Harmon/insar-management-system-v2
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: materialize distributed inputs in task pool

Browse Source
This commit is contained in:
Harmon
2026-06-15 14:51:17 +08:00
parent ca2dbfc032
commit 0d54eb9ba7
7 changed files with 252 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+7 -4
View File
@@ -59,15 +59,18 @@ ALLOWED_EXPORT_DIRS=
# 源数据目录
# -----------------------------------------------------------------------------
UNPACK_SOURCE_DIRS=D:\Archives
SOURCE_PRODUCT_DIRS=D:\LuTan1_Image_Pool;D:\Sentinel1_Image_Pool_ZIP
TASK_POOL_ROOT=D:\Task_Pool
DINSAR_TASK_POOL_ROOT=D:\Task_Pool\DInSAR
SBAS_TASK_POOL_ROOT=D:\Task_Pool\SBAS
SOURCE_PRODUCT_DIRS=D:\LuTan1_Image_Pool;D:\Sentinel1_Image_Pool_ZIP;\\DESKTOP-N16HJ84\InSAR_Storage_2\LuTan-1\Archive;\\DESKTOP-N16HJ84\InSAR_Storage_2\Sentinel-1\Archive
SENTINEL1_STORAGE_DIRS=D:\Sentinel1_Image_Pool
INSAR_STORAGE_DIRS=D:\LuTan1_Image_Pool
MONITOR_RADAR_DIRS=D:\LuTan1_Image_Pool
MONITOR_DINSAR_DIRS=D:\DInSARResult
ORBIT_SOURCE_DIRS=D:\LT1_data_lsarorbit;D:\Sentinel1_EOF_Pool
ORBIT_SOURCE_DIRS=D:\LT1_data_lsarorbit;D:\Sentinel1_EOF_Pool;\\DESKTOP-N16HJ84\InSAR_Storage_2\Orbit\LuTan-1;\\DESKTOP-N16HJ84\InSAR_Storage_2\Orbit\Sentinel-1
MONITOR_ORBIT_DIR=D:\LT1_data_lsarorbit
GF3_ARCHIVE_SOURCE_DIRS=D:\production_inputs\gf3\archives
GF3_ARCHIVE_SOURCE_DIRS=\\DESKTOP-N16HJ84\InSAR_Storage_1\GaoFen-3
GF3_ARCHIVE_EXTS=.zip,.tar,.tar.gz,.tgz
GF3_UNPACK_DELETE_ARCHIVE=true
GF3_LEGACY_GDAL_ENABLED=false
@@ -275,7 +278,7 @@ GAMMA_SBAS_RUNTIME_ID=gamma_sbas_runtime_v1
GAMMA_SBAS_WSL_DISTRO=Ubuntu-24.04
GAMMA_SBAS_PYTHON=/home/administrator/miniconda3/envs/insar_wsl_v1/bin/python
GAMMA_SBAS_ENV_SCRIPT=D:\Code\Insar_management_system_v2\deploy\wsl\profiles\gamma_env.sh
GAMMA_SBAS_WORK_ROOT=D:\production_runtime\sbas_insar_work
GAMMA_SBAS_WORK_ROOT=D:\Task_Pool\SBAS
GAMMA_SBAS_PRODUCT_ROOT=D:\production_results\timeseries\sbas
GAMMA_SBAS_TRIAL_ROOT=D:\production_runtime\gamma_ipta_trials
GAMMA_SBAS_SCRIPT_TEMPLATE_ROOT=D:\Code\Insar_management_system_v2\backend\templates\gamma_sbas
backend/app/config.py
+21 -1
View File
@@ -93,6 +93,14 @@ def _default_runtime_root(project_root: str) -> str:
return os.path.join(normalized_root, "runtime")
def _default_task_pool_root(project_root: str) -> str:
normalized_root = os.path.normpath(project_root)
drive, _tail = os.path.splitdrive(normalized_root)
if drive:
return os.path.join(drive + os.sep, "Task_Pool")
return os.path.join(normalized_root, "Task_Pool")
def _default_runtime_dir(project_root: str, *parts: str) -> str:
return os.path.join(_default_runtime_root(project_root), *parts)
@@ -187,6 +195,9 @@ class Settings(BaseSettings):
DB_SCHEMA_RESET_CONFIRM: bool = False
UNPACK_SOURCE_DIRS: str = ""
TASK_POOL_ROOT: str = ""
DINSAR_TASK_POOL_ROOT: str = ""
SBAS_TASK_POOL_ROOT: str = ""
SOURCE_PRODUCT_DIRS: str = ""
SENTINEL1_STORAGE_DIRS: str = ""
ORBIT_SOURCE_DIRS: str = ""
@@ -441,6 +452,12 @@ class Settings(BaseSettings):
"WATER_RESULTS_DIR",
os.path.join(backend_dir, "water_results"),
)
if not self.TASK_POOL_ROOT:
object.__setattr__(self, "TASK_POOL_ROOT", _default_task_pool_root(project_root))
if not self.DINSAR_TASK_POOL_ROOT:
object.__setattr__(self, "DINSAR_TASK_POOL_ROOT", os.path.join(self.TASK_POOL_ROOT, "DInSAR"))
if not self.SBAS_TASK_POOL_ROOT:
object.__setattr__(self, "SBAS_TASK_POOL_ROOT", os.path.join(self.TASK_POOL_ROOT, "SBAS"))
if not self.SAR_ANALYSIS_READY_ROOT:
object.__setattr__(
self,
@@ -780,7 +797,7 @@ class Settings(BaseSettings):
object.__setattr__(
self,
"GAMMA_SBAS_WORK_ROOT",
os.path.join(_default_runtime_root(project_root), "sbas_insar_work"),
self.SBAS_TASK_POOL_ROOT,
)
if not self.GAMMA_SBAS_PRODUCT_ROOT:
object.__setattr__(
@@ -990,6 +1007,9 @@ class Settings(BaseSettings):
os.makedirs(settings.RESULT_QUARANTINE_ROOT, exist_ok=True)
os.makedirs(settings.SAR_ANALYSIS_READY_ROOT, exist_ok=True)
os.makedirs(settings.SAR_ANALYSIS_WORK_ROOT, exist_ok=True)
os.makedirs(settings.TASK_POOL_ROOT, exist_ok=True)
os.makedirs(settings.DINSAR_TASK_POOL_ROOT, exist_ok=True)
os.makedirs(settings.SBAS_TASK_POOL_ROOT, exist_ok=True)
for path in split_env_paths(settings.GF3_ARCHIVE_SOURCE_DIRS):
os.makedirs(path, exist_ok=True)
for path in split_env_paths(settings.GF3_SARSCAPE_NATIVE_DIRS):
backend/app/copier.py
+118 -2
View File
@@ -2,6 +2,7 @@
import shutil
import asyncio
import tempfile
import tarfile
import zipfile
import json
import hashlib
@@ -43,6 +44,100 @@ def find_dinsar_source_to_copy(path: str) -> str:
return path
_DINSAR_ARCHIVE_SUFFIXES = (".tar.gz", ".tgz", ".zip", ".tar")
def _is_supported_archive(path: str) -> bool:
lower = str(path or "").lower()
return any(lower.endswith(suffix) for suffix in _DINSAR_ARCHIVE_SUFFIXES)
def _safe_archive_member_name(member_name: str, archive_path: str) -> str:
name = str(member_name or "").replace("\\", "/").strip("/")
if not name or name.startswith("../") or "/../" in f"/{name}/":
raise ValueError(f"Unsafe archive member path in {archive_path}: {member_name}")
if os.path.isabs(name) or os.path.splitdrive(name)[0]:
raise ValueError(f"Unsafe archive member path in {archive_path}: {member_name}")
return name
def _extract_archive_to_dir(archive_path: str, dest_dir: str) -> int:
if zipfile.is_zipfile(archive_path):
extracted = 0
with zipfile.ZipFile(archive_path) as zip_obj:
for info in zip_obj.infolist():
rel_name = _safe_archive_member_name(info.filename, archive_path)
dest_path = os.path.abspath(os.path.join(dest_dir, rel_name))
if not dest_path.startswith(os.path.abspath(dest_dir) + os.sep):
raise ValueError(f"Unsafe ZIP member path: {info.filename}")
if info.is_dir():
os.makedirs(dest_path, exist_ok=True)
continue
os.makedirs(os.path.dirname(dest_path), exist_ok=True)
with zip_obj.open(info, "r") as source, open(dest_path, "wb") as target:
shutil.copyfileobj(source, target, length=1024 * 1024)
extracted += 1
return extracted
if tarfile.is_tarfile(archive_path):
extracted = 0
with tarfile.open(archive_path, "r:*") as tar_obj:
for member in tar_obj:
rel_name = _safe_archive_member_name(member.name, archive_path)
dest_path = os.path.abspath(os.path.join(dest_dir, rel_name))
if not dest_path.startswith(os.path.abspath(dest_dir) + os.sep):
raise ValueError(f"Unsafe TAR member path: {member.name}")
if member.isdir():
os.makedirs(dest_path, exist_ok=True)
continue
if not member.isfile():
continue
source = tar_obj.extractfile(member)
if source is None:
continue
os.makedirs(os.path.dirname(dest_path), exist_ok=True)
with source, open(dest_path, "wb") as target:
shutil.copyfileobj(source, target, length=1024 * 1024)
extracted += 1
return extracted
raise ValueError(f"Unsupported archive format: {archive_path}")
def _materialize_dinsar_source(source_path: str, dest_dir: str) -> Dict[str, Any]:
normalized = os.path.normpath(os.path.abspath(str(source_path or "")))
if not os.path.exists(normalized):
raise FileNotFoundError(normalized)
if os.path.isdir(normalized):
shutil.copytree(normalized, dest_dir, dirs_exist_ok=True)
return {"mode": "copy_directory", "source_path": normalized}
if os.path.isfile(normalized) and _is_supported_archive(normalized):
os.makedirs(dest_dir, exist_ok=True)
extracted = _extract_archive_to_dir(normalized, dest_dir)
if extracted <= 0:
raise OSError(f"Archive extraction produced no files: {normalized}")
return {
"mode": "extract_archive",
"source_path": normalized,
"archive_path": normalized,
"extracted_files": extracted,
}
if os.path.isfile(normalized):
os.makedirs(dest_dir, exist_ok=True)
target = os.path.join(dest_dir, os.path.basename(normalized))
shutil.copy2(normalized, target)
return {
"mode": "copy_file",
"source_path": normalized,
"relative_path": os.path.basename(target),
}
raise FileNotFoundError(normalized)
def _resolve_orbit_dest_path(
orbit_dir: str,
role: str,
@@ -191,6 +286,7 @@ def _build_dinsar_pair_metadata(
package_format: str,
include_orbit_files: bool,
orbit_entries: List[Dict[str, Any]],
source_materialization: Optional[Dict[str, Any]] = None,
) -> Dict[str, Any]:
return {
"pair_key": item.get("pair_key"),
@@ -214,6 +310,7 @@ def _build_dinsar_pair_metadata(
"master_orbit_file_path": item.get("master_orbit_file_path"),
"slave_orbit_file_path": item.get("slave_orbit_file_path"),
"orbit_files": orbit_entries,
"source_materialization": source_materialization or {},
"scene_pair_uid": item.get("scene_pair_uid") or item.get("pair_uid"),
"pair_uid": item.get("pair_uid") or item.get("scene_pair_uid"),
"network_run_id": item.get("network_run_id"),
@@ -1094,8 +1191,26 @@ async def run_dinsar_copy_items(
failed_count += 1
continue
await asyncio.to_thread(shutil.copytree, master_src_path, master_dir, dirs_exist_ok=True)
await asyncio.to_thread(shutil.copytree, slave_src_path, slave_dir, dirs_exist_ok=True)
master_materialization = await asyncio.to_thread(
_materialize_dinsar_source,
master_src_path,
master_dir,
)
slave_materialization = await asyncio.to_thread(
_materialize_dinsar_source,
slave_src_path,
slave_dir,
)
source_materialization = {
"master": {
**master_materialization,
"target_relative_path": "master",
},
"slave": {
**slave_materialization,
"target_relative_path": "slave",
},
}
orbit_entries = await _copy_dinsar_orbit_files(
task_id,
item,
@@ -1112,6 +1227,7 @@ async def run_dinsar_copy_items(
"zip" if export_zip else "folder",
include_orbit_files,
orbit_entries,
source_materialization,
),
)
if export_zip and zip_path:
backend/app/services/root_registry_service.py
+29
View File
@@ -458,6 +458,35 @@ def _build_root_specs_from_settings() -> List[RootSpec]:
owner_engine="pyint",
)
)
specs.extend(
_iter_single_root_specs(
env_var="TASK_POOL_ROOT",
path=settings.TASK_POOL_ROOT,
root_role="task_pool_root",
display_name="Task Pool Root",
scan_mode="workspace",
)
)
specs.extend(
_iter_single_root_specs(
env_var="DINSAR_TASK_POOL_ROOT",
path=settings.DINSAR_TASK_POOL_ROOT,
root_role="task_pool_dinsar",
display_name="D-InSAR Task Pool",
scan_mode="workspace",
owner_engine="dinsar",
)
)
specs.extend(
_iter_single_root_specs(
env_var="SBAS_TASK_POOL_ROOT",
path=settings.SBAS_TASK_POOL_ROOT,
root_role="task_pool_sbas",
display_name="SBAS Task Pool",
scan_mode="workspace",
owner_engine="sbas",
)
)
specs.extend(
_iter_single_root_specs(
env_var="GAMMA_SBAS_WORK_ROOT",
docs/DINSAR_TASK_POOL_THREE_ENGINE_REFACTOR_20260614.md
+19
View File
@@ -210,3 +210,22 @@ Task_20250101_20250201
- Task_Pool 根路径需要明确配置项，建议新增 `DINSAR_TASK_POOL_ROOT`，默认 `D:\Task_Pool\DInSAR`。
- 中间文件清理需要先确认每个引擎的“可删目录”和“必须保留资产”清单，不能用一套规则覆盖全部。
- 前端 grouped 结果视图需要兼容旧 flat API 一段时间，避免已有页面一次性断裂。
## 2026-06-15 Task_Pool Materialize Update
Current direction:
- `TASK_POOL_ROOT` defaults to `D:\Task_Pool`.
- `DINSAR_TASK_POOL_ROOT` defaults to `D:\Task_Pool\DInSAR`.
- `SBAS_TASK_POOL_ROOT` defaults to `D:\Task_Pool\SBAS`.
- D-InSAR distribution materializes source inputs inside the task folder:
- directory sources are copied into `master/` and `slave/`;
- `S1_ZIP`, `LT1_ARCHIVE`, and other supported archives are extracted into `master/` and `slave/`;
- staged orbit files go into `orbit/`.
- Engines must consume local Task_Pool paths, not UNC source archive paths.
- `.dinsar_pair.json` records `source_materialization` so cleanup can distinguish copied directories, extracted archives, and staged files.
Cleanup implication:
- `master/`, `slave/`, `orbit/`, and engine `work/` folders are local materialized inputs/workspace and may be cleaned after all required results are registered.
- `publish/`, manifests, result assets, previews, and catalog metadata are preserved.
docs/SBAS_INSAR_CURRENT_WORKFLOW.md
+25
View File
@@ -252,3 +252,28 @@ GET /api/sbas-insar-products/{product_id}/assets/{asset_id}
- 选中候选可生成 Stack Manifest；
- 结果发布支持 GeoTIFF、预览图、监测点曲线和点矢量下载；
- 前端生产页和结果页构建通过。
## 2026-06-15 SBAS Task_Pool Update
Recommended SBAS work root:
```text
SBAS_TASK_POOL_ROOT=D:\Task_Pool\SBAS
GAMMA_SBAS_WORK_ROOT=D:\Task_Pool\SBAS
```
SBAS has its own Task_Pool sub-root and must not reuse `D:\Task_Pool\DInSAR`.
Recommended run layout:
```text
D:\Task_Pool\SBAS\<stack_task>
├─ task_manifest.json
├─ sbas_stack_manifest.json
├─ sources
├─ orbits
├─ work
└─ publish
```
Source archives remain on UNC. Selected scenes and orbit files are materialized under the SBAS task directory before Gamma/LandSAR execution. Cleanup may remove `sources`, `orbits`, and `work` after result registration, but must preserve manifests, `publish`, previews, and catalog assets.
docs/UNC_SOURCE_ARCHIVE_AND_MATERIALIZE_DESIGN_20260615.md
+33 -4
View File
@@ -23,13 +23,15 @@ This keeps the 20 TB storage useful for long-term source management while protec
- `LT1_ARCHIVE` and `GF3_ARCHIVE` extract to a local materialized directory.
- Directory assets return `DIRECTORY_READY`.
Default local materialize root is:
Default source materialization is task-scoped. D-InSAR and SBAS callers should pass a Task_Pool target directory:
```text
<PYINT_WORK_ROOT>\source_materialized\<source_format>
D:\Task_Pool\DInSAR\<task>\master
D:\Task_Pool\DInSAR\<task>\slave
D:\Task_Pool\SBAS\<stack>\sources\<YYYYMMDD>
```
Callers may pass `target_root` to force a D-InSAR Task_Pool or SBAS run-specific input directory.
The generic materialize endpoint still accepts `target_root` for ad hoc checks. Production callers must provide a Task_Pool destination.
## Production Boundary
@@ -104,6 +106,29 @@ Recommended source archive layout:
└─ S1*.EOF
```
Recommended local Task_Pool layout:
```text
D:\Task_Pool
├─ DInSAR
│ └─ <pair_task>
│ ├─ task_manifest.json
│ ├─ .dinsar_pair.json
│ ├─ master
│ ├─ slave
│ ├─ orbit
│ ├─ work
│ └─ publish
└─ SBAS
└─ <stack_task>
├─ task_manifest.json
├─ sbas_stack_manifest.json
├─ sources
├─ orbits
├─ work
└─ publish
```
Date folders are optional for the scanner because source and orbit inventory recurse through configured roots. They are recommended for operator readability and migration checks.
## Current Local Configuration Example
@@ -114,6 +139,10 @@ The local `.env` should keep legacy local roots and UNC roots side by side durin
SOURCE_PRODUCT_DIRS=D:\LuTan1_Image_Pool;D:\Sentinel1_Image_Pool_ZIP;\\DESKTOP-N16HJ84\InSAR_Storage_2\LuTan-1\Archive;\\DESKTOP-N16HJ84\InSAR_Storage_2\Sentinel-1\Archive
ORBIT_SOURCE_DIRS=D:\LT1_data_lsarorbit;D:\Sentinel1_EOF_Pool;\\DESKTOP-N16HJ84\InSAR_Storage_2\Orbit\LuTan-1;\\DESKTOP-N16HJ84\InSAR_Storage_2\Orbit\Sentinel-1
GF3_ARCHIVE_SOURCE_DIRS=\\DESKTOP-N16HJ84\InSAR_Storage_1\GaoFen-3
TASK_POOL_ROOT=D:\Task_Pool
DINSAR_TASK_POOL_ROOT=D:\Task_Pool\DInSAR
SBAS_TASK_POOL_ROOT=D:\Task_Pool\SBAS
GAMMA_SBAS_WORK_ROOT=D:\Task_Pool\SBAS
```
Do not store SMB credentials in `.env`. Credentials should be stored in Windows Credential Manager for the account that runs the backend/worker service.
@@ -167,7 +196,7 @@ Keep `ORBIT_POOL_ENVI` and `PYINT_ORBIT_POOL_TXT` local. Add a later sync/materi
After inventory scan verifies UNC assets:
1. D-InSAR Task_Pool stores source asset IDs and archive paths.
2. Task preparation materializes master/slave scenes and orbit files locally.
2. Task preparation materializes master/slave scenes and orbit files under `D:\Task_Pool\DInSAR\<task>`.
3. Engines run only against local Task_Pool paths.
4. Results register normally.
5. Local materialized inputs and intermediate products are eligible for cleanup after result registration.