pipeline_process.py revision 49358b75c25a44760e884245440dc96e55812d04
1"""Pipeline process that encapsulates the actual content. 2 3Part of the Chrome build flags optimization. 4 5The actual stages include the builder and the executor. 6""" 7 8__author__ = 'yuhenglong@google.com (Yuheng Long)' 9 10import multiprocessing 11 12# Pick an integer at random. 13POISONPILL = 975 14 15 16class PipelineProcess(multiprocessing.Process): 17 """A process that encapsulates the actual content pipeline stage. 18 19 The actual pipeline stage can be the builder or the tester. This process 20 continuously pull tasks from the queue until a poison pill is received. 21 Once a job is received, it will hand it to the actual stage for processing. 22 23 Each pipeline stage contains three modules. 24 The first module continuously pulls task from the input queue. It searches the 25 cache to check whether the task has encountered before. If so, duplicate 26 computation can be avoided. 27 The second module consists of a pool of workers that do the actual work, e.g., 28 the worker will compile the source code and get the image in the builder 29 pipeline stage. 30 The third module is a helper that put the result cost to the cost field of the 31 duplicate tasks. For example, if two tasks are equivalent, only one task, say 32 t1 will be executed and the other task, say t2 will not be executed. The third 33 mode gets the result from t1, when it is available and set the cost of t2 to 34 be the same as that of t1. 35 """ 36 37 def __init__(self, num_processes, name, cache, stage, task_queue, helper, 38 worker, result_queue): 39 """Set up input/output queue and the actual method to be called. 40 41 Args: 42 num_processes: Number of helpers subprocessors this stage has. 43 name: The name of this stage. 44 cache: The computed tasks encountered before. 45 stage: An int value that specifies the stage for this pipeline stage, for 46 example, build stage or test stage. This value will be used to retrieve 47 the keys in different stage. I.e., the flags set is the key in build 48 stage and the checksum is the key in the test stage. The key is used to 49 detect duplicates. 50 task_queue: The input task queue for this pipeline stage. 51 helper: The method hosted by the helper module to fill up the cost of the 52 duplicate tasks. 53 worker: The method hosted by the worker pools to do the actual work, e.g., 54 compile the image. 55 result_queue: The output task queue for this pipeline stage. 56 """ 57 58 multiprocessing.Process.__init__(self) 59 60 self._name = name 61 self._task_queue = task_queue 62 self._result_queue = result_queue 63 64 self._helper = helper 65 self._worker = worker 66 67 self._cache = cache 68 self._stage = stage 69 self._num_processes = num_processes 70 71 # the queues used by the modules for communication 72 manager = multiprocessing.Manager() 73 self._helper_queue = manager.Queue() 74 self._work_queue = manager.Queue() 75 76 def run(self): 77 """Busy pulling the next task from the queue for execution. 78 79 Once a job is pulled, this stage invokes the actual stage method and submits 80 the result to the next pipeline stage. 81 82 The process will terminate on receiving the poison pill from previous stage. 83 """ 84 85 # the worker pool 86 work_pool = multiprocessing.Pool(self._num_processes) 87 88 # the helper process 89 helper_process = multiprocessing.Process(target=self._helper, 90 args=(self._cache, 91 self._helper_queue, 92 self._work_queue, 93 self._result_queue)) 94 helper_process.start() 95 mycache = self._cache.keys() 96 97 while True: 98 task = self._task_queue.get() 99 if task == POISONPILL: 100 # Poison pill means shutdown 101 self._result_queue.put(POISONPILL) 102 break 103 104 task_key = task.get_key(self._stage) 105 if task_key in mycache: 106 # The task has been encountered before. It will be sent to the helper 107 # module for further processing. 108 self._helper_queue.put(task) 109 else: 110 # Let the workers do the actual work. 111 work_pool.apply_async(self._worker, args=(task, self._work_queue, 112 self._result_queue)) 113 mycache.append(task_key) 114 115 # Shutdown the workers pool and the helper process. 116 work_pool.close() 117 work_pool.join() 118 119 self._helper_queue.put(POISONPILL) 120 helper_process.join() 121