;    
> >>>
> >>> Have you tried:
> >>>
> >>> 	if (dst->used != jiffies)
> >>> 		dst->used = jiffies;
> >>>
> >>> If that isn't effective, you can tweak the test to decrease the
> >>> granularity of the value.  Basically, if dst->used is within
> >>> 1 HZ of jiffies, don't do the write.
> >>>
> >>> I suspect this might help a lot, and not require a new bridging
> >>> option.
> >>>     
> >>
> >> Yes, I actually have a patch titled "used granularity". :-) I've tested with different
> >> values and it does help but it either needs to be paired with another similar test for
> >> the "updated" field (since they share a write-heavy cache line) or they need to be
> >> in separate cache lines to avoid that dst's source port from causing the load HitM for
> >> all who check the value.
> >>
> >> I'll run some more tests and probably go this way for now.
> >>
> >> Thanks,
> >>  Nik
> >>  
> > 
> > Since used doesn't need HZ granularity, it reports values in clock_t resolution so
> > storing (and doing cmp and set would mean that it would only be 100 HZ
> >   
> 
> Yes, exactly what I'm currently testing. Will post the new set soon.
> Since HZ can be different a generic way to obtain the granularity for
> both should be clock_t_to_jiffies(1) if I'm not missing something.
> 
> 

USER_HZ is set by userspace ABI to 100 hz. HZ is configurable when kernel is built.