|By Brendan Gregg||
|January 14, 2014 11:00 AM EST||
"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.
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.
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:
- Instruction fetch
- Instruction decode
- Memory access
- 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.
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.
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.
You think you know what’s in your data. But do you? Most organizations are now aware of the business intelligence represented by their data. Data science stands to take this to a level you never thought of – literally. The techniques of data science, when used with the capabilities of Big Data technologies, can make connections you had not yet imagined, helping you discover new insights and ask new questions of your data. In his session at @ThingsExpo, Sarbjit Sarkaria, data science team lead ...
May. 2, 2016 11:00 PM EDT Reads: 998
Much of the value of DevOps comes from a (renewed) focus on measurement, sharing, and continuous feedback loops. In increasingly complex DevOps workflows and environments, and especially in larger, regulated, or more crystallized organizations, these core concepts become even more critical. In his session at @DevOpsSummit at 18th Cloud Expo, Andi Mann, Chief Technology Advocate at Splunk, will show how, by focusing on 'metrics that matter,' you can provide objective, transparent, and meaningfu...
May. 2, 2016 08:30 PM EDT Reads: 711
If there is anything we have learned by now, is that every business paves their own unique path for releasing software- every pipeline, implementation and practices are a bit different, and DevOps comes in all shapes and sizes. Software delivery practices are often comprised of set of several complementing (or even competing) methodologies – such as leveraging Agile, DevOps and even a mix of ITIL, to create the combination that’s most suitable for your organization and that maximize your busines...
May. 2, 2016 07:45 PM EDT Reads: 1,892
In his session at @ThingsExpo, Chris Klein, CEO and Co-founder of Rachio, will discuss next generation communities that are using IoT to create more sustainable, intelligent communities. One example is Sterling Ranch, a 10,000 home development that – with the help of Siemens – will integrate IoT technology into the community to provide residents with energy and water savings as well as intelligent security. Everything from stop lights to sprinkler systems to building infrastructures will run ef...
May. 2, 2016 07:00 PM EDT Reads: 1,053
SYS-CON Events announced today that Peak 10, Inc., a national IT infrastructure and cloud services provider, will exhibit at SYS-CON's 18th International Cloud Expo®, which will take place on June 7-9, 2016, at the Javits Center in New York City, NY. Peak 10 provides reliable, tailored data center and network services, cloud and managed services. Its solutions are designed to scale and adapt to customers’ changing business needs, enabling them to lower costs, improve performance and focus inter...
May. 2, 2016 06:30 PM EDT Reads: 1,309
In the world of DevOps there are ‘known good practices’ – aka ‘patterns’ – and ‘known bad practices’ – aka ‘anti-patterns.' Many of these patterns and anti-patterns have been developed from real world experience, especially by the early adopters of DevOps theory; but many are more feasible in theory than in practice, especially for more recent entrants to the DevOps scene. In this power panel at @DevOpsSummit at 18th Cloud Expo, moderated by DevOps Conference Chair Andi Mann, panelists will dis...
May. 2, 2016 06:00 PM EDT Reads: 719
Up until last year, enterprises that were looking into cloud services usually undertook a long-term pilot with one of the large cloud providers, running test and dev workloads in the cloud. With cloud’s transition to mainstream adoption in 2015, and with enterprises migrating more and more workloads into the cloud and in between public and private environments, the single-provider approach must be revisited. In his session at 18th Cloud Expo, Yoav Mor, multi-cloud solution evangelist at Cloudy...
May. 2, 2016 05:30 PM EDT Reads: 1,569
Artificial Intelligence has the potential to massively disrupt IoT. In his session at 18th Cloud Expo, AJ Abdallat, CEO of Beyond AI, will discuss what the five main drivers are in Artificial Intelligence that could shape the future of the Internet of Things. AJ Abdallat is CEO of Beyond AI. He has over 20 years of management experience in the fields of artificial intelligence, sensors, instruments, devices and software for telecommunications, life sciences, environmental monitoring, process...
May. 2, 2016 05:15 PM EDT Reads: 1,001
Increasing IoT connectivity is forcing enterprises to find elegant solutions to organize and visualize all incoming data from these connected devices with re-configurable dashboard widgets to effectively allow rapid decision-making for everything from immediate actions in tactical situations to strategic analysis and reporting. In his session at 18th Cloud Expo, Shikhir Singh, Senior Developer Relations Manager at Sencha, will discuss how to create HTML5 dashboards that interact with IoT devic...
May. 2, 2016 05:00 PM EDT Reads: 1,101
See storage differently! Storage performance problems have only gotten worse and harder to solve as applications have become largely virtualized and moved to a cloud-based infrastructure. Storage performance in a virtualized environment is not just about IOPS, it is about how well that potential performance is guaranteed to individual VMs for these apps as the number of VMs keep going up real time. In his session at 18th Cloud Expo, Dhiraj Sehgal, in product and marketing at Tintri, will discu...
May. 2, 2016 04:00 PM EDT Reads: 914
So, you bought into the current machine learning craze and went on to collect millions/billions of records from this promising new data source. Now, what do you do with them? Too often, the abundance of data quickly turns into an abundance of problems. How do you extract that "magic essence" from your data without falling into the common pitfalls? In her session at @ThingsExpo, Natalia Ponomareva, Software Engineer at Google, will provide tips on how to be successful in large scale machine lear...
May. 2, 2016 03:45 PM EDT Reads: 1,354
SYS-CON Events announced today that SoftLayer, an IBM Company, has been named “Gold Sponsor” of SYS-CON's 18th Cloud Expo, which will take place on June 7-9, 2016, at the Javits Center in New York, New York. SoftLayer, an IBM Company, provides cloud infrastructure as a service from a growing number of data centers and network points of presence around the world. SoftLayer’s customers range from Web startups to global enterprises.
May. 2, 2016 03:30 PM EDT Reads: 1,074
The IoTs 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. In his session at @ThingsExpo, Craig Sproule, CEO of Metavine, will demonstrate how to move beyond today's coding paradigm and share the must-have mindsets for removing complexity from the development proc...
May. 2, 2016 03:00 PM EDT Reads: 381
SYS-CON Events announced today that Ericsson has been named “Gold Sponsor” of SYS-CON's @ThingsExpo, which will take place on June 7-9, 2016, at the Javits Center in New York, New York. Ericsson is a world leader in the rapidly changing environment of communications technology – providing equipment, software and services to enable transformation through mobility. Some 40 percent of global mobile traffic runs through networks we have supplied. More than 1 billion subscribers around the world re...
May. 2, 2016 02:45 PM EDT Reads: 1,101