我一直在研究这个问题已有一段时间了，但似乎无法弄明白。我把它缩小到我的代码和操作系统（Linux上的Python 2.7.3）不同意应该运行哪些进程的情况。发生这种情况时，我的代码会永久挂起，但不会抛出任何异常。有时代码会运行几个小时，有时只运行几分钟，我无法弄清楚原因。这表现如下。谢谢你看一下，我真的在这里泡芙（双关语）。
代码输出：
创建离散字符矩阵
running PoolWorker_82 (72 triplets), pid 25777, ppid 24892
running PoolWorker_83 (72 triplets), pid 25778, ppid 24892
running PoolWorker_84 (72 triplets), pid 25779, ppid 24892
running PoolWorker_85 (72 triplets), pid 25780, ppid 24892
running PoolWorker_86 (72 triplets), pid 25781, ppid 24892
running PoolWorker_87 (72 triplets), pid 25782, ppid 24892
running PoolWorker_88 (72 triplets), pid 25783, ppid 24892
running PoolWorker_89 (90 triplets), pid 25784, ppid 24892
ps aux ...
的输出1000 24892 2.0 0.9 559948 151088 pts/0 Sl+ 09:14 0:16 p runsimulation.py
1000 25776 0.0 0.8 559932 138320 pts/0 S+ 09:19 0:00 p runsimulation.py
1000 26015 0.0 0.8 559948 138140 pts/0 S+ 09:22 0:00 p runsimulation.py
1000 26021 0.0 0.8 559948 138140 pts/0 S+ 09:22 0:00 p runsimulation.py
1000 26023 0.0 0.8 559948 138140 pts/0 S+ 09:22 0:00 p runsimulation.py
1000 26025 0.0 0.8 559948 138140 pts/0 S+ 09:22 0:00 p runsimulation.py
1000 26027 0.0 0.8 559948 138140 pts/0 S+ 09:22 0:00 p runsimulation.py
1000 26029 0.0 0.8 559948 138140 pts/0 S+ 09:22 0:00 p runsimulation.py
1000 26031 0.0 0.8 559948 138140 pts/0 S+ 09:22 0:00 p runsimulation.py
1000 26036 0.0 0.8 559948 138140 pts/0 S+ 09:22 0:00 p runsimulation.py
您可以看到父进程24982在那里，但工作者的pid却没有。通常情况下，这些都会匹配，我可以看到工作时CPU工作量达到100％，然后在迭代完成后它们都会消失。当它失败时，我得到pid不匹配和使用0.0％CPU的进程（第3列）。
我的代码的相关部分如下（与调用它们的顺序相反）：
使用rpy2：
调用函数进行R设置def create_R(dir):
"""
creates the r environment
@param dir: the directory for the output files
"""
r = robjects.r
importr("phangorn")
importr("picante")
importr("MASS")
importr("vegan")
r("options(expressions=500000)")
robjects.globalenv['outfile'] = os.path.abspath(os.path.join(dir, "trees.pdf"))
r('pdf(file=outfile, onefile=T)')
r("par(mfrow=c(2,3))")
r("""
generate_triplet = function(bits) {
triplet = replicate(bits, rTraitDisc(tree, model="ER", k=2,states=0:1))
triplet = t(apply(triplet, 1, as.numeric))
sums = rowSums(triplet)
if (length(which(sums==0)) > 0 && length(which(sums==3)) == 1) {
return(triplet)
}
return(generate_triplet(bits))
}
""")
r("""
get_valid_triplets = function(numsamples, needed, bits) {
tryCatch({
m = generate_triplet(bits)
while (ncol(m) < needed) {
m = cbind(m, generate_triplet(bits))
}
return(m)
}, error = function(e){print(message(e))}, warning = function(e){print(message(e))})
}
""")
在工人中调用的函数：
def __get_valid_triplets(num_samples, num_triplets, bits, q):
r = robjects.r
name = current_process().name.replace("-", "_")
timer = stopwatch.Timer()
log("\trunning %s (%d triplets), pid %d, ppid %d" % (name, num_triplets, current_process().pid, os.getppid()),
log_file)
r('%s = get_valid_triplets(%d, %d, %d)' % (name, num_samples, num_triplets, bits))
q.put((name, r[name]))
timer.stop()
log("\t%s complete (%s)" % (name, str(timer)), log_file)
设置池的功能，并使用apply_async调度worker。工作程序写入托管队列，该队列是池加入后的进程：
def __generate_candidate_discrete_matrix(num_cols, num_samples, sample_tree, bits, usable_cols):
assert isinstance(sample_tree, dendropy.Tree)
print "Creating discrete character matrix"
r = robjects.r
newick = sample_tree.as_newick_string()
num_samples = len(sample_tree.leaf_nodes())
robjects.globalenv['numcols'] = usable_cols
robjects.globalenv['newick'] = newick + ";"
r("tree = read.tree(text=newick)")
r('m = matrix(nrow=length(tree$tip.label))') #create empty matrix
r('m = m[,-1]') #drop the first NA column
num_procs = mp.cpu_count()
args = []
div, mod = divmod(usable_cols, num_procs)
[args.append(div) for i in range(num_procs)]
args[-1] += mod
for i, elem in enumerate(args):
div, mod = divmod(elem, bits)
args[-1] += mod
args[i] -= mod
manager = Manager()
pool = Pool(processes=num_procs, maxtasksperchild=1)
q = manager.Queue(maxsize=num_procs)
for arg in args:
pool.apply_async(__get_valid_triplets, (num_samples, arg, bits, q))
pool.close()
pool.join()
while not q.empty():
name, data = q.get()
robjects.globalenv[name] = data
r('m = cbind(m, %s)' % name)
r('m = m[,1:%d]' % usable_cols)
r('m = m[order(rownames(m)),]') # consistently order the rows
r('m = t(apply(m, 1, as.numeric))') # convert all factors given by rTraitDisc to numeric
a = r['m']
n = r('rownames(m)')
return a, n
最后，调用的第一个函数生成候选矩阵，确保它是有效的，如果没有，它将再次使用新矩阵。如果它有效，它会在R会话中存储一些内容并返回数据
def create_discrete_matrix(num_cols, num_samples, sample_tree, bits):
"""
Creates a discrete char matrix from a tree
@param num_cols: number of columns to create
@param sample_tree: the tree
@return: a r object of the matrix, and a list of the row names
@rtype: tuple(robjects.Matrix, list)
"""
r = robjects.r
usable_cols = find_usable_length(num_cols, bits)
a, n = __generate_candidate_discrete_matrix(num_cols, num_samples, sample_tree, bits, usable_cols)
assert isinstance(a, robjects.Matrix)
assert a.ncol == usable_cols
paralin_matrix, valid = __create_paralin_matrix(a)
if valid is False:
sample_tree = create_tree(num_samples, type = "S")
return create_discrete_matrix(num_cols, num_samples, sample_tree, bits)
else:
robjects.globalenv['paralin_matrix'] = paralin_matrix
r('rownames(paralin_matrix) = rownames(m)')
r('paralin_dist = as.dist(paralin_matrix, diag=T, upper=T)')
r("paralinear_cluster = hclust(paralin_dist, method='average')")
return sample_tree, a, n
答案 0 :(得分：0)
看起来这是由服务器重启（FML）修复的。但是，获得了有效的信息。将worker提交到池时，请确保在worker本身中捕获异常，而不是将它们捕获到调用pool.apply_async的方法中。
def __get_valid_triplets(num_samples, num_triplets, bits, q):
try:
r = robjects.r
name = current_process().name.replace("-", "_")
timer = stopwatch.Timer()
log("\trunning %s (%d triplets), pid %d, ppid %d" % (name, num_triplets, current_process().pid, os.getppid()),
log_file)
r('%s = get_valid_triplets(%d, %d, %d)' % (name, num_samples, num_triplets, bits))
q.put((name, r[name]))
timer.stop()
log("\t%s complete (%s)" % (name, str(timer)), log_file)
except Exception, e:
q.put("DEATH")
traceback.print_exc()