oh-my-batch 0.1.0.dev0__tar.gz → 0.1.0.dev1__tar.gz

{oh_my_batch-0.1.0.dev0 → oh_my_batch-0.1.0.dev1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: oh-my-batch
-Version: 0.1.0.dev0
+Version: 0.1.0.dev1
 Summary: 
 License: GPL
 Author: weihong.xu
@@ -118,13 +118,13 @@ You can use `omb job` to track the state of the jobs.
 ```bash
 
 omb job slurm \
-    submit tmp/*.slurm --max_tries 3 --wait --recovery lammps.recovery
+    submit tmp/*.slurm --max_tries 3 --wait --recovery lammps-jobs.json 
 ```
 
 The above command will submit the batch scripts to the job scheduler,
 and wait for the jobs to finish. If the job fails, it will retry for at most 3 times.
 
-The `--recovery` option will save the job information to `lammps.recovery` file,
+The `--recovery` option will save the job information to `lammps-jobs.json` file,
 if `omb job` is interrupted, you can run the exact same command to recover the job status, 
 so that you don't need to resubmit the jobs that are already submitted.
 

{oh_my_batch-0.1.0.dev0 → oh_my_batch-0.1.0.dev1}/README.md

@@ -100,12 +100,12 @@ You can use `omb job` to track the state of the jobs.
 ```bash
 
 omb job slurm \
-    submit tmp/*.slurm --max_tries 3 --wait --recovery lammps.recovery
+    submit tmp/*.slurm --max_tries 3 --wait --recovery lammps-jobs.json 
 ```
 
 The above command will submit the batch scripts to the job scheduler,
 and wait for the jobs to finish. If the job fails, it will retry for at most 3 times.
 
-The `--recovery` option will save the job information to `lammps.recovery` file,
+The `--recovery` option will save the job information to `lammps-jobs.json` file,
 if `omb job` is interrupted, you can run the exact same command to recover the job status, 
 so that you don't need to resubmit the jobs that are already submitted.

{oh_my_batch-0.1.0.dev0 → oh_my_batch-0.1.0.dev1}/oh_my_batch/job.py

@@ -69,9 +69,6 @@ class BaseJobManager:
         scripts = set(os.path.normpath(s) for s in expand_globs(script))
         logger.info('Scripts to submit: %s', scripts)
 
-        if recovery and recover_scripts != scripts:
-            raise ValueError('Scripts to submit are different from scripts in recovery file')
-
         for script_file in scripts:
             if script_file not in recover_scripts:
                 jobs.append(new_job(script_file))
@@ -108,19 +105,21 @@ class Slurm(BaseJobManager):
 
     def _update_jobs(self, jobs: List[dict], max_tries: int, submit_opts: str):
         # query job status
-        job_ids = ','.join(j['id'] for j in jobs if j['id'])
-        query_cmd = f'{self._sacct_bin} -X -P -j {job_ids} --format=JobID,JobName,State'
-
-        user = os.environ.get('USER')
-        if user:
-            query_cmd += f' -u {user}'
-
-        cp = shell_run(query_cmd)
-        if cp.returncode != 0:
-            logger.error('Failed to query job status: %s', cp.stderr.decode('utf-8'))
-            return jobs
-        logger.info('Job status: %s', cp.stdout.decode('utf-8'))
-        new_state = parse_csv(cp.stdout.decode('utf-8'))
+        job_ids = [j['id'] for j in jobs if j['id']]
+        if job_ids:
+            query_cmd = f'{self._sacct_bin} -X -P --format=JobID,JobName,State -j {",".join(job_ids)}'
+            user = os.environ.get('USER')
+            if user:
+                query_cmd += f' -u {user}'
+
+            cp = shell_run(query_cmd)
+            if cp.returncode != 0:
+                logger.error('Failed to query job status: %s', cp.stderr.decode('utf-8'))
+                return jobs
+            logger.info('Job status: %s', cp.stdout.decode('utf-8'))
+            new_state = parse_csv(cp.stdout.decode('utf-8'))
+        else:
+            new_state = []
 
         for job in jobs:
             for row in new_state:

{oh_my_batch-0.1.0.dev0 → oh_my_batch-0.1.0.dev1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "oh-my-batch"
-version = "0.1.0.dev0"
+version = "0.1.0.dev1"
 description = ""
 authors = ["weihong.xu <xuweihong.cn@gmail.com>"]
 license = "GPL"