fix: fix mount (#1001)

* docs: document extra_volumes dict format in DockerConf

* feat: accept dict values in extra_volumes to specify bind and mode

* fix: skip invalid PDF reports to prevent infinite loop

* from break to raise self.LoopTerminationError

* format with black

---------

Co-authored-by: Young <afe.young@gmail.com>
This commit is contained in:
Linlang
2025-06-28 20:01:14 +08:00
committed by GitHub
parent 05b584b184
commit 976b86664f
2 changed files with 17 additions and 4 deletions
+9 -3
View File
@@ -602,6 +602,10 @@ class DockerConf(EnvConf):
default_entry: str # the entry point of the image
extra_volumes: dict = {}
"""It accept a dict of volumes, which can be either
{<host_path>: <container_path>} or
{<host_path>: {"bind": <container_path>, "mode": <mode, ro/rw/default is extra_volume_mode>}}
"""
extra_volume_mode: str = "ro" # by default. only the mount_path should be writable, others are changed to read-only
# Sometime, we need maintain some extra data for the workspace.
# And the extra data may be shared and the downloading can be time consuming.
@@ -662,7 +666,9 @@ class QlibDockerConf(DockerConf):
image: str = "local_qlib:latest"
mount_path: str = "/workspace/qlib_workspace/"
default_entry: str = "qrun conf.yaml"
extra_volumes: dict = {str(Path("~/.qlib/").expanduser().resolve().absolute()): "/root/.qlib/"}
extra_volumes: dict = {
str(Path("~/.qlib/").expanduser().resolve().absolute()): {"bind": "/root/.qlib/", "mode": "rw"}
}
shm_size: str | None = "16g"
enable_gpu: bool = True
enable_cache: bool = False
@@ -854,12 +860,12 @@ class DockerEnv(Env[DockerConf]):
if self.conf.extra_volumes is not None:
for lp, rp in self.conf.extra_volumes.items():
volumes[lp] = {"bind": rp, "mode": self.conf.extra_volume_mode}
volumes[lp] = rp if isinstance(rp, dict) else {"bind": rp, "mode": self.conf.extra_volume_mode}
cache_path = "/tmp/sample" if "/sample/" in "".join(self.conf.extra_volumes.keys()) else "/tmp/full"
Path(cache_path).mkdir(parents=True, exist_ok=True)
volumes[cache_path] = {"bind": T("scenarios.data_science.share:scen.cache_path").r(), "mode": "rw"}
for lp, rp in running_extra_volume.items():
volumes[lp] = {"bind": rp, "mode": self.conf.extra_volume_mode}
volumes[lp] = rp if isinstance(rp, dict) else {"bind": rp, "mode": self.conf.extra_volume_mode}
volumes = normalize_volumes(cast(dict[str, str | dict[str, str]], volumes), self.conf.mount_path)