Click here to close now.


@DevOpsSummit Authors: Pat Romanski, Wayne Ariola, AppDynamics Blog, XebiaLabs Blog, Elizabeth White

Related Topics: @CloudExpo, Java IoT, Microservices Expo, Containers Expo Blog, @BigDataExpo, SDN Journal

@CloudExpo: Book Excerpt

Book Excerpt: Systems Performance: Enterprise and the Cloud | Part 1

CPUs drive all software and are often the first target for systems performance analysis

"This excerpt is from the book, "Systems Performance: Enterprise and the Cloud", authored by Brendan Gregg, published by Prentice Hall Professional, Oct. 2013, ISBN 9780133390094, Copyright © 2014 Pearson Education, Inc. For more info, please visit the publisher site:

CPUs drive all software and are often the first target for systems performance analysis. Modern systems typically have many CPUs, which are shared among all running software by the kernel scheduler. When there is more demand for CPU resources than there are resources available, process threads (or tasks) will queue, waiting their turn. Waiting can add significant latency during the runtime of applications, degrading performance.

The usage of the CPUs can be examined in detail to look for performance improvements, including eliminating unnecessary work. At a high level, CPU usage by process, thread, or task can be examined. At a lower level, the code path within applications and the kernel can be profiled and studied. At the lowest level, CPU instruction execution and cycle behavior can be studied.

This chapter consists of five parts:

  • Background introduces CPU-related terminology, basic models of CPUs, and key CPU performance concepts.
  • Architecture introduces processor and kernel scheduler architecture.
  • Methodology describes performance analysis methodologies, both observa- tional and experimental.
  • Analysis describes CPU performance analysis tools on Linux- and Solaris- based systems, including profiling, tracing, and visualizations.
  • Tuning includes examples of tunable parameters.

The first three sections provide the basis for CPU analysis, and the last two show its practical application to Linux- and Solaris-based systems.

The effects of memory I/O on CPU performance are covered, including CPU cycles stalled on memory and the performance of CPU caches. Chapter 7, Memory, continues the discussion of memory I/O, including MMU, NUMA/UMA, system interconnects, and memory busses.

For reference, CPU-related terminology used in this chapter includes the following:

  • Processor: the physical chip that plugs into a socket on the system or pro- cessor board and contains one or more CPUs implemented as cores or hard- ware threads.
  • Core: an independent CPU instance on a multicore processor. The use of cores is a way to scale processors, called chip-level multiprocessing (CMP).
  • Hardware thread: a CPU architecture that supports executing multiple threads in parallel on a single core (including Intel's Hyper-Threading Tech- nology), where each thread is an independent CPU instance. One name for this scaling approach is multithreading.
  • CPU instruction: a single CPU operation, from its instruction set. There are instructions for arithmetic operations, memory I/O, and control logic.
  • Logical CPU: also called a virtual processor,1 an operating system CPU instance (a schedulable CPU entity). This may be implemented by the processor as a hardware thread (in which case it may also be called a virtual core), a core, or a single-core processor.
  • Scheduler: the kernel subsystem that assigns threads to run on CPUs.
  • Run queue: a queue of runnable threads that are waiting to be serviced by
  • CPUs. For Solaris, it is often called a dispatcher queue.

Other terms are introduced throughout this chapter. The Glossary includes basic terminology for reference, including CPU, CPU cycle, and stack. Also see the terminology sections in Chapters 2 and 3.

The following simple models illustrate some basic principles of CPUs and CPU per- formance. Section 6.4, Architecture, digs much deeper and includes implementation- specific details.

CPU Architecture
Figure 1 shows an example CPU architecture, for a single processor with four cores and eight hardware threads in total. The physical architecture is pictured, along with how it is seen by the operating system.

Figure 1: CPU architecture

Each hardware thread is addressable as a logical CPU, so this processor appears as eight CPUs. The operating system may have some additional knowledge of topology, such as which CPUs are on the same core, to improve its scheduling decisions.

CPU Memory Caches
Processors provide various hardware caches for improving memory I/O perfor- mance. Figure 2 shows the relationship of cache sizes, which become smaller and faster (a trade-off) the closer they are to the CPU.

The caches that are present, and whether they are on the processor (integrated) or external to the processor, depend on the processor type. Earlier processors pro- vided fewer levels of integrated cache.

Figure 2: CPU cache sizes

CPU Run Queues
Figure 3 shows a CPU run queue, which is managed by the kernel scheduler.

Figure 3: CPU run queue

The thread states shown in the figure, ready to run and on-CPU, are covered in Figure 3.7 in Chapter 3, Operating Systems.

The number of software threads that are queued and ready to run is an impor- tant performance metric indicating CPU saturation. In this figure (at this instant) there are four, with an additional thread running on-CPU. The time spent waiting on a CPU run queue is sometimes called run-queue latency or dispatcher-queue latency. In this book, the term scheduler latency is used instead, as it is appropri- ate for all dispatcher types, including those that do not use queues (see the discus- sion of CFS in Section 6.4.2, Software).

For multiprocessor systems, the kernel typically provides a run queue for each CPU and aims to keep threads on the same run queue. This means that threads are more likely to keep running on the same CPUs, where the CPU caches have cached their data. (These caches are described as having cache warmth, and the approach to favor CPUs is called CPU affinity.) On NUMA systems, memory locality may also be improved, which also improves performance (this is described in Chapter 7, Memory).

It also avoids the cost of thread synchronization (mutex locks) for queue operations, which would hurt scalability if the run queue was global and shared among all CPUs.

The following are a selection of important concepts regarding CPU performance, beginning with a summary of processor internals: the CPU clock rate and how instructions are executed. This is background for later performance analysis, particularly for understanding the cycles-per-instruction (CPI) metric.

Clock Rate
The clock is a digital signal that drives all processor logic. Each CPU instruction may take one or more cycles of the clock (called CPU cycles) to execute. CPUs exe- cute at a particular clock rate; for example, a 5 GHz CPU performs 5 billion clock cycles per second.

Some processors are able to vary their clock rate, increasing it to improve performance or decreasing it to reduce power consumption. The rate may be varied on request by the operating system, or dynamically by the processor itself. The ker- nel idle thread, for example, can request the CPU to throttle down to save power.

Clock rate is often marketed as the primary feature of the processor, but this can be a little misleading. Even if the CPU in your system appears to be fully utilized (a bottleneck), a faster clock rate may not speed up performance-it depends on what those fast CPU cycles are actually doing. If they are mostly stall cycles while waiting on memory access, executing them more quickly doesn't actually increase the CPU instruction rate or workload throughput.

CPUs execute instructions chosen from their instruction set. An instruction includes the following steps, each processed by a component of the CPU called a functional unit:

  1. Instruction fetch
  2. Instruction decode
  3. Execute
  4. Memory access
  5. Register write-back

The last two steps are optional, depending on the instruction. Many instructions operate on registers only and do not require the memory access step.

Each of these steps takes at least a single clock cycle to be executed. Memory access is often the slowest, as it may take dozens of clock cycles to read or write to main memory, during which instruction execution has stalled (and these cycles while stalled are called stall cycles). This is why CPU caching is important, as described in Section 6.4: it can dramatically reduce the number of cycles needed for memory access.

Instruction Pipeline
The instruction pipeline is a CPU architecture that can execute multiple instructions in parallel, by executing different components of different instructions at the same time. It is similar to a factory assembly line, where stages of production can be executed in parallel, increasing throughput.

Consider the instruction steps previously listed. If each were to take a single clock cycle, it would take five cycles to complete the instruction. At each step of this instruction, only one functional unit is active and four are idle. By use of pipe- lining, multiple functional units can be active at the same time, processing differ- ent instructions in the pipeline. Ideally, the processor can then complete one instruction with every clock cycle.

Instruction Width
But we can go faster still. Multiple functional units can be included of the same type, so that even more instructions can make forward progress with each clock cycle. This CPU architecture is called superscalar and is typically used with pipe- lining to achieve a high instruction throughput.

The instruction width describes the target number of instructions to process in parallel. Modern processors are 3-wide or 4-wide, meaning they can complete up to three or four instructions per cycle. How this works depends on the processor, as there may be different numbers of functional units for each stage.

Cycles per instruction (CPI) is an important high-level metric for describing where a CPU is spending its clock cycles and for understanding the nature of CPU utilization. This metric may also be expressed as instructions per cycle (IPC), the inverse of CPI.

A high CPI indicates that CPUs are often stalled, typically for memory access. A low CPI indicates that CPUs are often not stalled and have a high instruction throughput. These metrics suggest where performance tuning efforts may be best spent.

Memory-intensive workloads, for example, may be improved by installing faster memory (DRAM), improving memory locality (software configuration), or reducing the amount of memory I/O. Installing CPUs with a higher clock rate may not improve performance to the degree expected, as the CPUs may need to wait the same amount of time for memory I/O to complete. Put differently, a faster CPU may mean more stall cycles but the same rate of completed instructions.

The actual values for high or low CPI are dependent on the processor and processor features and can be determined experimentally by running known work- loads. As an example, you may find that high-CPI workloads run with a CPI at ten or higher, and low CPI workloads run with a CPI at less than one (which is possi- ble due to instruction pipelining and width, described earlier).

It should be noted that CPI shows the efficiency of instruction processing, but not of the instructions themselves. Consider a software change that added an inefficient software loop, which operates mostly on CPU registers (no stall cycles): such a change may result in a lower overall CPI, but higher CPU usage and utilization.

CPU utilization is measured by the time a CPU instance is busy performing work during an interval, expressed as a percentage. It can be measured as the time a CPU is not running the kernel idle thread but is instead running user-level application threads or other kernel threads, or processing interrupts.

High CPU utilization may not necessarily be a problem, but rather a sign that the system is doing work. Some people also consider this an ROI indicator: a highly utilized system is considered to have good ROI, whereas an idle system is considered wasted. Unlike with other resource types (disks), performance does not degrade steeply under high utilization, as the kernel supports priorities, preemption, and time sharing. These together allow the kernel to understand what has higher priority, and to ensure that it runs first.

The measure of CPU utilization spans all clock cycles for eligible activities, including memory stall cycles. It may seem a little counterintuitive, but a CPU may be highly utilized because it is often stalled waiting for memory I/O, not just executing instructions, as described in the previous section.

CPU utilization is often split into separate kernel- and user-time metrics.

More Stories By Brendan Gregg

Brendan Gregg, Lead Performance Engineer at Joyent, analyzes performance and scalability throughout the software stack. As Performance Lead and Kernel Engineer at Sun Microsystems (and later Oracle), his work included developing the ZFS L2ARC, a pioneering file system technology for improving performance using flash memory. He has invented and developed many performance tools, including some that ship with Mac OS X and Oracle® Solaris™ 11. His recent work has included performance visualizations for Linux and illumos kernel analysis. He is coauthor of DTrace (Prentice Hall, 2011) and Solaris™ Performance and Tools (Prentice Hall, 2007).

Comments (0)

Share your thoughts on this story.

Add your comment
You must be signed in to add a comment. Sign-in | Register

In accordance with our Comment Policy, we encourage comments that are on topic, relevant and to-the-point. We will remove comments that include profanity, personal attacks, racial slurs, threats of violence, or other inappropriate material that violates our Terms and Conditions, and will block users who make repeated violations. We ask all readers to expect diversity of opinion and to treat one another with dignity and respect.

@DevOpsSummit Stories
SYS-CON Events announced today that has been named a "Bronze Sponsor" of SYS-CON's @DevOpsSummit Silicon Valley, which will take place November 3-5, 2015, at the Santa Clara Convention Center in Santa Clara, CA. provides open-source software ELK turned into a log analytics platform that is simple, infinitely- scalable, highly available, and secure.
DevOps has often been described in terms of CAMS: Culture, Automation, Measuring, Sharing. While we’ve seen a lot of focus on the “A” and even on the “M”, there are very few examples of why the “C" is equally important in the DevOps equation. In her session at @DevOps Summit, Lori MacVittie, of F5 Networks, will explore HTTP/1 and HTTP/2 along with Microservices to illustrate why a collaborative culture between Dev, Ops, and the Network is critical to ensuring success.
Today, we are in the middle of a paradigm shift as we move from managing applications on VMs and containers to embracing everything that the cloud and XaaS (Everything as a Service) has to offer. In his session at 17th Cloud Expo, Kevin Hoffman, Advisory Solutions Architect at Pivotal Cloud Foundry, will provide an overview of 12-factor apps and migrating enterprise apps to the cloud. Kevin Hoffman is an Advisory Solutions Architect for Pivotal Cloud Foundry, and has spent the past 20 years building enterprise and mobile software for small businesses, massive enterprises, and everything in ...
DevOps delivers remarkable results. But does it help all of IT? Can traditional ‘mode 1’ IT benefit as much as innovative ‘mode 2’? How about the rest of your business? Or have you just shifted your bottleneck? And if so, what can you do about it? Improving dev and ops is necessary, but not sufficient. It often just shifts the burden sideways (e.g., to PMs, SQA, InfoSec, DBAs, NOC, etc.), upstream (to the PMO, Controller, Business Liaison, etc.), or downstream (to TechPubs, Service Desk, Training, etc.).
SYS-CON Events announced today that Alert Logic, the leading provider of Security-as-a-Service solutions for the cloud, has been named “Bronze Sponsor” of SYS-CON's 17th International Cloud Expo® and DevOps Summit 2015 Silicon Valley, which will take place November 3–5, 2015, at the Santa Clara Convention Center in Santa Clara, CA. Alert Logic provides Security-as-a-Service for on-premises, cloud, and hybrid IT infrastructures, delivering deep security insight and continuous protection for customers at a lower cost than traditional security solutions.
Clearly the way forward is to move to cloud be it bare metal, VMs or containers. One aspect of the current public clouds that is slowing this cloud migration is cloud lock-in. Every cloud vendor is trying to make it very difficult to move out once a customer has chosen their cloud. In his session at 17th Cloud Expo, Naveen Nimmu, CEO of Clouber, Inc., will advocate that making the inter-cloud migration as simple as changing airlines would help the entire industry to quickly adopt the cloud without worrying about any lock-in fears. In fact by having standard APIs for IaaS would help PaaS expl...
Culture is the most important ingredient of DevOps. The challenge for most organizations is defining and communicating a vision of beneficial DevOps culture for their organizations, and then facilitating the changes needed to achieve that. Often this comes down to an ability to provide true leadership. As a CIO, are your direct reports IT managers or are they IT leaders? The hard truth is that many IT managers have risen through the ranks based on their technical skills, not their leadership ability. Many are unable to effectively engage and inspire, creating forward momentum in the direction...
Mobile, social, Big Data, and cloud have fundamentally changed the way we live. “Anytime, anywhere” access to data and information is no longer a luxury; it’s a requirement, in both our personal and professional lives. For IT organizations, this means pressure has never been greater to deliver meaningful services to the business and customers.
Clutch is now a Docker Authorized Consulting Partner, having completed Docker's certification course on the "Docker Accelerator for CI Engagements." More info about Clutch's success implementing Docker can be found here. Docker is an open platform for developers and system administrators to build, ship and run distributed applications. With Docker, IT organizations shrink application delivery from months to minutes, frictionlessly move workloads between data centers and the cloud and achieve 20x greater efficiency in their use of computing resources. Inspired by an active community and trans...
For almost two decades, businesses have discovered great opportunities to engage with customers and even expand revenue through digital systems, including web and mobile applications. Yet, even now, the conversation between the business and the technologists that deliver these systems is strained, in large part due to misaligned objectives. In his session at DevOps Summit, James Urquhart, Senior Vice President of Performance Analytics at SOASTA, Inc., will discuss how measuring user outcomes – including how the performance, flow and content of your digital systems affects those outcomes – ca...
DevOps is gaining traction in the federal government – and for good reasons. Heightened user expectations are pushing IT organizations to accelerate application development and support more innovation. At the same time, budgetary constraints require that agencies find ways to decrease the cost of developing, maintaining, and running applications. IT now faces a daunting task: do more and react faster than ever before – all with fewer resources.
The cloud has reached mainstream IT. Those 18.7 million data centers out there (server closets to corporate data centers to colocation deployments) are moving to the cloud. In his session at 17th Cloud Expo, Achim Weiss, CEO & co-founder of ProfitBricks, will share how two companies – one in the U.S. and one in Germany – are achieving their goals with cloud infrastructure. More than a case study, he will share the details of how they prioritized their cloud computing infrastructure deployments and the details they’ve learned. From performance to network configurations, they've got interesting...
Decisions about budgets and resources are often made without IT even having a seat at the table. As technologist we understand the value of DevOps - but do your business counterparts? If they don't, your DevOps initiatives could lose funding before they start. In her session at DevOps Summit, Jeanne Morain, Strategist / Author at iSpeak Cloud, LLC, will provide insights on how to bridge the gap between business and technology leaders. Attendees will learn prescriptive guidance on balancing workloads, critical communication processes and considerations for building out a solid return-on-inves...
The modern software development landscape consists of best practices and tools that allow teams to deliver software in a near-continuous manner. By adopting a culture of automation, measurement and sharing, the time to ship code has been greatly reduced, allowing for shorter release cycles and quicker feedback from customers and users. Still, with all of these tools and methods, how can teams stay on top of what is taking place across their infrastructure and codebase? Hopping between services and command line interfaces creates context-switching that slows productivity, efficiency, and may le...
While testing is often ignored when it comes to DevOps - it could be the most important aspect of achieving true DevOps success. Without rethinking automated testing from the ground-up, the entire DevOps productivity gain cannot be realized. Large tech companies build their own rapid test automation that runs in minutes across functional, performance, security and other tests. In his session at DevOps Summit, Kevin Surace, CEO of Appvance, will discuss how we learn from these real-world successes and achieve a 95% time reduction in creating and running automated unified tests. Otherwise ent...
SYS-CON Events announced today that JFrog, maker of Artifactory, the popular Binary Repository Manager, will exhibit at SYS-CON's @DevOpsSummit Silicon Valley, which will take place on November 3–5, 2015, at the Santa Clara Convention Center in Santa Clara, CA. Based in California, Israel and France, founded by longtime field-experts, JFrog, creator of Artifactory and Bintray, has provided the market with the first Binary Repository solution and a software distribution social platform.
SYS-CON Events announced today that IBM Cloud Data Services has been named “Bronze Sponsor” of SYS-CON's 17th Cloud Expo, which will take place on November 3–5, 2015, at the Santa Clara Convention Center in Santa Clara, CA. IBM Cloud Data Services offers a portfolio of integrated, best-of-breed cloud data services for developers focused on mobile computing and analytics use cases.
Docker is hot. However, as Docker container use spreads into more mature production pipelines, there can be issues about control of Docker images to ensure they are production-ready. Is a promotion-based model appropriate to control and track the flow of Docker images from development to production? In his session at DevOps Summit, Fred Simon, Co-founder and Chief Architect of JFrog, will demonstrate how to implement a promotion model for Docker images using a binary repository, and then show how to distribute them to any kind of consumer, being it a customer or a data center.
DevOps is speeding towards the IT world like a freight train and the hype around it is deafening. There is no reason to be afraid of this change as it is the natural reaction to the agile movement that revolutionized development just a few years ago. By definition, DevOps is the natural alignment of IT performance to business profitability. The relevance of this has yet to be quantified but it has been suggested that the route to the CEO’s chair will come from the IT leaders that successfully make the transition to a DevOps model. If this still seems foreign to you, I recommend reading up on D...
SYS-CON Events announced today that Cloud Raxak has been named “Media & Session Sponsor” of SYS-CON's 17th Cloud Expo, which will take place on November 3–5, 2015, at the Santa Clara Convention Center in Santa Clara, CA. Raxak Protect automates security compliance across private and public clouds. Using the SaaS tool or managed service, developers can deploy cloud apps quickly, cost-effectively, and without error.
The principles behind DevOps are not new - for decades people have been automating system administration and decreasing the time to deploy apps and perform other management tasks. However, only recently did we see the tools and the will necessary to share the benefits and power of automation with a wider circle of people. In his session at DevOps Summit, Bernard Sanders, Chief Technology Officer at CloudBolt Software, will explore the latest tools including Puppet, Chef, Docker, and CMPs needed to move from an insulated culture where automation is absent or hoarded to one where the power of ...
SYS-CON Media announced that Splunk, a provider of the leading software platform for real-time Operational Intelligence, has launched an ad campaign on Big Data Journal. Splunk software and cloud services enable organizations to search, monitor, analyze and visualize machine-generated big data coming from websites, applications, servers, networks, sensors and mobile devices. The ads focus on delivering ROI - how improved uptime delivered $6M in annual ROI, improving customer operations by mining large volumes of unstructured data, and how data tracking delivers uptime when it matters most.
As a company adopts a DevOps approach to software development, what are key things that both the Dev and Ops side of the business must keep in mind to ensure effective continuous delivery? In his session at DevOps Summit, Mark Hydar, Head of DevOps, Ericsson TV Platforms, will share best practices and provide helpful tips for Ops teams to adopt an open line of communication with the development side of the house to ensure success between the two sides.
At first adopted by enterprises to consolidate physical servers, virtualization is now widely used in cloud computing to offer elasticity and scalability. On the other hand, Docker has developed a new way to handle Linux containers, inspired by version control software such as Git, which allows you to keep all development versions. In his session at 17th Cloud Expo, Dominique Rodrigues, the co-founder and CTO of Nanocloud Software, will discuss how in order to also handle QEMU / KVM virtual machines versions, they have developed a new tool, called Vm_commit, which can create commits, backup ...
Even though you are running an agile development process, that doesn’t necessarily mean that your performance testing is being conducted in a truly agile way. Saving performance testing for a “final sprint” before release still treats it like a waterfall development step, with all the cost and risk that comes with that. In this post, we will show you how to make load testing happen early and often by putting SLAs on the agile task board.