From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from wes1-so1.wedos.net (wes1-so1.wedos.net [46.28.106.15]) by dpdk.org (Postfix) with ESMTP id 0611C9655 for ; Thu, 19 May 2016 13:56:10 +0200 (CEST) Received: from pcviktorin.fit.vutbr.cz (pcviktorin.fit.vutbr.cz [147.229.13.147]) by wes1-so1.wedos.net (Postfix) with ESMTPSA id 3r9Tzs4mCrzBjb; Thu, 19 May 2016 13:56:09 +0200 (CEST) Date: Thu, 19 May 2016 13:54:26 +0200 From: Jan Viktorin To: Bruce Richardson Cc: Jerin Jacob , dev@dpdk.org, thomas.monjalon@6wind.com, konstantin.ananyev@intel.com, jianbo.liu@linaro.org Message-ID: <20160519135426.4f7bd499@pcviktorin.fit.vutbr.cz> In-Reply-To: <20160519085047.GA17500@bricha3-MOBL3> References: <1463579863-32053-1-git-send-email-jerin.jacob@caviumnetworks.com> <20160518164300.GA12324@bricha3-MOBL3> <20160518185011.GA4432@localhost.localdomain> <20160519085047.GA17500@bricha3-MOBL3> Organization: RehiveTech MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Subject: Re: [dpdk-dev] [PATCH] mbuf: make rearm_data address naturally aligned X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 19 May 2016 11:56:10 -0000 On Thu, 19 May 2016 09:50:48 +0100 Bruce Richardson wrote: > On Thu, May 19, 2016 at 12:20:16AM +0530, Jerin Jacob wrote: > > On Wed, May 18, 2016 at 05:43:00PM +0100, Bruce Richardson wrote: > > > On Wed, May 18, 2016 at 07:27:43PM +0530, Jerin Jacob wrote: > > > > To avoid multiple stores on fast path, Ethernet drivers > > > > aggregate the writes to data_off, refcnt, nb_segs and port > > > > to an uint64_t data and write the data in one shot > > > > with uint64_t* at &mbuf->rearm_data address. > > > > > > > > Some of the non-IA platforms have store operation overhead > > > > if the store address is not naturally aligned.This patch > > > > fixes the performance issue on those targets. > > > > > > > > Signed-off-by: Jerin Jacob > > > > --- > > > > > > > > Tested this patch on IA and non-IA(ThunderX) platforms. > > > > This patch shows 400Kpps/core improvement on ThunderX + ixgbe + vector environment. > > > > and this patch does not have any overhead on IA platform. Hello, I can confirm a very small improvement in our synthetic tests based on the PMD null (ARM Cortex-A9). For a single-core (1C) test, there is now a lower overhead and it is more stable with different packet lengths. However, when running dual-core (2C), the result is slightly slower but again, it seems to be more stable. Without this patch (cycles per packet): length: 64 128 256 512 1024 1280 1518 1C 488 544 487 454 543 488 515 2C 433 433 431 433 433 461 443 Applied this patch (cycles per packet): length: 64 128 256 512 1024 1280 1518 1C 472 472 472 472 473 472 473 2C 435 435 435 435 436 436 436 Regards Jan > > > > > > > > Have tried an another similar approach by replacing "buf_len" with "pad" > > > > (in this patch context), > > > > Since it has additional overhead on read and then mask to keep "buf_len" intact, > > > > not much improvement is not shown. > > > > ref: http://dpdk.org/ml/archives/dev/2016-May/038914.html > > > > > > > > --- > > > While this will work and from your tests doesn't seem to have a performance > > > impact, I'm not sure I particularly like it. It's extending out the end of > > > cacheline0 of the mbuf by 16 bytes, though I suppose it's not technically using > > > up any more space of it. > > > > Extending by 2 bytes. Right ?. Yes, I guess, Now we using only 56 out of 64 bytes > > in the first 64-byte cache line. > > > > > > > > What I'm wondering about though, is do we have any usecases where we need a > > > variable buf_len for packets for RX. These mbufs come directly from a mempool, > > > which is generally understood to be a set of fixed-sized buffers. I realise that > > > this change was made in the past after some discussion, but one of the key points > > > there [at least to my reading] was that - even though nobody actually made a > > > concrete case where they had variable-sized buffers - having support for them > > > made no performance difference. > > > > > > The latter part of that has now changed, and supporting variable-sized mbufs > > > from an mbuf pool has a perf impact. Do we definitely need that functionality, > > > because the easiest fix here is just to move the rxrearm marker back above > > > mbuf_len as it was originally in releases like 1.8? > > > > And initialize the buf_len with mp->elt_size - sizeof(struct rte_mbuf). > > Right? > > > > I don't have a strong opinion on this, I can do this if there is no > > objection on this. Let me know. > > > > However, I do see in future, "buf_len" may belong at the end of the first 64 byte > > cache line as currently "port" is defined as uint8_t, IMO, that is less. > > We may need to increase that uint16_t. The reason why I think that > > because, Currently in ThunderX HW, we do have 128VFs per socket for > > built-in NIC, So, the two node configuration and one external PCIe NW card > > configuration can easily go beyond 256 ports. > > > Ok, good point. If you think it's needed, and if we are changing the mbuf > structure, it might be a good time to extend that field while you are at it, save > a second ABI break later on. > > /Bruce > > > > > > > Regards, > > > /Bruce > > > > > > Ref: http://dpdk.org/ml/archives/dev/2014-December/009432.html > > > -- Jan Viktorin E-mail: Viktorin@RehiveTech.com System Architect Web: www.RehiveTech.com RehiveTech Brno, Czech Republic