rt/snapraid
1
0
Fork 0
mirror of https://github.com/amadvance/snapraid.git synced 2026-10-26 10:51:54 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

More log_tags to make explicit the devices state

Browse source
This commit is contained in:
Andrea Mazzoleni 2025-12-18 12:10:20 +01:00
parent 352e641e84
commit 30e329d4f3
6 changed files with 302 additions and 72 deletions
Download patch file Download diff file Expand all files Collapse all files

41
cmdline/mingw.c
View file

@ -710,7 +710,7 @@ static void windows_errno(DWORD error)
errno = EIO;
break;
default :
log_fatal("Unexpected Windows error %d.\n", (int)error);
log_fatal("Unexpected Windows error %lu.\n", error);
errno = EIO;
break;
}
@ -2526,6 +2526,7 @@ retry:
f = _wpopen(cmd, L"rt");
if (!f) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from popen).\n", u16tou8(conv_buf, cmd));
return -1;
/* LCOV_EXCL_STOP */
@ -2534,6 +2535,7 @@ retry:
if (smartctl_attribute(f, file, name, smart, serial, vendor, model) != 0) {
/* LCOV_EXCL_START */
pclose(f);
log_tag("device:%s:%s:shell\n", file, name);
return -1;
/* LCOV_EXCL_STOP */
}
@ -2544,6 +2546,7 @@ retry:
if (ret == -1) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from pclose).\n", u16tou8(conv_buf, cmd));
return -1;
/* LCOV_EXCL_STOP */
@ -2612,6 +2615,7 @@ retry:
f = _wpopen(cmd, L"rt");
if (!f) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from popen).\n", u16tou8(conv_buf, cmd));
return -1;
/* LCOV_EXCL_STOP */
@ -2620,6 +2624,7 @@ retry:
if (smartctl_flush(f, file, name) != 0) {
/* LCOV_EXCL_START */
pclose(f);
log_tag("device:%s:%s:shell\n", file, name);
return -1;
/* LCOV_EXCL_STOP */
}
@ -2630,6 +2635,7 @@ retry:
if (ret == -1) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from pclose).\n", u16tou8(conv_buf, cmd));
return -1;
/* LCOV_EXCL_STOP */
@ -2654,12 +2660,16 @@ retry:
}
}
if (ret == 0)
if (ret == 0) {
log_tag("device:%s:%s:active\n", file, name);
*power = POWER_ACTIVE;
else if (ret == 3)
} else if (ret == 3) {
log_tag("device:%s:%s:standby\n", file, name);
*power = POWER_STANDBY;
else
} else {
log_tag("device:%s:%s:unknown\n", file, name);
*power = POWER_UNKNOWN;
}
return 0;
}
@ -2695,6 +2705,7 @@ retry:
f = _wpopen(cmd, L"rt");
if (!f) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from popen).\n", u16tou8(conv_buf, cmd));
return -1;
/* LCOV_EXCL_STOP */
@ -2703,6 +2714,7 @@ retry:
if (smartctl_flush(f, file, name) != 0) {
/* LCOV_EXCL_START */
pclose(f);
log_tag("device:%s:%s:shell\n", file, name);
return -1;
/* LCOV_EXCL_STOP */
}
@ -2713,6 +2725,7 @@ retry:
if (ret == -1) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from pclose).\n", u16tou8(conv_buf, cmd));
return -1;
/* LCOV_EXCL_STOP */
@ -2739,11 +2752,14 @@ retry:
if (ret != 0) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:exit:%d\n", file, name, ret);
log_fatal("Failed to run '%s' with return code %xh.\n", u16tou8(conv_buf, cmd), ret);
return -1;
/* LCOV_EXCL_STOP */
}
log_tag("device:%s:%s:down\n", file, name);
return 0;
}
@ -2766,7 +2782,7 @@ static int devdownifup(uint64_t device, const char* name, const char* smartctl,
/**
* Spin up a device.
*/
static int devup(const char* wfile)
static int devup(uint64_t device, const char* name, const char* wfile)
{
wchar_t conv_buf[CONV_MAX];
HANDLE h;
@ -2774,11 +2790,16 @@ static int devup(const char* wfile)
DISK_GEOMETRY dg;
DWORD bytes;
void* buffer;
char file[128];
snprintf(file, sizeof(file), "/dev/pd%" PRIu64, device);
/* open the volume */
h = CreateFileW(convert(conv_buf, wfile), GENERIC_READ, FILE_SHARE_READ | FILE_SHARE_WRITE, 0, OPEN_EXISTING, FILE_FLAG_NO_BUFFERING | FILE_FLAG_WRITE_THROUGH, 0);
if (h == INVALID_HANDLE_VALUE) {
windows_errno(GetLastError());
DWORD error = GetLastError();
windows_errno(error);
log_tag("device:%s:%s:error:%lu\n", file, name, error);
return -1;
}
@ -2788,6 +2809,7 @@ static int devup(const char* wfile)
DWORD error = GetLastError();
CloseHandle(h);
windows_errno(error);
log_tag("device:%s:%s:error:%lu\n", file, name, error);
return -1;
}
@ -2796,6 +2818,7 @@ static int devup(const char* wfile)
DWORD error = GetLastError();
CloseHandle(h);
windows_errno(error);
log_tag("device:%s:%s:error:%lu\n", file, name, error);
return -1;
}
@ -2804,6 +2827,7 @@ static int devup(const char* wfile)
DWORD error = GetLastError();
CloseHandle(h);
windows_errno(error);
log_tag("device:%s:%s:error:%lu\n", file, name, error);
return -1;
}
@ -2811,11 +2835,14 @@ static int devup(const char* wfile)
DWORD error = GetLastError();
VirtualFree(buffer, 0, MEM_RELEASE);
windows_errno(error);
log_tag("device:%s:%s:error:%lu\n", file, name, error);
return -1;
}
VirtualFree(buffer, 0, MEM_RELEASE);
log_tag("device:%s:%s:up\n", file, name);
return 0;
}
@ -2829,7 +2856,7 @@ static void* thread_spinup(void* arg)
start = tick_ms();
if (devup(devinfo->wfile) != 0) {
if (devup(devinfo->device, devinfo->name, devinfo->wfile) != 0) {
/* LCOV_EXCL_START */
return (void*)-1;
/* LCOV_EXCL_STOP */

24
cmdline/state.c
View file

@ -2717,6 +2717,14 @@ static void state_read_content(struct snapraid_state* state, const char* path, S
/* LCOV_EXCL_STOP */
}
/* log the info read from the content file */
log_tag("content_disk:%s:%" PRIu64 ":%" PRIu64 ":%u:%s\n",
buffer,
v_total_blocks * (uint64_t)state->block_size,
v_free_blocks * (uint64_t)state->block_size,
v_pos,
uuid);
/* find the disk */
disk = find_disk_by_name(state, buffer);
if (!disk) {
@ -2814,9 +2822,13 @@ static void state_read_content(struct snapraid_state* state, const char* path, S
state->parity[v_level].free_blocks = v_free_blocks;
/* log the info read from the content file */
log_tag("content:%s:0:%s:%s:%" PRIi64 "\n", lev_config_name(v_level),
state->parity[v_level].split_map[0].path,
log_tag("content_parity:%s:%" PRIu64 ":%" PRIu64 ":%u:%s:%s:%" PRIi64 "\n",
lev_config_name(v_level),
v_total_blocks * (uint64_t)state->block_size,
v_free_blocks * (uint64_t)state->block_size,
0,
state->parity[v_level].split_map[0].uuid,
state->parity[v_level].split_map[0].path,
state->parity[v_level].split_map[0].size);
}
} else if (c == 'Q') {
@ -2937,9 +2949,13 @@ static void state_read_content(struct snapraid_state* state, const char* path, S
state->parity[v_level].split_map[s].size = v_size;
/* log the info read from the content file */
log_tag("content:%s:%u:%s:%s:%" PRIi64 "\n", lev_config_name(v_level), s,
state->parity[v_level].split_map[s].path,
log_tag("content_parity:%s:%" PRIu64 ":%" PRIu64 ":%u:%s:%s:%" PRIi64 "\n",
lev_config_name(v_level),
v_total_blocks * (uint64_t)state->block_size,
v_free_blocks * (uint64_t)state->block_size,
s,
state->parity[v_level].split_map[s].uuid,
state->parity[v_level].split_map[s].path,
state->parity[v_level].split_map[s].size);
}
}

27
cmdline/unix.c
View file

@ -1168,6 +1168,7 @@ static int devsmart(dev_t device, const char* name, const char* smartctl, uint64
f = popen(cmd, "r");
if (!f) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from popen).\n", cmd);
return -1;
/* LCOV_EXCL_STOP */
@ -1176,6 +1177,7 @@ static int devsmart(dev_t device, const char* name, const char* smartctl, uint64
if (smartctl_attribute(f, file, name, smart, serial, vendor, model) != 0) {
/* LCOV_EXCL_START */
pclose(f);
log_tag("device:%s:%s:shell\n", file, name);
return -1;
/* LCOV_EXCL_STOP */
}
@ -1186,12 +1188,14 @@ static int devsmart(dev_t device, const char* name, const char* smartctl, uint64
if (!WIFEXITED(ret)) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:error:abort\n", file, name);
log_fatal("Failed to run '%s' (not exited).\n", cmd);
return -1;
/* LCOV_EXCL_STOP */
}
if (WEXITSTATUS(ret) == 127) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from sh).\n", cmd);
return -1;
/* LCOV_EXCL_STOP */
@ -1236,6 +1240,7 @@ static int devprobe(dev_t device, const char* name, const char* smartctl, int* p
f = popen(cmd, "r");
if (!f) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from popen).\n", cmd);
return -1;
/* LCOV_EXCL_STOP */
@ -1244,6 +1249,7 @@ static int devprobe(dev_t device, const char* name, const char* smartctl, int* p
if (smartctl_flush(f, file, name) != 0) {
/* LCOV_EXCL_START */
pclose(f);
log_tag("device:%s:%s:shell\n", file, name);
return -1;
/* LCOV_EXCL_STOP */
}
@ -1254,22 +1260,27 @@ static int devprobe(dev_t device, const char* name, const char* smartctl, int* p
if (!WIFEXITED(ret)) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:abort\n", file, name);
log_fatal("Failed to run '%s' (not exited).\n", cmd);
return -1;
/* LCOV_EXCL_STOP */
}
if (WEXITSTATUS(ret) == 127) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from sh).\n", cmd);
return -1;
/* LCOV_EXCL_STOP */
}
if (WEXITSTATUS(ret) == 0) {
log_tag("device:%s:%s:active\n", file, name);
*power = POWER_ACTIVE;
} else if (WEXITSTATUS(ret) == 3) {
log_tag("device:%s:%s:standby\n", file, name);
*power = POWER_STANDBY;
} else {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:exit:%d\n", file, name, WEXITSTATUS(ret));
log_fatal("Failed to run '%s' with return code %xh.\n", cmd, WEXITSTATUS(ret));
return -1;
/* LCOV_EXCL_STOP */
@ -1311,6 +1322,7 @@ static int devdown(dev_t device, const char* name, const char* smartctl)
f = popen(cmd, "r");
if (!f) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from popen).\n", cmd);
return -1;
/* LCOV_EXCL_STOP */
@ -1319,6 +1331,7 @@ static int devdown(dev_t device, const char* name, const char* smartctl)
if (smartctl_flush(f, file, name) != 0) {
/* LCOV_EXCL_START */
pclose(f);
log_tag("device:%s:%s:shell\n", file, name);
return -1;
/* LCOV_EXCL_STOP */
}
@ -1329,23 +1342,28 @@ static int devdown(dev_t device, const char* name, const char* smartctl)
if (!WIFEXITED(ret)) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:abort\n", file, name);
log_fatal("Failed to run '%s' (not exited).\n", cmd);
return -1;
/* LCOV_EXCL_STOP */
}
if (WEXITSTATUS(ret) == 127) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:shell\n", file, name);
log_fatal("Failed to run '%s' (from sh).\n", cmd);
return -1;
/* LCOV_EXCL_STOP */
}
if (WEXITSTATUS(ret) != 0) {
/* LCOV_EXCL_START */
log_tag("device:%s:%s:exit:%d\n", file, name, WEXITSTATUS(ret));
log_fatal("Failed to run '%s' with return code %xh.\n", cmd, WEXITSTATUS(ret));
return -1;
/* LCOV_EXCL_STOP */
}
log_tag("device:%s:%s:down\n", file, name);
return 0;
}
#endif
@ -1372,7 +1390,7 @@ static int devdownifup(dev_t device, const char* name, const char* smartctl, int
* Spin up a specific device.
*/
#if HAVE_LINUX_DEVICE
static int devup(dev_t device)
static int devup(dev_t device, const char* name)
{
char file[PATH_MAX];
int ret;
@ -1398,6 +1416,7 @@ static int devup(dev_t device)
if (f < 0) {
/* LCOV_EXCL_START */
free(buf);
log_tag("device:%s:%s:error:%d\n", file, name, errno);
log_fatal("Failed to open device '%u:%u'.\n", major(device), minor(device));
return -1;
/* LCOV_EXCL_STOP */
@ -1408,6 +1427,7 @@ static int devup(dev_t device)
/* LCOV_EXCL_START */
close(f);
free(buf);
log_tag("device:%s:%s:error:%d\n", file, name, errno);
log_fatal("Failed to read device '%u:%u'.\n", major(device), minor(device));
return -1;
/* LCOV_EXCL_STOP */
@ -1417,11 +1437,14 @@ static int devup(dev_t device)
if (ret < 0) {
/* LCOV_EXCL_START */
free(buf);
log_tag("device:%s:%s:error:%d\n", file, name, errno);
log_fatal("Failed to close device '%u:%u'.\n", major(device), minor(device));
return -1;
/* LCOV_EXCL_STOP */
}
log_tag("device:%s:%s:up\n", file, name);
free(buf);
return 0;
}
@ -1442,7 +1465,7 @@ static void* thread_spinup(void* arg)
start = tick_ms();
if (devup(devinfo->device) != 0) {
if (devup(devinfo->device, devinfo->name) != 0) {
/* LCOV_EXCL_START */
return (void*)-1;
/* LCOV_EXCL_STOP */

116
doc/snapraid_log.1
View file

@ -146,7 +146,7 @@ The absolute path to a content file being used (escaped).
Content files store the metadata (like file hashes and timestamps)
for the array.
.TP
.B content:<parity_level>:<split_index>:<path>:<uuid>:<size>
.B content_parity:<parity_level>:<size>:<free_size>:<split_index>:<uuid>:<path>:<file_size>
The parity files as stored in the content file.
.RS 4
.PD 0
@ -154,23 +154,53 @@ The parity files as stored in the content file.
.I <parity_level>
One of \`parity\`, \`2\-parity\`, ..., \`6\-parity\`.
.HP 4
.I <size>
The size of the data in the disk.
.HP 4
.I <free_size>
The free size in the disk at the time of the
latest \`sync\`.
.HP 4
.I <split_index>
The split index (uint). If no
multiple split parity is configured, there is only the
index 0.
.HP 4
.I <uuid>
The UUID of the disk containing the path.
.HP 4
.I <path>
The path (escaped).
.HP 4
.I <uuid>
The UUID of the partition containing the path.
.HP 4
.I <size>
.I <file_size>
The size of the parity file. Size is \-1 if not yet
fixed, meaning it can grow. This happens for the
latest split.
.PD
.RE
.TP
.B content_disk:<disk_name>:<size>:<free_size>:<parity_index>:<uuid>
The data disk as stored in the content file.
.RS 4
.PD 0
.HP 4
.I <disk_name>
Name of the data disk.
.HP 4
.I <size>
The size of the data in the disk.
.HP 4
.I <free_size>
The free size in the disk at the time of the
latest \`sync\`.
.HP 4
.I <parity_index>
The disk position in the parity computation.
.HP 4
.I <uuid>
The UUID of the disk filesystem.
.PD
.RE
.SH DIAGNOSTICS TAGS
.TP
.B version:<version>
@ -1510,7 +1540,11 @@ The rotation rate (uint64, RPM).
.RE
.TP
.B attr:<device_file>:<disk_name>:flags:<flags_decimal>:<flags_hex>
Logs the SMART status flags from the utility (e.g., smartctl).
Logs the SMART status flags from the \`smartctl\` utility.
Per the smartctl manpage, these flags are bit\-mapped
to indicate specific issues like \[dq]Command line did not parse\[dq],
\[dq]Device could not be opened\[dq], or \[dq]SMART status check
returned \'DISK FAILING\'\[dq].
.RS 4
.PD 0
.HP 4
@ -1557,30 +1591,68 @@ The probability of at least one disk failure in
.RS 4
the next year (double).
.RE
.SH COMMAND PROBE TAGS
This section describes the tags output with the \`probe\` command.
.PP
Note that a \`<disk_name>\` may be associated with more \`<device_file>\`,
in case the logical disk uses more physical disks. In such a case,
you\'ll see multiple tags for the same \`<disk_name>\` but with different
\`<device_file>\`.
.SS Device Power State
Tags used to report the power state of each device.
.SH DEVICE STATUS TAGS
These tags log the lifecycle of hardware interactions and external
command execution. They are primarily output during the \`up\`
(spin\-up), \`down\` (spin\-down), and \`probe\` (power state check)
commands.
.TP
.B probe:<device_file>:<disk_name>:<power_state>
Logs the detected power state of a device.
.B device:<device_file>:<disk_name>:active
Logs that the device was confirmed to be in an active power
state after a status probe.
.RS 4
.PD 0
.HP 4
.I <device_file>
The file path of the device (e.g., /dev/sdb).
The system path to the device node.
.HP 4
.I <disk_name>
The configured name of the disk.
The SnapRAID internal disk disk_name.
.PD
.RE
.TP
.B device:<device_file>:<disk_name>:standby
Logs that the device was confirmed to be in a standby/spun\-down
state.
.TP
.B device:<device_file>:<disk_name>:up
Logs a successful spin\-up operation via direct O_DIRECT
read.
.TP
.B device:<device_file>:<disk_name>:down
Logs a successful spin\-down operation initiated via the
smartctl command.
.TP
.B device:<device_file>:<disk_name>:shell
Logs a failure in the command shell execution environment.
.TP
.B device:<device_file>:<disk_name>:error:<errno>
Logs a low\-level system error during direct file operations.
This is triggered when open(), read(), or close()
calls fail during a spin\-up attempt.
.RS 4
.PD 0
.HP 4
.I <power_state>
The numerical power state: 0: Unknown,
1: StandBy, 2: Active.
.I <errno>
The standard integer error number provided by
the OS.
.PD
.RE
.TP
.B device:<device_file>:<disk_name>:error:abort
Logs that an external process (smartctl) failed to complete
normally, such as being terminated by a signal rather than
exiting.
.TP
.B device:<device_file>:<disk_name>:exit:<exit_code>
Logs that the external command (smartctl) returned a non\-zero
exit code that was not explicitly recognized as a valid state.
.RS 4
.PD 0
.HP 4
.I <exit_code>
The integer exit status returned by the
process.
.PD
.RE
.SH ERROR TAGS

84
doc/snapraid_log.d
View file

@ -112,19 +112,32 @@ Configuration Tags
Content files store the metadata (like file hashes and timestamps)
for the array.
=content:<parity_level>:<split_index>:<path>:<uuid>:<size>
=content_parity:<parity_level>:<size>:<free_size>:<split_index>:<uuid>:<path>:<file_size>
The parity files as stored in the content file.
<parity_level> - One of `parity`, `2-parity`, ..., `6-parity`.
<size> - The size of the data in the disk.
<free_size> - The free size in the disk at the time of the
latest `sync`.
<split_index> - The split index (uint). If no
multiple split parity is configured, there is only the
index 0.
<uuid> - The UUID of the disk containing the path.
<path> - The path (escaped).
<uuid> - The UUID of the partition containing the path.
<size> - The size of the parity file. Size is -1 if not yet
<file_size> - The size of the parity file. Size is -1 if not yet
fixed, meaning it can grow. This happens for the
latest split.
=content_disk:<disk_name>:<size>:<free_size>:<parity_index>:<uuid>
The data disk as stored in the content file.
<disk_name> - Name of the data disk.
<size> - The size of the data in the disk.
<free_size> - The free size in the disk at the time of the
latest `sync`.
<parity_index> - The disk position in the parity computation.
<uuid> - The UUID of the disk filesystem.
Diagnostics Tags
=version:<version>
The version of SnapRAID run.
@ -961,7 +974,11 @@ Command Smart Tags
<rate> - The rotation rate (uint64, RPM).
=attr:<device_file>:<disk_name>:flags:<flags_decimal>:<flags_hex>
Logs the SMART status flags from the utility (e.g., smartctl).
Logs the SMART status flags from the `smartctl` utility.
Per the smartctl manpage, these flags are bit-mapped
to indicate specific issues like "Command line did not parse",
"Device could not be opened", or "SMART status check
returned 'DISK FAILING'".
<flags_decimal> - The raw flags value (uint64, decimal).
<flags_hex> - The raw flags value (uint64, hexadecimal).
@ -985,24 +1002,53 @@ Command Smart Tags
<array_prob> - The probability of at least one disk failure in
the next year (double).
Command Probe Tags
This section describes the tags output with the `probe` command.
Device Status Tags
These tags log the lifecycle of hardware interactions and external
command execution. They are primarily output during the `up`
(spin-up), `down` (spin-down), and `probe` (power state check)
commands.
Note that a `<disk_name>` may be associated with more `<device_file>`,
in case the logical disk uses more physical disks. In such a case,
you'll see multiple tags for the same `<disk_name>` but with different
`<device_file>`.
=device:<device_file>:<disk_name>:active
Logs that the device was confirmed to be in an active power
state after a status probe.
Device Power State
Tags used to report the power state of each device.
<device_file> - The system path to the device node.
<disk_name> - The SnapRAID internal disk disk_name.
=probe:<device_file>:<disk_name>:<power_state>
Logs the detected power state of a device.
=device:<device_file>:<disk_name>:standby
Logs that the device was confirmed to be in a standby/spun-down
state.
<device_file> - The file path of the device (e.g., /dev/sdb).
<disk_name> - The configured name of the disk.
<power_state> - The numerical power state: 0: Unknown,
1: StandBy, 2: Active.
=device:<device_file>:<disk_name>:up
Logs a successful spin-up operation via direct O_DIRECT
read.
=device:<device_file>:<disk_name>:down
Logs a successful spin-down operation initiated via the
smartctl command.
=device:<device_file>:<disk_name>:shell
Logs a failure in the command shell execution environment.
=device:<device_file>:<disk_name>:error:<errno>
Logs a low-level system error during direct file operations.
This is triggered when open(), read(), or close()
calls fail during a spin-up attempt.
<errno> - The standard integer error number provided by
the OS.
=device:<device_file>:<disk_name>:error:abort
Logs that an external process (smartctl) failed to complete
normally, such as being terminated by a signal rather than
exiting.
=device:<device_file>:<disk_name>:exit:<exit_code>
Logs that the external command (smartctl) returned a non-zero
exit code that was not explicitly recognized as a valid state.
<exit_code> - The integer exit status returned by the
process.
Error Tags
These tags report specific errors that occur on data disks during the

82
doc/snapraid_log.txt
View file

@ -118,19 +118,32 @@ scanning the disk and reading the list of files.
Content files store the metadata (like file hashes and timestamps)
for the array.
content:<parity_level>:<split_index>:<path>:<uuid>:<size>
content_parity:<parity_level>:<size>:<free_size>:<split_index>:<uuid>:<path>:<file_size>
The parity files as stored in the content file.
<parity_level> - One of `parity`, `2-parity`, ..., `6-parity`.
<size> - The size of the data in the disk.
<free_size> - The free size in the disk at the time of the
latest `sync`.
<split_index> - The split index (uint). If no
multiple split parity is configured, there is only the
index 0.
<uuid> - The UUID of the disk containing the path.
<path> - The path (escaped).
<uuid> - The UUID of the partition containing the path.
<size> - The size of the parity file. Size is -1 if not yet
<file_size> - The size of the parity file. Size is -1 if not yet
fixed, meaning it can grow. This happens for the
latest split.
content_disk:<disk_name>:<size>:<free_size>:<parity_index>:<uuid>
The data disk as stored in the content file.
<disk_name> - Name of the data disk.
<size> - The size of the data in the disk.
<free_size> - The free size in the disk at the time of the
latest `sync`.
<parity_index> - The disk position in the parity computation.
<uuid> - The UUID of the disk filesystem.
3 DIAGNOSTICS TAGS
==================
@ -1003,7 +1016,11 @@ values.
<rate> - The rotation rate (uint64, RPM).
attr:<device_file>:<disk_name>:flags:<flags_decimal>:<flags_hex>
Logs the SMART status flags from the utility (e.g., smartctl).
Logs the SMART status flags from the `smartctl` utility.
Per the smartctl manpage, these flags are bit-mapped
to indicate specific issues like "Command line did not parse",
"Device could not be opened", or "SMART status check
returned 'DISK FAILING'".
<flags_decimal> - The raw flags value (uint64, decimal).
<flags_hex> - The raw flags value (uint64, hexadecimal).
@ -1028,26 +1045,55 @@ Tags logging the overall failure probabilities for the array.
the next year (double).
15 COMMAND PROBE TAGS
15 DEVICE STATUS TAGS
=====================
This section describes the tags output with the `probe` command.
These tags log the lifecycle of hardware interactions and external
command execution. They are primarily output during the `up`
(spin-up), `down` (spin-down), and `probe` (power state check)
commands.
Note that a `<disk_name>` may be associated with more `<device_file>`,
in case the logical disk uses more physical disks. In such a case,
you'll see multiple tags for the same `<disk_name>` but with different
`<device_file>`.
device:<device_file>:<disk_name>:active
Logs that the device was confirmed to be in an active power
state after a status probe.
---- 15.0.1 Device Power State ----
Tags used to report the power state of each device.
<device_file> - The system path to the device node.
<disk_name> - The SnapRAID internal disk disk_name.
probe:<device_file>:<disk_name>:<power_state>
Logs the detected power state of a device.
device:<device_file>:<disk_name>:standby
Logs that the device was confirmed to be in a standby/spun-down
state.
<device_file> - The file path of the device (e.g., /dev/sdb).
<disk_name> - The configured name of the disk.
<power_state> - The numerical power state: 0: Unknown,
1: StandBy, 2: Active.
device:<device_file>:<disk_name>:up
Logs a successful spin-up operation via direct O_DIRECT
read.
device:<device_file>:<disk_name>:down
Logs a successful spin-down operation initiated via the
smartctl command.
device:<device_file>:<disk_name>:shell
Logs a failure in the command shell execution environment.
device:<device_file>:<disk_name>:error:<errno>
Logs a low-level system error during direct file operations.
This is triggered when open(), read(), or close()
calls fail during a spin-up attempt.
<errno> - The standard integer error number provided by
the OS.
device:<device_file>:<disk_name>:error:abort
Logs that an external process (smartctl) failed to complete
normally, such as being terminated by a signal rather than
exiting.
device:<device_file>:<disk_name>:exit:<exit_code>
Logs that the external command (smartctl) returned a non-zero
exit code that was not explicitly recognized as a valid state.
<exit_code> - The integer exit status returned by the
process.
16 ERROR TAGS