As the breadth and depth of the ACI solution continues to grow, so does customer interest. Many customers who have invested in, and continue to invest in, the Nexus 2000-7000 switches find the ACI vision very compelling. So, this leads to a logical question regarding how an existing Nexus 2000-7000 fabric will integrate with an ACI fabric.
In short, customers can leverage current Nexus products and add ACI capabilities to their data centers in an incremental manner. Integrating ACI into an existing Nexus environment will not require replacement of existing Nexus switches. The benefits of ACI policy can be extended to apps on both physical and virtual servers within the existing Nexus fabric. This can be achieved as follows (double click on the graphic below to launch the 3+ minute presentation):
In this scenario, the existing Nexus fabric is serving as an optimized transport for an ACI overlay solution. However, this solution is very different from other industry overlay solutions. It’s different in that the ACI overlay provides integrated/embedded support for both physical and virtual servers, it allows use of existing L4-7 infrastructure, while providing the automation functionality of the ACI policy model.
If you’d like to learn more, there is a summary, as well as a white paper available. There is also this video whiteboard session that covers a subset of the elements mentioned above.
Tags: ACI, cloud, data center, network, networking, nexus, technology
Superior Platforms, Scale, and Operational Simplicity
Data Center trends like Virtualization, Solid State Drives, DC consolidation and Data Explosion are putting a tremendous amount of strain on the infrastructure. These challenges need targeted and multifaceted approach. It has to be holistic solution to the problems rather than point products for each unique problem. Data Centers require improvements in performance, flexibility, scalability, and reliability and ease of management. To address that Cisco revamped the MDS product line, the journey we started last year when we introduced 9710 and 9250i.
9710 – Director Class Switch with 3x the performance of any director, 384 ports of line rate 16G FC, highest reliability and flexibility.
9250i – Services Appliance supporting 10G FCIP, 16G FC and 10G FCoE in addition to IO Acceleration, Data Mobility Migration in compact 2 RU form factor.
We had a great success with the product line with steepest ramp and amazing customer feedback. Building on the success we have added new members to the product family and extended the innovation to allow for simpler management and scalable deployments.
a) Three New Products
- MDS 9148S – Industries’ most versatile affordable 1RU switch with High-Performance, Easy of Deployment, Enterprise-class features
- MDS 9706 – Unprecedented investment protection with high performance, reliability and multi-protocol flexibility
- High Density line rate 10G FCoE Card – For customers to adopt high density FCoE in incremental non-disruptive fashion on the existing FC footprint without forklift upgrades.
b) New Scalable Deployment Options
- Much Higher Scalability for SAN Infrastructures.
- Dynamic FCoE over Fabric Path
- Data migration enhancements for speed, scale and resiliency
c) New Management Features
- Hardware based FC Congestion Detection and Recovery
- Integration with Industry leading Platforms
- End to End Visibility
- Switch Health Score
With the addition of new members Cisco not only has best of the breed products but also broadest product portfolio. This allows customers to design the SAN precisely to their needs from small departmental SANs to the largest enterprises, from traditional LAN, SAN networks to fully converged fabric and everything in between.
Attend the Webinar on August 12th 8:00 PST to learn more : Register Now
Lets look at the capabilities of each product in little more detail
Cisco MDS 9148S: High-Performance, Easy to Deploy, Enterprise-class Fabric Switch
Versatile: 9148S pay as you grow model allows customers to start from small base and grow . It allows customers to grow from 12 Ports to 24, 36 and finally 48 without any rip and replace. It allows customers to go from 2/4/8G to 16G FC speeds. It is not only the most affordable switch shipping today across all the possible configurations but with 2x the range of ports it allows unparalleled scalability for future growth.
Ease of use: Power On Auto provisioning which allows 9148 and 9148S to automate switch setup. From getting DHCP, to downloading and applying the software to the final configuration is done automatically. Quick configuration wizard allows the box to be configured in an easy way. It shares the same NxOS as rest of the MDS and Nexus products. Power on Auto Provisioning (POAP) is important for large scale data centers where 9148S will be used as Top of the Rack (ToR) switch and distributed throughout the data center. This saves customer to go from box to box with the serial cable and program them individually. It allows for rapid, error free and consistent provisioning.
Enterprise Class switch: It offers the rich Enterprise features like non-disruptive software upgrade,32 Virtual SANs (VSANs), Inter-VSAN Routing (IVR), QOS, PortChannels, N-Port ID Virtualization (NPIV), N-Port Virtualization (NPV), Comprehensive Security in addition to redundant power supplies and fans. Its first of the kind switch in the industry to allow hardware based slow drain detection and recovery. It has back to front airflow.
Customer Use Case: Customer will use the 9148S to design small SAN environments like departmental SANs. Larger Enterprises will use 9148S as ToR Switch for ease of cabling and ease of Management. In addition to that 9148S will be used for BC/DR or remote locations. Pay as you go model is very attractive to customers as it allows them to grow the port count from 12 to 48 without any price penalty as their network demands grow.
Cisco MDS 9706: Extending MDS 9710 Director Qualities to a Smaller Form Factor
It is the highest performance director in the industry. It provides 3X the bandwidth compared to any compact director in the industry. Not only it provide 192 ports line rate performance at 16G but it is designed to provide line rate performance at 32G FC and 40G FCoE when those line cards are introduced without the forklift upgrades using the same type of fabric cards. With 6 fabric cards it provides 1.5Tbps of bandwidth per slot.
In addition to that this is industries first class of directors to offer Redundancy on all critical components including fabric cards. Smaller failure domain, Forward error correction, multi-point CRC checks, predictable and consistent performance for both latency and throughput.
Small to medium enterprises will use 9706 as Middle of the row and end of row switch in addition line rate 16G performance allows it to be used for connectivity to targets in addition to host connectivity. It will be used for both edge core and edge-core-edge designs.
In addition to the pod like deployments where 9RU form factor and 192 ports of line rate at 16G is very attractive.
Some of the specs of the switch are enumerated below
- 1.5 Tbps per slot switching capability
192 ports of 16G FC line rate today with 100% head room to grow to 32G FC) without forklift upgrade
- Industries Highest Reliability
N+1 Fabric redundancy, smaller failure domains, Forward Error Correction, CRC error checks at multiple points, In service software upgrades, Crossbar design with central arbitration and Virtual Output Queuing ensure customers not only get highest availability but also predictable and consistent throughput independent of the traffic profile.
With ability to support both FC and FCoE line cards. With capability to support 2/4/8/10/16G FC and 10G FCoE today and performance to support 32G FC and 40G FCoE on the same footprint.
Industry’s Highest-Density FCoE Module on a FC Director
With 48 ports this has the highest port density and greatest flexibility in the industry. Without any restrictions Cisco customers can now orchestrate FC, FCoE and mixed solutions. FCoE line card afford customers ability to design FC solutions and incrementally deploy FCoE without forklift upgrades and meeting the same features, reliability and availability as afforded by FC.
In addition to hardware we added extensive capabilities to enable small size to cloud scale deployments.
To support large scale out and scale up deployment models we have increased the scalability limits for the SAN infrastructure. The industry leading scalability numbers allow Cisco customer’s unprecedented future proofing and scalability to Scale out or Scale-up. Finally the Data Mobility Migration has 2x the speed and 8x the scale and higher resiliency.
Simplifying SAN Management
In addition to enhanced capabilities in Cisco tools MDS family is integrated with industry standard tools to provide faster configurations like automated zoning. Some of the examples of the tools are UCS Director, EMC ViPR, Microsoft System Center VMM and IBM PpowerVC.
To address complexity in the data-centers Cisco is focused on SAN Management simplification. First and foremost that is top of mind for customers is slow drain. If there are slow draining devices in the network it chokes the entire fabric. These conditions are transient, extremely difficult to isolate, debug and fix. To detect and recover for these conditions Cisco introduced Slow Drain Detection and Recovery in software in previous generation of devices. Now with the new products we have provided the support for these devices to run the slow drain detection and recovery in the hardware rather than waiting for software to come around polling individual ports every 100 ms which is a life time in the data center. As the table below shows with hardware based slow drain the detection speed has increased 100 times and recovery is of the order of nano seconds rather than 100ms.
||Recovery Action Latency – Start and Stop
||MDS 9500MDS 9148
||MDS 9700, MDS 9250i, MDS 9148S
For more info read this whitepaper
In addition to that Data Center Network Manager (DCNM) provides end to end visibility from hosts (virtual or Physical) through switches (MDS or Nexus) into the storage arrays independent of the protocol. DCNM is single pane of glass visibility into the Data Center for both SAN and LAN.
Host Path Redundancy Analysis checks the network every 24 hours or customer designated interval if there is end to end dual paths from Host to the target. It checks against port down situations, VSAN mismatches, VSAN Segmentation, LUN mismatches as well as makes sure both the ports are not on the same line cards. Similar activity that used to take months is now completed on the fly every 24 hours reducing risk and time to repair. Further more administrators are not surprised by an outage as they have complete visibility for the dual paths. Furthermore having both the paths up allows to mitigate any silent failures as well as avoid outages if one of the SAN fails.
Switch health score is another unique capability of DCNM to track switch health over time. It allows customer to quickly determine level of risk, isolate and fix the alerts resulting in low health score and track the health of the SAN over time.
As I started the discussion today Data Centers need a holistic approach to solving the challenges of the data center. Customers not only need higher performance, investment protection, lower opex and capex, reliability but also ease of management and tightly integrated end to end solution. The solutions and capabilities I described allows us to solve the challenges faced by data centers not only today for the years to come. We introduced MDS products in 2002 and since then we have introduced industries first innovation, just few examples out of that are enumerated below. We will continue to innovate in this space for the next decade.
Sr. Product Manager, DCBU
“The best time to plant a tree was 20 years ago. The second best time is now”
Tags: 16 Gigabit, 16G FC, 16Gb, 16Gb Fibre Channel, 192 Port, 9148S, 9706, 9710, architecture, availability, best practices, Cisco, cloud, Cloud Computing, Consolidation, convergence, data center, Data Mobility Manager, DCNM, design, Director, dmm, FCIP, FCoE, Fibre Channel, Fibre Channel over Ethernet, IO accelerator, it-as-a-service, MDS, MDS design, nexus, NX-OS, reliability, SAN, Storage, storage area networks, switch, switching, Unified Data Center, Unified Fabric, virtualization
Cisco has a broad base of data center customers with a diverse set of requirements and we meet their needs with Nexus – the most comprehensive switching portfolio in the industry. This week, we are making announcements for both the Nexus 9000 series and the Nexus 3000 series that provide design and deployment flexibility for our commercial, enterprise, service provider, as well as cloud customers. Key points of the announcement include:
- ACI (Application Centric Infrastructure) is shipping this month;
- Additional linecard and chassis options provide customer choice and flexibility;
- 100G linecards for the Nexus 9500 will be available in Q4CY14 and will offer the highest density in the industry; and
- New starter kits and bundles help customers ease transitions.
The Nexus 9000 Series
ACI is shipping this month
The Nexus 9000 series can operate in standard NX-OS mode or in ACI mode. In either case the Nexus 9000 portfolio delivers the value of the “5 P’s” of Power efficiency, Price, Port density, Performance, and Programmability. NX-OS mode provides customers with the value of the NX-OS operating system used by tens of thousands of customers in data centers around the world. ACI mode adds to NX-OS capabilities by providing an application driven policy model, integration of hardware and software, and centralized visibility, among other things. ACI requires a controller and switch software. Both are shipping this month. It is important to note that the pricing for this solution is simple and predictable. There is a perpetual license for each leaf switch. Other pricing approaches in the industry are monthly and are based on varying elements like number of VM’s. Comparing the two approaches is somewhat like comparing a cell phone bill that is either flat rate or usage based. Personally, I like the simplicity and predictability of flat rate. See The Future of Networking, as well as SDN and Beyond for additional details on new ACI announcements and how they can take you beyond SDN.
Additional linecard and chassis options underscore flexibility
We’ll consider how flexibility is delivered for both modular and fixed platforms. For modular switching, the Nexus 9500 modular chassis family offers different line card options that can be mixed in the same chassis and allow customers to “dial up” or “dial down” their design based upon the price, performance, feature set, and scale they want to achieve. There are basically 3 different ‘flavors’, all of which are now shipping:
- The Nexus 9500 X9400 set of 1/10G and 40G line cards are based on merchant silicon and provide industry-leading price and performance compared to other merchant silicon switches. These provide a very cost effective solution ideal for traditional modular data center designs.
- The Nexus 9500 X9500 set of 1/10G and 40G line cards are sometimes referred to as “merchant plus” because they have custom Cisco ASICs, in addition to merchant silicon, and are ideal for customers that need performance together with additional buffering and VXLAN routing capabilities. The X9500 line cards can be used in future ACI designs as well.
- The Nexus 9500 X9600 set of 40G line cards provide performance without compromise even for small packet sizes.
The Nexus 9300 series offers ACI capabilities (ala the X9500 linecards in item 2 above) in a fixed form factor. For customers interested in a merchant only fixed form factor, we offer the Nexus 3000 family. This week, we announced the new Nexus 3164, which provides 64 ports of 40G and is a great solution for 40G access or space constrained aggregation.
We are also announcing 100G linecards that we believe will deliver industry leading port density of up to 128 ports of 100G in a single chassis. 100G for both the X9400 and X9600 series will be available for the Nexus 9500 in Q4CY14. Cisco will offer an 8 port 100G X9400 line card and a 12 port 100G X9600 line card.
New starter kits and bundles ease transitions
There are numerous packages available to ease transitions – from 1G to 10G, 10G to 40G, or from traditional networks to ACI. There are 2 bundles I want to quickly call out. The first provides a smooth transition for customers with older End of Row Catalyst 6500’s in their data centers. It occupies the same rack space and uses the same cabling as they currently have, but provides 10X the performance. The second is basically an ACI starter kit, providing the APIC, spine switches and leaf switches, even optical cables – everything required to set up and get started with an ACI pod.
In summary, Cisco is continuing its rapid pace of innovation and execution around ACI and data center switching overall. Ultimately, this means customers gain choice, flexibility and true innovation to support their business needs.
Tags: ACI, application centric infrastructure, Cisco, cloud, data center, data center switch, network, networking, nexus, Nexus 3000, Nexus 9000, SDN, switch
We embarked upon this episode with an agenda. Take a sample of the building momentum around Cisco ACI. The growing benefits, details and momentum behind the Application Centric Infrastructure. First announced in November 2013 and just before we start shipping.
In my estimation, we saw five areas worth highlighting from Cisco Live:
- Cisco is ready to ship ACI
- Partnerships and joint use-cases are resonating with customers
- Strong integrations with APIC through OpFlex
- Partners see strong customer demand
- Partner are getting ready to ship ACI-based solutions
Great Q&A with Soni Jiandani from Network World’s John Dix: Cisco describes its SDN Vision She nails Cisco’s ACI vs. SDN messaging and any confusion you may still have with the positionoing. She also puts good context around the OpFlex protocol.
Our show is a great sneak peak for this summer’s blockbuster release of ACI Fabric Mode and the APIC Controller. If you need to catch up. Be sure and review the launch details we covered for ACI in November 2013: TWTV136: Inside the Application Centric Infrastructure
The key elements for ACI in that episode were:
- Application Awareness – top down control based on what was important
- A new, tighter coupling between software and hardware
- Recognition that virtualization on the compute side had not been accompanied by requisite innovation on the network wide – potential for wasted opportunity.
- East West traffic was growing gangbusters in the data center and needed assisted.
We walk through the following components of the offering:
- APIC – Centralized cluster controller
- Northbound API for standardized communication and control from Applications that need to interact with the Fabric
- Southbound API for third party network services integration
- Profiles – Application Network Profiles – the logical representation of all components of the application and its interdependencies on the application fabric
- ACI Fabric – new stateless hardware within the Nexus portfolio, 9000 series
So what was still missing?
– APIC GUI – How would we interact?
– Migration plan – Clarity on how to leverage within existing networks
– Southbound interface – more details on network control
– Partner Plans – who would support?
And that formed much of what we wanted to cover for today’s show – filling in the blanks on the momentum…just before the big release this summer.
Shashi Kiran level on set on what has been accomplished.
Ronak Desai, Director of Software Development walked Jimmy Ray through the new APIC interface.
I got a chance to ask Mike Cohen about OpFlex and where it fits.
And finally, Jimmy Ray weighed in with his view on partner support and the growth we are seeing for the Eco-System.
Please to enjoy!
Tags: 9000, 9k, ACI, cisco live, ciscolive, nexus, OpFlex, SDN, TechWiseTV