Showing posts with label Testing. Show all posts
Showing posts with label Testing. Show all posts

Tuesday, January 7, 2020

Anritsu intros Oscilloscope 53-Gbaud Clock Recovery Unit

Anritsu introduced a Clock Recovery Unit (CRU) option for its BERTWave MP2110A oscilloscope that supports trigger clock generation from a 53-Gbaud PAM4 optical signal.

When combined with existing oscilloscope functionality, the new 53-Gbaud CRU can evaluate various PAM4 optical modules during development and manufacturing compared to solutions requiring external sampling oscilloscopes.

Anritsu said it developed the 53-Gbaud CRU for the BERTWave MP2110A sampling oscilloscope to address expanding PAM4 signal analysis requirements. The solution is more economical than a sampling oscilloscope that requires a separate trigger clock signal synchronized with the data signal to conduct PAM4 measurements. This is due to the fact that optical modules outputting PAM4 signals typically do not have a trigger signal. The BERTWave MP2110A can be used by engineers to more efficiently evaluate the physical layer of 25G to 400G optical transceiver modules and equipment components, such as optical cables, used by data centers, Core/Metro networks, 4G/5G mobile backhaul, and 5G mobile fronthaul.

https://www.anritsu.com/en-US/test-measurement/news/news-releases/2019/2019-12-20-us01

Tuesday, December 10, 2019

Spirent signs over 100 deal for 5G related testing in 2019

Spirent Communications closed more than 100 5G-related deals during 2019.

The company says cites accelerated deployment timetables that require complex testing and the need to incorporate assurance into new, next-gen networks for guaranteed quality. Spirent is now engaged in more than 150 global 5G initiatives with a broad mix of operators, device makers, network equipment manufacturers, academic institutions, government and cloud providers.

In addition, Spirent notes that more than half of its 5G business is taking place in the Asia-Pacific region as countries like South Korea gain traction with customized offerings tailored to data-hungry subscribers consuming high-bandwidth content such as AR and VR. In China, the company is supporting nationwide efforts to prepare the transport network and data center architecture for mass market deployments. About one-third of Spirent’s 5G deals are in the Americas, with the remainder across Europe. 5G transport, 5G core and 5G RAN projects comprise the majority of deals as operators pursue a range of network rollout strategies.

“If you took the industry’s pulse early last year, all eyes were on 2020 for mass movement in 5G, but those timetables have been turned on their heads as operators navigate an expanding set of market dynamics that demand speed and scale,” said Spirent Head of 5G Steve Douglas.

www.spirent.com/solutions/5g-network-testing

Thursday, December 5, 2019

Spirent intros 100G and Crypto performance testing

Spirent Communications introduced a C200 appliance for 100G and Crypto performance testing.

The C200, which represents a significant expansion of the Spirent CyberFlood security and application performance testing solution family, is a 1RU appliance providing connectivity at 10G, 25G, 40G, 50G, and 100G. The C200 offers up to 16 x 10G or 4 x 100G ports per appliance. Multiple C200s can be combined to offer 48 x 100G or 192 x 10G ports, delivering more than 3.5Tbps of application layer testing capacity in 12U of rack space.

The C200 with CyberFlood supports NetSecOPEN standards-based testing methodologies, that better reflect how modern security and content inspection solutions will perform under a variety of real-world traffic conditions and threats. In addition, the C200 supports Spirent’s legacy Avalanche solution, which provides extensive client emulation and application services load testing on a massive scale.

https://www.spirent.com/Products/CyberFlood

Wednesday, November 6, 2019

Anritsu intros 116G PAM4 error detector for 400 GbE and 800 GbE

Anritsu introduced a PAM4 Error Detector (ED) module supporting 116-Gbps bit error rate tests for its Signal Quality Analyzer-R MP1900A series.

Anritsu said its MP1900A instrument delivers error-free measurement of PAM4 signals at 116 Gbpss with industry-best operation bit rates and high Rx sensitivity performance. Combined with the previously released MP1900A series PAM4 Pattern Generator that supports high-accuracy BER measurements of PAM4 signals, the BERT allows engineers to accurately evaluate bit error rates of 400 GbE/800 GbE communications equipment and devices.



Anritsu releases 400GbE PAM4 BER Test

Anritsu announced the commercial release of its 64-Gbaud PAM4 Pulse Pattern Generator (PPG) and 32-Gbaud PAM4 Error Detector (ED) for use in 400GbE testing.

The new PAM4 BERT modules can be installed in the Anritsu Signal Quality Analyzer-R MP1900A series to implement a bit-error-rate test solution using either the 26.5625 Gbaud PAM4 x 8 lanes or 53.125- Gbaud PAM4 x 4 lanes methods. When using the PAM4 method to encode data as four amplitude levels, the gap between signal levels is one-third compared to the NRZ method, which reduces the unit time per symbol at higher baud rates, emphasizing the importance of signal quality in achieving high-speed transmissions.

Thursday, September 12, 2019

UNH-IOL offers cable testing for automotive Ethernet

The University of New Hampshire InterOperability Laboratory (UNH-IOL) introduced OPEN Alliance TC9 Cable Testing to their Automotive Ethernet Test Group.

The UNH-IOL is now an approved test lab for 1000BASE-T1 cable testing to OPEN Alliance TC9, which allows for cable manufacturers to have unshielded and shielded twisted-pair cables tested for conformance for Automotive Ethernet applications.

As part of UNH-IOL’s Automotive Ethernet Test Services, the new TC9 Cable Testing service allows customers to verify their automotive cable assemblies and harnesses meet the OPEN Alliance requirements supported by Automotive OEMs, providing customers with confidence that the results are accurate and certified. This new service is now apart of the suite of OPEN Alliance testing the lab offers including TC1, TC10, and TC12 test specifications for PHY Conformance.

“Until now, the UNH-IOL’s Automotive Ethernet testing services focused on silicon validation testing for Automotive PHYs,” said Curtis Donahue, senior manager, Ethernet Technologies UNH-IOL. “By including OPEN Alliance TC9 testing, we’re expanding our Ethernet physical layer expertise to the cable and wire community; hoping to better support the Single Pair Ethernet industries.”

In addition, the UNH-IOL offers Automotive Testing for 100BASE-T1 and 1000BASE-T1 compliance, including physical layers (PHY) and electronic control units (ECU) and offers testing solutions with their custom FPGA test tool, BitPhyer, which is designed to test the IEEE 802.3™ MAC, Flow Control, PCS, and RS layers for Ethernet devices.

Sunday, July 21, 2019

Ixia intros Cloud Peak NFVi Benchmarking Solution

Ixia, which is a division of Keysight Technologies, introduced its "Cloud Peak" benchmarking solution for Network Functions Virtualization infrastructure (NFVi).

Cloud Peak offers service providers the following key benefits:

  • Simplified NFVi benchmarking via a web-based, easy-to-use automation solution
  • An Open Platform for NFV (OPNFV) that integrates the powerful, but complex OPNFV Yardstick framework for infrastructure compliance
  • Elastic workloads that scale from testing a single server to a datacenter
  • Powerful analytics that provide extensive reporting and real-time dashboards
  • Cloud Peak delivers a rigorous set of methodologies to understand the capabilities and performance of an infrastructure under varied conditions, to evaluate design tradeoffs, upgrades and component swaps, and to identify performance bottlenecks. 
  • Cloud Peak’s first release focuses on VMware vCenter and OpenStack, the leading carrier platforms for NFV and VMWare NFV infrastructure.

“NFVi adds a new layer of complexity, yet it enables service providers to accelerate NFV deployment and realize its business benefits,” said Sunil Kalidindi, vice president of product management for Keysight’s Ixia Solutions Group. “With NFVi, the burden of system-level testing shifts from the network equipment provider to the service provider who needs to integrate the virtual network functions with their own customized server infrastructure. Cloud Peak enables the service provider to characterize the infrastructure to understand what it can handle, how to improve it, and if it is reaching its capacity.”

http://www.keysight.com

Thursday, February 28, 2019

Infovista expands 5G testing and planning capabilities

Infovista announced new versions of its TEMS Investigation and Planet network planning and test solutions for mobile operators.

With this release, Infovista introduces support for 5G smartphones based on the Qualcomm X50 chipset. With initial support of Qualcomm based devices and plans for agnostic device support, customers will be able to choose between different test devices and scanners to support 5G NR network testing. This allows early adopters of 5G NR to gain insight into the performance of different smartphones and their interaction with real 5G NR networks ensuring QoE for subscribers. Infovista is now delivering this solution to a number of 5G NR Mobile Operators and to several global infrastructure suppliers.

Infovista also announced a new version of its RF planning tool, Planet. Planet now provides customers with new, unprecedented levels of accuracy and performance including, enhanced 3D capabilities, and its ability to use big data to predict data traffic. Infovista has also improved accuracy by producing high-definition GeoData and 5G antenna patterns.

https://www.infovista.com/products/tems-portfolio

Wednesday, December 19, 2018

Keysight, Qualcomm test 5G NR Standalone Data Transfer

Keysight Technologies and Qualcomm have demonstrated a 3GPP 5G New Radio (NR) standalone (SA) mode IP data transfer.

The testing, which used Keysight’s 5G network emulation solutions and a mobile smartphone form-factor test device consisting of a 5G modem and antenna modules from Qualcomm, was achieved using a network configuration that combines the latest 3GPP Release 15.3.0 5G NR technologies.

The companies described the achievement an important milestone that enables mobile operators to deploy 5G NR SA mode, which does not rely on an anchor in the LTE network, to deliver enhanced Mobile Broadband (eMBB) services required by many 5G use cases.

“We are delighted that Keysight’s expertise and innovations in 5G solutions are helping us in the next major milestone of achieving IP data transfer in standalone mode,” says Jon Detra, vice president, engineering, Qualcomm Technologies, Inc. “With 5G commercialization starting in the first half of 2019, Qualcomm Technologies joining forces with Keysight, helps enable the entire mobile ecosystem to make 5G a commercial reality.”

Monday, December 10, 2018

Keysight's validated for 5G NR device certification

Keysight Technologies' 5G Conformance Toolset is the first test solution to be approved for 5G New Radio (NR) device certification by PTCRB, a certification forum comprised of select leading cellular operators, accelerating commercial availability of 5G mobile devices across the ecosystem.

The milestone was achieved as a result of the extended collaboration between Keysight and Qualcomm focused on verifying the validity and behavior of the radio frequency (RF) and protocol conformance test specifications as defined by 3GPP.

“The PTCRB approval of Keysight’s 5G conformance test solution establishes an important milestone and enables Keysight to help the global mobile ecosystem accelerate 5G product design development and validation,” said Kailash Narayanan, vice president of Keysight’s wireless test group. “Keysight’s close collaborations with market makers and influential participation in standardization organizations have contributed to the realization of this industry-first achievement, facilitating early 5G commercial deployment.”

Sunday, September 9, 2018

UNH-IOL intros 50/100/200/400 Ethernet - PAM4 testing

The University of New Hampshire InterOperability Laboratory (UNH-IOL) is introducing a testing service covering the new IEEE 802.3bs and the new IEEE 802.3cd specification for 50, 100, 200 and 400 Gigabit Ethernet based on PAM4 signaling.

The new services are for electrical and optical conformance testing of 50, 100, 200 and 400 Gigabit Ethernet specifications, with plans to offer interoperability testing as new higher speed Ethernet products enter into development and, eventually, the market.

UNH-IOL said the need for Ethernet speeds exceeding existing 100 Gigabit (based on 25G NRZ signaling) is being driven by exponentially increasing capacity demands across the board. Cloud service providers are looking to the higher efficiency and density that 50Gb/s PAM4 technologies (scalable up to 400Gb/s) Ethernet offers as they build out massive cloud-scale data centers, while the surge in mobile connectivity has telecoms pursuing higher speed Ethernet services. Additionally, bandwidth demand continues to grow at data centers tasked to service high-bandwidth, rich media applications such as video streaming, online gaming and digital marketing. In response, the UNH-IOL has taken a leading step to provide Ethernet stakeholders with testing services for 50, 100, 200 and 400 Gigabit through the multi-million dollar investment in new state of the art testing equipment.

“Today, a diverse array of applications and markets are driving the need for higher-speed, higher-density and lower cost connectivity solutions. Advances in new signaling technology is enabling the industry to rapidly deploy optimized solutions that achieve higher data rates to meet this demand,” said Mike Klempa, UNH-IOL Ethernet and Storage Technical Manager. “The investment in new equipment to test to these higher Ethernet speeds follows in line with UNH-IOL’s commitment to provide the most comprehensive Ethernet testing in a rapidly changing industry and also allows us to leverage our expertise in past 100Gb/s testing to help control testing costs at these evolving signaling types.”


Thursday, April 19, 2018

Empirix lands $19M contract with Tier 1 North American mobile operator

Empirix has been awarded a 3-year contract valued at US$19 million.

The unnamed, tier 1 North American mobile operator selected Empirix to improve the quality of performance for their mobile voice, VoWiFi and VoLTE networks, to score and increase customer experience satisfaction, and reduce OpEx related to MTTR.

Empirix provides an end-to-end view of voice service over any radio technology with real time analytics for a proactive and predictive approach to the service. The software solution, which is comprised of Empirix’s EXMS and IntelliSight solutions, will identify Quality of Experience anomalies and ensure customer satisfaction and operational efficiencies of the provider’s new network by establishing Quality of Service baselines and measuring performance gains.

Wednesday, April 11, 2018

EXFO's quarterly sales rise 7.8% to US$64.7 million

EXFO reported sales of US$64.7 million in the second quarter of fiscal 2018, up 7.8% year-over-year. Sales were up 5.2% to US$128.1 million at the halfway mark of the company's fiscal year. 

In January 2018, EXFO assumed full control of Astellia, a global leader in the performance analysis of mobile networks and subscriber experience.

Sales, excluding the one-month contribution of Astellia, attained US$62.9 million in the second quarter of 2018 compared to US$60.0 million in the second quarter of 2017. Astellia contributed US$1.8 million in sales in the second quarter and first half of 2018. Astellia's sales were reduced by US$0.3 million to account for acquisition-related fair value adjustment of deferred revenue.

IFRS net loss attributable to the parent interest totaled US$4.7 million, or US$0.08 per share, in the second quarter of fiscal 2018 and US$2.0 million, or US$0.04 per share, at the halfway mark of the fiscal year. In comparison, net earnings attributable to the parent interest totaled US$1.0 million, or US$0.02 per diluted share, in the second quarter of 2017 and US$4.3 million, or US$0.08 per diluted share, in the first half of 2017.

Adjusted EBITDA totaled US$2.5 million, or 3.9% of sales, in the second quarter of 2018 and US$8.6 million, or 6.7% of sales, in the first half of the fiscal year.

"I am thrilled with the closing of the Astellia acquisition as it positions EXFO among the top five providers worldwide of service assurance solutions," said Philippe Morin, EXFO's Chief Executive Officer. "Together, we have created a strong critical mass with solutions deployed at more than 250 network operators, while our global sales organizations have been merged to maximize cross-selling opportunities. Similarly, our unique portfolio of complementary technologies will be combined to deliver unmatched capabilities in high-growth markets like NFV/SDN, IoT and 5G. Although this transformative acquisition involves a short-term financial impact, we expect the additional sales volume, cross-selling opportunities, efficiencies as well as complementary technology and service offerings will contribute to earnings growth in fiscal 2019."

"In addition, I am pleased with the strong performance from our Physical-layer product line in the second quarter of 2018," Mr. Morin added.


EXFO to acquire Astellia for mobile subscriber awareness

EXFO has launched an all-cash voluntary tender offer to acquire all of the outstanding shares of Astellia, a provider of network and subscriber intelligence solutions for mobile operators. EXFO already holds 33.1% of Astellia's equity.

The offer is proposed at a price of EUR 10 per Astellia share, valuing the entirety of Astellia's equity (on a fully diluted basis) at approximately €25.9 million.

Astellia's real-time monitoring and troubleshooting solution optimizes networks end-to-end, from radio to core.  The company is based in France with significant operations in Spain and a strong presence in Canada, Lebanon, Morocco and South Africa.

"We aim to combine the two companies and create a global leader in the service assurance and analytics industry", said Germain Lamonde, EXFO's founder and Executive Chairman of the Board. "Combining our complementary base of customers, technologies and competencies, as well as our similar corporate cultures, will enable the development of game-changing solutions and services within a large market in rapid transition—all this in the best interests of our customers, employees and shareholders."

Tuesday, April 3, 2018

Spirent adds scale testing for the new TLS v1.3 encryption protocol

Spirent Communications has expanded the functionality of its CyberFlood and Avalanche solutions by adding performance and scale testing for the new TLS v1.3 encryption protocol.

The new functionality enables testing and stressing traffic capacities on TLS v1.3-enabled devices and endpoint applications.

TLS (transport layer security) enables secure communication between web browsers and servers on the Internet. TLS v1.3 is the latest version and is quickly becoming the de facto encryption standard.

“TLS v1.3 will ultimately improve security and privacy for Internet users; however, there is risk with new standards and new potential holes in customers’ security,” said David DeSanto, director of products and threat research at Spirent Communications. “With Spirent’s performance and scale testing of this bleeding edge cryptographic standard, customers can validate that they are securely deployed, that they can achieve their desired performance, and that they know where the skeletons are in their TLS v1.3 deployments. With this capability, Spirent is helping to secure the future of the connected world.”

Wednesday, March 21, 2018

ETSI and OPNFV announce co-located testing

ETSI and OPNFV announced plans to co-locate their next community testing events in Sophia Antipolis, France.

The third ETSI NFV PlugtestsTM event will be held between 29 May and 8 June 2018, and the OPNFV Fraser Plugfest will be held from 4 to 8 June.

“Effective interoperability is the goal of any standards activity, and ETSI NFV adopted an approach oriented towards actually exercising and demonstrating interoperability from its start in 2012, evolving from Proofs of Concepts to Plugtests activities,” says Diego Lopez, chairman of ETSI ISG NFV. “This event is a new opportunity to strengthen the current cooperation with relevant open-source communities in the NFV landscape.”

Wednesday, March 14, 2018

Keysight builds mmWave testbed with Ball Aerospace and Anokiwave

Keysight Technologies is working with Ball Aerospace and Anokiwave to validate the first commercial 5G NR active array antenna product designs in the 26 GHz band.

The Keysight 5G NR-ready measurement testbed offers the precision that base station and component designers require to extensively explore the performance edges of a new class of active antenna systems in the “European Pioneer Band.”

“As our network equipment manufacturing customers are racing to be first to market, they expect to acquire velocity through their development cycle by leveraging their test solutions at each stage, from R&D to design verification to manufacturing,” said Giampaolo Tardioli, vice president of the Network Infrastructure Unit, Keysight Technologies. “Keysight modular hardware and software solutions seamlessly combine metrology-grade mmWave hardware and format-specific software measurements. These customers can now scale from today’s 4G evolved designs (under 6 GHz) into the new mmWave bands, and accelerate a faster transition into production, with minimum cost.”

The Ball Aerospace-built 256-element array uses Anokiwave integrated circuits, and was designed to deliver 5G modulation in GHz-wide bandwidths in either a single-beam mode or in MIMO applications for up to 4 concurrent beams with up to +60 dBm EIRP.

Thursday, February 1, 2018

VIAVI to Acquire Cobham's wireless test and measurement businesses

Viavi Solutions agreed to acquire the Test and Measurement business of Cobham plc for $455 million in cash.

Viavi said the acquisition strengthens its competitive position in 5G deployment and diversifies the company into military, public safety and avionics test markets. 

Cobham AvComm and Wireless T&M provides testing solutions for communication service providers' networks from the radio access network through to the network core. It has also served military, public safety and aviation markets for decades with its trusted land-mobile radio and avionics test solutions. The business generated more than $200 million of revenues in calendar year 2017.

"This combination is another step in our NSE strategy of driving operational scale and monetizing our NOL assets," said Oleg Khaykin, President and CEO of VIAVI. "Cobham AvComm and Wireless T&M are recognized leaders with a world-class team that has a long track record of successfully bringing innovative solutions to market. Together, we expect new opportunities to grow through channel expansion and technology sharing as we address rapidly emerging opportunities in 5G, software-defined and virtualized test."

Thursday, January 25, 2018

Intel, Huawei and DT complete 5G NR over-the-air test

Intel, Deutsche Telecom and Huawei conducted an over-the-air test showcasing 5G interoperability and development testing (IODT) based on the Release 15 NSA 5G NR specification.

The test used Huawei's 5G commercial base station and Intel's third-generation 5G NR Mobile Trial Platform. The configuration was based on the largest C-band cell bandwidth defined by the 5G NR standard, incorporating the latest Massive MIMO multi-antenna and beamforming technology. Massive MIMO uses a large array of antennas to provide precise control of a beam to improve network coverage and to reduce overall network interference.

Tuesday, January 16, 2018

UNH-IOL tests 1000BASE-T1 in automotive Ethernet

The University of New Hampshire InterOperability Laboratory (UNH-IOL) is adding two new services to its Automotive Ethernet Test Services menu:

  • 1000BASE-T1 Physical Medium Attachment (PMA) sublayer testing and 
  • 100BASE-T1 interoperability testing. 

“With the standardization of single-pair Gigabit Ethernet (1000BASE-T1) coming two years ago, chip manufacturers and silicon vendors are now tasked with ensuring their offerings can provide reliable and resilient functionality in environments where noise and electromagnetic interference concerns must be thoroughly addressed,” said Curtis Donahue, Senior Manager, Ethernet Technologies UNH-IOL. “Ethernet is established as the base solution for advanced automotive applications, such as self-driving cars and assuring reliable network interconnectivity. Launching the 1000BASE-T1 test service at the UNH-IOL sets the stage for allowing silicon vendors and Tier 1 automotive suppliers to streamline product developments and advance technologies that will help drive further innovation in the industry.”

Sunday, December 17, 2017

EXFO to acquire Astellia for mobile subscriber awareness

EXFO has launched an all-cash voluntary tender offer to acquire all of the outstanding shares of Astellia, a provider of network and subscriber intelligence solutions for mobile operators. EXFO already holds 33.1% of Astellia's equity.

The offer is proposed at a price of EUR 10 per Astellia share, valuing the entirety of Astellia's equity (on a fully diluted basis) at approximately €25.9 million.

Astellia's real-time monitoring and troubleshooting solution optimizes networks end-to-end, from radio to core.  The company is based in France with significant operations in Spain and a strong presence in Canada, Lebanon, Morocco and South Africa.

"We aim to combine the two companies and create a global leader in the service assurance and analytics industry", said Germain Lamonde, EXFO's founder and Executive Chairman of the Board. "Combining our complementary base of customers, technologies and competencies, as well as our similar corporate cultures, will enable the development of game-changing solutions and services within a large market in rapid transition—all this in the best interests of our customers, employees and shareholders."

Tuesday, October 3, 2017

100G - Challenges for Performance and Security Visibility Monitoring

by Brendan O’Flaherty, CEO, cPacket Networks

The 100Gbps Ethernet transport network is here, and the use cases for transport at 100Gbps are multiplying. The previous leap in network bandwidths was from 10Gbps to 40Gbps, and 40Gbps networks are prevalent today. However, while 40Gbps networks are meeting bandwidth and performance requirements in many enterprises, the “need for speed” to handle data growth in the enterprise simply cannot be tamed.

As companies continue to grow in scale, and as their data needs become more complex, 100Gbps (“100G”) offers the bandwidth and efficiency they desperately need. In addition, 100G better utilizes existing fiber installations and increases density, which significantly improves overall data center efficiency.

A pattern of growth in networks is emerging, and it seems to reflect the hypergrowth increases in data on corporate networks just over the last five years. In fact, the now-famous Gilder’s Law states that backbone bandwidth on a single cable is now a thousand times greater than the average monthly traffic exchanged across the entire global communications infrastructure five years ago.

A look at the numbers tells the story well. IDC says that 10G Ethernet switches are set to lose share, while 100G switches are set to double. Crehan Research (see Figure 1) says that 100G port shipments will pass 40G shipments in 2017, and will pass 10G shipments in 2021.



Figure 1: 100G Port Shipments Reaching Critical Mass, as 40G and 10G Shipments Decline

100 Gigabit by the Numbers

The increase in available link speeds and utilization creates new challenges for both the architectures upon which traditional network monitoring solutions are based and for the resolution required to view network behavior accurately. Let’s look at some numbers:

100G Capture to Disk

Traditional network monitoring architectures depend on the ability to bring network traffic to a NIC and write that data to disk for post-analysis. Let’s look at the volume of data involved at 100G:



(1)




(2)




(3)

By equation (3), at 100 Gbps on one link, in one direction, a one-terabyte disk will be filled in 80 seconds. Extending this calculation for one day, in order to store the amount of data generated on one 100 Gbps link in only one direction, 0.96 petabytes of storage is required:




(4)

Not only is this a lot of data (0.96 petabytes is about 1,000 terabytes, equivalent to 125 8TB desktop hard drives), but as of this writing (Aug 2017), a high-capacity network performance solution from a leading vendor can store approximately 300 terabytes, or only eight hours of network data from one highly utilized link.

100G in the Network – What is a Burst, and What is Its Impact?

A microburst can be defined as a period during which traffic is transmitted over the network at line rate (the maximum capacity of the link). Microbursts in the datacenter are quite common – often by design of the applications running in the network. Three common reasons are:

  • Traffic from two (or more) sources to one destination. This scenario is sometimes considered uncommon due to the low utilization of the source traffic, although this impression is the result of lack of accuracy in measurements, as we’ll see when we look at the amount of data in a one-millisecond burst.
  • Throughput maximizations. Many common operating system optimizations to reduce the overhead of disk operations or NIC offloading of interrupts will cause trains of packets to occur on the wire.
  • YouTube/Netflix ON/OFF buffer loading. Common to these two applications but frequently used with other video streaming applications is buffer loading from 64KB to 2MB – once again, this ON/OFF transmission of traffic inherently gives rise to bursty behavior in the network.
The equations below translate 100 gigabits per second (1011 bits/second) into bytes per millisecond:



(5)



(6)

The amount of data in a one-millisecond spike of data is greater than the total amount of (shared) memory resources available in a standard switch. This means that a single one-millisecond spike can cause packet drops in the network. For protocols such as TCP, the data will be retransmitted; however, the exponential backoff mechanisms will result in degraded performance. For UDP packets, the lost packets will translate to choppy voice or video, or gaps in market data feeds for algorithm trading platforms. In both cases, since the packet drops cannot be predicted in advance because the spikes and bursts will go undetected without millisecond monitoring resolution, the result will be intermittent behavior that is difficult to troubleshoot.

Network Monitoring Architecture


Typical Monitoring Stack
The typical network monitoring stack is described in Figure 2. At the bottom is the infrastructure – the switches, routers and firewalls that make up the network. Next, in the blue layer are TAPs and SPAN ports – TAPs are widely deployed due to their low cost, and most infrastructure devices provide some number of SPAN ports. The traffic from these TAPs and SPANs is then taken to an aggregation device (or matrix switch or “packet broker”) – at this point, a high number of links, typically 96 10G, are taken to a small number of tool ports, usually four 10G ports (a standard high-performance configuration). At the top are the network tools – these tools take the network traffic fed to them from the aggregation layer and provide the graphs, analytics and drilldowns that form dashboards/visualization.


Figure 2: Typical Network Monitoring Stack

Scalability of Network Monitoring Stack

Let’s now evaluate how this typical monitoring stack scales in high-speed environments.

·         Infrastructure: As evidenced by the transition to 100G, the infrastructure layer appears to be scaling well.

·         TAP/SPAN: TAPs are readily available and match the speeds found in the infrastructure layer. SPANs can be oversubscribed or alter timing, leading to loss of visibility and inaccurate assumptions about production traffic behavior.

·         Aggregation: The aggregation layer is where the scaling issues become problematic. As in the previous example, if 48 links are monitored by four 10G tool ports, the ratio of “traffic in” to monitoring capability is 96:4 (96 is the result of 48 links in two directions) or, reducing, an oversubscription ratio of 24:1. Packet drops due to oversubscription mean that network traffic is not reaching the tools – there are many links or large volumes of traffic that are not being monitored.

·         Tools: The tools layer is dependent on data acquisition and data storage, which translates to the dual technical hurdles of capturing all the data at the NIC as well as writing this data to disk for analysis. Continuing the example, at 96x10G to 4x10G at 10G, the percentage of traffic measured (assuming fully utilized links) is 4x10G/96x10G, or 4.2%. As the network increases to 100G (but the performance of monitoring tools does not), the percentage of traffic monitored drops further to 4x10G/96x100G, or 0.42%.

It is difficult to provide actionable insights into network behavior when only 0.42% of network traffic is monitored, especially during levels of high activity or security attacks.
Figure 3: Scalability of Network Monitoring Stack

Current Challenges with Traditional Monitoring Environments

Monitoring Requirements in the Datacenter

Modern datacenter monitoring has a number of requirements if it is to be comprehensive:  
  • Monitoring Must Be Always-On. Always-on network performance monitoring means being able to see all of the traffic and being able to perform drill-downs to packets of interest on the network without the delay incurred in activating and connecting a network tool only after an issue has been reported (which leads to reactive customer support rather than the proactive awareness necessary to address issues before customers are affected). Always-on KPIs at high resolution provide a constant stream of information for efficient network operations.
  • Monitoring Must Inspect All Packets. To be comprehensive, NPM must inspect every packet and every bit at all speeds—and without being affected by high traffic rates or minimum-sized packets. NPM solutions that drop packets (or only monitor 0.24% of the packets) as data rates increase do not provide the accuracy, by definition, to understand network behavior when accuracy is most needed – when the network is about to fail due to high load or a security attack.
  • High Resolution is Critical. Resolution down to 1ms was not mandatory in the days when 10Gbps networks prevailed. But there’s no alternative today: 1ms resolution is required for detecting problems such as transients, bursts and spikes at 100Gbps.
  • Convergence of Security and Performance Monitoring (NOC/SOC Integration). Security teams and network performance teams are often looking for the same data, with the goal of interpreting it based on their area of focus. Spikes and microbursts might represent a capacity issue for performance engineers but may be early signs of probing by an attacker to a security engineer. Growing response time may reflect server loads to a performance engineer or may indicate a reflection attack to the infosec team. Providing the tools to allow correlation of these events, given the same data, is essential to efficient security and performance engineering applications.
A Look Ahead

100G is just the latest leap in Ethernet-based transport in the enterprise. With 100G port shipments growing at the expense of 40G and 10G, the technology is on a trajectory to become the dominant data center speed by 2021. According to Light Reading, “We are seeing huge demand for 100G in the data center and elsewhere and expect the 100G optical module market to become very competitive through 2018, as the cost of modules is reduced and production volumes grow to meet the demand. The first solutions for 200G and 400G are already available. The industry is now working on cost-reduced 100G, higher-density 400G, and possible solutions for 800G and 1.6 Tbit/s.”


See also