Archive for April, 2018
-
April 30, 2018
ARMADA 3720 SoC Enables Ground-Breaking Modular Router from CZ.NIC
By Maen Suleiman, Senior Software Product Line Manager, Marvell
Marvell ARMADA® embedded processors are part of another exciting networking solution for a crowdfunding project and are helping “power” the global open hardware and software engineering community as innovative new products are developed. CZ.NIC, an open source networking research team based in the Czech Republic, just placed its Turris MOX modular networking appliance on the Indiegogo® platform and has already obtained over $110,000 in financial backing.
MOX has a highly flexible modular arrangement. Central to this is a network processing module featuring a Marvell® ARMADA 3720 network processing system-on-chip (SoC). This powerful yet energy efficient 64-bit device includes dual Cortex®-A53 ARM® processor cores and an extensive array of high speed IOs (PCIe 2.0, 2.5 GbE, USB 3.0, etc.).
Figure 1: The MOX Solution from CZ.NIC
The MOX concept is simple to understand. Rather than having to procure a router with excessive features and resources that all add to the cost but actually prove to be superfluous, users can just buy a single MOX that can subsequently be extended into whatever form of network appliance a user needs. Attachment of additional modules means that specific functionality can be provided to meet exact user expectations. There is an Ethernet module that adds 4 GbE ports, a fiber module that adds fiber optic SFP connectivity, and an extension module that adds a mini PCIe connection. At a later stage, if requirements change, it is possible for that same MOX to be repurposed into a completely different appliance by adding appropriate modules.
Figure 2: The MOX Add-On Modules - Base, Extension, Ethernet and SFPThe MOX units run on Turris OS, an open source operating system built on top of the extremely popular OpenWrt® embedded Linux® distribution (as supported by Marvell’s ARMADA processors). This gives the appliance a great deal of flexibility, allowing it to execute a wide variety of different networking functions that enable it to operate as an email server, web server, firewall, etc. Additional MOX modules are already under development and will be available soon.
This project follows on CZ.NIC’s previous crowdfunding campaign using Marvell’s ARMADA SoC processing capabilities for the Turris Omnia high performance open source router - which gained huge public interest and raised 9x its original investment target. Turris MOX underlines the validity of the open source software ecosystem that has been built up around the ARMADA SoC to help customers bring their ideas to life.
Click here to learn more on this truly unique Indiegogo campaign.
-
April 05, 2018
VMware vSAN ReadyNode Recipes Can Use Substitutions
By Todd Owens, Field Marketing Director, Marvell
VMware vSAN ReadyNode Recipes Can Use Substitutions When you are baking a cake, at times you substitute in different ingredients to make the result better. The same can be done with VMware vSAN ReadyNode configurations or recipes. Some changes to the documented configurations can make the end solution much more flexible and scalable. VMware allows certain elements within a vSAN ReadyNode bill of materials (BOM) to be substituted. In this VMware BLOG, the author outlines that server elements in the bom can change including:- CPU
- Memory
- Caching Tier
- Capacity Tier
- NIC
- Boot Device
Ok, so we know what substitutions we can make in these vSAN storage solutions. What are the benefits to the customer for making this change?
There are several benefits to the HPE/Cavium technology compared to the other adapter offerings.
- HPE 520/620 Series adapters support Universal RDMA – the ability to support both RoCE and IWARP RDMA protocols with the same adapter.
- Why Does This Matter? Universal RDMA offers flexibility in choice when low-latency is a requirement. RoCE works great if customers have already deployed using lossless Ethernet infrastructure. iWARP is a great choice for greenfield environments as it works on existing networks, doesn’t require complexity of lossless Ethernet and thus scales infinitely better.
- Concurrent Network Partitioning (NPAR) and SR-IOV
- NPAR (Network Partitioning) allows for virtualization of the physical adapter port. SR-IOV Offloadmove management of the VM network from the Hypervisor (CPU) to the Adapter. With HPE/Cavium adapters, these two technologies can work together to optimize the connectivity for virtual server environments and offload the Hypervisor (and thus CPU) from managing VM traffic, while providing full Quality of Service at the same time.
- Storage Offload
- Ability to reduce CPU utilization by offering iSCSI or FCoE Storage offload on the adapter itself. The freed-up CPU resources can then be used for other, more critical tasks and applications. This also reduces the need for dedicated storage adapters, connectivity hardware and switches, lowering overall TCO for storage connectivity.
- Offloads in general – In addition to RDMA, Storage and SR-IOV Offloads mentioned above, HPE/Cavium Ethernet adapters also support TCP/IP Stateless Offloads and DPDK small packet acceleration offloads as well. Each of these offloads moves work from the CPU to the adapter, reducing the CPU utilization associated with I/O activity. As mentioned in my previous blog, because these offloads bypass tasks in the O/S Kernel, they also mitigate any performance issues associated with Spectre/Meltdown vulnerability fixes on X86 systems.
- Adapter Management integration with vCenter – All HPE/Cavium Ethernet adapters are managed by Cavium’s QCC utility which can be fully integrated into VMware v-Center. This provides a much simpler approach to I/O management in vSAN configurations.
-
April 02, 2018
Understanding Today’s Network Telemetry Requirements
By Tal Mizrahi, Feature Definition Architect, Marvell
There have, in recent years, been fundamental changes to the way in which networks are implemented, as data demands have necessitated a wider breadth of functionality and elevated degrees of operational performance. Accompanying all this is a greater need for accurate measurement of such performance benchmarks in real time, plus in-depth analysis in order to identify and subsequently resolve any underlying issues before they escalate.
The rapidly accelerating speeds and rising levels of complexity that are being exhibited by today’s data networks mean that monitoring activities of this kind are becoming increasingly difficult to execute. Consequently more sophisticated and inherently flexible telemetry mechanisms are now being mandated, particularly for data center and enterprise networks.
A broad spectrum of different options are available when looking to extract telemetry material, whether that be passive monitoring, active measurement, or a hybrid approach. An increasingly common practice is the piggy-backing of telemetry information onto the data packets that are passing through the network. This tactic is being utilized within both in-situ OAM (IOAM) and in-band network telemetry (INT), as well as in an alternate marking performance measurement (AM-PM) context.
At Marvell, our approach is to provide a diverse and versatile toolset through which a wide variety of telemetry approaches can be implemented, rather than being confined to a specific measurement protocol. To learn more about this subject, including longstanding passive and active measurement protocols, and the latest hybrid-based telemetry methodologies, please view the video below and download our white paper.
WHITE PAPER, Network Telemetry Solutions for Data Center and Enterprise Networks
