Carefully examine trade-offs involving optimizing for throughput or for response time.
- [Instructor] If you want the best throughput,…that is if you want to get as much work done…in a time interval as possible,…then that's typically what we think servers do.…To have the best throughput, you want to have…few context switches.…You don't want to be switching back and forth…between processes, you want a process to run for awhile…and get some work done, and then switch to another one.…That means, you want longer time slices,…and that means it's better to run few things at a time,…maybe one per processor so that you don't have to…switch back and forth between things.…
We measure throughput in things like transactions per second…megabytes per minute, and so forth.…When we configure the Linux kernel,…there are a number of choices…for whether it's preemptible or not,…and preemption means context switch.…So how your kernel's configured can effect…responsiveness versus throughput.…Response time, is responding to some sort of event,…and if you want to have improved response time,…that means you want to have the response be quick.…
- Timing techniques
- Packages for performance
- Identifying and optimizing CPU bottlenecks
- Finding memory bottlenecks
- Diagnosing disk bottlenecks
Skill Level Advanced
1. Performance Overview
2. CPU Bottlenecks
3. Memory Bottlenecks
4. Disk Bottlenecks
- Mark as unwatched
- Mark all as unwatched
Are you sure you want to mark all the videos in this course as unwatched?
This will not affect your course history, your reports, or your certificates of completion for this course.Cancel
Take notes with your new membership!
Type in the entry box, then click Enter to save your note.
1:30Press on any video thumbnail to jump immediately to the timecode shown.
Notes are saved with you account but can also be exported as plain text, MS Word, PDF, Google Doc, or Evernote.