U ʹj*@sjddlZddlZddlmZmZddlmZmZmZm Z m Z m Z m Z ddl mmmmZddlmZmZddlmZddlmZddlmZmZddlmZdd lm Z dd l!m"Z"dd l#m$Z$d d dgZ%e$e&Z'eGdd d Z(Gdd d Z)e ee*dfe ee*dddZ+e e e e*e e,fdddZ-e(e ee*dfe eee,efdddZ.dS)N) dataclassfield)AnyCallableDictListOptionalTupleUnion)eventsmetrics) WorkerSpec)LocalElasticAgent)SignalExceptionStd)ChildFailedError)RendezvousParameters)parse_rendezvous_endpoint) get_logger LaunchConfigelastic_launch launch_agentc@s"eZdZUdZeed<eed<eed<dZeed<dZeed<dZ eed <d Z eed <e e d Z eeefed <dZeed<dZeed<dZeed<dZeed<dZeeed<ejZeeeeeffed<ejZeeeeeffed<e e d Zeeefed<dZeeed<ddZdS)ra Creates a rendezvous config. Args: min_nodes: Minimum amount of nodes that the user function will be launched on. Elastic agent ensures that the user function start only when the min_nodes amount enters the rendezvous. max_nodes: Maximum amount of nodes that the user function will be launched on. nproc_per_node: On each node the elastic agent will launch this amount of workers that will execute user defined function. rdzv_backend: rdzv_backend to use in the rendezvous (zeus-adapter, etcd). rdzv_endpoint: The endpoint of the rdzv sync. storage. rdzv_configs: Key, value pair that specifies rendezvous specific configuration. rdzv_timeout: Legacy argument that specifies timeout for the rendezvous. It is going to be removed in future versions, see the note below. The default timeout is 900 seconds. run_id: The unique run id of the job (if not passed a unique one will be deduced from run environment - flow workflow id in flow - or auto generated). role: User defined role of the worker (defaults to "trainer"). max_restarts: The maximum amount of restarts that elastic agent will conduct on workers before failure. monitor_interval: The interval in seconds that is used by the elastic_agent as a period of monitoring workers. start_method: The method is used by the elastic agent to start the workers (spawn, fork, forkserver). log_dir: base log directory where log files are written. If not set, one is created in a tmp dir but NOT removed on exit. redirects: configuration to redirect stdout/stderr to log files. Pass a single ``Std`` enum to redirect all workers, or a mapping keyed by local_rank to selectively redirect. tee: configuration to "tee" stdout/stderr to console + log file. metrics_cfg: configuration to initialize metrics. local_addr: address of the local node if any. If not set, a lookup on the local machine's FQDN will be performed. ..note: `rdzv_timeout` is a legacy argument that will be removed in future. Set the timeout via `rdzv_configs['timeout']` min_nodes max_nodesnproc_per_noderun_idZ default_rolerole rdzv_endpointZetcd rdzv_backend)default_factory rdzv_configs rdzv_timeout max_restartsmonitor_intervalspawn start_methodNlog_dir redirectstee metrics_cfg local_addrcCs4d}|jdkr|j|jd<nd|jkr0||jd<dS)Nir"timeout)r#r!)selfZdefault_timeoutr1]/var/www/html/bwave/python/venv/lib/python3.8/site-packages/torch/distributed/launcher/api.py __post_init__Zs   zLaunchConfig.__post_init__)__name__ __module__ __qualname____doc__int__annotations__rstrrrrrdictr!rrr#r%r'floatr)r*rrNONEr+r r,r-r.r3r1r1r1r2rs& *        c@s2eZdZdZeeeedfdddZddZ dS)ra Launches an torchelastic agent on the container that invoked the entrypoint. 1. Pass the ``entrypoint`` arguments as non ``kwargs`` (e.g. no named parameters)/ ``entrypoint`` can be a function or a command. 2. The return value is a map of each worker's output mapped by their respective global rank. Usage :: def worker_fn(foo): # ... def main(): # entrypoint is a function. outputs = elastic_launch(LaunchConfig, worker_fn)(foo) # return rank 0's output return outputs[0] # entrypoint is a command and ``script.py`` is the python module. outputs = elastic_launch(LaunchConfig, "script.py")(args) outputs = elastic_launch(LaunchConfig, "python")("script.py") N)config entrypointcCs||_||_dSN)_config _entrypoint)r0r>r?r1r1r2__init__}szelastic_launch.__init__cGst|j|jt|Sr@)rrArBlist)r0argsr1r1r2__call__szelastic_launch.__call__) r4r5r6r7rr rr:rCrFr1r1r1r2rbs  )r?rEreturncCsFt|tr|jSt|tr>|tjkr8tdd|DdS|SndSdS)aRetrieve entrypoint name with the rule: 1. If entrypoint is a function, use ``entrypoint.__qualname__``. 2. If entrypoint is a string, check its value: 2.1 if entrypoint equals to ``sys.executable`` (like "python"), use the first element from ``args`` which does not start with hifen letter (for example, "-u" will be skipped). 2.2 otherwise, use ``entrypoint`` value. 3. Otherwise, return empty string. css|]}|ddkr|VqdS)r-Nr1).0argr1r1r2 s z'_get_entrypoint_name..rN) isinstancerr4r:sys executablenext)r?rEr1r1r2_get_entrypoint_names   rP)rdzv_parametersrGcCsX|jdkrdS|j}|}|s(tdt|dd\}}|dkrPtd|d||fS)NZstatic)NNzKEndpoint is missing in endpoint. Try to add --master-addr and --master-portr") default_portzport is missing in endpoint: z. Try to specify --master-port)backendendpointstrip ValueErrorr)rQrT master_addr master_portr1r1r2_get_addr_and_ports  rY)r>r?rErGc Cs|js&ttj}td|||_t||}td||j |j |j |j|j |j |j|j|j|j|jd tf|j |j |j|j |j |jd|j}t|\}}t|j|j |t|t||j|j|j|j|||jd }t||j|jd} d} zzLt!"t!#|j| $} t%&| '| (r4t)|| j*d| j+WWjSt)k rVYnNt,k r~d } t%&| -Yn&t.k rt%&| -YnXW5| r|j XdS) Nz3config has no run_id, generated a random run_id: %saStarting elastic_operator with launch configs: entrypoint : %(entrypoint)s min_nodes : %(min_nodes)s max_nodes : %(max_nodes)s nproc_per_node : %(nproc_per_node)s run_id : %(run_id)s rdzv_backend : %(rdzv_backend)s rdzv_endpoint : %(rdzv_endpoint)s rdzv_configs : %(rdzv_configs)s max_restarts : %(max_restarts)s monitor_interval : %(monitor_interval)s log_dir : %(log_dir)s metrics_cfg : %(metrics_cfg)s ) r?rrrrrrr!r%r'r*r-)rSrTrrrr.) rZlocal_world_sizer?rE rdzv_handlerr%r'r+r,rWrXr.)specr)r*T)namefailuresF)/rr:uuiduuid4r8loggerwarningrPinforrrrrr!r%r'r*r-rr.rYr rtuple rdzv_registryZget_rendezvous_handlerr+r,rr)rZshutdownr Zinitialize_metricsZ MetricsConfigrunr recordZget_event_succeededZ is_failedrr]Z return_valuesrZget_event_failed Exception) r>r?rErZentrypoint_namerQrWrXr[ZagentZ shutdown_rdzvresultr1r1r2rs      )/rMr^ dataclassesrrtypingrrrrrr r Z-torch.distributed.elastic.rendezvous.registry distributedZelasticZ rendezvousregistryrdZtorch.distributed.elasticr r Z*torch.distributed.elastic.agent.server.apir Z:torch.distributed.elastic.agent.server.local_elastic_agentrZ)torch.distributed.elastic.multiprocessingrrZ0torch.distributed.elastic.multiprocessing.errorsrZ$torch.distributed.elastic.rendezvousrZ*torch.distributed.elastic.rendezvous.utilsrZ'torch.distributed.elastic.utils.loggingr__all__r4r`rrr:rPr8rYrr1r1r1r2s:$       E(