Welcome!

DevOps Journal Authors: Liz McMillan, Rex Morrow, Datical, Pat Romanski, Elizabeth White, Carmen Gonzalez

Related Topics: Cloud Expo, Java, SOA & WOA, Virtualization, Big Data Journal, SDN Journal

Cloud Expo: 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.

Terminology
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.

Models
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.

Concepts
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.

Instruction
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.

CPI, IPC
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.

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 ElasticBox is holding a Hackathon at DevOps Summit, November 6 from 12 pm -4 pm at the Santa Clara Convention Center in Santa Clara, CA. You can enter as an individual or team of up to 10 developers. A New Star Is Born Every Month! All completed ElasticBoxes will then be sent to a judging panel - 12 winners will be featured on the ElasticBox website in 2015. All entrants will receive five full enterprise licenses for one year + ElasticBox headphones + Elasti...
SYS-CON Events announced today that Calm.io has been named “Bronze Sponsor” of DevOps Summit Silicon Valley, which will take place on November 4–6, 2014, at the Santa Clara Convention Center in Santa Clara, CA. Calm.io is a cloud orchestration platform for AWS, vCenter, OpenStack, or bare metal, that runs your CL tools puppet, Chef, shell, git, Jenkins, nagios, and will soon support New Relic and Docker. It can run hosted, or on premise and provides VM automation / expiry, self-service portals,...
Blue Box has closed a $10 million Series B financing. The round was led by a strategic investor and included participation from prior investors including Voyager Capital and Founders Collective, as well as the Blue Box executive team. This round follows a $4.3 million Series A closed in December of 2012 and led by Voyager Capital. In May of this year, the company announced general availability of its private cloud as a service offering, Blue Box Cloud. Since that release, the company has dem...
The speed of product development has increased massively in the past 10 years. At the same time our formal secure development and SDL methodologies have fallen behind. This forces product developers to choose between rapid release times and security. In his session at DevOps Summit, Michael Murray, Director of Cyber Security Consulting and Assessment at GE Healthcare, will examine the problems and present some solutions for moving security in to the DevOps lifecycle to ensure that we get fast A...
SYS-CON Events announced today that Zentera Systems, an industry visionary delivering hybrid-cloud management solutions, will exhibit at DevOps Summit Silicon Valley, which will take place on November 4–6, 2014, at the Santa Clara Convention Center in Santa Clara, CA. Zentera Systems, Inc.™ is a Silicon Valley based private company, providing a Cloud Federation Platform (CFP) built on a virtualization architecture with patent-pending technology to address virtual network, cloud firewall, data p...
Software development, like manufacturing, is a craft that requires the application of creative approaches to solve problems given a wide range of constraints. However, while engineering design may be craftwork, the production of most designed objects relies on a standardized and automated manufacturing process. By contrast, much of moving an application from prototype to production and, indeed, maintaining the application through its lifecycle has often remained craftwork. In his session at De...
High performing enterprise Software Quality Assurance (SQA) teams validate systems are ready for use – getting most actively involved as components integrate and form complete systems. These teams catch and report on defects, making sure the customer gets the best software possible. SQA teams have leveraged automation and virtualization to execute more thorough testing in less time – bringing Dev and Ops together, ensuring production readiness. Does the emergence of DevOps mean the end of Enterp...
In his keynote at DevOps Summit, David Tesar, Microsoft Technical Evangelist on Microsoft Azure and DevOps, will discuss how Microsoft teams who have made huge progress with a DevOps transformation effectively utilize operations staff and how challenges were overcome. Regardless of whether you are a startup or a mature enterprise, whether you are using PaaS, Micro Services, or Containerization, walk away with some practical tips where Ops can make a significant impact working with the developmen...
Cloudwick, the leading big data DevOps service and solution provider to the Fortune 1000, announced Big Loop, its multi-vendor operations platform. Cloudwick Big Loop creates greater collaboration between Fortune 1000 IT staff, developers and their database management systems as well as big data vendors. This allows customers to comprehensively manage and oversee their entire infrastructure, which leads to more successful production cluster operations, and scale-out. Cloudwick Big Loop supports ...

POMPTON LAKES, N.J., Oct. 17, 2014 /PRNewswire/ -- Kubisys announced today its namesake CID Platform, which automatically captures production environments and orchestrates the provisioning and deployment of replicas for development, testing and QA. The Kubisys CID Platform makes it easy for developers of mission critical multi-tier applications, such as Microsoft Dynamics AX, to follow DevOps practices for continuous delivery. The Oct. 20, 2014 04:00 PM EDT  Reads: 1,710

The recent trends like cloud computing, social, mobile and Internet of Things are forcing enterprises to modernize in order to compete in the competitive globalized markets. However, enterprises are approaching newer technologies with a more silo-ed way, gaining only sub optimal benefits. The Modern Enterprise model is presented as a newer way to think of enterprise IT, which takes a more holistic approach to embracing modern technologies. This model makes use of Composable Enterprise framework ...
Through the magic of cloud computing, infrastructure is no longer the long pole in the IT process. Organizations can now set up the infrastructure they require within minutes instead of weeks. However, removing this bottleneck has exposed another; application delivery is the next issue to be resolved. With the ongoing move to digital-first enterprises, companies are now faced with a software-intensive business environment. Simply put, IT needs to figure out how to accelerate the application depl...
There's fog coming to the world of IT. Some people are calling this "The Cloud." This fog turns everything inside out. It will take your monolithic applications, the guts of which are contained within large bodies of code, and break them apart so that discrete units of functionality are contained within their own process, exposed through an interface for others to see. Complexity is moving from the inside of a few large processes to the outside of many smaller processes. People are rightly sca...
This is part of the ever-expanding "Microservices and PaaS" blog series covering the rapidly evolving use of microservices in modern cloud software projects. Parts I and II introduced microservices concepts and discussed patterns and practices being spearheaded by microservices pioneers, notably Netflix, who were represented at a recent microservices meetup that was the genesis of this series. Part III presented a list of challenges and pitfalls that adopters of microservices face. This list is...
In their session at DevOps Summit, Stan Klimoff, CTO of Qubell, and Mike Becker, Senior Data Engineer for RingCentral, will share the lessons learned from implementing CI/CD pipeline on AWS for a customer analytics project powered by Cloudera Hadoop, HP Vertica and Tableau. Stan Klimoff is CTO of Qubell, the enterprise DevOps platform. Stan has more than a decade of experience building distributed systems for companies such as eBay, Cisco and Seagate. Qubell is helping enterprises to become mor...
The impact of DevOps in the cloud era is potentially profound. DevOps helps businesses deliver new features continuously, reduce cycle time and achieve sustained innovation by applying agile and lean principles to assist all stakeholders in an organization that develop, operate, or benefit from the business’ lifecycle. In his session at DevOps Summit, Prashanth Chandrasekar, General Manager at Rackspace, will exam whether / how companies can work with external DevOps specialists to achieve "De...
I just recently wrote a blog about BOTs causing unwanted traffic on our servers. Right after I wrote this blog I was notified about yet another “interesting” and unusual load behavior on our download page which is used by customers to download latest product versions and updates. If you see such a load behavior you typically assume that you just released a new product version or maybe an update to our agents and many people are downloading it like crazy. Unfortunately that was not the case. The...
SYS-CON Events announced today that O'Reilly Media has been named “Media Sponsor” of SYS-CON's 15th International Cloud Expo®, which will take place on November 4–6, 2014, at the Santa Clara Convention Center in Santa Clara, CA. O'Reilly Media spreads the knowledge of innovators through its books, online services, magazines, and conferences. Since 1978, O'Reilly Media has been a chronicler and catalyst of cutting-edge development, homing in on the technology trends that really matter and spurri...
SYS-CON Events announced today that Gigaom Research has been named "Media Sponsor" of SYS-CON's 15th International Cloud Expo®, which will take place on November 4-6, 2014, at the Santa Clara Convention Center in Santa Clara, CA. Ashar Baig, Research Director, Cloud, at Gigaom Research, will also lead a Power Panel on the topic "Choosing the Right Cloud Option." Gigaom Research provides timely, in-depth analysis of emerging technologies for individual and corporate subscribers. Gigaom Research'...
Today, almost every company has a directory that needs to be managed. Spending valuable company time monitoring servers, provisioning and deprovisioning users, auditing, and assessing security concerns takes away from the core competency of the team – building product and delivering to customers quickly. DaaS takes on the burden of those tasks, and allows the team to focus on what they do best. In his session at DevOps Summit, Rajat Bahargava, Co-Founder, Chairman, and President & CEO of JumpClo...