本文将回顾一下Linux 2.6的任务调度器及其最重要的一些属性。
This article reviews the Linux 2.6 task scheduler and its most important attributes.
数据处理单元可以响应于从任务调度器所提供的任务开始信号来执行任务。
The data processing units may perform tasks in response to task start signals provided from the task scheduler.
任务调度器向导 (task scheduler wizard)用来调度两种任务。
The task scheduler wizard is a tool used to schedule two different types of tasks.
数据处理单元可以完成如任务调度器所指令的任务，向调度器传送任务结束信号并且转换到备用状态。
The data processing units may complete the tasks as instructed by the task scheduler, transmit task end signals to the scheduler and transition into standby states.
系统包括测试脚本生成器、测试任务定义模块、测试任务调度器、测试任务运行台、统计报表模块和人员管理模块。
The system includes testing scripts generator, test task definition module, test task scheduler, test task running platform, accounting and report form module.
这被称为O(1)调度器，因为其在固定时间内工作，而无论要调度的任务数量。
It was called the o (1) scheduler, because it operated in constant time, regardless of the number of tasks to schedule.
调度器的工作非常简单：它在优先级最高的队列中选择一个任务来执行。
The job of the scheduler is simple: choose the task on the highest priority list to execute.
在这种调度器中，调度任务所花费的时间是一个系统中任务个数的函数。
In this type of scheduler, the time it takes to schedule a task is a function of the number of tasks in the system.
调度器还需要面对一些互相冲突的目标，例如既要为关键实时任务最小化响应时间，又要最大限度地提高CPU 的总体利用率。
The scheduler can also be faced with such conflicting goals as minimizing response times for critical real-time tasks while maximizing overall CPU utilization.
O(1) 调度器扩展性更好而且包含交互性，提供了大量启示用于确定任务是受I/O 限制还是受处理器限制。
The O(1) scheduler was much more scalable and incorporated interactivity metrics with numerous heuristics to determine whether tasks were I/O-bound or processor-bound.
在2.6版本的内核之前，当很多任务都处于活动状态时，调度器有很明显的限制。
Before the 2.6 kernel, the scheduler had a significant limitation when many tasks were active.
一个托管编程模型，支持数据并行处理，任务并行处理，并通过一个通用的工作调度器统一协调并行运行的硬件。
A managed programming model for data parallelism, task parallelism, and coordination on parallel hardware unified by a common work scheduler.
注意：某些特殊的任务(比如删除调度器中的任务)只在InformixServerVersion 11.50和更高版本上得到支持。
Note: Certain specialized tasks, like deleting a task from the scheduler, are supported only on Informix Server, Version 11.50 and later.
调度器将时间分割成epoch，每个epoch中，每个任务允许执行到其时间切片用完。
The 2.4 scheduler divided time into epochs, and within each epoch, every task was allowed to execute up to its time slice.
最后，启动空任务，现在调度器就可以接管控制权了（在调用 cpu_idle 之后）。
Finally, the idle task is started and the scheduler can now take control (after the call to cpu_idle).
有一个名为ph _ threshold的sysadmin表，它用来存储调度器任务的阈值。
There is a sysadmin table called ph_threshold that is used to store thresholds for the scheduler tasks.
DynamicServer中的调度器包含下表所示的任务。
The scheduler in the Dynamic Server contains the tasks shown in the following table.
对于负载平衡程序，调度模块实现了迭代器，使用它遍历由调度模块管理的所有任务，从而进行负载平衡。
For the load balancer, scheduling modules implement iterators that are used to walk through all the tasks managed by that scheduling module to do load balancing.
线程在作业调度器上调度，所以理论上讲，该机器不应该用于执行任何子任务。
Threads are scheduled on the job dispatcher, so ideally this machine should not be used to execute any subtasks.
每200毫秒，调度程序就执行一次负载平衡调节，以便重新分配任务负载，维持处理器之间的平衡。
Every 200 milliseconds, the scheduler performs load balancing to redistribute the task loading to maintain a balance across the processor complex.
窗格指出哪些服务器、调度程序和服务可用，且支持这样的管理任务，比如启动和停止服务或设置属性。
The Scorecard pane indicates which servers, dispatchers, and services are available and allows for administrative tasks such as starting and stopping the service or setting properties.
运行服务器在启动时接通作业调度器，并通知作业调度器它已准备就绪，可以接受要执行的任务了。
The run server contacts the job dispatcher when it starts up and informs the job dispatcher that it is ready to accept tasks for execution.
如果服务速率低于新工作的到达速率，则服务器将会跟不上，在有托管任务可对其进行调度前，新工作都将排队等候。
If the service rate drops below the arrival rate of new work, the server falls behind and new work is queued up until a managed task becomes available to dispatch it.
在服务器上直接完成相同的操作要涉及大量的数据库和表，所以OAT极大地简化了整个任务调度和监视过程。
Since doing the same on the server directly involves working with a lot of databases and tables, OAT makes the whole process of task scheduling and monitoring extremely simple.
这意味着一个任务可以在任何处理器上进行调度——这对于负载均衡来说是好事，但是对于内存缓存来说却是个灾难。
This meant a task could be scheduled on any processor — which can be good for load balancing but bad for memory caches.
通用调度器最后为此任务提供处理器。
The generic scheduler finally provides the processor to this task.
还请注意调度器在繁忙和非繁忙任务中是公平的，给予它们大概相同的处理器访问量。
Also note that the scheduler is fair across the busy and non-busy tasks, giving them roughly the same amount of processor access.
任务调度是操作系统设计的一个重要方面，从桌面操作系统调度器到实时调度器和嵌入式操作系统调度器。
Task scheduling is an important aspect to operating system design, from desktop operating system schedulers to real-time schedulers and embedded operating system schedulers.
在任务负载非常重时，处理器会因调度消耗掉大量的时间，用于任务本身的时间就非常少了。
At very high loads, the processor can be consumed with scheduling and devote little time to the tasks themselves.
例如，每个调度器提供一种方式，添加要调度的任务、调出要运行的下一个任务、提供给调度器等等。
For example, each scheduler provides a way to add a task to be scheduled, pull the next task to be run, yield to the scheduler, and so on.
应用推荐