Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756740AbZANWeY (ORCPT ); Wed, 14 Jan 2009 17:34:24 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754223AbZANWeP (ORCPT ); Wed, 14 Jan 2009 17:34:15 -0500 Received: from serrano.cc.columbia.edu ([128.59.29.6]:65247 "EHLO serrano.cc.columbia.edu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754136AbZANWeO (ORCPT ); Wed, 14 Jan 2009 17:34:14 -0500 Message-ID: <496E67DA.7050503@cs.columbia.edu> Date: Wed, 14 Jan 2009 17:31:54 -0500 From: Oren Laadan Organization: Columbia University User-Agent: Thunderbird 2.0.0.19 (X11/20090105) MIME-Version: 1.0 To: balbir@linux.vnet.ibm.com CC: Andrew Morton , Linus Torvalds , containers@lists.linux-foundation.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-api@vger.kernel.org, Thomas Gleixner , Serge Hallyn , Dave Hansen , Ingo Molnar , "H. Peter Anvin" , Alexander Viro , Mike Waychison Subject: Re: [RFC v12][PATCH 01/14] Create syscalls: sys_checkpoint, sys_restart References: <1230542187-10434-1-git-send-email-orenl@cs.columbia.edu> <1230542187-10434-2-git-send-email-orenl@cs.columbia.edu> <20090114180441.GD21516@balbir.in.ibm.com> In-Reply-To: <20090114180441.GD21516@balbir.in.ibm.com> Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 7bit X-No-Spam-Score: Local Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1676 Lines: 41 Balbir Singh wrote: > * Oren Laadan [2008-12-29 04:16:14]: > >> Create trivial sys_checkpoint and sys_restore system calls. They will >> enable to checkpoint and restart an entire container, to and from a >> checkpoint image file descriptor. >> >> The syscalls take a file descriptor (for the image file) and flags as >> arguments. For sys_checkpoint the first argument identifies the target >> container; for sys_restart it will identify the checkpoint image. >> >> A checkpoint, much like a process coredump, dumps the state of multiple >> processes at once, including the state of the container. The checkpoint >> image is written to (and read from) the file descriptor directly from >> the kernel. This way the data is generated and then pushed out naturally >> as resources and tasks are scanned to save their state. This is the >> approach taken by, e.g., Zap and OpenVZ. >> >> By using a return value and not a file descriptor, we can distinguish >> between a return from checkpoint, a return from restart (in case of a >> checkpoint that includes self, i.e. a task checkpointing its own >> container, or itself), and an error condition, in a manner analogous >> to a fork() call. >> >> We don't use copyin()/copyout() because it requires holding the entire > > ^^^^^^^^^^^^^^^^^^^ Do you mean get_user_pages(), > copy_to/from_user()? Yes, I meant copy_to/from_user() ... Oren. -- 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/