@@ -98,7 +98,7 @@ remain as such. Reloading the kernel module will drop this information. There's
an alternative way of mounting multiple-device filesystem without the need for
prior scanning. See the mount option 'device'.
-*stats* [-z] <path>|<device>::
+*stats* [-zs] <path>|<device>::
Read and print the device IO error statistics for all devices of the given
filesystem identified by <path> or for a single <device>. See section *DEVICE
STATS* for more information.
@@ -108,6 +108,9 @@ STATS* for more information.
-z::::
Print the stats and reset the values to zero afterwards.
+-s::::
+Set bit 6 of the return-code if any error statistics are non-zero.
+
*usage* [options] <path> [<path>...]::
Show detailed information about internal allocations in devices.
+
@@ -231,6 +234,9 @@ EXIT STATUS
*btrfs device* returns a zero exit status if it succeeds. Non zero is
returned in case of failure.
+If the '-s' option is used, *btrfs device stats* will add 64 to the
+exit status if any of the error counters is non-zero.
+
AVAILABILITY
------------
*btrfs* is part of btrfs-progs.
@@ -376,6 +376,7 @@ static const char * const cmd_device_stats_usage[] = {
"Show current device IO stats.",
"",
"-z show current stats and reset values to zero",
+ "-s return non-zero if any stat counter is not zero",
NULL
};
@@ -389,14 +390,18 @@ static int cmd_device_stats(int argc, char **argv)
int i;
int c;
int err = 0;
+ int status = 0;
__u64 flags = 0;
DIR *dirstream = NULL;
- while ((c = getopt(argc, argv, "z")) != -1) {
+ while ((c = getopt(argc, argv, "zs")) != -1) {
switch (c) {
case 'z':
flags = BTRFS_DEV_STATS_RESET;
break;
+ case 's':
+ status = 1;
+ break;
case '?':
default:
usage(cmd_device_stats_usage);
@@ -440,7 +445,7 @@ static int cmd_device_stats(int argc, char **argv)
if (ioctl(fdmnt, BTRFS_IOC_GET_DEV_STATS, &args) < 0) {
error("DEV_STATS ioctl failed on %s: %s",
path, strerror(errno));
- err = 1;
+ err |= 1;
} else {
char *canonical_path;
@@ -457,31 +462,51 @@ static int cmd_device_stats(int argc, char **argv)
"devid:%llu", args.devid);
}
- if (args.nr_items >= BTRFS_DEV_STAT_WRITE_ERRS + 1)
+ if (args.nr_items >= BTRFS_DEV_STAT_WRITE_ERRS + 1) {
printf("[%s].write_io_errs %llu\n",
canonical_path,
(unsigned long long) args.values[
BTRFS_DEV_STAT_WRITE_ERRS]);
- if (args.nr_items >= BTRFS_DEV_STAT_READ_ERRS + 1)
+ if ((status == 1) && (args.values[BTRFS_DEV_STAT_WRITE_ERRS] > 0)) {
+ err |= 64;
+ }
+ }
+ if (args.nr_items >= BTRFS_DEV_STAT_READ_ERRS + 1) {
printf("[%s].read_io_errs %llu\n",
canonical_path,
(unsigned long long) args.values[
BTRFS_DEV_STAT_READ_ERRS]);
- if (args.nr_items >= BTRFS_DEV_STAT_FLUSH_ERRS + 1)
+ if ((status == 1) && (args.values[BTRFS_DEV_STAT_READ_ERRS] > 0)) {
+ err |= 64;
+ }
+ }
+ if (args.nr_items >= BTRFS_DEV_STAT_FLUSH_ERRS + 1) {
printf("[%s].flush_io_errs %llu\n",
canonical_path,
(unsigned long long) args.values[
BTRFS_DEV_STAT_FLUSH_ERRS]);
- if (args.nr_items >= BTRFS_DEV_STAT_CORRUPTION_ERRS + 1)
+ if ((status == 1) && (args.values[BTRFS_DEV_STAT_FLUSH_ERRS] > 0)) {
+ err |= 64;
+ }
+ }
+ if (args.nr_items >= BTRFS_DEV_STAT_CORRUPTION_ERRS + 1) {
printf("[%s].corruption_errs %llu\n",
canonical_path,
(unsigned long long) args.values[
BTRFS_DEV_STAT_CORRUPTION_ERRS]);
- if (args.nr_items >= BTRFS_DEV_STAT_GENERATION_ERRS + 1)
+ if ((status == 1) && (args.values[BTRFS_DEV_STAT_CORRUPTION_ERRS] > 0)) {
+ err |= 64;
+ }
+ }
+ if (args.nr_items >= BTRFS_DEV_STAT_GENERATION_ERRS + 1) {
printf("[%s].generation_errs %llu\n",
canonical_path,
(unsigned long long) args.values[
BTRFS_DEV_STAT_GENERATION_ERRS]);
+ if ((status == 1) && (args.values[BTRFS_DEV_STAT_GENERATION_ERRS] > 0)) {
+ err |= 64;
+ }
+ }
free(canonical_path);
}
Currently, `btrfs device stats` returns non-zero only when there was an error getting the counter values. This is fine for when it gets run by a user directly, but is a serious pain when trying to use it in a script or for monitoring since you need to parse the (not at all machine friendly) output to check the counter values. This patch adds an option ('-s') which causes `btrfs device stats` to set bit 6 in the return code if any of the counters are non-zero. This greatly simplifies checking from a script or monitoring software if any errors have been recorded. In the event that this switch is passed and an error occurs reading the stats, the return code will have bit 0 set (so if there are errors reading counters, and the counters which were read were non-zero, the return value will be 65). Signed-off-by: Austin S. Hemmelgarn <ahferroin7@gmail.com> --- Changes since v1: * Switched to using bit 6 instead of bit 7 so we don't stomp on Bash's manipulation of return codes. Thanks to Mike Fleetwood for reminding me about this. Documentation/btrfs-device.asciidoc | 8 +++++++- cmds-device.c | 39 ++++++++++++++++++++++++++++++------- 2 files changed, 39 insertions(+), 8 deletions(-)