Cover Comment Detail
get:
Show a cover comment.
patch:
Update a cover comment.
put:
Update a cover comment.
GET /api/covers/898/comments/722/?format=api
{ "id": 722, "web_url": "http://patchwork.dpdk.org/comment/722/", "msgid": "<CAKXZ7egJB5wQs_tTC4=fmiUDS0WM_Y2r6t0+xeMQ3RO69rFj0g@mail.gmail.com>", "list_archive_url": "https://inbox.dpdk.org/dev/CAKXZ7egJB5wQs_tTC4=fmiUDS0WM_Y2r6t0+xeMQ3RO69rFj0g@mail.gmail.com", "date": "2024-05-15T14:50:13", "subject": "Re: [PATCH v6 0/2] Methodology change for hugepage configuration", "submitter": { "id": 3281, "url": "http://patchwork.dpdk.org/api/people/3281/?format=api", "name": "Nicholas Pratte", "email": "npratte@iol.unh.edu" }, "content": ">What's the difference between this version and v4?\n\nVersion 5 was a response to your suggestions regarding the semantics\nof the hugepage variable names as it relates to countable or\nuncountable nouns. This patch, which was originally just a single\npatch, was expanded into a patch series since the variable changes\nsuggested are sort of logically independent of the original patch;\nthere were talks about potentially making this a separate patch\nentirely, but we agreed that a patch series for this change is\nappropriate.\n\nBut, to answer a question that I think you are indirectly asking, I\nran into some issues when sending out the latest version of this\npatch. While the latest version of this patch, version 6, was sent\nlast week and does show up on patchwork, it seems like the emails\nnever reached the mailing list for some (I just asked Patrick in the\noffice and he cannot seem to find them).\n\n> \"type\": \"object\",\n> \"description\": \"Optional hugepage configuration. If not specified, hugepages won't be configured and DTS will use system configuration.\",\n> \"properties\": {\n>- \"amount\": {\n>+ \"quantity\": {\n> \"type\": \"integer\",\n>- \"description\": \"The amount of hugepages to configure. Hugepage size will be the system default.\"\n>+ \"description\": \"The number of hugepages to configure. Hugepage size will be the system default.\"\n> },\n> \"force_first_numa\": {\n> \"type\": \"boolean\",\n\nThe only change that version 6 made is in reference to the suggestion\nthat Bruce made in a separate thread; I changed the description text\nfrom \"amount of\" to \"number of.\"\n\nHopefully this answers your question. Again, I ran into some issues\nsending the latest version out for this patch\n\nOn Mon, May 13, 2024 at 5:53 AM Juraj Linkeš <juraj.linkes@pantheon.tech> wrote:\n>\n> What's the difference between this version and v4?\n>\n> On Tue, May 7, 2024 at 7:44 PM Nicholas Pratte <npratte@iol.unh.edu> wrote:\n> >\n> > In order to prevent accidental misconfiguration of hugepages at runtime,\n> > the following changes are made to only allow for configuration of 2MB\n> > hugepages within the DTS config.yaml. In the previous implementation, a\n> > default hugepage size was selected via the size listed in /proc/meminfo.\n> > The problem with this implementation is that, assuming the end-user has\n> > made prior modifications to the system, /proc/meminfo may default to\n> > hugepage sizes that are not recommended to be configured at runtime\n> > (i.e. 1GB hugepages). This can lead to two problems: overallocation of\n> > hugepages (which may crash the remote host) configuration of hugepages\n> > sizes that are not recommended during runtime. In this new implementation,\n> > we stipulate that any runtime hugepage configuration size that is not 2MB\n> > is considered an outlier. If the end-user would like to configure either\n> > 1GB hugepages or any unique hugepage size outside of 2MB, then they should\n> > make these configurations either at startup (in the case of 1GB hugepages)\n> > or runtime outside of DTS configuration (if a user would like hugepages\n> > that are not 2MB). In either case, the expectation is that, if wish to\n> > use hugepage sizes that are not 2MB, you will make these changes outside\n> > and prior to the initialization of DTS.\n> >\n> > The end-user has two options: remove the option for hugepage\n> > configuration in the conf.yaml, or keep the option and specify the\n> > amount of 2MB hugepages desired. In the case of the former, then we assume\n> > that hugepages are already configured prior to DTS initialization. In\n> > the latter case, the user must define the amount of 2MB hugepages to be\n> > configured at runtime. If the amount of 2MB hugepages requested exceeds\n> > the amount of 2MB hugepages already configured on the system, then the\n> > system will remount hugepages to cover the difference. If the amount of\n> > hugepages requested is either greater than or equal to the amount\n> > already configured on the system, then nothing is done.\n> >\n> > Nicholas Pratte (2):\n> > dts: Change hugepage runtime config to 2MB Exclusively\n> > dts: Change hugepage 'amount' to a different term\n> >\n> > doc/guides/tools/dts.rst | 6 ++++-\n> > dts/conf.yaml | 8 +++---\n> > dts/framework/config/__init__.py | 8 +++---\n> > dts/framework/config/conf_yaml_schema.json | 12 ++++-----\n> > dts/framework/config/types.py | 4 +--\n> > dts/framework/testbed_model/linux_session.py | 28 +++++++++++---------\n> > dts/framework/testbed_model/node.py | 4 ++-\n> > dts/framework/testbed_model/os_session.py | 7 ++++-\n> > 8 files changed, 45 insertions(+), 32 deletions(-)\n> >\n> > --\n> > 2.44.0\n> >", "headers": { "Return-Path": "<dev-bounces@dpdk.org>", "X-Original-To": "patchwork@inbox.dpdk.org", "Delivered-To": "patchwork@inbox.dpdk.org", "Received": [ "from mails.dpdk.org (mails.dpdk.org [217.70.189.124])\n\tby inbox.dpdk.org (Postfix) with ESMTP id 7817E44037;\n\tWed, 15 May 2024 16:50:27 +0200 (CEST)", "from mails.dpdk.org (localhost [127.0.0.1])\n\tby mails.dpdk.org (Postfix) with ESMTP id EE8524025C;\n\tWed, 15 May 2024 16:50:26 +0200 (CEST)", "from mail-lj1-f181.google.com (mail-lj1-f181.google.com\n [209.85.208.181])\n by mails.dpdk.org (Postfix) with ESMTP id A729E4021D\n for <dev@dpdk.org>; Wed, 15 May 2024 16:50:25 +0200 (CEST)", "by mail-lj1-f181.google.com with SMTP id\n 38308e7fff4ca-2e67dc957b7so3527851fa.3\n for <dev@dpdk.org>; Wed, 15 May 2024 07:50:25 -0700 (PDT)" ], "DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=iol.unh.edu; s=unh-iol; t=1715784625; x=1716389425; darn=dpdk.org;\n h=content-transfer-encoding:cc:to:subject:message-id:date:from\n :in-reply-to:references:mime-version:from:to:cc:subject:date\n :message-id:reply-to;\n bh=fl8yP5xLiGR39qczXrF4eNUjXCHiLDiPq4+igUnE7+s=;\n b=aH6sbNv8q9Tcot1vslN8ErHpgvGz8ODYgooG5nHcHrK6LrupILioP12xfhrn83Vsws\n LK1ymaoDj9NqyGFXhyh3StvxZWPzEAddF/W4GJnRfDVZuEafWLM9ViNPBrRDKgN3Pun9\n GgGzCpkIj3qIBVP+l3uo+pa1P08iclViWipk8=", "X-Google-DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed;\n d=1e100.net; s=20230601; t=1715784625; x=1716389425;\n h=content-transfer-encoding:cc:to:subject:message-id:date:from\n :in-reply-to:references:mime-version:x-gm-message-state:from:to:cc\n :subject:date:message-id:reply-to;\n bh=fl8yP5xLiGR39qczXrF4eNUjXCHiLDiPq4+igUnE7+s=;\n b=DbWxqIOpW1mMC8EiGrZrj9gKYWysxioZNJz7re1bXxeYTqiX/AmvQJFzPWbVPaIHhu\n PneP9W9IJJUxiFhCVArjwNWYpiwBlqnNgSq1xL2EfrfetCCHqTWRPHBqQ8ApD6MRDPY5\n UySN5RarMQYwXFpJ6gnvtzGODqtG8+QdnLnE65vMFR4PaqrY/jPwPoRAabIXEaG6npkl\n TuS+0Sy6BJ6LBeOe4G+SeHG2O47s4Rnd0wrPiTZ01BAriXuaLZPF7W+FC0T8AXsUwH+z\n JcFex4UGO7eFtu1DhZoQ7T4qLmCn0oioMyNR7JR2KalXt2UIge2IqrX0DPSEn9e2Ed8v\n n/tw==", "X-Forwarded-Encrypted": "i=1;\n AJvYcCXmJo5jS8u/fL3Z9Nx8RmcYR/o/PjYGW/3va1v35RRV+2CMyfo2NOyiDi6bCISpgClC5GrBXLVk3w582B4=", "X-Gm-Message-State": "AOJu0YwEwDT0ulFfOoRTsCIsMXxbPisVElR0Ud9sb39rHcxMzY2yP2gl\n UtmRc42irdTlYmkgOTfObvoNUFFAu44zJjXSyWRfgj5yzT5WXupI8JTAOcmq0rVex4HrkiSV8w/\n 76l9PR2flIK8rNb3YkLZQgkMdQ94ze3SuYHW8Pw==", "X-Google-Smtp-Source": "\n AGHT+IEL697eLkRufx/SOoaxP9xLBYWwxj4frejUtBsJJMaV5mNDREvrchuVayfM75Ov4uB0vMZ9vFerccdUL6OlQsM=", "X-Received": "by 2002:a2e:8e93:0:b0:2de:d4ef:47d8 with SMTP id\n 38308e7fff4ca-2e5204b9e24mr92739741fa.3.1715784624938; Wed, 15 May 2024\n 07:50:24 -0700 (PDT)", "MIME-Version": "1.0", "References": "<20240430184533.29247-4-npratte@iol.unh.edu>\n <20240507174430.29403-1-npratte@iol.unh.edu>\n <CAOb5WZb0yzv1yVzXayGDhvFKE2nTexLHUQxp9fja1-iFEURoCQ@mail.gmail.com>", "In-Reply-To": "\n <CAOb5WZb0yzv1yVzXayGDhvFKE2nTexLHUQxp9fja1-iFEURoCQ@mail.gmail.com>", "From": "Nicholas Pratte <npratte@iol.unh.edu>", "Date": "Wed, 15 May 2024 10:50:13 -0400", "Message-ID": "\n <CAKXZ7egJB5wQs_tTC4=fmiUDS0WM_Y2r6t0+xeMQ3RO69rFj0g@mail.gmail.com>", "Subject": "Re: [PATCH v6 0/2] Methodology change for hugepage configuration", "To": "=?utf-8?q?Juraj_Linke=C5=A1?= <juraj.linkes@pantheon.tech>", "Cc": "probb@iol.unh.edu, bruce.richardson@intel.com,\n Honnappa.Nagarahalli@arm.com, thomas@monjalon.net, jspewock@iol.unh.edu,\n yoan.picchi@foss.arm.com, mb@smartsharesystems.com,\n wathsala.vithanage@arm.com, paul.szczepanek@arm.com, dev@dpdk.org", "Content-Type": "text/plain; charset=\"UTF-8\"", "Content-Transfer-Encoding": "quoted-printable", "X-BeenThere": "dev@dpdk.org", "X-Mailman-Version": "2.1.29", "Precedence": "list", "List-Id": "DPDK patches and discussions <dev.dpdk.org>", "List-Unsubscribe": "<https://mails.dpdk.org/options/dev>,\n <mailto:dev-request@dpdk.org?subject=unsubscribe>", "List-Archive": "<http://mails.dpdk.org/archives/dev/>", "List-Post": "<mailto:dev@dpdk.org>", "List-Help": "<mailto:dev-request@dpdk.org?subject=help>", "List-Subscribe": "<https://mails.dpdk.org/listinfo/dev>,\n <mailto:dev-request@dpdk.org?subject=subscribe>", "Errors-To": "dev-bounces@dpdk.org" }, "addressed": null }