From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?UTF-8?B?QW5kcsOpcyBMYWdhciBDYXZpbGxh?= Subject: Re: [Xen-users] Announcing the first release of SnowFlock Date: Sat, 13 Sep 2008 19:37:12 -0400 Message-ID: <48CC4EA8.6070306@cs.toronto.edu> References: <48CACC69.4070900@cs.toronto.edu> <90eb1dc70809121342oc4fe4aeucaaca5e7fee30087@mail.gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <90eb1dc70809121342oc4fe4aeucaaca5e7fee30087@mail.gmail.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Javier Guerra Cc: xen-devel@lists.xensource.com, xen-research@lists.xensource.com List-Id: xen-devel@lists.xenproject.org The more technical details of memory on demand etc can be found in our technical report: http://www.cs.toronto.edu/pub/reports/csrg/578/csrg-578-snowflock-LagarCavilla2008.pdf Thanks for your interest! Andres Javier Guerra wrote: > On Fri, Sep 12, 2008 at 3:09 PM, Andres Lagar-Cavilla > wrote: > >> More technically: >> Snowflock is our prototype implementation of the / Impromptu Cluster (IC)/ >> abstraction. In an IC, an application encapsulated inside a virtual machine >> (VM) is swiftly forked into multiple copies that execute on different >> physical hosts, and then disappear when the computation ends. ICs simplify >> the development of parallel applications and reduces management burden by >> enabling the instantiation of new stateful computing elements: workers that >> need no setup time because they have a memory of the application state >> achieved up to the point of forking. This approach combines the benefits of >> cluster-based parallelism with those of running inside a VM. >> >> Snowflock provides swift parallel VM cloning that makes it possible for >> Internet applications to deliver near-interactive performance for >> resource-intensive highly-parallelizable tasks. Snowflock makes use of four >> key techniques: /VM descriptors/ (condensed VM images that allow for >> sub-second suspension of a running VM and resumption of a of replicas); a >> /memory-on-demand/ subsystem that lazily populates the VM's memory image >> during runtime; a set of / avoidance heuristics/ that minimize the amount of >> VM memory state to be fetched on demand; and a /multicast distribution/ >> system for commodity Ethernet networking hardware that makes the overhead of >> instantiating multiple VMs similar to that of instantiating a single one. >> > > just reading the docs.... i find it nice how you can drive the > duplication of VMs from within the VM. great for grids. > > could you elaborate about the memory-on-demand? i couldn't find > anything about it on the manual, and it seems like a major advantage. > >