From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga04.intel.com (mga04.intel.com [192.55.52.120]) by dpdk.org (Postfix) with ESMTP id 4C4475B1C for ; Tue, 6 Mar 2018 12:03:21 +0100 (CET) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by fmsmga104.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 06 Mar 2018 03:03:21 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.47,431,1515484800"; d="scan'208";a="35858205" Received: from aburakov-mobl.ger.corp.intel.com (HELO [10.237.220.141]) ([10.237.220.141]) by fmsmga001.fm.intel.com with ESMTP; 06 Mar 2018 03:03:20 -0800 To: dev@dpdk.org Cc: Bruce Richardson , jianfeng.tan@intel.com, keith.wiles@intel.com References: <06149b2941712f7abe5c02602d444b5a6937ea2f.1520000413.git.anatoly.burakov@intel.com> From: "Burakov, Anatoly" Message-ID: <427df582-b695-c894-f861-0461116d6150@intel.com> Date: Tue, 6 Mar 2018 11:03:18 +0000 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:52.0) Gecko/20100101 Thunderbird/52.6.0 MIME-Version: 1.0 In-Reply-To: <06149b2941712f7abe5c02602d444b5a6937ea2f.1520000413.git.anatoly.burakov@intel.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit Subject: Re: [dpdk-dev] [PATCH v4 2/5] eal: use file to check if secondary process is ready 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: Tue, 06 Mar 2018 11:03:22 -0000 On 02-Mar-18 3:14 PM, Anatoly Burakov wrote: > Previously, IPC would remove sockets it considers to be "inactive" > based on whether they have responded. We also need to prevent > sending messages to processes that are active, but haven't yet > finished initialization. > > This will create a "init file" per socket which will be removed > after initialization is complete, to prevent primary process from > sending messages to a process that hasn't finished its > initialization. > > Signed-off-by: Anatoly Burakov > --- Self-NACK on this patch. Secondary processes may initialize data structures, which means IPC has to be active during init. Each subsystem will therefore have to synchronize access to IPC on their own. (For example, memory hotplug will only block IPC for a short period between rte_config_init() and init of memory/heap init) -- Thanks, Anatoly