台湾人眼里的华为

www.net130.com     日期:2006-8-13    浏览次数:
作者:陈怀临    出处:系统软件研究所

我们先来看一下一个CISCO HFR(HUGE FASTR ROUTER) 方面的新闻。 
2004年5月25日,CISCO终於宣布了其姍姍来迟的最高端的ROUTER。www.lightreading.com是这样发布评论的。 

连接LINK:http://www.lightreading.com/document.asp?doc_id=53319 

Cisco Systems Inc. (Nasdaq: CSCO - message board) unveiled its next-generation core router today, a move that some analysts believe could herald the overhaul of Cisco“s entire product line, even down to enterprise boxes (see Cisco Launches HFR ). 
The long-awaited HFR is a multichassis "terabit" router meant to compete with boxes from Avici Systems Inc. (Nasdaq: AVCI - message board; Frankfurt: 
BVC7), Chiaro Networks Inc., Hyperchip Inc., Juniper Networks Inc. (Nasdaq: JNPR - message board), and Procket Networks Inc. 

After more than four years in development, the box is making its debut today under its real name: the Carrier Routing System, or CRS-1 (no word on whether 
rapper KRS-ONE has been tapped as a spokesman). 

The CRS-1 truly is huge and fast, with a capacity of 640 Gbit/s in a 7-foot rack. It scales to 72 shelves rather than the 18 reported by sources, for an unreal 46 Tbit/s maximum capacity, or 1,152 OC768 ports. (Cisco reports 
this as 92 Tbit/s, using its usual convention of counting ingress and egress capacity separately.) 

But CRS-1 wasn“t intended to be just a big router, says Mike Volpi, senior VP and general manager of Cisco“s Routing Technology Group. Rather, Cisco wanted to start afresh to build an IP box that would suit telecom carriers“ 
needs for years to come. The software is engineered to produce the "permanent and continuous operation" demanded in the voice network, Volpi says. "It“s designed to be Class 5-like in its carrier manageability." 

读者请注意: 

(1)。 分析人员认为HFR将带来CISCO所有产品线(包括ENTERPRISE企业方面的OVERHUAL(全面检查,或全面结构性的考察)。笔者註:通常我们说一个产品是设计给TELCOM/CARRIER的或给ENTERPRISE的。这两方面是很不同的对产品的要求。) 

(2) 「Long-awaited" HFR...为什麼说」期待已久的「HFR?期待了多久?做了4年半!只有4。5年吗?从开始规划到5/25/04,6年都有了。几乎每个从CISCO出来的或在那里的都知道这个项目。一个太重要,太不可能完成的项目了。 

HFR或CRS-1仅仅是一个高速的ROUTER吗?不是,不仅仅是。HFR而且是CISCO的下一代完整的操作系统。我们下面再来读一下这方面的摘要。 

」......Most significantly, the CRS-1 deviates from Cisco“s Internetwork Operating System (IOS), the software that runs on nearly all its platforms. The new software is called IOS XR, but it“s been built from scratch. The transition is analogous to Microsoft Corp. (Nasdaq: MSFT - message board) 
moving from DOS-based operating systems to Windows NT, says analyst Stephen Kamman of CIBC World Markets. 
Just as NT did, IOS XR could begin trickling down to lower-level systems, eventually permeating Cisco“s entire portfolio, including edge and enterprise 
boxes. "The question is how quickly they can push that software through the product line," Kamman says. 
Analyst Debra Mielke of Treillage Network Strategies Inc. notes that the amount of firepower behind CRS-1 -- including the involvement of Volpi and chief development officer Mario Mazzola -- indicates Cisco has plans going 
beyond this one box. "I absolutely believe that all the innovation in [the CRS-1] will go throughout the product set," she says. "They wouldn“t have put all that money into [the technology] unless they were going to use it 
for something much more." Kamman believes the first step will be the "Son of HFR" box, a half-sized CRS-1 intended to replace the aging GSR 12000 line (see Sources: Cisco Building “Son of HFR“ ). Cisco officials won“t acknowledge the half-sized CRS-1; Volpi says only that future enhancements to the platform are planned.「 

读者请注意:Most significantly,也就是说,HFR的意义更为重要的方面是,一个崭新的嵌入式操作系统IOX XR。CISCO过去的操作系统就是眾所周知的IOS(与华为打官司的就是这个)。业界认为IOX XR的TRANSITION(注意:转变)重要性就相当与当年微软的WINDOWS与DOS的区别一样,可见其意义重大。 为什麼要用「转变」或」过渡「这个词?因为IOS的基础架构已经不能满足CISCO发 展的需要。如分析员所言,HFR的IOX XR可以被分解成小的模块,被非常容易的用在 
低端系统上,最后在所有的CISCO系统产品上。 

让我们再看另外的一些话,」CISCO在HFR CSR-1上面的心血巨大,例如,ROUTING BUSINESS UNIT的GM(总管)Volpi和首席开发员(CHIEF DEVELOPMENT OFFICER)Mario Mazzola的介入,证明CISCO绝不是简单的做一个高速ROUTER CRS-1。IOX XR将为CISCO拥抱下一代IP技术做好充分的準备,比如VOICE OVER IP方 面等等。 

CISCO推出这个新操作系统是下了大决心的。如果只是为了一个高性能ROUTER,CISCO可以在IOS基础上,如GSR12000的基础上改造。但为什麼不呢?笔者也不知道。但我们可以从公布的一些新闻中猜测一些背景来。 

在HFR系统中,一个很重要的部件是一个新的ROUTING CHIP。这个芯片是非常有意思的。一个有192个CPU CORE在一个DIE上。 

请看TENSILICA的消息发布:http://www.tensilica.com/html/pr_2004_08_02.html 
大家再来看一下CISCO的英雄,这个芯片的主设计师http://newsroom.cisco.com/dlls/innovators/ 
Core_IP/rajiv_deshmukh_profile.html 

下面这个LINK也透露了一些技术细节。 
http://www.eetimes.com/showArticle.jhtml?articleID=26806315 

通过上述的一下信息,我们可以得出如下结果: 
* NPU: From Tensilica Inc. www.tensilica.com 
* Every 12 NPU being a Cluster. 
* Every NPU with own L1 cache; A cluster shares L2. 
* Total 16 Clusters /* 16*12 = 192 NPU */ 
* Packets are distributed into clusters. 
* Two Extra Processor Core: One for Mgt; One for Debug 
* Fabric: IBM .13 
* Software Arch: Non pipeline based:-) 
* Programming Approach: C/C++ 

从文章可知,这个芯片的名字叫SPP。TAPOUT回来是2002年的岁末。接近200个CPU CORE的可编程网络处理器。读者不妨思考一下,在这个芯片上如何配置系统软件,逻辑如何划分。各种TRADE-OFF折衷如何考虑。。。 这是一个非常艰巨的项目。要同时具有理论水平和实际经验。更为重要的是,要对 IOS的LEGACY方面瞭如指掌。 

笔者个人估计,CISCO**不得不重新考虑其整个的操作系统的结构的原因之一正是因为这个强大的NPU。 

当然其他更深层的原因是,CISCO想通过这个项目设计出一个世界一流的,可扩展的,可伸缩的ROUTER。如果继续用那个庞大的IOS体系结构,这将是MISSION IMPOSSIBLE的。 所以,CISCO必须从整个系统软件结构上来思考。 

读者可以接著阅读如下文章: 
http://www.lightreading.com/document.asp?doc_id=42847 

Architecture 
The HFR router can be configured in one of three architectures: single core; dual core, interconnected with 1.2 Tbit/s parallel-optical-link (Paroli cables); or multicore, with two core chassis that interconnect up to 18 chassis. 

Software 

As mentioned, Cisco has developed an entirely new operating system for the HFR. The command line interface looks a lot like Cisco“s Internetwork Operating System (IOS), the software that runs most routers today. The IOS and the 
new operating system likely share a lot of the same code, but they are very different architecturally. Unlike IOS, the new OS is modular and runs different software packages that enable various large feature sets, such as management, MPLS, routing protocols, multicast, and security. 

正如评论所言,这个新的操作系统必须是非常模块化的,可以做的COMPONENT COMPUTING的范畴,可以是PLUG AND PLAY的。这也是为什麼CISCO的计划:HFR的软件体系结构将一步一步蔓延到所有的产品系列上。为了达到这个目标,不能达到上述软件设计目标,将不会能实现其长远计划。 

CISCO的这一重大举措是有风险的。这不是在学校做点东西,发篇文章。CISCO的下一代操作系统的成败,可能会影响CISCO的生存。这个决定没有JOHN CHAMLES的同意是谁也不敢轻易决定的。CISCO是一个PLATform的公司,说到本质上,其是一个系统软件公司。 

我们来看一看业界对这个新操作系统的一些负面评价: 
「Critics point out that the new OS could take years to stabilize. That would put the HFR at an apparent disadvantage against, say, Juniper“s T640 routers, which run that company“s established JunOS operating system. "[The CSR-1 is] an interesting departure from IOS. There“s the potential for [Cisco] to create more problems with their customer base," says Karen Livoli, senior product marketing manager at Juniper.」 

一个新的系统软件是需要时间来考验,通过CUSTOMER ISSUE来提高其稳定性等等。这个风险是很大的。特别对於CISCO的许多客户是TELCOM或CARRIER。 那麼CISCO为什麼还要这样作呢?在IOS的基础上接著发展不可以吗?答案是:IOS已经不能承担CISCO的MISSION了。IOS的体系结构是一个单纯的EXECUTIVE模型,非模块话,没有足够的保护,没有各种逻辑在不同空间的划分,另外一个CRITICAL的原因是,由於IOS长年的发展,来自许多被购买的公司的代码,IOS已经变成了一个巨大的怪物,一个根本无扩展性可言的系统(笔者註:有点像早期的VXWORKS系统,和传统的UNIX KERNEL,如LINUX。好歹LINUX还有一个LKM机制使得人们可以比较容易的来裁决系统)等等。这使得IOS很难面临CISCO的未来挑战,比如所有的系统产品SHARE一个INFRASTRUCTURE软件。不同德产品系列只要简单的添加模块/进程就可以。 

让我们来看看业界的评论: 
」Cisco needed to make the software change someday, even if it“s painful, analysts say. Because it“s not modular, IOS is a step behind JunOS and other software -- something IOS XR is intended to correct 「 

「Moreover, Cisco keeps adding to IOS piecemeal, as if it were the world“s largest ball of twine. "Imagine five years from now, if they hadn“t built this new software and they tried to keep IOS going. That thing would be a beast," Kamman says.」 

CISCO必须这样做,虽然这是非常痛苦的事情。。。IOS的结构不如JUNIPER的JUNOS。。。 

我们会在以后的文章里会介绍JUNOS的体系结构。并且指出JUNOS也是存在非常多的问题的,比如其大量的IN-KERNEL代码在CONTROL PLANE的BSD KERNEL里是一个非常重要的错误;其PFE端的PROPRIETARY 的MICRO-KERNEL也是使得整个JUNOS操作系统变得非常不容易移植,集成的主要原因之一。。 

那麼IOX到底是一个什麼东西呢?IOX的基础软件是一个基於微内核的网络操作系统。 

「IOS XR helps Cisco catch up in areas such as hot upgrades of software and separation of control, data, and management planes. The software is based on a kernel licensed from QNX Software Systems, but tailored for the job. "We have made some pretty substantial modifications to [the QNX code] that are Cisco proprietary," Volpi says. 」 

当然,就像JUNOS把BSD的很多部分都改动了一样,QNX NEUTRINO也是完整的被INTEGRATED INTO THE WHOLE SYSTEM。CISCO付QNX源代码的钱是不用说的了。从上述的业界评论,我们不无同意IOX最大优点之一是:通过整个基於MICRO-KERNEL的体系结构调整,CISCO使得其下一代网络操作系统的软件可以PLUG AND PLAY;可以非常容易的将CONTROL,DATA,MANAGEMENT分开(笔者註:这一点是非常非常重要,而且困难的。)。 

这就是CISCO的技术目标。看起来简单,坐起来非常的不容易。5到6年的EFFORTS。笔者听说,大约有3,4百人在这个项目中。大家想想其R&D的费用,光工资要多少?而且这样的项目的成功还不可知,要待市场和时间来考验。但是,我们发现,CISCO下了决心,MADE IT。 

为什麼? 
因为只有这样,CISCO的系统才能更加稳定。 

因为只有这样,CISCO的系统才能有高扩展性。 

因为只有这样,CISCO的系统才能有高PERformANCE。 ACCELERATION的LOGIC才能非常容易的被挪到DATA PLANE的CRITICAL PATH上。 

因为只有这样,CISCO的系统才能非常容易的将THIRD PARTY的软件集成起来。而不是手工的将其他的系统PORT到IOS上。才可以在技术上迅速的消化并且变成原有系统的一个ADD-ON value。 

因为只有这样,CISCO才能达到上述目标,才能进军其下一个企业发展的战略目标:IP服务性(SERVICE)公司。网络设备的MARGIN一定是越来越小。就像PC一样,有一天,卖设备是养不活员工的。然而,SERVICE是个无底洞。目前也只有IBM,HP,特别是IBM,等这样的巨型公司发展到或在朝这个方向这个境界。INTEL目前正出自从一个芯片公司往PLATform设备公司的方向上转变,离SERVICE还很遥远。 

而对一个提供SERVICE公司来说,其产品的可兼容性,可扩展性,稳定性,极容易与THRID PARTY的产品的互操作性就变得非常CRITICAL。 

我想这也就是CISCO不得不忍受PAIN和5年的时间,在HFR上从新OVERHAUL其系统软件基础体系结构,并突出IOX的原因之一吧。 

话说到这,华为,作为一个观察者(如果华为存在这样的观察者的话),应该想和做些什麼? 

本新闻共3页,当前在第3页  1  2  3  

相关新闻
推荐文章