Merge pull request #8281 from Aztorius/no-cache-option

Add BORG_USE_CHUNKS_ARCHIVE env var, fixes #8280

docs/faq.rst

@@ -720,18 +720,8 @@ will make the subsequent rebuilds faster (because it needs to transfer less data
 from the repository). While being faster, the cache needs quite some disk space,
 which might be unwanted.
 
-There is a temporary (but maybe long lived) hack to avoid using lots of disk
-space for chunks.archive.d (see :issue:`235` for details):
-
-::
-
-    # this assumes you are working with the same user as the backup.
-    cd ~/.cache/borg/$(borg config id)
-    rm -rf chunks.archive.d ; touch chunks.archive.d
-
-This deletes all the cached archive chunk indexes and replaces the directory
-that kept them with a file, so borg won't be able to store anything "in" there
-in future.
+You can disable the cached archive chunk indexes by setting the environment
+variable ``BORG_USE_CHUNKS_ARCHIVE`` to ``no``.
 
 This has some pros and cons, though:
 

docs/usage/general/environment.rst.inc

@@ -67,6 +67,9 @@ General:
         When set to a numeric value, this determines the maximum "time to live" for the files cache
         entries (default: 20). The files cache is used to determine quickly whether a file is unchanged.
         The FAQ explains this more detailed in: :ref:`always_chunking`
+    BORG_USE_CHUNKS_ARCHIVE
+        When set to no (default: yes), the ``chunks.archive.d`` folder will not be used. This reduces
+        disk space usage but slows down cache resyncs.
     BORG_SHOW_SYSINFO
         When set to no (default: yes), system information (like OS, Python version, ...) in
         exceptions is not shown.

src/borg/cache.py

@@ -521,6 +521,7 @@ class LocalCache(CacheStatsMixin):
         self.cache_mode = cache_mode
         self.timestamp = None
         self.txn_active = False
+        self.do_cache = os.environ.get("BORG_USE_CHUNKS_ARCHIVE", "yes").lower() in ["yes", "1", "true"]
 
         self.path = cache_dir(self.repository, path)
         self.security_manager = SecurityManager(self.repository)
@@ -910,10 +911,6 @@ class LocalCache(CacheStatsMixin):
 
         self.begin_txn()
         with cache_if_remote(self.repository, decrypted_cache=self.repo_objs) as decrypted_repository:
-            # TEMPORARY HACK:
-            # to avoid archive index caching, create a FILE named ~/.cache/borg/REPOID/chunks.archive.d -
-            # this is only recommended if you have a fast, low latency connection to your repo (e.g. if repo is local).
-            self.do_cache = os.path.isdir(archive_path)
             self.chunks = create_master_idx(self.chunks)
 
     def check_cache_compatibility(self):

src/borg/testsuite/archiver/checks.py

@@ -319,6 +319,23 @@ def test_check_cache(archivers, request):
         check_cache(archiver)
 
 
+def test_env_use_chunks_archive(archivers, request, monkeypatch):
+    archiver = request.getfixturevalue(archivers)
+    create_test_files(archiver.input_path)
+    monkeypatch.setenv("BORG_USE_CHUNKS_ARCHIVE", "no")
+    cmd(archiver, "rcreate", RK_ENCRYPTION)
+    repository_id = bin_to_hex(_extract_repository_id(archiver.repository_path))
+    cache_path = os.path.join(archiver.cache_path, repository_id)
+    cmd(archiver, "create", "test", "input")
+    assert os.path.exists(cache_path)
+    assert os.path.exists(os.path.join(cache_path, "chunks.archive.d"))
+    assert len(os.listdir(os.path.join(cache_path, "chunks.archive.d"))) == 0
+    cmd(archiver, "rdelete", "--cache-only")
+    monkeypatch.setenv("BORG_USE_CHUNKS_ARCHIVE", "yes")
+    cmd(archiver, "create", "test2", "input")
+    assert len(os.listdir(os.path.join(cache_path, "chunks.archive.d"))) > 0
+
+
 # Begin Remote Tests
 def test_remote_repo_restrict_to_path(remote_archiver):
     original_location, repo_path = remote_archiver.repository_location, remote_archiver.repository_path