SGE集群上的python Java最大堆大小

5 月，3 周 Questions & Answers 764

我有一个用python编写的管道，用Java调用一些进程。管道以两种可能的模式运行，本地模式（单个节点上）或SGE集群上

当我将选项设置为集群模式时，日志中的错误消息如下所示

Invalid maximum heap size: -Xmx4g -jar
Error: Could not create the Java Virtual Machine.
Error: A fatal exception has occurred. Program will exit.

在本地模式下，没有错误，也没有问题

我的问题是什么会导致这样的错误

我在本地或集群上运行作业的类如下

class LocalJobManager(JobManager):
    def __init__(self):
        self.cmd_strs = []

    def add_job(self, cmd, cmd_args, **kwargs):
        cmd_str = ' '.join([cmd, ] + [str(x) for x in cmd_args])

        self.cmd_strs.append(cmd_str)

    def run_job(self, cmd, cmd_args, **kwargs):
        cmd_str = ' '.join([cmd, ] + [str(x) for x in cmd_args])

        self._run_cmd(cmd_str)

    def wait(self):
        for cmd_str in self.cmd_strs:
            self._run_cmd(cmd_str)

    def _run_cmd(self, cmd_str):
        '''
        Throw exception if run command fails
        '''
        process = subprocess.Popen(cmd_str, stdin=subprocess.PIPE, shell=True)

        process.stdin.close()

        sts = os.waitpid(process.pid, 0)

        if sts[1] != 0:
            raise Exception('Failed to run {0}\n'.format(cmd_str))

class ClusterJobManager(JobManager):
    def __init__(self, log_dir=None):
        import drmaa

        self._drmaa = drmaa

        self.log_dir = log_dir

        if self.log_dir is not None:
            make_directory(self.log_dir)

        self.session = self._drmaa.Session()

        self.session.initialize()

        self.job_ids = Queue()

        self._lock = threading.Lock()

    def add_job(self, cmd, cmd_args, mem=4, max_mem=10, num_cpus=1):
        job_id = self._run_job(cmd, cmd_args, mem, max_mem, num_cpus)

        self.job_ids.put(job_id)

    def run_job(self, cmd, cmd_args, mem=4, max_mem=10, num_cpus=1):
        job_id = self._run_job(cmd, cmd_args, mem, max_mem, num_cpus)

        self._check_exit_status(job_id)

    def wait(self):
        self._lock.acquire()

        job_ids = []

        while not self.job_ids.empty():
            job_ids.append(self.job_ids.get())

        self.session.synchronize(job_ids, self._drmaa.Session.TIMEOUT_WAIT_FOREVER, False)

        self._lock.release()

        for job_id in job_ids:
            self._check_exit_status(job_id)

    def close(self):
        self.session.control(self._drmaa.Session.JOB_IDS_SESSION_ALL, self._drmaa.JobControlAction.TERMINATE)

        self.session.exit()

    def _run_job(self, cmd, cmd_args, mem, max_mem, num_cpus):
        job_template = self._init_job_template(cmd, cmd_args, mem, max_mem, num_cpus)

        job_id = self.session.runJob(job_template)

        self.session.deleteJobTemplate(job_template)

        return job_id

    def _init_job_template(self, cmd, cmd_args, mem, max_mem, num_cpus):
        job_template = self.session.createJobTemplate()

        job_template.remoteCommand = cmd

        job_template.args = [str(x) for x in cmd_args]

        job_template.workingDirectory = os.getcwd()

        if self.log_dir is not None:
            job_template.errorPath = ':' + self.log_dir

            job_template.outputPath = ':' + self.log_dir

        job_template.nativeSpecification = '-l mem_free={mem}G,mem_token={mem}G,h_vmem={max_mem}G -V -w n -pe ncpus {num_cpus}'.format(**locals())

        return job_template

    def _check_exit_status(self, job_id):
        return_value = self.session.wait(job_id, self._drmaa.Session.TIMEOUT_WAIT_FOREVER)

        if return_value.exitStatus != 0:
            raise Exception('Job {0} failed with exit status {1}.'.format(return_value.jobId,
                                                                          return_value.exitStatus))

通常无法创建Java虚拟机（正如我在某个论坛上读到的）是由语法错误引起的，即使调用的命令是正确的并且在本地工作，除了上面显示的在集群上运行作业的类之外，还运行除Java以外的所有对象

谢谢

Python中文网

有 Java 编程相关的问题?

SGE集群上的python Java最大堆大小

共 (1) 个答案

# 1 楼答案