Welcome!

Release Management Authors: Jnan Dash, Liz McMillan, Lori MacVittie, Gilad Parann-Nissany, Carmen Gonzalez

Related Topics: Microsoft Cloud, Open Source Cloud, IoT User Interface, Silverlight, Release Management , CRM

Microsoft Cloud: Blog Feed Post

Performance Tuning Windows 2012: Network Subsystem | Part 1

NDIS, the protocol stack, and user mode applications

Offload Capabilities
Offloading tasks can reduce CPU usage on the server, which improves the overall system performance. The network stack in Windows 2012 (and prior versions of the OS) can offload one or more tasks to a network adapter permitted you have an adapter with offload capabilities. The table below lists the details about offload capabilities:

Receive-side scaling (RSS) is a network driver technology that enables the efficient distribution of network receive processing across multiple CPUs in multiprocessor systems.

Checksum calculation

The network stack can offload the calculation and validation of Transmission Control Protocol (TCP) and User Datagram Protocol (UDP) checksums on send and receive code paths. It can also offload the calculation and validation of IPv4 and IPv6 checksums on send and receive code paths.

IP security authentication and encryption

The TCP/IP transport layer can offload the calculation and validation of encrypted checksums for authentication headers and Encapsulating Security Payloads (ESPs). The TCP/IP transport layer can also offload the encryption and decryption of ESPs.

Segmentation of large TCP packets

The TCP/IP transport layer supports Large Send Offload v2 (LSOv2). With LSOv2, the TCP/IP transport layer can offload the segmentation of large TCP packets to the hardware.

Receive Segment Coalescing (RSC)

RSC is the ability to group packets together to minimize the header processing that is necessary for the host to perform. A maximum of 64 KB of received payload can be coalesced into a single larger packet for processing.

Receive-Side Scaling (RSS)

Receive-Side Scaling (RSS)
Windows Server 2012 (as well as Windows Server 2008 R2, and Windows Server 2008) supports Receive Side Scaling (RSS). RSS directs network processing to up to one logical processor per core. For example, given a server with Intel Hyper-Threading and 4 cores (8 logical processors), RSS will use no more than 4 logical processors for network processing.
RSS distributes incoming network I/O packets among logical processors so that packets that belong to the same TCP connection are processed on the same logical processor. RSS also load balances UDP unicast and multicast traffic from Windows Server 2012, and it routes related flows (as determined by hashing the source and destination addresses) to the same logical processor, preserving the order of related arrivals. Windows Server 2012 provides the following methods to tune RSS behavior:

· Windows PowerShell: Get-NetAdapterRSS, Set-NetAdapterRSS, Enable-NetAdapterRss, Disable-NetAdapterRss. These cmdlets allow you to view and modify RSS parameters.

· RSS Profiles: Used to determine which logical processors are assigned to which network adapter. Possible profiles are:

o Closest. Logical processor numbers near the network adapter’s base RSS processor are preferred. Windows may rebalance logical processors dynamically based on load.

o ClosestStatic. Logical processor numbers near the network adapter’s base RSS processor are preferred. Windows will not rebalance logical processors dynamically based on load.

o NUMA. Logical processor numbers will tend to be selected on different NUMA nodes to distribute the load. Windows may rebalance logical processors dynamically based on load.

o NUMAStatic. This is the default profile. Logical processor numbers will tend to be selected on different NUMA nodes to distribute the load. Windows will not rebalance logical processors dynamically based on load.

o Conservative: RSS uses as few processors as possible to sustain the load. This option helps reduce the number of interrupts.

You can use the set-netadapterRSS cmdlet to choose how many logical processors can be used for RSS on a per-network adapter basis, the starting offset for the range of logical processors, and which node the network adapter allocates memory from:

· MaxProcessors: Sets the maximum number of RSS processors to be used, ensuring application traffic is bound to a maximum number of processors on an interface.

set-netadapterRSS –Name “Ethernet” –MaxProcessors <value>

· BaseProcessorGroup: Sets the base processor group of a NUMA node, affecting the processor array used by RSS.

set-netadapterRSS –Name “Ethernet” –BaseProcessorGroup <value>

· MaxProcessorGroup: Sets the Max processor group of a NUMA node, affecting the processor array used by RSS.

set-netadapterRSS –Name “Ethernet” –MaxProcessorGroup <value>

· BaseProcessorNumber: Sets the base processor number of a NUMA node, allowing partitioning processors across network adapters and specifying the first logical processor in the range of RSS processors that is assigned to each adapter.

set-netadapterRSS –Name “Ethernet” –BaseProcessorNumber <Byte Value>

· NumaNode: The NUMA node that each network adapter can allocate memory from.

set-netadapterRSS –Name “Ethernet” –NumaNodeID <value>

· NumberofReceiveQueues: If your logical processors seem to be underutilized for receive traffic, you can try increasing the number of RSS queues from the default of 2 to the maximum number supported.

set-netadapterRSS –Name “Ethernet” –NumberOfReceiveQueues <value>

RSS does not provide any interaction with virtual machines, instead you can configure VMQ. RSS can be enabled for virtual machines in the case of SR-IOV because the virtual function driver supports RSS capability. In this case, the guest and the host will have the benefit of RSS. The host however, does not get RSS capability because the virtual switch is enabled with SR-IOV.

Receive-Segment Coalescing (RSC)
Receive Segment Coalescing can improve performance by reducing the number of IP headers that are processed for a given amount of received data.  You should use RSC to tune performance of received data by grouping (or coalescing) smaller packets into larger units. This can reduce latency and increase throughput for received heavy workloads. On network adapters supporting RSC, make sure that it is enabled, unless you have low latency, low throughput networking needs that benefit from RSC being turned off.

In Windows Server 2012 you can use the following PowerShell cmdlets to configure RSC capable adapters: Enable-NetAdapterRsc, Disable-NetRsc, Get-NetAdapterAdvancedProperty, and Set-NetAdapterAdvancedProperty. RSC can be examined using the cmdlets Get-NetAdapterRSC and Get-NetAdapterStatistics. The Get cmdlet shows if RSC is enabled and if TCP enables RSC to be in operational state. In the example above, IPv4 RSC is enabled. To understand failures, you can view the coalesced bytes or exceptions caused by entering the following command:

PS C:\Users\Administrator> $x = Get-NetAdapterStatistics “myAdapter”

PS C:\Users\Administrator> $x.rscstatistics

CoalescedBytes : 0

CoalescedPackets : 0

CoalescingEvents : 0

CoalescingExceptions : 0

RSC and virtualization
If the host adapter is not bound to the virtual switch, RSC is supported on the physical host. If the adapter is bound to the virtual switch, Windows 2012 will disable RSC on the physical host.
RSC can be enabled for a virtual machine when SR-IOV is enabled. In this case, virtual functions will support RSC capability; hence, virtual machines will also get the benefit of RSC.

Network Adapter Resources

A few network adapters actively manage their resources to achieve optimum performance. Several network adapters let the administrator manually configure resources by using the Advanced Networking tab for the adapter. For such adapters, you can set the values of a number of parameters including the number of receive buffers and send buffers.  In Windows Server 2012, you can configure advanced network settings using the following PowerShell cmdlets:

  • Get-NetAdapterAdvancedProperty
  • SetNetAdapterAdvancedProperty
  • Enable-NetAdapter
  • Enable-NetAdapterBinding
  • Enable-NetAdapterChecksumOffload
  • Enable-NetAdapterLso
  • Enable-NetAdapterIPSecOffload
  • Enable-NetAdapterPowerManagemetn
  • Enable-NetAdapterQos
  • Enable-NetAdapterRDMA
  • Enable-NetAdapter
  • Enable-NetAdapterSriov

Message-Signaled Interrupts (MSI/MSI-X)
Network adapters that support MSI/MSI-X can target specific logical processors. If your network adapter also support RSS, then a logical processor can be dedicated to servicing interrupts and deferred procedure calls (DPCs) for a given TCP connection. This will greatly improve performance, by preserving the TCP cache.

Interrupt Moderation
Lastly, we’ll discuss interrupt moderation. Some network adapters expose different interrupt moderation levels, or buffer coalescing parameters, or both. You definitely should consider buffer coalescing when the network adapter does not perform interrupt moderation. Interrupt moderation will reduce CPU utilization because it minimizes the per-buffer processing cost, but you should consider that interrupt-moderation  and buffer coalescing can have a negative impact on latency-sensitive situations. The table below lists the suggested adapter features for various server roles.

Role

Checksum offload

Large Send Offload (LSO)

Receive-side scaling (RSS)

Receive Segment Coalescing (RSC)

File server

X

X

X

X

Web server

X

X

X

Mail server (short-lived connections)

X

X

Database server

X

X

X

FTP server

X

X

X

Media server

X

X

X

These settings serve as guidelines only . Depending on the workload, your network adapter(s), and your specific situation, your experience can be different. In our next article we’ll go deeper into tuning the network adapter and utilizing some of the features we discussed.

Read the original blog entry...

More Stories By Hovhannes Avoyan

Hovhannes Avoyan is the CEO of PicsArt, Inc.,

@ThingsExpo Stories
The Internet of Things will challenge the status quo of how IT and development organizations operate. Or will it? Certainly the fog layer of IoT requires special insights about data ontology, security and transactional integrity. But the developmental challenges are the same: People, Process and Platform and how we integrate our thinking to solve complicated problems. In his session at 19th Cloud Expo, Craig Sproule, CEO of Metavine, will demonstrate how to move beyond today's coding paradigm ...
The cloud market growth today is largely in public clouds. While there is a lot of spend in IT departments in virtualization, these aren’t yet translating into a true “cloud” experience within the enterprise. What is stopping the growth of the “private cloud” market? In his general session at 18th Cloud Expo, Nara Rajagopalan, CEO of Accelerite, explored the challenges in deploying, managing, and getting adoption for a private cloud within an enterprise. What are the key differences between wh...
SYS-CON Events has announced today that Roger Strukhoff has been named conference chair of Cloud Expo and @ThingsExpo 2016 Silicon Valley. The 19th Cloud Expo and 6th @ThingsExpo will take place on November 1-3, 2016, at the Santa Clara Convention Center in Santa Clara, CA. "The Internet of Things brings trillions of dollars of opportunity to developers and enterprise IT, no matter how you measure it," stated Roger Strukhoff. "More importantly, it leverages the power of devices and the Interne...
"We work in the area of Big Data analytics and Big Data analytics is a very crowded space - you have Hadoop, ETL, warehousing, visualization and there's a lot of effort trying to get these tools to talk to each other," explained Mukund Deshpande, head of the Analytics practice at Accelerite, in this SYS-CON.tv interview at 18th Cloud Expo, held June 7-9, 2016, at the Javits Center in New York City, NY.
The idea of comparing data in motion (at the sensor level) to data at rest (in a Big Data server warehouse) with predictive analytics in the cloud is very appealing to the industrial IoT sector. The problem Big Data vendors have, however, is access to that data in motion at the sensor location. In his session at @ThingsExpo, Scott Allen, CMO of FreeWave, discussed how as IoT is increasingly adopted by industrial markets, there is going to be an increased demand for sensor data from the outermos...
UAS, drones or unmanned aircraft, no matter what you call them — this was their week. Our news stream was flooded with updates on the newly announced rules and regulations for commercial UAS from the FAA. So, naturally we have dedicated this week’s top news round up to highlight some of our favorite UAS stories.
Internet of @ThingsExpo has announced today that Chris Matthieu has been named tech chair of Internet of @ThingsExpo 2016 Silicon Valley. The 6thInternet of @ThingsExpo will take place on November 1–3, 2016, at the Santa Clara Convention Center in Santa Clara, CA.
CenturyLink has announced that application server solutions from GENBAND are now available as part of CenturyLink’s Networx contracts. The General Services Administration (GSA)’s Networx program includes the largest telecommunications contract vehicles ever awarded by the federal government. CenturyLink recently secured an extension through spring 2020 of its offerings available to federal government agencies via GSA’s Networx Universal and Enterprise contracts. GENBAND’s EXPERiUS™ Application...
Basho Technologies has announced the latest release of Basho Riak TS, version 1.3. Riak TS is an enterprise-grade NoSQL database optimized for Internet of Things (IoT). The open source version enables developers to download the software for free and use it in production as well as make contributions to the code and develop applications around Riak TS. Enhancements to Riak TS make it quick, easy and cost-effective to spin up an instance to test new ideas and build IoT applications. In addition to...
In addition to all the benefits, IoT is also bringing new kind of customer experience challenges - cars that unlock themselves, thermostats turning houses into saunas and baby video monitors broadcasting over the internet. This list can only increase because while IoT services should be intuitive and simple to use, the delivery ecosystem is a myriad of potential problems as IoT explodes complexity. So finding a performance issue is like finding the proverbial needle in the haystack.
When people aren’t talking about VMs and containers, they’re talking about serverless architecture. Serverless is about no maintenance. It means you are not worried about low-level infrastructural and operational details. An event-driven serverless platform is a great use case for IoT. In his session at @ThingsExpo, Animesh Singh, an STSM and Lead for IBM Cloud Platform and Infrastructure, will detail how to build a distributed serverless, polyglot, microservices framework using open source tec...
The IoT is changing the way enterprises conduct business. In his session at @ThingsExpo, Eric Hoffman, Vice President at EastBanc Technologies, discussed how businesses can gain an edge over competitors by empowering consumers to take control through IoT. He cited examples such as a Washington, D.C.-based sports club that leveraged IoT and the cloud to develop a comprehensive booking system. He also highlighted how IoT can revitalize and restore outdated business models, making them profitable ...
Presidio has received the 2015 EMC Partner Services Quality Award from EMC Corporation for achieving outstanding service excellence and customer satisfaction as measured by the EMC Partner Services Quality (PSQ) program. Presidio was also honored as the 2015 EMC Americas Marketing Excellence Partner of the Year and 2015 Mid-Market East Partner of the Year. The EMC PSQ program is a project-specific survey program designed for partners with Service Partner designations to solicit customer feedbac...
Apixio Inc. has raised $19.3 million in Series D venture capital funding led by SSM Partners with participation from First Analysis, Bain Capital Ventures and Apixio’s largest angel investor. Apixio will dedicate the proceeds toward advancing and scaling products powered by its cognitive computing platform, further enabling insights for optimal patient care. The Series D funding comes as Apixio experiences strong momentum and increasing demand for its HCC Profiler solution, which mines unstruc...
IoT offers a value of almost $4 trillion to the manufacturing industry through platforms that can improve margins, optimize operations & drive high performance work teams. By using IoT technologies as a foundation, manufacturing customers are integrating worker safety with manufacturing systems, driving deep collaboration and utilizing analytics to exponentially increased per-unit margins. However, as Benoit Lheureux, the VP for Research at Gartner points out, “IoT project implementers often ...
"delaPlex is a software development company. We do team-based outsourcing development," explained Mark Rivers, COO and Co-founder of delaPlex Software, in this SYS-CON.tv interview at 18th Cloud Expo, held June 7-9, 2016, at the Javits Center in New York City, NY.
In his general session at 18th Cloud Expo, Lee Atchison, Principal Cloud Architect and Advocate at New Relic, discussed cloud as a ‘better data center’ and how it adds new capacity (faster) and improves application availability (redundancy). The cloud is a ‘Dynamic Tool for Dynamic Apps’ and resource allocation is an integral part of your application architecture, so use only the resources you need and allocate /de-allocate resources on the fly.
Connected devices and the industrial internet are growing exponentially every year with Cisco expecting 50 billion devices to be in operation by 2020. In this period of growth, location-based insights are becoming invaluable to many businesses as they adopt new connected technologies. Knowing when and where these devices connect from is critical for a number of scenarios in supply chain management, disaster management, emergency response, M2M, location marketing and more. In his session at @Th...
Machine Learning helps make complex systems more efficient. By applying advanced Machine Learning techniques such as Cognitive Fingerprinting, wind project operators can utilize these tools to learn from collected data, detect regular patterns, and optimize their own operations. In his session at 18th Cloud Expo, Stuart Gillen, Director of Business Development at SparkCognition, discussed how research has demonstrated the value of Machine Learning in delivering next generation analytics to imp...
In his keynote at 18th Cloud Expo, Andrew Keys, Co-Founder of ConsenSys Enterprise, provided an overview of the evolution of the Internet and the Database and the future of their combination – the Blockchain. Andrew Keys is Co-Founder of ConsenSys Enterprise. He comes to ConsenSys Enterprise with capital markets, technology and entrepreneurial experience. Previously, he worked for UBS investment bank in equities analysis. Later, he was responsible for the creation and distribution of life sett...