Performance Tuning for Linux Servers [Electronic resources] نسخه متنی

اینجــــا یک کتابخانه دیجیتالی است

با بیش از 100000 منبع الکترونیکی رایگان به زبان فارسی ، عربی و انگلیسی

Performance Tuning for Linux Servers [Electronic resources] - نسخه متنی

Sandra K. Johnson

| نمايش فراداده ، افزودن یک نقد و بررسی
افزودن به کتابخانه شخصی
ارسال به دوستان
جستجو در متن کتاب
بیشتر
تنظیمات قلم

فونت

اندازه قلم

+ - پیش فرض

حالت نمایش

روز نیمروز شب
جستجو در لغت نامه
بیشتر
لیست موضوعات
توضیحات
افزودن یادداشت جدید








Requirements for System Tracing



To capture useful information for troubleshooting a performance problem, follow these guidelines before you begin to trace a system:



Use the right tool for the right step of your analysis. If the data that the tool you use is not reliable because it is the wrong tool for the job, your time is wasted analyzing the wrong data or application.



Ensure that the system that is being traced has enough memory and storage. For example, if there is not enough memory, swapping occurs, which can distort the results.



Know the overhead of the tool you are using. If the tool is very intrusive into your system, the performance analysis might be inaccurate.



Use a defined test scenario to make your measurements. It is imperative that you use a consistent set of steps for the measurements and that the results are repeatable. Measure the same functions in the same order during each step of the analysis.



Use a controlled environment. Do not allow other processes or functions to be performed during the measurements and traces unless they are part of the measurement scenario. After you have applied fixes based on the results of the measure-ments and traces, you can begin a new round of testing with new applications added to the mix. The best rule of thumb is to keep the scenario simple and know what is running when.









Requirements for System Tracing



To capture useful information for troubleshooting a performance problem, follow these guidelines before you begin to trace a system:



Use the right tool for the right step of your analysis. If the data that the tool you use is not reliable because it is the wrong tool for the job, your time is wasted analyzing the wrong data or application.



Ensure that the system that is being traced has enough memory and storage. For example, if there is not enough memory, swapping occurs, which can distort the results.



Know the overhead of the tool you are using. If the tool is very intrusive into your system, the performance analysis might be inaccurate.



Use a defined test scenario to make your measurements. It is imperative that you use a consistent set of steps for the measurements and that the results are repeatable. Measure the same functions in the same order during each step of the analysis.



Use a controlled environment. Do not allow other processes or functions to be performed during the measurements and traces unless they are part of the measurement scenario. After you have applied fixes based on the results of the measure-ments and traces, you can begin a new round of testing with new applications added to the mix. The best rule of thumb is to keep the scenario simple and know what is running when.




/ 227