Netvisor powers the Rackscale Architecture from Intel/Supermicro

On May 5th, 2014, we announced that Pluribus Networks Netvisor is now powering the switch blades on the new Intel blade chassis announced by Supermicro Inc. Its creating quite a stir and is a proud moment for everyone at Pluribus Networks and Supermicro who made this possible.

There are several reasons why Netvisor is the ideal Hypervisor to power the switching blades:

• Integrated Openstack Controller with Horizon and REST APIs as the only management that is needed – The entire Netvisor cluster-fabric and the virtual/physical switching on the compute blades is exported to Openstack via neutron plugins and extensions. Our Freedom series Server-Switches also bundle the full Openstack controller allowing the entire rack of microblades to be managed as one unit via Openstack Horizon GUI. For people wanting to manage the network layer via traditional tools, Netvisor also offers a full featured cli to manage teh cluster-fabric along with high performance and multithreaded native C and Java APIs. Netvisor also provides multiple virtualized services with H/W offload. So services like NAT, DNS/DHCP, IP-Pools, Routing, Load balancing, etc are integrated via Openstack Horizon to support multi-tenancy at scale.
• Netvisor is a Distributed Plug and Play Hypervisor – The Supermicro blade chassis has 4 switch blades and 14 server blades. This is where the racks are going with micro servers etc. In a typical rack, you will have 7 such chassis giving you 98 server blades and 28 switch blades plus two top of the rack switches. An ideal platform for Rackscale computing that HPC and Private Cloud needs. In such architecture, you can’t deal with individual switches. Netvisor provides a full plug-and-play architecture with zero touch provisioning and entire switching infrastructure appears as one cluster-fabric with synchronized state and configuration sharing with no cabling mess. The entire cluster-fabric protocol and algorithm is based on TCP/IP with no special ASIC and H/W.
• Application level Analytics and Debuggability – Netvisor has in built support for looking at all physical servers, virtual machines and applications without needing any probes or agent software. The addition of Freedom series as Top of the Rack layer allows users to track millions or VMs and application level flows in real time as well as historical data. Helps with capacity planning, audit, congestion analytics, VM life cycle management, application level performance and debuggability analysis. In multi-tenancy enviroments, Netvisor allows each individual tenant to analyze its own VM, applications, and Services.
• Netvisor powers all types of switching platforms – Just the way server Hypervisor are now ubiquitously running from laptops to desktops to high end servers, Netvisor also supports Micro switch blades to the ODM Top of the Rack switches and more powerful Server-Switches.
• Netvisor runs on every possible control plane – On the Supermicro switch blades, Netvisor runs on a Avaton based control processor with 8Gb of memory and limited Flash storage. On other switches, it uses single to dual socket Xeon with 512Gb RAM and Fusion-io based storage.
• Netvisor is full Open – It runs on all open platforms is built from best of the breed Open source OS with addition for switching, Cluster-Fabric, and switch Virtualization. Run it as traditional switch mode or with your users choice of Linux (Ubuntu and Fedora by default).

Use Netvisor with Openstack on Supermicro’s blade chassis along with the Freedom series Top of the Rack to run the most dense and power efficient Rackscale Architecture today.

Netvisor powers Rackscale Architecture

Crossbow on Big F#@!ing Webtone Switch

Back in the days of SUN Microsystem, Scott McNealy asked us to build a big F#@!ing Webtone Switch. At that time, the underlying pieces weren’t there but over last few years the possibilities have opened up. We now have the switch chips from Broadcom and Intel that switch at 1.2Tbps in H/W. From a OS view, 1.2 Tbps of switching at 300ns latency is great but the more amazing thing is PCIe as a control plane which allows 20-40Gbps of control plane B/W where you can change switch registers, L2/L3-tables, TCAMs, etc at nano-second rates.

So after more than three years of work and million lines of C code, the Pluribus Network’s engineering team has the switch chip under Crossbow control. For people who are not sure what I am talking about, in 2005 project Crossbow invented virtual switching inside a server hypervisor and introduced hardware based Virtual NICs and dynamic polling to get 40Gbps of bandwidth through a server OS. The details were published in “Crossbow: From Hardware Virtualized NICs to Virtualized Networks” in ACM Sigcomm VISA 09.

In the goal to benefit from merchent silicon ecosystem and orchestrate the entire infrastructure using Open source OS on switches, the industry has been going on suboptimal paths. The most notable efforts around a centralized controller can barely deal with the scale of single switch and typically requires sending a packet to a controller running on a separate server. The latency of these transactions (typically in milliseconds to seconds) defeats the required reaction time in microseconds in virtualized environments where Network resources are shared. The other approach of just throwing the Intel or Broadcom SDK on a whitebox switch with Linux and Quagga doesn’t really solve the control plane problem. The Broadcom and Intel SDK are crafted for their specific switch chips and meant for configuration ease and not for high speed control plane software.

By bringing the Crossbow Architecture on the switch chip where it is part of the Network OS directly controlling the switch chip via the PCIe allowsus to get following benefit:

• Integrated Switch Hardware with fully programmable Control Plane allowing the performance and scale necessary to deal with 10Gbps switches (the distributed control plane is part of the Network OS running on the switch itself).
• Enable applications like DDoS, IDS, Firewall, Load Balancer, routing, messaging, etc that need to be in network to run on the switch itself and benefit from the H/W offload, high speed snooping, and flow capability that switch chip offers via C, Java, Perl, Python, etc programming interfaces in UNIX/Linux environment. Development, Deployment and Resource provisioning of these applications on Crossbow enabled switches is same as current server mechanisms and uses the existing tool chain (gcc/gdb, kvm, etc).
• Bring the benefit of merchent silicon ecosystem on switches under Openstack control enabling faster pace of innovation and cost advantages.

As we get ready to roll Netvisor (and its open source version – openNetvisor) out, I will discuss more details on this blog in near future.