Windows Performance Monitor

Front-end time is a dynamic target monitoring, the application needs to consider the large data volume and multi-user concurrency, the performance of the system is an important measure of the implementation of the solution. Here is a simple record of performance monitoring and simple analysis in Windows.

General operating system performance is mainly related to the main problems are: Processor usage, memory footprint, disk i/0 operations, and network traffic.

View Windows performance, most of the cases are the Windows Task Manager " , you can pass the " command Line " Input in : Taskmgr to eject the task Manager. The Task Manager can view:CPU usage, memory utilization, and Network Transmission volume situation.

using Windows Task Manager is intuitive and theUI works fine. However, there are some drawbacks, such as: The performance parameters can be referenced is not comprehensive, can not record performance for a long time and no performance report log and so on.

Perfmon Performance Monitor is Windows comes with a performance tool that can provide some basic data about the operating system, such as memory, CPU , IO , Network-related information, while providing graphical reports, logs, tracking and alerting functions. Can be entered through the perfmon of cmd .

Perfmon The counters are divided into four main types: Processor performance counters, memory performance counters, disk performance counters, and network performance counters.

The object here refers to the Performance monitor object .  There will be multiple counters for any one object -[ counter name ] - and there may be multiple instances ..  This is true when there are multiple processors in the system or if the system has more than one hard drive.

Here are a few common counters that describe the format: [Object ]: [ counter name ] [ explanation / description ]

processor performance Counters

Processor objects focus primarily on the CPU in the system . Note that some systems have multiple CPU, counter to each of the CPU will have a separate instance to display.

Processor:% Processor time

Current processor Time for all processes [ i.e. CPU Utilization ] If the value continues to exceed 95% , theCPU is the bottleneck. % Processor time value =100%-Idle Process ratio [ i.e.: idle thread (idle thread)],theCPU is fine when the idle thread is executed.

Processor : % User time

is the CPU time consumed by the non-core operation of the system , if it is a database server,%user The reason for the large value is probably that the database is sorted or the function operation consumes too much CPU time, so you can consider optimizing the database system.

Memory Performance Counters

Memory : Available Mbytes

The amount of memory that can be used. If the indicator's data is small, there may be a memory problem with the system

Memory : pages/sec

indicates the number of pages fetched from disk due to hardware page faults, or the number of pages written to disk to free working set space due to a page fault. Generally if the pages/sec continues above hundreds of, then you should study the paging activity further. There may be a need to increase memory to reduce the need for page breaks. A large value of pages/sec does not necessarily indicate a memory problem, but may be caused by a program running a memory-mapped file. A high ratio of counters indicates excessive paging .

memory:page faults/sec and the memory:page reads/sec The counter measures memory performance.

page faults occur when the virtual memory page referenced by the process is not in memory, andmemory:page faults/sec represents the number of page faults. If a page is already in main memory, or if it is being used by another process that is sharing this page, then the page will not be paged in from disk.

memory:page reads/sec is to read the disk to extract the number of pages required to resolve the page error. In general, these two counters reflect the frequency of access to the disk, and the lower the value, the less the response time.

network performance counters

main view Network Interface Object

Network interface:bytes received/sec

How much data is received per second Bytes, This data is combined Bytes total/sec Analysis

Network interface:bytes sent/sec

How much data is sent per second Bytes, This data is combined Bytes total/sec Analysis

Network interface:bytes total/sec

What is the total number of machines accepted and sent? Bytes It is recommended not to exceed the bandwidth 50%

Network interface:packets/sec

the number of packets per second, based on the actual data size, no recommended thresholds, the data combined Bytes total/sec Analysis

Performance analysis

1 , Memory analysis methods

Memory analysis is used to determine if the system has a memory bottleneck and whether it needs to improve the performance of the system by means of additional memory.

The counters that memory analysis needs to use: The Memories category and The counters for the physical Disk category. The main methods and steps of memory analysis:

(1) First View memory:available Mbytes Indicators

If the indicator data is small, the system may have a memory problem, you need to continue the following steps to further analysis.

(2) Note memory:pages/sec , Pages read/sec and the Page faults/sec the value

The operating system uses the disk better to improve the amount of memory available to the system or to improve its efficiency. These three metrics directly reflect the frequency with which the operating system is swapping disks.

pages/sec values persist above hundreds of, there may be memory issues. a pages/sec value does not necessarily indicate a memory problem, possibly caused by a program running a memory-mapped file.

Page faults/sec Indicates the number of page failures per second, and the more page failures, the more times the operating system reads to memory. You need to see the count value for Pages read/sec , which has a threshold of 5and if the count is more than 5, You can determine that there is a memory problem.

(3) according to Physical Disk counter value analysis performance bottleneck

The analysis of the physical Disk counter object includes the Page reads/sec and %disk time and aerage Disk Queue Length . If Pages read/sec is low, %disk time and Average Disk Queue Length value is high, there may be a disk bottleneck. However, if the queue length increases while the Pages read/sec is not lowered, then there is insufficient memory.

2. Processor Analysis Method

(1) First Look System : %total Processor time The count value of the performance counter

The value of this counter reflects the overall processor utilization of the server, which reminds the average utilization of all CPUs for multiprocessor systems . If the value continues to exceed %, the entire system is facing a processor bottleneck and needs to increase performance by increasing the processor.

Note: In multiprocessor systems, the data itself is small, but the PUT Direct load condition is extremely uneven and should be seen as a system-generated processor bottleneck.

(2) next look at each CPU of the Processor : \%processor Time and the Processor : \%user Time and the Processor : \%privileged Time

Processor:%user Time is consumed by non-core operations of the system CPU time, if the value is large, consider whether a friendly algorithm can be used

lower this value. If the server is a database server, The reason why the processor\%user time value is large is that the database is sorted or the function operation consumes too much CPU . You can consider optimizing your database system at this point.

(3) Research System Processor bottlenecks

View The value of the system:processor Queue Length counter when the value of the counter is greater than The total number of CPUs + 1 , the processor block is generated. When the processor's %process time is high, it is generally blocked with the processor, but when processor blocking occurs,Processor:%process time meter

The value of the digital device is not necessarily large, you must find the cause of the processor blocking.

3 . Disk I/O Analysis Method

(1) calculate the per-disk I/O number

per-disk I/O the number of disks that can be used to I/O The ability to compare, if each disk is calculated I/O The number exceeds the nominal disk I/O capability, the performance bottleneck of the disk does exist.

(2) with the processor:privileged Time Merging for analysis

If in the Physical disk counter, only the%disk time is larger, the other values are relatively moderate, the hard disk may be a bottleneck. A memory leak can occur if several values are larger and the value continues to exceed

(3) according to Disk Sec/transfer for Analysis

In general, this value is defined as less than 15ms excellent, ~ 30ms between for good, - ~ 60ms between to be acceptable, over 60ms you need to consider replacing the hard drive or RAID Way out.

4 . Process Analysis Methods

(1) View the process's Process :% Processor Time value

The% Processor time of each process reflects the processor times consumed by the process. By comparing the processor time consumed by different processes, you can see which process has consumed the most processor time in the performance test process, which can be optimized for the application accordingly.

(2) View page failures generated by each process

page invalidation (obtained via process :pagefailures/sec counter) and System page invalidation can be generated with each process ( can be obtained by memory:page failures/sec counter ) , To determine which process generated the most page failures, the process is either a process that requires a lot of memory, or it is a very active process that can be analyzed.

(3) Understanding the process's Process : Private Bytes

Process : Private Bytes refers to the current number of bytes allocated by the process that cannot be shared with other processes. This counter is primarily used to determine whether a process has a memory leak during performance testing. For example, for a WEB application on top of IIS , we can focus on monitoring the Private of the inetinfo process Bytes,

If the process is in a performance test, the Private Bytes The counter value is increasing, or the performance test is stopped after a period of time, the process's Private Bytes Continues at a high level, it indicates that the application has a memory leak.

5 . Network Analysis Method

(1) Network interface:bytes total/sec In order to send and receive bytes, the counter value can be used to determine whether the network link speed is a bottleneck, by comparing the value of the counter with the current network bandwidth.

(2) with the processor:privileged Time Merging for analysis

If in the Physical disk counter, only the%disk time is larger, the other values are relatively moderate, the hard disk may be a bottleneck. A memory leak can occur if several values are larger and the value continues to exceed

Source: http://www.cnblogs.com/upDOoGIS/archive/2010/11/19/1881970.html