30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315 | def collect_ssh_pixi(
*,
task_group_id: int,
task_group_activity_id: int,
ssh_config: SSHConfig,
tasks_base_dir: str,
tar_gz_file: FractalUploadedFile,
) -> None:
"""
Collect a task package over SSH
This function runs as a background task, therefore exceptions must be
handled.
NOTE: since this function is sync, it runs within a thread - due to
starlette/fastapi handling of background tasks (see
https://github.com/encode/starlette/blob/master/starlette/background.py).
Arguments:
task_group_id:
task_group_activity_id:
ssh_config:
tasks_base_dir:
Only used as a `safe_root` in `remove_dir`, and typically set to
`user_settings.ssh_tasks_dir`.
tar_gz_file:
"""
LOGGER_NAME = f"{__name__}.ID{task_group_activity_id}"
# Work within a temporary folder, where also logs will be placed
with TemporaryDirectory() as tmpdir:
log_file_path = Path(tmpdir) / "log"
logger = set_logger(
logger_name=LOGGER_NAME,
log_file_path=log_file_path,
)
logger.info("START")
with next(get_sync_db()) as db:
db_objects_ok, task_group, activity = get_activity_and_task_group(
task_group_activity_id=task_group_activity_id,
task_group_id=task_group_id,
db=db,
logger_name=LOGGER_NAME,
)
if not db_objects_ok:
return
with SingleUseFractalSSH(
ssh_config=ssh_config,
logger_name=LOGGER_NAME,
) as fractal_ssh:
try:
# Check SSH connection
ssh_ok = check_ssh_or_fail_and_cleanup(
fractal_ssh=fractal_ssh,
task_group=task_group,
task_group_activity=activity,
logger_name=LOGGER_NAME,
log_file_path=log_file_path,
db=db,
)
if not ssh_ok:
return
# Check that the (remote) task_group path does not exist
if fractal_ssh.remote_exists(task_group.path):
error_msg = f"{task_group.path} already exists."
logger.error(error_msg)
fail_and_cleanup(
task_group=task_group,
task_group_activity=activity,
logger_name=LOGGER_NAME,
log_file_path=log_file_path,
exception=FileExistsError(error_msg),
db=db,
)
return
# Create remote `task_group.path` and `script_dir_remote`
# folders
script_dir_remote = Path(
task_group.path, SCRIPTS_SUBFOLDER
).as_posix()
fractal_ssh.mkdir(folder=task_group.path, parents=True)
fractal_ssh.mkdir(folder=script_dir_remote, parents=True)
# Write tar.gz file locally and send it to remote path,
# and set task_group.archive_path
tar_gz_filename = tar_gz_file.filename
archive_path = (
Path(task_group.path) / tar_gz_filename
).as_posix()
tmp_archive_path = Path(tmpdir, tar_gz_filename).as_posix()
logger.info(f"Write tar.gz file into {tmp_archive_path}")
with open(tmp_archive_path, "wb") as f:
f.write(tar_gz_file.contents)
fractal_ssh.send_file(
local=tmp_archive_path,
remote=archive_path,
)
task_group.archive_path = archive_path
task_group = add_commit_refresh(obj=task_group, db=db)
settings = Inject(get_settings)
replacements = {
(
"__PIXI_HOME__",
settings.pixi.versions[task_group.pixi_version],
),
("__PACKAGE_DIR__", task_group.path),
("__TAR_GZ_PATH__", task_group.archive_path),
(
"__IMPORT_PACKAGE_NAME__",
task_group.pkg_name.replace("-", "_"),
),
("__SOURCE_DIR_NAME__", SOURCE_DIR_NAME),
("__FROZEN_OPTION__", ""),
(
"__TOKIO_WORKER_THREADS__",
str(settings.pixi.TOKIO_WORKER_THREADS),
),
(
"__PIXI_CONCURRENT_SOLVES__",
str(settings.pixi.PIXI_CONCURRENT_SOLVES),
),
(
"__PIXI_CONCURRENT_DOWNLOADS__",
str(settings.pixi.PIXI_CONCURRENT_DOWNLOADS),
),
}
logger.info("installing - START")
# Set status to ONGOING and refresh logs
activity.status = TaskGroupActivityStatusV2.ONGOING
activity.log = get_current_log(log_file_path)
activity = add_commit_refresh(obj=activity, db=db)
common_args = dict(
script_dir_local=(
Path(tmpdir, SCRIPTS_SUBFOLDER)
).as_posix(),
script_dir_remote=script_dir_remote,
prefix=(
f"{int(time.time())}_"
f"{TaskGroupActivityActionV2.COLLECT}"
),
logger_name=LOGGER_NAME,
fractal_ssh=fractal_ssh,
)
# Run the three pixi-related scripts
stdout = _customize_and_run_template(
template_filename="pixi_1_extract.sh",
replacements=replacements,
**common_args,
)
logger.debug(f"STDOUT: {stdout}")
activity.log = get_current_log(log_file_path)
activity = add_commit_refresh(obj=activity, db=db)
stdout = _customize_and_run_template(
template_filename="pixi_2_install.sh",
replacements=replacements,
**common_args,
)
logger.debug(f"STDOUT: {stdout}")
activity.log = get_current_log(log_file_path)
activity = add_commit_refresh(obj=activity, db=db)
stdout = _customize_and_run_template(
template_filename="pixi_3_post_install.sh",
replacements=replacements,
**common_args,
)
logger.debug(f"STDOUT: {stdout}")
activity.log = get_current_log(log_file_path)
activity = add_commit_refresh(obj=activity, db=db)
# Parse stdout
parsed_output = parse_collect_stdout(stdout)
package_root_remote = parsed_output["package_root"]
venv_size = parsed_output["venv_size"]
venv_file_number = parsed_output["venv_file_number"]
project_python_wrapper = parsed_output[
"project_python_wrapper"
]
source_dir = Path(
task_group.path, SOURCE_DIR_NAME
).as_posix()
fractal_ssh.run_command(cmd=f"chmod 755 {source_dir} -R")
# Read and validate remote manifest file
manifest_path_remote = (
f"{package_root_remote}/__FRACTAL_MANIFEST__.json"
)
pkg_manifest_dict = fractal_ssh.read_remote_json_file(
manifest_path_remote
)
logger.info(f"Loaded {manifest_path_remote=}")
pkg_manifest = ManifestV2(**pkg_manifest_dict)
logger.info("Manifest is a valid ManifestV2")
logger.info("_prepare_tasks_metadata - start")
task_list = prepare_tasks_metadata(
package_manifest=pkg_manifest,
package_version=task_group.version,
package_root=Path(package_root_remote),
project_python_wrapper=Path(project_python_wrapper),
)
logger.info("_prepare_tasks_metadata - end")
logger.info(
"create_db_tasks_and_update_task_group - " "start"
)
create_db_tasks_and_update_task_group_sync(
task_list=task_list,
task_group_id=task_group.id,
db=db,
)
logger.info("create_db_tasks_and_update_task_group - end")
# NOTE: see issue 2626 about whether to keep `pixi.lock`
# files in the database
remote_pixi_lock_file = Path(
task_group.path,
SOURCE_DIR_NAME,
"pixi.lock",
).as_posix()
pixi_lock_contents = fractal_ssh.read_remote_text_file(
remote_pixi_lock_file
)
# Update task_group data
logger.info(
"Add env_info, venv_size and venv_file_number "
"to TaskGroupV2 - start"
)
task_group.env_info = pixi_lock_contents
task_group.venv_size_in_kB = int(venv_size)
task_group.venv_file_number = int(venv_file_number)
task_group = add_commit_refresh(obj=task_group, db=db)
logger.info(
"Add env_info, venv_size and venv_file_number "
"to TaskGroupV2 - end"
)
# Finalize (write metadata to DB)
logger.info("finalising - START")
activity.status = TaskGroupActivityStatusV2.OK
activity.timestamp_ended = get_timestamp()
activity = add_commit_refresh(obj=activity, db=db)
logger.info("finalising - END")
logger.info("END")
reset_logger_handlers(logger)
except Exception as collection_e:
# Delete corrupted package dir
try:
logger.info(
f"Now delete remote folder {task_group.path}"
)
fractal_ssh.remove_folder(
folder=task_group.path,
safe_root=tasks_base_dir,
)
logger.info(
f"Deleted remoted folder {task_group.path}"
)
except Exception as e_rm:
logger.error(
"Removing folder failed. "
f"Original error: {str(e_rm)}"
)
fail_and_cleanup(
task_group=task_group,
task_group_activity=activity,
log_file_path=log_file_path,
logger_name=LOGGER_NAME,
exception=collection_e,
db=db,
)
|