Scenario: due to a block device error, the kernel fails to persist some file content. Even so, read() always returns the file content accurately. The first FICLONE returns EIO, but every subsequent FICLONE or copy_file_range() operates as though the file were all zeros. How feasible is it change FICLONE and copy_file_range() such that they instead find the bytes that read() finds? - Kernel is 6.0.0-1-sparc64-smp from Debian sid, running in a Solaris-hosted VM. - The VM is gcc202 from https://cfarm.tetaneutral.net/machines/list/. Accounts are available. - The outcome is still reproducible in FICLONE issued two days after the original block device error. I haven't checked whether it survives a reboot. - The "sync" command did not help. - The block device errors have been ongoing for years. If curious, see https://postgr.es/m/CA+hUKGKfrXnuyk0Z24m8x4_eziuC3kLSaCmEeKPO1DVU9t-qtQ@xxxxxxxxxxxxxx for details. (Fixing the sunvdc driver is out of scope for this thread.) Other known symptoms are failures in truncate() and fsync(). The system has been generally usable for applications not requiring persistence. I saw the FICLONE problem after the system updated coreutils from 8.32-4.1 to 9.1-1. That introduced a "cp" that uses FICLONE. My current workaround is to place a "cp" in my PATH that does 'exec /usr/bin/cp --reflink=never "$@"' The trouble emerged at a "cp". To capture more details, I replaced "cp" with "trace-cp" containing: sum "$1" strace cp "$@" 2>&1 | sed -n '/^geteuid/,$p' sum "$2" Output from that follows. FICLONE returns EIO. "cp" then falls back to copy_file_range(), which yields an all-zeros file: 47831 16384 pg_wal/000000030000000000000003 geteuid() = 1450 openat(AT_FDCWD, "/home/nm/src/pg/backbranch/extra/src/test/recovery/tmp_check/t_028_pitr_timelines_primary_data/archives/000000030000000000000003", O_RDONLY|O_PATH|O_DIRECTORY) = -1 ENOENT (No such file or directory) fstatat64(AT_FDCWD, "pg_wal/000000030000000000000003", {st_mode=S_IFREG|0600, st_size=16777216, ...}, 0) = 0 openat(AT_FDCWD, "pg_wal/000000030000000000000003", O_RDONLY) = 4 fstatat64(4, "", {st_mode=S_IFREG|0600, st_size=16777216, ...}, AT_EMPTY_PATH) = 0 openat(AT_FDCWD, "/home/nm/src/pg/backbranch/extra/src/test/recovery/tmp_check/t_028_pitr_timelines_primary_data/archives/000000030000000000000003", O_WRONLY|O_CREAT|O_EXCL, 0600) = 5 ioctl(5, BTRFS_IOC_CLONE or FICLONE, 4) = -1 EIO (Input/output error) fstatat64(5, "", {st_mode=S_IFREG|0600, st_size=0, ...}, AT_EMPTY_PATH) = 0 fadvise64_64(4, 0, 0, POSIX_FADV_SEQUENTIAL) = 0 copy_file_range(4, NULL, 5, NULL, 9223372035781033984, 0) = 16777216 copy_file_range(4, NULL, 5, NULL, 9223372035781033984, 0) = 0 close(5) = 0 close(4) = 0 _llseek(0, 0, [0], SEEK_CUR) = 0 close(0) = 0 close(1) = 0 close(2) = 0 exit_group(0) = ? +++ exited with 0 +++ 00000 16384 /home/nm/src/pg/backbranch/extra/src/test/recovery/tmp_check/t_028_pitr_timelines_primary_data/archives/000000030000000000000003 Subsequent FICLONE returns 0 and yields an all-zeros file. Test script: set -x broken_source=t_028_pitr_timelines_node_pitr_data/pgdata/pg_wal/000000030000000000000003 dest=$HOME/tmp/discard sum "$broken_source" : 'FICLONE returns 0 and yields an all-zeros file' strace cp --reflink=always "$broken_source" "$dest" 2>&1 | sed -n '/^geteuid/,$p' sum "$dest"; rm "$dest" : 'copy_file_range() returns 0 and yields an all-zeros file' strace -e copy_file_range cat "$broken_source" >"$dest" sum "$dest"; rm "$dest" : 'read() gets the intended bytes' cat "$broken_source" | cat >"$dest" sum "$dest"; rm "$dest" Test script output: + broken_source=t_028_pitr_timelines_node_pitr_data/pgdata/pg_wal/000000030000000000000003 + dest=/home/nm/tmp/discard + sum t_028_pitr_timelines_node_pitr_data/pgdata/pg_wal/000000030000000000000003 49522 16384 t_028_pitr_timelines_node_pitr_data/pgdata/pg_wal/000000030000000000000003 + : FICLONE returns 0 and yields an all-zeros file + strace cp --reflink=always t_028_pitr_timelines_node_pitr_data/pgdata/pg_wal/000000030000000000000003 /home/nm/tmp/discard + sed -n /^geteuid/,$p geteuid() = 1450 openat(AT_FDCWD, "/home/nm/tmp/discard", O_RDONLY|O_PATH|O_DIRECTORY) = -1 ENOENT (No such file or directory) fstatat64(AT_FDCWD, "t_028_pitr_timelines_node_pitr_data/pgdata/pg_wal/000000030000000000000003", {st_mode=S_IFREG|0600, st_size=16777216, ...}, 0) = 0 openat(AT_FDCWD, "t_028_pitr_timelines_node_pitr_data/pgdata/pg_wal/000000030000000000000003", O_RDONLY) = 3 fstatat64(3, "", {st_mode=S_IFREG|0600, st_size=16777216, ...}, AT_EMPTY_PATH) = 0 openat(AT_FDCWD, "/home/nm/tmp/discard", O_WRONLY|O_CREAT|O_EXCL, 0600) = 4 ioctl(4, BTRFS_IOC_CLONE or FICLONE, 3) = 0 close(4) = 0 close(3) = 0 _llseek(0, 0, 0x7feffddf1c0, SEEK_CUR) = -1 ESPIPE (Illegal seek) close(0) = 0 close(1) = 0 close(2) = 0 exit_group(0) = ? +++ exited with 0 +++ + sum /home/nm/tmp/discard 00000 16384 /home/nm/tmp/discard + rm /home/nm/tmp/discard + : copy_file_range() returns 0 and yields an all-zeros file + strace -e copy_file_range cat t_028_pitr_timelines_node_pitr_data/pgdata/pg_wal/000000030000000000000003 copy_file_range(3, NULL, 1, NULL, 9223372035781033984, 0) = 16777216 copy_file_range(3, NULL, 1, NULL, 9223372035781033984, 0) = 0 +++ exited with 0 +++ + sum /home/nm/tmp/discard 00000 16384 /home/nm/tmp/discard + rm /home/nm/tmp/discard + : read() gets the intended bytes + cat t_028_pitr_timelines_node_pitr_data/pgdata/pg_wal/000000030000000000000003 + cat + sum /home/nm/tmp/discard 49522 16384 /home/nm/tmp/discard + rm /home/nm/tmp/discard
