Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754827Ab2FMVnb (ORCPT ); Wed, 13 Jun 2012 17:43:31 -0400 Received: from wolverine01.qualcomm.com ([199.106.114.254]:5338 "EHLO wolverine01.qualcomm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754420Ab2FMVna (ORCPT ); Wed, 13 Jun 2012 17:43:30 -0400 X-IronPort-AV: E=McAfee;i="5400,1158,6741"; a="200789025" Message-ID: <1476f0476a2dcfc6f7db9dbb4be0ab2b.squirrel@www.codeaurora.org> In-Reply-To: References: <000601cd47ab$8ad77c50$a08674f0$%jun@samsung.com> <000001cd489c$115f03b0$341d0b10$%jun@samsung.com> <113bb1f38dbc386f1adfc580e10dc2e5.squirrel@www.codeaurora.org> Date: Wed, 13 Jun 2012 14:43:25 -0700 (PDT) Subject: Re: [PATCH v7 1/3] mmc: core: Add packed command feature of eMMC4.5 From: merez@codeaurora.org To: "S, Venkatraman" Cc: merez@codeaurora.org, "Seungwon Jeon" , linux-mmc@vger.kernel.org, linux-kernel@vger.kernel.org, "Chris Ball" , "Subhash Jadavani" User-Agent: SquirrelMail/1.4.17 MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7BIT X-Priority: 3 (Normal) Importance: Normal Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3378 Lines: 90 On Wed, June 13, 2012 12:49 pm, S, Venkatraman wrote: > On Wed, Jun 13, 2012 at 12:45 AM, wrote: >> >>> S, Venkatraman wrote: >>>> On Mon, Jun 11, 2012 at 1:53 PM, Seungwon Jeon >>>> wrote: >>>> > This patch adds packed command feature of eMMC4.5. >>>> > The maximum number for packing read(or write) is offered >>>> > and exception event relevant to packed command which is >>>> > used for error handling is enabled. If host wants to use >>>> > this feature, MMC_CAP2_PACKED_CMD should be set. >>>> > >>>> > Signed-off-by: Seungwon Jeon >>>> >>>> Can you please post some clear performance benchmarks with your >>>> patchset >>>> ? >>>> Given that #merez claims to see a significant performance drop for >>>> reads, it will be >>>> good to compare notes. >>>> If it's not too much trouble, both CFQ and deadline scheduler figures >>>> would be useful, on a >>>> set of read only, write only and parallel read write usecases. >>>> >>>> I can also try to replicate your results if you can publish the exact >>>> configuration you used >>>> for testing (example: iozone parameters) >>> I'm checking the merez's result. >>> Currently packed command is effective on write. >>> When running packed write with iozone, there is 25% performance gains. >>> (ex: iozone -az -i0 -I -s 10m -f /target/test -e) >>> >> Our tests shows performance gain of 50-60% in scenarios of only write >> lmdd >> operations. >> >> As I mentioned in the write packing control thread the degradation of >> read >> performance in case of mix read/write operations appears also without >> write packing. Therefore I don't think it should stop us from approving >> the write packing patch, that gives a significant improvement to the >> write >> performance. >> The read performance degradation should be resolved regardless of the >> write packing patch. >> > > One further question - when you say "degradation of read performance > in case of mix > read/write operations appears also without write packing", what > exactly does that mean? > Degradation w.r.to to read-only test ? Or any expected throughput ? I meant w.r. to read only test. > > If the scenario you mention is accurate, I was actually thinking that > we should recommend to merge > read packing first, then merge write packing once the read performance > issue is well understood. I don't know if you followed the early discussion of this patch but the read throughput was not proved as efficient and in some of the cases it also caused degradation of the read performance. Therefore, we don't intend to merge it yet. > > I am all for better performance with packing control etc, but the > overall code complexity is really > increasing more than necessary. I want to make sure that it is really > worth the effort. In my opinion a gain of 50%-60% of the write performance worth the complexity of the code and the effort to fix the issues it reveals. > > Thanks, > Venkat. > -- Sent by consultant of Qualcomm Innovation Center, Inc. Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/