Keep unrecoverable files quarantined until fix completion

This commit is contained in:
Andrea Mazzoleni 2026-08-17 22:20:30 +02:00
parent 65e6564e13
commit 036b099eae
3 changed files with 83 additions and 31 deletions

View file

@ -690,6 +690,17 @@ static int file_post(struct snapraid_state* state, int fix, block_off_t i, struc
/* finish the fix process if it's the last block of the files */
if (fix) {
int was_unrecoverable;
if (handle[j].file != file) {
/* LCOV_EXCL_START */
log_fatal(EINTERNAL, "Internal inconsistency in file handle '%s' instead of '%s'\n",
handle[j].file != 0 ? handle[j].file->sub : "<none>", file->sub);
os_abort();
/* LCOV_EXCL_STOP */
}
was_unrecoverable = handle[j].is_unrecoverable;
/*
* Mark that we finished with this file
* to identify later any NOT finished ones
@ -698,7 +709,6 @@ static int file_post(struct snapraid_state* state, int fix, block_off_t i, struc
/* if the file is damaged, meaning that a fix failed */
if (file_flag_has(file, FILE_IS_DAMAGED)) {
/* rename it to .unrecoverable */
char path[PATH_MAX];
char path_to[PATH_MAX];
@ -706,27 +716,28 @@ static int file_post(struct snapraid_state* state, int fix, block_off_t i, struc
pathprint(path_to, sizeof(path_to), "%s%s.unrecoverable", disk->dir, file->sub);
/* ensure to close the file before renaming */
if (handle[j].file == file) {
ret = handle_close(&handle[j]);
ret = handle_close(&handle[j]);
if (ret != 0) {
/* LCOV_EXCL_START */
log_tag("%s:%" PRIu64 ":%s:%s: Close error. %s.\n", es(errno), i, disk->name, esc_tag(file->sub), strerror(errno));
log_fatal_errno(errno, disk->name);
return -1;
/* LCOV_EXCL_STOP */
}
/* a previous recovery is already quarantined */
if (!was_unrecoverable) {
ret = rename(path, path_to);
if (ret != 0) {
/* LCOV_EXCL_START */
log_tag("%s:%" PRIu64 ":%s:%s: Close error. %s.\n", es(errno), i, disk->name, esc_tag(file->sub), strerror(errno));
log_fatal(errno, "Error renaming '%s%s'. %s.\n", disk->dir, file->sub, strerror(errno));
log_tag("%s:%" PRIu64 ":%s:%s: Rename error. %s.\n", es(errno), i, disk->name, esc_tag(file->sub), strerror(errno));
log_fatal_errno(errno, disk->name);
return -1;
/* LCOV_EXCL_STOP */
}
}
ret = rename(path, path_to);
if (ret != 0) {
/* LCOV_EXCL_START */
log_fatal(errno, "Error renaming '%s%s'. %s.\n", disk->dir, file->sub, strerror(errno));
log_tag("%s:%" PRIu64 ":%s:%s: Rename error. %s.\n", es(errno), i, disk->name, esc_tag(file->sub), strerror(errno));
log_fatal_errno(errno, disk->name);
return -1;
/* LCOV_EXCL_STOP */
}
log_tag("status:unrecoverable:%s:%s\n", disk->name, esc_tag(file->sub));
msg_info("unrecoverable %s\n", fmt_term(disk, file->sub));
@ -734,8 +745,40 @@ static int file_post(struct snapraid_state* state, int fix, block_off_t i, struc
goto close_and_continue;
}
/*
* This rename is the file-level recovery commit point. Keep the file
* quarantined until every block was processed without FILE_IS_DAMAGED;
* block-by-block promotion could expose an incomplete recovery.
*/
if (was_unrecoverable) {
char path[PATH_MAX];
char path_from[PATH_MAX];
pathprint(path, sizeof(path), "%s%s", disk->dir, file->sub);
pathprint(path_from, sizeof(path_from), "%s%s.unrecoverable", disk->dir, file->sub);
ret = handle_close(&handle[j]);
if (ret != 0) {
/* LCOV_EXCL_START */
log_tag("%s:%" PRIu64 ":%s:%s: Close error. %s.\n", es(errno), i, disk->name, esc_tag(file->sub), strerror(errno));
log_fatal_errno(errno, disk->name);
return -1;
/* LCOV_EXCL_STOP */
}
ret = rename(path_from, path);
if (ret != 0) {
/* LCOV_EXCL_START */
log_fatal(errno, "Error renaming '%s'. %s.\n", path_from, strerror(errno));
log_tag("%s:%" PRIu64 ":%s:%s: Rename error. %s.\n", es(errno), i, disk->name, esc_tag(file->sub), strerror(errno));
log_fatal_errno(errno, disk->name);
return -1;
/* LCOV_EXCL_STOP */
}
}
/* if the file is not fixed, meaning that it is untouched */
if (!file_flag_has(file, FILE_IS_FIXED)) {
if (!file_flag_has(file, FILE_IS_FIXED) && !was_unrecoverable) {
/* nothing to do, but close the file */
goto close_and_continue;
}
@ -756,11 +799,8 @@ static int file_post(struct snapraid_state* state, int fix, block_off_t i, struc
/* LCOV_EXCL_STOP */
}
/*
* Reopen it as readonly, as to set the mtime readonly access it's enough
* we know that the file exists because it has the FILE_IS_FIXED tag
*/
ret = handle_open(&handle[j], file, state->file_mode, 0);
/* reopen the promoted file for writing, as required to set the mtime on Windows */
ret = handle_create(&handle[j], file, state->file_mode);
if (ret != 0) {
/* LCOV_EXCL_START */
log_tag("%s:%" PRIu64 ":%s:%s: Open error. %s.\n", es(errno), i, disk->name, esc_tag(file->sub), strerror(errno));
@ -2341,4 +2381,3 @@ int state_check(struct snapraid_state* state, int fix, block_off_t blockstart, b
return 0;
}

View file

@ -32,6 +32,7 @@ int handle_create(struct snapraid_handle* handle, struct snapraid_file* file, in
/* initial values, changed later if required */
handle->created = 0;
handle->is_unrecoverable = 0;
handle->readonly_errno = 0;
/*
@ -56,26 +57,32 @@ int handle_create(struct snapraid_handle* handle, struct snapraid_file* file, in
/* if failed for missing file */
if (handle->f == -1 && errno == ENOENT) {
char path_from[PATH_MAX];
char path_unrecoverable[PATH_MAX];
/* check if exists a .unrecoverable copy, and rename to the real one */
pathprint(path_from, sizeof(path_from), "%s.unrecoverable", handle->path);
/* check if exists a .unrecoverable copy */
pathprint(path_unrecoverable, sizeof(path_unrecoverable), "%s.unrecoverable", handle->path);
/*
* Reuse a previous partial recovery as the starting point for a
* multistep fix. Readable CHG blocks in this file are intentionally
* preserved because their current hash is not available.
* Open a previous recovery directly as .unrecoverable, keeping it
* quarantined until the whole file is processed successfully. Promoting
* it now could expose an incomplete or unverified file if this fix aborts
* or fails again. Reuse it for a multistep fix, preserving readable CHG
* blocks because their current hash is not available.
*/
if (rename(path_from, handle->path) == 0) {
/* open for read write */
handle->f = open(handle->path, flags | O_RDWR);
} else {
handle->f = open(path_unrecoverable, flags | O_RDWR);
if (handle->f != -1) {
handle->is_unrecoverable = 1;
pathcpy(handle->path, sizeof(handle->path), path_unrecoverable);
} else if (errno == ENOENT) {
/* create it */
handle->f = open(handle->path, flags | O_RDWR | O_CREAT, 0600);
if (handle->f != -1) {
/* mark it as created if really done */
handle->created = 1;
}
} else {
/* report the path that failed to open */
pathcpy(handle->path, sizeof(handle->path), path_unrecoverable);
}
}
@ -165,6 +172,7 @@ int handle_open(struct snapraid_handle* handle, struct snapraid_file* file, int
/* for sure not created */
handle->created = 0;
handle->is_unrecoverable = 0;
handle->readonly_errno = 0;
/*
@ -232,6 +240,7 @@ int handle_close(struct snapraid_handle* handle)
handle->file = 0;
handle->f = -1;
handle->valid_size = 0;
handle->is_unrecoverable = 0;
return -1;
/* LCOV_EXCL_STOP */
}
@ -241,6 +250,7 @@ int handle_close(struct snapraid_handle* handle)
handle->file = 0;
handle->f = -1;
handle->valid_size = 0;
handle->is_unrecoverable = 0;
handle->readonly_errno = 0;
return 0;
@ -424,6 +434,7 @@ struct snapraid_handle* handle_mapping(struct snapraid_state* state, unsigned* h
handle[j].file = 0;
handle[j].f = -1;
handle[j].valid_size = 0;
handle[j].is_unrecoverable = 0;
handle[j].readonly_errno = 0;
handle[j].bw = 0;
}

View file

@ -20,6 +20,7 @@ struct snapraid_handle {
struct advise_struct advise; /**< Advise information. */
data_off_t valid_size; /**< Size of the valid data. */
int created; /**< If the file was created, otherwise it was already existing. */
int is_unrecoverable; /**< If the open descriptor refers to the .unrecoverable path. */
int readonly_errno; /**< Non-zero if opened read-only as fallback. */
struct snapraid_bw* bw; /**< Context for bandwidth limiting. */
};
@ -28,6 +29,7 @@ struct snapraid_handle {
* Create a file.
* The file is created if missing, and opened with write access.
* If the file is created, the handle->created is set.
* If a previous .unrecoverable file is opened, the handle->is_unrecoverable is set.
* The initial size of the file is stored in the file->st struct.
* If the file cannot be opened for write access, it's opened with read-only access.
* The read-only access works only if the file has already the correct size and doesn't need to be modified.