Mailing-List: contact dev-help@harmony.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@harmony.apache.org
Received-SPF: pass (nike.apache.org: domain of alexei.fedotov@gmail.com
 designates 209.85.220.214 as permitted sender)
DomainKey-Signature: a=rsa-sha1; c=nofws;
        d=gmail.com; s=gamma;
        h=mime-version:in-reply-to:references:date:message-id:subject:from:to
         :content-type:content-transfer-encoding;
        b=BtHPKNsJnv7hRIjG7mU/122HIQLgONrOkHkLTL7VnYtWt55uEbOhxVx7sXuvE9Iy4q
         VDwbr+eLsI+02f9e1glWvti9EfAHa+d2L9MIW7och9lAlFZwNyk9d8IVGDhBvFeQtQic
         rR0ZvOEp20g8j9P3WuaiYBwk/ii7HWAvtwAOI=
MIME-Version: 1.0
In-Reply-To: <4AFD8DF2.8060406@gmail.com>
References: <4AC4BA89.3020004@gmail.com>
	 <c30d70960911051243y7b34aaban4a66514e67e7c7f2@mail.gmail.com>
	 <4AF8006A.8030001@gmail.com>
	 <6554f93c0911090905s7f0b1610i5a594ccca8583fe6@mail.gmail.com>
	 <4AFBE9AF.9000704@gmail.com>
	 <c30d70960911120307i5ba8ce6idc1d466bc83861bb@mail.gmail.com>
	 <6554f93c0911121120p5da1af37pb23ff8846859ebf4@mail.gmail.com>
	 <4AFD8DF2.8060406@gmail.com>
Date: Mon, 16 Nov 2009 14:01:09 +0300
Message-ID: <c30d70960911160301w3ba4b5fejb0fd68f4c436022@mail.gmail.com>
Subject: Re: [classlib] Fixing an unsafe reference in InputStream
From: Alexei Fedotov <alexei.fedotov@gmail.com>
To: dev@harmony.apache.org
Content-Type: text/plain; charset=KOI8-R
Content-Transfer-Encoding: quoted-printable

I support reluctance in fixing performance. AFAIK, no performance
change should be done without demonstrating incerase on real loads.

2009/11/13 Tim Ellison <t.p.ellison@gmail.com>:
> On 12/Nov/2009 19:20, Vijay Menon wrote:
>> Right, writes - even unsynchronized ones - to the same cache line are
>> problematic. =9AHere's a good quick read on this:
>> http://en.wikipedia.org/wiki/MESI_protocol. =9ARecent Intel architecture=
s
>> adapt this protocol. =9AHere's the interesting bit:
>>
>> A write may only be performed if the cache line is in the Modified or
>> Exclusive state. If it is in the Shared state, all other cached copies m=
ust
>> be invalidated first. This is typically done by a broadcast operation kn=
own
>> as *Read For Ownership (RFO)*.
>>
>>
>> If two cores continually write to the same cache line, they'll repeatedl=
y
>> invalidate each other.
>
> Thanks for the pointers.
>
> Given that the current code has been there since time immemorial and is
> not broken, I'm inclined to leave it for now and pick this thread up
> again after M12. =9AThat'll give us time to see what the difference is
> between the local and static versions (though if I were a betting person
> I'd say skip is used infrequently enough that nobody's app will notice).
>
> Regards,
> Tim
>


--=20
With best regards / =D3 =CE=C1=C9=CC=D5=DE=DB=C9=CD=C9 =D0=CF=D6=C5=CC=C1=
=CE=C9=D1=CD=C9,
Alexei Fedotov / =E1=CC=C5=CB=D3=C5=CA =E6=C5=C4=CF=D4=CF=D7,
http://www.telecom-express.ru/
http://harmony.apache.org/
http://www.expressaas.com/
http://openmeetings.googlecode.com/