From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by dpdk.org (Postfix) with ESMTP id 0DE222B95 for ; Thu, 26 Jul 2018 11:30:33 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga002.jf.intel.com ([10.7.209.21]) by fmsmga103.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 26 Jul 2018 02:30:31 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.51,404,1526367600"; d="scan'208";a="77975855" Received: from aburakov-mobl1.ger.corp.intel.com (HELO [10.237.220.86]) ([10.237.220.86]) by orsmga002.jf.intel.com with ESMTP; 26 Jul 2018 02:30:29 -0700 To: Thomas Monjalon Cc: dev@dpdk.org, john.mcnamara@intel.com, zhihong.wang@intel.com, qian.q.xu@intel.com, yu.y.liu@intel.com, lei.a.yao@intel.com, maxime.coquelin@redhat.com References: <0957f38f12ba6df24f0b48f24fe8236a6ce50efc.1532434698.git.anatoly.burakov@intel.com> <23947652.nx9p32IzIJ@xps> From: "Burakov, Anatoly" Message-ID: Date: Thu, 26 Jul 2018 10:30:28 +0100 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.9.1 MIME-Version: 1.0 In-Reply-To: <23947652.nx9p32IzIJ@xps> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit Subject: Re: [dpdk-dev] [PATCH] Revert "mem: allocate in reverse to reduce fragmentation" X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 26 Jul 2018 09:30:34 -0000 On 26-Jul-18 10:18 AM, Thomas Monjalon wrote: > 24/07/2018 14:21, Anatoly Burakov: >> This reverts commit 179f916e88e4a0fdd5ad4d20e226771d3d271c41. >> >> A few regressions with virtio/vhost have been discovered, due to the >> strong dependency of virtio/vhost on the underlying memory layout. >> Specifically, virtio/vhost share all memory pages starting from the >> beginning of the segment, while the patch above made it so that the >> memory is always allocated from the top of VA space, not from the >> bottom. >> >> Signed-off-by: Anatoly Burakov > > Applied with this fun title: > mem: revert reversed allocation > Next time i'll submit a patch which will revert reverted reverse allocation :) -- Thanks, Anatoly