Welcome!

DevOps Journal Authors: Liz McMillan, Yeshim Deniz, Pat Romanski, Elizabeth White, Mike Kavis

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.


Latest Stories from DevOps Journal
Qubell, an innovator in application deployment and configuration management, empowers online companies to do what they have never been able to do before: put into consumers' hands innovative new features and services, almost as fast as they can conceive them, without sacrificing control, reliability or uptime. Qubell emerged from stealth in the summer of 2013 (see related press release) and announced that Kohl's completed its initial implementation (see press release). Founded by pioneers in enterprise cloud applications and services, Qubell has its headquarters in Menlo Park, Calif. For more information, visit qubell.com.
Founded in 1997, ActiveState is a global leader providing software application development and management solutions. The Company's products include: Stackato, a commercially supported Platform-as-a-Service (PaaS) that harnesses open source technologies such as Cloud Foundry and Docker; dynamic language distributions ActivePerl, ActivePython and ActiveTcl; and developer tools such as the popular Komodo Edit and Komodo IDE. Headquartered in Vancouver, Canada, ActiveState is trusted by customers and partners worldwide, across many industries including telecommunications, aerospace, software, financial services and CPG. ActiveState is proven for the enterprise: More than two million developers and 97% of Fortune 1000 companies use ActiveState's solutions to develop, distribute, and manage their software applications. Global customers like Bank of America, CA, Cisco, HP, Lockheed Martin and Siemens rely on ActiveState for faster development, ensuring IT governance and compliance, and accelerating time-to-market.
BlueBox bridge the chasm between development and infrastructure. Hosting providers are taking standardization and automation too far. For many app developers it does nothing but spawn mayhem and more work. They have to figure out how their creations live on a pre-fab infrastructure solution full of constraints. Operations-as-a-Service is what BlueBox does. BlueBox utilizes development tools such as OpenStack, EMC Razor, Opscode’s Chef and BlueBox's proprietary tools give the power to do the unorthodox things which most hosting providers shun.
SYS-CON Events announced today that Serena Software 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. Serena Software supports DevOps and Continuous Delivery by providing application deployment automation and software release management solutions to replace slow and error-prone manual processes. 2,500 enterprises around the world trust Serena to help them develop and deploy better software.
DevOps Summit at Cloud Expo Silicon Valley announced today a limited time free "Expo Plus" registration option through September. On site registration price of $1,95 will be set to 'free' for delegates who register during special offer. To take advantage of this opportunity, attendees can use the coupon code, and secure their registration to attend all keynotes, DevOps Summit sessions at Cloud Expo, expo floor, and SYS-CON.tv power panels. Registration page is located at the DevOps Summit site. Your DevOps Summit registration will also allow access to @ThingsExpo sessions and exhibits. Register For DevOps Summit "FREE" (limited time) ▸ Here
The old monolithic style of building enterprise applications just isn't cutting it any more. It results in applications and teams both that are complex, inefficient, and inflexible, with considerable communication overhead and long change cycles. Microservices architectures, while they've been around for a while, are now gaining serious traction with software organizations, and for good reasons: they enable small targeted teams, rapid continuous deployment, independent updates, true polyglot languages and persistence layers, and a host of other benefits. But truly adopting a microservices architecture requires dramatic changes across the entire organization, and a DevOps culture is absolutely essential.
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 Enterprise SQA? Does the SQA function become redundant?
Achieve continuous delivery of applications by leveraging ElasticBox and Jenkins. In his session at DevOps Summit, Monish Sharma, VP of Customer Success at ElasticBox, will demonstrate how you can achieve the following using ElasticBox and the ElasticBox Jenkins Plugin: Create consistency across dev, staging, and production environments Continuous delivery across multiple clouds to handle high loads Ensure consistent policy management across environments: tagging, admin boxes, traceability Spin up machines and environments quickly Deploy applications to any cloud Enable real-time collaboration between developers and operations
Docker offers a new, lightweight approach to application portability. Applications are shipped using a common container format and managed with a high-level API. Their processes run within isolated namespaces that abstract the operating environment independently of the distribution, versions, network setup, and other details of this environment. This "containerization" has often been nicknamed "the new virtualization." But containers are more than lightweight virtual machines. Beyond their smaller footprint, shorter boot times, and higher consolidation factors, they also bring a lot of new features and use cases that were not possible with classical virtual machines.
WaveMaker CEO Samir Ghosh is taking a new pass at aPaas, and leveraging the increasingly popular Docker open-source platform, with the announcement of WaveMaker Enterprise. The new version of the company's eponymous software “enables instant, end-to-end custom web app creation and management by professional and non-professional developers (alike) and development teams,” according to the company. We asked Samir a few questions about this, and here's what he had to say: Cloud Computing Journal: You've mentioned the previous challenge of business-side developers making that jump from design to deployment. What sort of learning curve will they still face with Wavemaker Enterprise? Samir Ghosh: “Business-side developers” can include non-programming business users or professional developers under tight schedules or with limited mobile or front-end programming expertise. Both can use WaveMaker to meet their app development needs, but may have different deployment needs. I think business users just want their app to run as easily as possible. In WaveMaker, they can literally click a button and their application will run, either on our public cloud or on the enterprise’s private...