fuse4dbricks 0.7.5__tar.gz → 0.7.7__tar.gz

{fuse4dbricks-0.7.5 → fuse4dbricks-0.7.7}/.github/workflows/test.yml

@@ -1,80 +1,80 @@
-name: Test and lint
-
-on:
-  push:
-    branches: [ main ]
-    tags: [ 'v*' ]
-  pull_request:
-    branches: [ main ]
-
-# Security hardening: restricts the GITHUB_TOKEN to read-only access
-permissions:
-  contents: read
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v6
-
-    - name: Set up Python 3.11
-      uses: actions/setup-python@v6
-      with:
-        python-version: "3.11"
-        # Caches pip packages to speed up subsequent runs
-        cache: 'pip'
-
-    - name: Install system dependencies for pyfuse3
-      run: |
-        sudo apt-get update
-        sudo apt-get install -y libfuse3-dev fuse3 pkg-config
-
-    - name: Install Python dependencies
-      run: |
-        python -m pip install --upgrade pip
-        # wheel is required to build the pyfuse3 C-extension correctly
-        pip install wheel flake8 pytest
-        pip install  --group dev .
-
-    - name: Lint with flake8
-      run: |
-        # stop the build if there are Python syntax errors or undefined names
-        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-        # exit-zero treats all errors as warnings.
-        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
-
-    - name: Run tests
-      run: |
-        pytest .
-
-    - name: Install pypa/build
-      run: python3 -m pip install uv
-    - name: Build a binary wheel and a source tarball
-      run: uv build
-    - name: Store the distribution packages
-      uses: actions/upload-artifact@v7
-      with:
-        name: python-package-distributions
-        path: dist/
-
-  publish-to-pypi:
-    name: Publish package to PyPI
-    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
-    needs:
-    - build
-    runs-on: ubuntu-latest
-    environment:
-      name: pypi
-      url: https://pypi.org/p/fuse4dbricks
-    permissions:
-      id-token: write
-    steps:
-    - name: Download all the dists
-      uses: actions/download-artifact@v6
-      with:
-        name: python-package-distributions
-        path: dist/
-    - name: Publish distribution to PyPI
-      uses: pypa/gh-action-pypi-publish@release/v1
+name: Test and lint
+
+on:
+  push:
+    branches: [ main ]
+    tags: [ 'v*' ]
+  pull_request:
+    branches: [ main ]
+
+# Security hardening: restricts the GITHUB_TOKEN to read-only access
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout code
+      uses: actions/checkout@v6
+
+    - name: Set up Python 3.11
+      uses: actions/setup-python@v6
+      with:
+        python-version: "3.11"
+        # Caches pip packages to speed up subsequent runs
+        cache: 'pip'
+
+    - name: Install system dependencies for pyfuse3
+      run: |
+        sudo apt-get update
+        sudo apt-get install -y libfuse3-dev fuse3 pkg-config
+
+    - name: Install Python dependencies
+      run: |
+        python -m pip install --upgrade pip
+        # wheel is required to build the pyfuse3 C-extension correctly
+        pip install wheel flake8 pytest
+        pip install  --group dev .
+
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings.
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+
+    - name: Run tests
+      run: |
+        pytest .
+
+    - name: Install pypa/build
+      run: python3 -m pip install uv
+    - name: Build a binary wheel and a source tarball
+      run: uv build
+    - name: Store the distribution packages
+      uses: actions/upload-artifact@v7
+      with:
+        name: python-package-distributions
+        path: dist/
+
+  publish-to-pypi:
+    name: Publish package to PyPI
+    if: startsWith(github.ref, 'refs/tags/')  # only publish to PyPI on tag pushes
+    needs:
+    - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/fuse4dbricks
+    permissions:
+      id-token: write
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v8
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1

{fuse4dbricks-0.7.5 → fuse4dbricks-0.7.7}/CHANGELOG.md

@@ -1,3 +1,12 @@
+# 0.7.7 (2026-10-01)
+
+- Add --num-download-workers and --prefetch-mb to control prefetching
+  and parallel downloads.
+
+# 0.7.6 (2026-08-07)
+
+- Force push. Bump for traceability.
+
 # 0.7.5 (2026-08-06)
 
 - Fix fatal startup/runtime errors exiting with status 0 instead of 1.

{fuse4dbricks-0.7.5 → fuse4dbricks-0.7.7}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: fuse4dbricks
-Version: 0.7.5
+Version: 0.7.7
 Summary: FUSE driver for Databricks Unity Catalog Volumes.
 Project-URL: Homepage, https://github.com/zeehio/fuse4dbricks
 Author-email: Sergio Oller <sergioller@gmail.com>

{fuse4dbricks-0.7.5 → fuse4dbricks-0.7.7}/fuse4dbricks/fs/data_manager.py

@@ -116,7 +116,7 @@ class DownloadScheduler:
 
 
 class DataManager:
-    def __init__(self, uc_client: UnityCatalogClient, persistence: DiskPersistence, ram_cache_mb = 512, num_workers=10):
+    def __init__(self, uc_client: UnityCatalogClient, persistence: DiskPersistence, ram_cache_mb = 512, num_workers=10, prefecth_mb=80):
         """
         uc_client: client to download chunks from UC
         persistence: where to store downloaded chunks on disk
@@ -129,6 +129,9 @@ class DataManager:
         self._inflight_coalescer: InflightCoalescer[_CacheKey] = InflightCoalescer()
         "Inflight coalescer for downloads identified by (fs_path, chunk_id, mtime, gen)"
 
+        if num_workers < 1:
+            raise ValueError("num_workers must be >= 1")
+
         self._download_scheduler = DownloadScheduler(process_request=self._process_request, num_workers=num_workers)
 
         # Per-path cache generation. Bumped on a local write so previously cached
@@ -138,6 +141,11 @@ class DataManager:
         # max number of chunks to cache in memory
         max_ram_chunks = int(ram_cache_mb*1024*1024 / self.chunk_size)
         self._ram_cache: RamCache[_CacheKey] = RamCache(max_entries = max_ram_chunks)
+        prefetch_bytes = prefecth_mb * 1024 * 1024
+        chunks_to_prefetch = int(prefetch_bytes / self.chunk_size)
+        if chunks_to_prefetch < 0:
+            chunks_to_prefetch = 0
+        self._chunks_to_prefetch = chunks_to_prefetch
 
     def close(self) -> None:
         self._download_scheduler.close()
@@ -296,7 +304,7 @@ class DataManager:
                         self._read_chunk, fs_path, chunk_id, mtime, gen, chunk_size, ctx, chunks
                     )
         # fetch ahead next 10 chunks once we are beyond chunk 0 (avoid prefetching too much on `head *` command)
-        num_chunks_to_prefetch = 10 if end_chunk > 0 else 1
+        num_chunks_to_prefetch = self._chunks_to_prefetch if end_chunk > 0 else min(1, self._chunks_to_prefetch)
         chunks_to_prefetch = []
         for i in range(num_chunks_to_prefetch):
             chunk_to_prefetch = end_chunk + 1 + i

{fuse4dbricks-0.7.5 → fuse4dbricks-0.7.7}/fuse4dbricks/main.py

@@ -95,6 +95,18 @@ def parse_args():
         default=30,
         help="Default TTL for metadata cache entries in seconds",
     )
+    parser.add_argument(
+        "--prefetch_mb",
+        type=int,
+        default=80,
+        help="Amount of data to prefetch in MB for each file",
+    )
+    parser.add_argument(
+        "--num-download-workers",
+        type=int,
+        default=10,
+        help="Number of concurrent download workers",
+    )
     parser.add_argument(
         "--metadata-cache-ttl-catalog-sec",
         type=int,
@@ -242,7 +254,7 @@ async def async_main():
     persistence = DiskPersistence(data_cache_dir, max_size_gb=args.disk_cache_gb, max_age_days=args.disk_cache_max_days)
 
     inode_manager = InodeManager()
-    data_manager = DataManager(uc_client, persistence, ram_cache_mb=args.ram_cache_mb)
+    data_manager = DataManager(uc_client, persistence, ram_cache_mb=args.ram_cache_mb, num_workers=args.num_download_workers, prefetch_mb=args.prefetch_mb)
     metadata_manager = MetadataManager(uc_client, ttl=args.metadata_cache_ttl_sec, max_entries=args.metadata_cache_max_entries, ttl_catalog=args.metadata_cache_ttl_catalog_sec, ttl_negative=args.metadata_cache_ttl_negative_sec, inode_manager=inode_manager)
     # On a 401, the token is invalidated and re-resolved (possibly to a
     # different principal); drop the cached principal so authz re-derives it.

{fuse4dbricks-0.7.5 → fuse4dbricks-0.7.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "fuse4dbricks"
-version = "0.7.5"
+version = "0.7.7"
 description = "FUSE driver for Databricks Unity Catalog Volumes."
 readme = "README.md"
 requires-python = ">=3.11"