ash
69 lines
3.0 KiB
Diff
69 lines
3.0 KiB
Diff
(NB: we drop the NEWS change to avoid conflicts)
|
|
|
|
From 64b8fdb5b4767e0f833486507c3eae46ed1b40f8 Mon Sep 17 00:00:00 2001
|
|
From: =?UTF-8?q?P=C3=A1draig=20Brady?= <P@draigBrady.com>
|
|
Date: Thu, 30 Oct 2025 13:02:48 +0000
|
|
Subject: [PATCH] copy: don't avoid copy-offload upon SEEK_HOLE indicating
|
|
non-sparse
|
|
|
|
* src/copy-file-data.c (infer_scantype): Fall back to a plain copy
|
|
if SEEK_HOLE indicates non-sparse, as zero copy avoids copy offload.
|
|
This was seen with transparently compressed files on OpenZFS.
|
|
* tests/cp/sparse-perf.sh: Add a test case even though it might
|
|
only trigger on compressed file systems that don't support reflink.
|
|
* NEWS: Mention the bug fix.
|
|
Addresses https://github.com/coreutils/coreutils/issues/122
|
|
---
|
|
NEWS | 8 ++++++++
|
|
src/copy-file-data.c | 11 +++++++++--
|
|
tests/cp/sparse-perf.sh | 10 ++++++++++
|
|
3 files changed, 27 insertions(+), 2 deletions(-)
|
|
|
|
diff --git a/src/copy-file-data.c b/src/copy-file-data.c
|
|
index 9eb6f47244f0a62c2f4934c7663794fd4dcf21bf..8fd25fee9201eda7bd0a8caf01f02821a3390448 100644
|
|
--- a/src/copy-file-data.c
|
|
+++ b/src/copy-file-data.c
|
|
@@ -481,12 +481,19 @@ infer_scantype (int fd, struct stat const *sb, off_t pos,
|
|
if (scan_inference->hole_start < sb->st_size)
|
|
return LSEEK_SCANTYPE;
|
|
|
|
- /* Though the file likely has holes, SEEK_DATA and SEEK_HOLE
|
|
+ /* Though the file may have holes, SEEK_DATA and SEEK_HOLE
|
|
didn't find any. This can happen with file systems like
|
|
circa-2025 squashfs that support SEEK_HOLE only trivially.
|
|
- Fall back on ZERO_SCANTYPE. */
|
|
+ This can also happen due to transparent file compression,
|
|
+ which can also indicate fewer than the usual number of blocks. */
|
|
+
|
|
if (lseek (fd, pos, SEEK_SET) < 0)
|
|
return ERROR_SCANTYPE;
|
|
+
|
|
+ /* we prefer to return PLAIN_SCANTYPE here so that copy offload
|
|
+ continues to be used. Falling through to ZERO_SCANTYPE would be
|
|
+ less performant in the compressed file case. */
|
|
+ return PLAIN_SCANTYPE;
|
|
}
|
|
}
|
|
else if (pos < scan_inference->ext_start || errno == ENXIO)
|
|
diff --git a/tests/cp/sparse-perf.sh b/tests/cp/sparse-perf.sh
|
|
index 5a283c1fe65816a36342d9f583c1ed787947bf10..5ee984c527d7d8b6395d4193fcf81804b1135b8a 100755
|
|
--- a/tests/cp/sparse-perf.sh
|
|
+++ b/tests/cp/sparse-perf.sh
|
|
@@ -35,6 +35,16 @@ cmp $other_partition_sparse k2 || fail=1
|
|
grep ': avoided' cp.out && { cat cp.out; fail=1; }
|
|
|
|
|
|
+# Create a large-non-sparse-but-compressible file
|
|
+# Ensure we don't avoid copy offload which we saw with
|
|
+# transparent compression on OpenZFS at least
|
|
+# (as that triggers our sparse heuristic).
|
|
+mls='might-look-sparse'
|
|
+yes | head -n1M > "$mls" || framework_failure_
|
|
+cp --debug "$mls" "$mls.cp" >cp.out || fail=1
|
|
+cmp "$mls" "$mls.cp" || fail=1
|
|
+grep ': avoided' cp.out && { cat cp.out; fail=1; }
|
|
+
|
|
|
|
# Create a large-but-sparse file on the current partition.
|
|
# We disable relinking below, thus verifying SEEK_HOLE support
|