TapTap/FastSync
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

feat(basis): rsync quick-check default + FastSync-only --verify-basis

Browse Source 
- default basis match is rsync's metadata quick-check (size + mtime; size-only
  drops mtime; -I disables), no mandatory content digest
- new long-only --verify-basis (wire bool, protocol stays 2.28.0) restores the
  strict whole-file content equality
- --copy-dest re-applies source attributes; basis-hit 256 MiB cap removed by
  streaming the copy/hash; basis miss keeps the normal payload bound
- compare/copy/link-dest rows -> caveat; tally 116/13/28
This commit is contained in:
TapTap
2026-09-19 15:55:51 +02:00
parent 8ec8cb7203
commit 67076bf218
23 changed files with 940 additions and 255 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/integration/test_differential_parity.py
+111 -4
View File
@@ -28,6 +28,7 @@ from common import ( # noqa: E402
ServerManager,
TEST_DATA_DIR,
clean_dir,
get_dest_received_dir,
)
from parity_caveats import ASPECTS, caveat_for # noqa: E402
import parity_harness as H # noqa: E402
@@ -350,7 +351,9 @@ def _result_aspects(result):
_STANDALONE_REFS = {
"incremental_modified": "-i/--itemize-changes + incremental second run",
"compare_dest": "--compare-dest",
"copy_dest": "--copy-dest",
"link_dest": "--link-dest",
"verify_basis": "--verify-basis (FastSync-only)",
"added_and_deleted": "--delete across two runs",
"added_and_deleted_seed": "--delete across two runs",
"one_file_system": "-x/--one-file-system",
@@ -411,14 +414,17 @@ def test_compare_dest_skips_basis(parity_server_factory):
fdst = os.path.join(TEST_DATA_DIR, "parity_cmpd_fdst")
clean_dir(src)
_mk(os.path.join(src, "f.txt"), b"basis-content\n")
_pin(os.path.join(src, "f.txt"), _OLD_MTIME)
server = parity_server_factory(SUPER)
rel = os.path.abspath(src).lstrip(os.sep)
# rsync resolves --compare-dest relative to the destination dir; FastSync
# resolves it under the receive root and appends the mirrored source path.
# Both rely on rsync's size+mtime quick-check, so the basis mtime is pinned
# to the source's to keep the match deterministic across a second boundary.
def seed(_src, rroot, froot):
_mk(os.path.join(rroot, "basis", "f.txt"), b"basis-content\n")
_mk(os.path.join(fdst, "basis", rel, "f.txt"), b"basis-content\n")
_mk(os.path.join(rroot, "basis", "f.txt"), b"basis-content\n", _OLD_MTIME)
_mk(os.path.join(fdst, "basis", rel, "f.txt"), b"basis-content\n", _OLD_MTIME)
def extra(_src, rroot, froot, _rs, _fs):
out = []
@@ -446,12 +452,13 @@ def test_link_dest_hardlinks_basis(parity_server_factory):
fdst = os.path.join(TEST_DATA_DIR, "parity_linkd_fdst")
clean_dir(src)
_mk(os.path.join(src, "f.txt"), b"link-basis-content\n")
_pin(os.path.join(src, "f.txt"), _OLD_MTIME)
server = parity_server_factory(SUPER)
rel = os.path.abspath(src).lstrip(os.sep)
def seed(_src, rroot, froot):
_mk(os.path.join(rroot, "basis", "f.txt"), b"link-basis-content\n")
_mk(os.path.join(fdst, "basis", rel, "f.txt"), b"link-basis-content\n")
_mk(os.path.join(rroot, "basis", "f.txt"), b"link-basis-content\n", _OLD_MTIME)
_mk(os.path.join(fdst, "basis", rel, "f.txt"), b"link-basis-content\n", _OLD_MTIME)
def extra(_src, rroot, froot, _rs, _fs):
r_basis = os.stat(os.path.join(rroot, "basis", "f.txt")).st_ino
@@ -474,6 +481,106 @@ def test_link_dest_hardlinks_basis(parity_server_factory):
_run_and_check(case_id, result)
@requires_rsync
@parity
def test_copy_dest_copies_basis(parity_server_factory):
"""--copy-dest: a basis match is materialized as an independent copy with the
source's attributes, matching rsync (copy then fix attributes)."""
case_id = "copy_dest"
src = os.path.join(TEST_DATA_DIR, "parity_copyd_src")
rdst = os.path.join(TEST_DATA_DIR, "parity_copyd_rdst")
fdst = os.path.join(TEST_DATA_DIR, "parity_copyd_fdst")
clean_dir(src)
_mk(os.path.join(src, "f.txt"), b"copy-basis-content\n")
_pin(os.path.join(src, "f.txt"), 1_600_000_000)
os.chmod(os.path.join(src, "f.txt"), 0o755)
server = parity_server_factory(SUPER)
rel = os.path.abspath(src).lstrip(os.sep)
def seed(_src, rroot, froot):
# Basis content matches the source; give the basis a different mode so a
# wrong "keep basis attributes" implementation is visible.
_mk(os.path.join(rroot, "basis", "f.txt"), b"copy-basis-content\n",
1_600_000_000)
os.chmod(os.path.join(rroot, "basis", "f.txt"), 0o644)
_mk(os.path.join(fdst, "basis", rel, "f.txt"), b"copy-basis-content\n",
1_600_000_000)
os.chmod(os.path.join(fdst, "basis", rel, "f.txt"), 0o644)
def extra(_src, rroot, froot, _rs, _fs):
out = []
bases = {"rsync": os.path.join(rroot, "basis", "f.txt"),
"fastsync": os.path.join(fdst, "basis", rel, "f.txt")}
for label, root in (("rsync", rroot), ("fastsync", froot)):
target = os.path.join(root, "f.txt")
if not os.path.exists(target):
out.append(f"{label}: f.txt missing")
continue
if os.stat(target).st_ino == os.stat(bases[label]).st_ino:
out.append(f"{label}: f.txt is hard-linked, not copied")
if (os.stat(target).st_mode & 0o777) != 0o755:
out.append(f"{label}: f.txt mode "
f"{oct(os.stat(target).st_mode & 0o777)} != 0o755")
return out
result = H.run_differential(
src, rdst, fdst,
["-a", "--copy-dest=basis"],
["-a", f"--copy-dest={os.path.join(fdst, 'basis')}", "--incremental"],
server, seed=seed, ignore_paths=("basis",), extra_check=extra,
compare_modes=True)
_run_and_check(case_id, result)
@requires_rsync
@parity
def test_verify_basis_restores_strict_content(parity_server_factory):
"""Default matches rsync's metadata quick-check; FastSync-only
`--verify-basis` restores strict content equality and transfers the source
when a same-size/different-content basis would otherwise be trusted."""
case_id = "verify_basis"
src = os.path.join(TEST_DATA_DIR, "parity_vbasis_src")
rdst = os.path.join(TEST_DATA_DIR, "parity_vbasis_rdst")
fdst = os.path.join(TEST_DATA_DIR, "parity_vbasis_fdst")
clean_dir(src)
_mk(os.path.join(src, "f.txt"), b"AAAA\n")
_pin(os.path.join(src, "f.txt"), _OLD_MTIME)
server = parity_server_factory(SUPER)
rel = os.path.abspath(src).lstrip(os.sep)
def seed(_src, rroot, froot):
# Same size and mtime as the source, different bytes: a metadata
# quick-check trusts it; --verify-basis must not.
for root, basis_rel in ((rroot, os.path.join("basis", "f.txt")),
(fdst, os.path.join("basis", rel, "f.txt"))):
_mk(os.path.join(root, basis_rel), b"BBBB\n", _OLD_MTIME)
# Default: both tools trust the basis (rsync's quick check), so the
# destination carries the basis bytes and the trees match.
result = H.run_differential(
src, rdst, fdst,
["-a", "--link-dest=basis"],
["-a", f"--link-dest={os.path.join(fdst, 'basis')}", "--incremental"],
server, seed=seed, ignore_paths=("basis",))
_run_and_check(case_id + "_default", result)
# --verify-basis (FastSync only): the digest mismatch rejects the basis and
# the source is transferred, so the destination is the source bytes. rsync
# has no such flag; assert the FastSync outcome directly against the source.
fdst2 = os.path.join(TEST_DATA_DIR, "parity_vbasis_fdst2")
clean_dir(fdst2)
for root, basis_rel in ((fdst2, os.path.join("basis", rel, "f.txt")),):
_mk(os.path.join(root, basis_rel), b"BBBB\n", _OLD_MTIME)
result, _ = H.run_fastsync(src, fdst2,
["-a", f"--link-dest={os.path.join(fdst2, 'basis')}",
"--incremental", "--verify-basis"], server.port)
assert result.returncode == 0, (result.stderr or result.stdout)[:300]
target = os.path.join(get_dest_received_dir(fdst2, src), "f.txt")
with open(target, "rb") as fh:
assert fh.read() == b"AAAA\n", \
"--verify-basis must reject the same-size/different-content basis"
@requires_rsync
@parity
def test_added_and_deleted_between_runs(parity_server_factory):