summaryrefslogtreecommitdiffstats
path: root/health
diff options
context:
space:
mode:
Diffstat (limited to 'health')
-rw-r--r--health/Makefile.am1
-rw-r--r--health/REFERENCE.md35
-rw-r--r--health/health.c81
-rw-r--r--health/health.d/boinc.conf4
-rw-r--r--health/health.d/btrfs.conf9
-rw-r--r--health/health.d/cockroachdb.conf10
-rw-r--r--health/health.d/disks.conf10
-rw-r--r--health/health.d/exporting.conf2
-rw-r--r--health/health.d/httpcheck.conf5
-rw-r--r--health/health.d/ioping.conf1
-rw-r--r--health/health.d/mdstat.conf2
-rw-r--r--health/health.d/net.conf18
-rw-r--r--health/health.d/nvme.conf1
-rw-r--r--health/health.d/ping.conf3
-rw-r--r--health/health.d/plugin.conf11
-rw-r--r--health/health.d/portcheck.conf3
-rw-r--r--health/health.d/redis.conf4
-rw-r--r--health/health.d/vsphere.conf8
-rw-r--r--health/health.d/web_log.conf12
-rw-r--r--health/health.d/windows.conf4
-rw-r--r--health/health.h4
-rw-r--r--health/health_config.c93
-rw-r--r--health/health_json.c170
-rw-r--r--health/health_log.c9
24 files changed, 200 insertions, 300 deletions
diff --git a/health/Makefile.am b/health/Makefile.am
index ea1b6e961..0ef55c75e 100644
--- a/health/Makefile.am
+++ b/health/Makefile.am
@@ -69,6 +69,7 @@ dist_healthconfig_DATA = \
health.d/nvme.conf \
health.d/nut.conf \
health.d/pihole.conf \
+ health.d/plugin.conf \
health.d/ping.conf \
health.d/postgres.conf \
health.d/portcheck.conf \
diff --git a/health/REFERENCE.md b/health/REFERENCE.md
index b95dc852e..a36edd8cf 100644
--- a/health/REFERENCE.md
+++ b/health/REFERENCE.md
@@ -241,7 +241,8 @@ Netdata parses the following lines. Beneath the table is an in-depth explanation
| [`delay`](#alarm-line-delay) | no | Optional hysteresis settings to prevent floods of notifications. |
| [`repeat`](#alarm-line-repeat) | no | The interval for sending notifications when an alarm is in WARNING or CRITICAL mode. |
| [`options`](#alarm-line-options) | no | Add an option to not clear alarms. |
-| [`host labels`](#alarm-line-host-labels) | no | List of labels present on a host. |
+| [`host labels`](#alarm-line-host-labels) | no | Restrict an alarm or template to a list of matching labels present on a host. |
+| [`chart labels`](#alarm-line-chart-labels) | no | Restrict an alarm or template to a list of matching labels present on a host. |
| [`info`](#alarm-line-info) | no | A brief description of the alarm. |
The `alarm` or `template` line must be the first line of any entity.
@@ -446,6 +447,9 @@ For example, you can create a template on the `disk.io` context, but filter it t
families: sda sdb
```
+Please note that the use of the `families` filter is planned to be deprecated in upcoming Netdata releases.
+Please use [`chart labels`](#alarm-line-chart-labels) instead.
+
#### Alarm line `lookup`
This line makes a database lookup to find a value. This result of this lookup is available as `$this`.
@@ -696,6 +700,35 @@ host labels: installed = 201*
See our [simple patterns docs](https://github.com/netdata/netdata/blob/master/libnetdata/simple_pattern/README.md) for more examples.
+#### Alarm line `chart labels`
+
+Similar to host labels, the `chart labels` key can be used to filter if an alarm will load or not for a specific chart, based on
+whether these chart labels match or not.
+
+The list of chart labels present on each chart can be obtained from http://localhost:19999/api/v1/charts?all
+
+For example, each `disk_space` chart defines a chart label called `mount_point` with each instance of this chart having
+a value there of which mount point it monitors.
+
+If you have an e.g. external disk mounted on `/mnt/disk1` and you don't wish any related disk space alerts running for
+it (but you do for all other mount points), you can add the following to the alert's configuration:
+
+```yaml
+chart labels: mount_point=!/mnt/disk1 *`
+```
+
+The `chart labels` is a space-separated list that accepts simple patterns. If you use multiple different chart labels,
+then the result is an OR between them. i.e. the following:
+
+```yaml
+chart labels: mount_point=/mnt/disk1 device=sda`
+```
+
+Will create the alert if the `mount_point` is `/mnt/disk1` or the `device` is `sda`. Furthermore, if a chart label name
+is specified that does not exist in the chart, the chart won't be matched.
+
+See our [simple patterns docs](https://github.com/netdata/netdata/blob/master/libnetdata/simple_pattern/README.md) for more examples.
+
#### Alarm line `info`
The info field can contain a small piece of text describing the alarm or template. This will be rendered in
diff --git a/health/health.c b/health/health.c
index 5c2b85bc5..df4798a20 100644
--- a/health/health.c
+++ b/health/health.c
@@ -412,17 +412,13 @@ static inline void health_alarm_execute(RRDHOST *host, ALARM_ENTRY *ae) {
// find the previous notification for the same alarm
// which we have run the exec script
// exception: alarms with HEALTH_ENTRY_FLAG_NO_CLEAR_NOTIFICATION set
+ RRDCALC_STATUS last_executed_status = -3;
if(likely(!(ae->flags & HEALTH_ENTRY_FLAG_NO_CLEAR_NOTIFICATION))) {
- uint32_t id = ae->alarm_id;
- ALARM_ENTRY *t;
- for(t = ae->next; t ; t = t->next) {
- if(t->alarm_id == id && t->flags & HEALTH_ENTRY_FLAG_EXEC_RUN)
- break;
- }
+ int ret = sql_health_get_last_executed_event(host, ae, &last_executed_status);
- if(likely(t)) {
+ if (likely(ret == 1)) {
// we have executed this alarm notification in the past
- if(t && t->new_status == ae->new_status) {
+ if(last_executed_status == ae->new_status) {
// don't send the notification for the same status again
debug(D_HEALTH, "Health not sending again notification for alarm '%s.%s' status %s", ae_chart_name(ae), ae_name(ae)
, rrdcalc_status2string(ae->new_status));
@@ -561,6 +557,7 @@ static inline void health_alarm_execute(RRDHOST *host, ALARM_ENTRY *ae) {
ae->flags |= HEALTH_ENTRY_FLAG_EXEC_IN_PROGRESS;
ae->exec_spawn_serial = spawn_enq_cmd(command_to_run);
enqueue_alarm_notify_in_progress(ae);
+ health_alarm_log_save(host, ae);
} else {
error("Failed to format command arguments");
}
@@ -628,35 +625,32 @@ static inline void health_alarm_log_process(RRDHOST *host) {
// remember this for the next iteration
host->health_last_processed_id = first_waiting;
- bool cleanup_excess_log_entries = host->health_log.count > host->health_log.max;
-
- if (!cleanup_excess_log_entries)
- return;
-
- // cleanup excess entries in the log
+ //delete those that are updated, no in progress execution, and is not repeating
netdata_rwlock_wrlock(&host->health_log.alarm_log_rwlock);
- ALARM_ENTRY *last = NULL;
- unsigned int count = host->health_log.max * 2 / 3;
- for(ae = host->health_log.alarms; ae && count ; count--, last = ae, ae = ae->next) ;
-
- if(ae && last && last->next == ae)
- last->next = NULL;
- else
- ae = NULL;
-
- while(ae) {
- debug(D_HEALTH, "Health removing alarm log entry with id: %u", ae->unique_id);
-
- ALARM_ENTRY *t = ae->next;
-
- if(likely(!(ae->flags & HEALTH_ENTRY_FLAG_IS_REPEATING))) {
- health_alarm_wait_for_execution(ae);
+ ALARM_ENTRY *prev = host->health_log.alarms;
+ for(ae = host->health_log.alarms; ae ; ae = ae->next) {
+
+ if((likely(!(ae->flags & HEALTH_ENTRY_FLAG_IS_REPEATING)) &&
+ (ae->flags & HEALTH_ENTRY_FLAG_UPDATED) &&
+ (ae->flags & HEALTH_ENTRY_FLAG_SAVED) &&
+ !(ae->flags & HEALTH_ENTRY_FLAG_EXEC_IN_PROGRESS))
+ ||
+ ((ae->new_status == RRDCALC_STATUS_REMOVED) &&
+ (ae->flags & HEALTH_ENTRY_FLAG_SAVED) &&
+ (ae->when + 3600 < now_realtime_sec())))
+ {
+
+ if (ae == host->health_log.alarms) {
+ host->health_log.alarms = ae->next;
+ prev = ae->next;
+ } else {
+ prev->next = ae->next;
+ }
health_alarm_log_free_one_nochecks_nounlink(ae);
- host->health_log.count--;
- }
-
- ae = t;
+ ae = prev;
+ } else
+ prev = ae;
}
netdata_rwlock_unlock(&host->health_log.alarm_log_rwlock);
@@ -904,8 +898,24 @@ static int update_disabled_silenced(RRDHOST *host, RRDCALC *rc) {
return 0;
}
+static void sql_health_postpone_queue_removed(RRDHOST *host __maybe_unused) {
+#ifdef ENABLE_ACLK
+ if (netdata_cloud_setting) {
+ struct aclk_sync_host_config *wc = (struct aclk_sync_host_config *)host->aclk_sync_host_config;
+ if (unlikely(!wc)) {
+ return;
+ }
+
+ if (wc->alert_queue_removed >= 1) {
+ wc->alert_queue_removed+=6;
+ }
+ }
+#endif
+}
+
static void health_execute_delayed_initializations(RRDHOST *host) {
RRDSET *st;
+ bool must_postpone = false;
if (!rrdhost_flag_check(host, RRDHOST_FLAG_PENDING_HEALTH_INITIALIZATION)) return;
rrdhost_flag_clear(host, RRDHOST_FLAG_PENDING_HEALTH_INITIALIZATION);
@@ -941,8 +951,11 @@ static void health_execute_delayed_initializations(RRDHOST *host) {
rrdvar_store_for_chart(host, st);
}
rrddim_foreach_done(rd);
+ must_postpone = true;
}
rrdset_foreach_done(st);
+ if (must_postpone)
+ sql_health_postpone_queue_removed(host);
}
/**
diff --git a/health/health.d/boinc.conf b/health/health.d/boinc.conf
index 7d7a4fdae..6f37787d7 100644
--- a/health/health.d/boinc.conf
+++ b/health/health.d/boinc.conf
@@ -8,7 +8,6 @@
component: BOINC
os: *
hosts: *
- families: *
lookup: average -10m unaligned of comperror
units: tasks
every: 1m
@@ -26,7 +25,6 @@ component: BOINC
component: BOINC
os: *
hosts: *
- families: *
lookup: average -10m unaligned of upload_failed
units: tasks
every: 1m
@@ -44,7 +42,6 @@ component: BOINC
component: BOINC
os: *
hosts: *
- families: *
lookup: average -10m unaligned of total
units: tasks
every: 1m
@@ -62,7 +59,6 @@ component: BOINC
component: BOINC
os: *
hosts: *
- families: *
lookup: average -10m unaligned of active
calc: ($boinc_total_tasks >= 1) ? ($this) : (inf)
units: tasks
diff --git a/health/health.d/btrfs.conf b/health/health.d/btrfs.conf
index ab63ff28d..97b7a3a94 100644
--- a/health/health.d/btrfs.conf
+++ b/health/health.d/btrfs.conf
@@ -6,7 +6,6 @@
component: File system
os: *
hosts: *
- families: *
calc: 100 - ($unallocated * 100 / ($unallocated + $data_used + $data_free + $meta_used + $meta_free + $sys_used + $sys_free))
units: %
every: 10s
@@ -23,7 +22,6 @@ component: File system
component: File system
os: *
hosts: *
- families: *
calc: $used * 100 / ($used + $free)
units: %
every: 10s
@@ -40,7 +38,6 @@ component: File system
component: File system
os: *
hosts: *
- families: *
calc: ($used + $reserved) * 100 / ($used + $free + $reserved)
units: %
every: 10s
@@ -57,7 +54,6 @@ component: File system
component: File system
os: *
hosts: *
- families: *
calc: $used * 100 / ($used + $free)
units: %
every: 10s
@@ -74,7 +70,6 @@ component: File system
component: File system
os: *
hosts: *
- families: *
units: errors
lookup: max -10m every 1m of read_errs
warn: $this > 0
@@ -89,7 +84,6 @@ component: File system
component: File system
os: *
hosts: *
- families: *
units: errors
lookup: max -10m every 1m of write_errs
warn: $this > 0
@@ -104,7 +98,6 @@ component: File system
component: File system
os: *
hosts: *
- families: *
units: errors
lookup: max -10m every 1m of flush_errs
warn: $this > 0
@@ -119,7 +112,6 @@ component: File system
component: File system
os: *
hosts: *
- families: *
units: errors
lookup: max -10m every 1m of corruption_errs
warn: $this > 0
@@ -134,7 +126,6 @@ component: File system
component: File system
os: *
hosts: *
- families: *
units: errors
lookup: max -10m every 1m of generation_errs
warn: $this > 0
diff --git a/health/health.d/cockroachdb.conf b/health/health.d/cockroachdb.conf
index 1f227841e..09e4f9d40 100644
--- a/health/health.d/cockroachdb.conf
+++ b/health/health.d/cockroachdb.conf
@@ -6,7 +6,7 @@
class: Utilization
type: Database
component: CockroachDB
- calc: $capacity_used_percent
+ calc: $total
units: %
every: 10s
warn: $this > (($status >= $WARNING) ? (80) : (85))
@@ -20,7 +20,7 @@ component: CockroachDB
class: Utilization
type: Database
component: CockroachDB
- calc: $capacity_usable_used_percent
+ calc: $usable
units: %
every: 10s
warn: $this > (($status >= $WARNING) ? (80) : (85))
@@ -36,7 +36,7 @@ component: CockroachDB
class: Errors
type: Database
component: CockroachDB
- calc: $ranges_unavailable
+ calc: $unavailable
units: num
every: 10s
warn: $this > 0
@@ -49,7 +49,7 @@ component: CockroachDB
class: Errors
type: Database
component: CockroachDB
- calc: $ranges_underreplicated
+ calc: $under_replicated
units: num
every: 10s
warn: $this > 0
@@ -64,7 +64,7 @@ component: CockroachDB
class: Utilization
type: Database
component: CockroachDB
- calc: $sys_fd_open/$sys_fd_softlimit * 100
+ calc: $open/$sys_fd_softlimit * 100
units: %
every: 10s
warn: $this > 80
diff --git a/health/health.d/disks.conf b/health/health.d/disks.conf
index fd207fbc1..7bd4f120c 100644
--- a/health/health.d/disks.conf
+++ b/health/health.d/disks.conf
@@ -16,7 +16,7 @@
component: Disk
os: linux freebsd
hosts: *
- families: !/dev !/dev/* !/run !/run/* *
+chart labels: mount_point=!/dev !/dev/* !/run !/run/* *
calc: $used * 100 / ($avail + $used)
units: %
every: 1m
@@ -33,7 +33,7 @@ component: Disk
component: Disk
os: linux freebsd
hosts: *
- families: !/dev !/dev/* !/run !/run/* *
+chart labels: mount_point=!/dev !/dev/* !/run !/run/* *
calc: $used * 100 / ($avail + $used)
units: %
every: 1m
@@ -59,7 +59,6 @@ component: Disk
# on: disk.space
# os: linux freebsd
# hosts: *
-# families: *
# lookup: min -10m at -50m unaligned of avail
# calc: ($this - $avail) / (($now - $after) / 3600)
# every: 1m
@@ -75,7 +74,6 @@ component: Disk
# on: disk.space
# os: linux freebsd
# hosts: *
-# families: *
# calc: ($disk_fill_rate > 0) ? ($avail / $disk_fill_rate) : (inf)
# units: hours
# every: 10s
@@ -101,7 +99,6 @@ component: Disk
# on: disk.inodes
# os: linux freebsd
# hosts: *
-# families: *
# lookup: min -10m at -50m unaligned of avail
# calc: ($this - $avail) / (($now - $after) / 3600)
# every: 1m
@@ -116,7 +113,6 @@ component: Disk
# on: disk.inodes
# os: linux freebsd
# hosts: *
-# families: *
# calc: ($disk_inode_rate > 0) ? ($avail / $disk_inode_rate) : (inf)
# units: hours
# every: 10s
@@ -141,7 +137,6 @@ component: Disk
component: Disk
os: linux freebsd
hosts: *
- families: *
lookup: average -10m unaligned
units: %
every: 1m
@@ -163,7 +158,6 @@ component: Disk
component: Disk
os: linux
hosts: *
- families: *
lookup: average -10m unaligned
units: ms
every: 1m
diff --git a/health/health.d/exporting.conf b/health/health.d/exporting.conf
index 06f398c6e..f1030a317 100644
--- a/health/health.d/exporting.conf
+++ b/health/health.d/exporting.conf
@@ -1,6 +1,5 @@
template: exporting_last_buffering
- families: *
on: exporting_data_size
class: Latency
type: Netdata
@@ -15,7 +14,6 @@ component: Exporting engine
to: dba
template: exporting_metrics_sent
- families: *
on: exporting_data_size
class: Workload
type: Netdata
diff --git a/health/health.d/httpcheck.conf b/health/health.d/httpcheck.conf
index 2008b000d..81748b9e0 100644
--- a/health/health.d/httpcheck.conf
+++ b/health/health.d/httpcheck.conf
@@ -1,7 +1,6 @@
# This is a fast-reacting no-notification alarm ideal for custom dashboards or badges
template: httpcheck_web_service_up
- families: *
on: httpcheck.status
class: Utilization
type: Web Server
@@ -14,7 +13,6 @@ component: HTTP endpoint
to: silent
template: httpcheck_web_service_bad_content
- families: *
on: httpcheck.status
class: Workload
type: Web Server
@@ -29,7 +27,6 @@ component: HTTP endpoint
to: webmaster
template: httpcheck_web_service_bad_status
- families: *
on: httpcheck.status
class: Workload
type: Web Server
@@ -44,7 +41,6 @@ component: HTTP endpoint
to: webmaster
template: httpcheck_web_service_timeouts
- families: *
on: httpcheck.status
class: Latency
type: Web Server
@@ -59,7 +55,6 @@ component: HTTP endpoint
to: webmaster
template: httpcheck_web_service_no_connection
- families: *
on: httpcheck.status
class: Errors
type: Other
diff --git a/health/health.d/ioping.conf b/health/health.d/ioping.conf
index 8b498ad3c..2786cbd62 100644
--- a/health/health.d/ioping.conf
+++ b/health/health.d/ioping.conf
@@ -1,5 +1,4 @@
template: ioping_disk_latency
- families: *
on: ioping.latency
class: Latency
type: System
diff --git a/health/health.d/mdstat.conf b/health/health.d/mdstat.conf
index ed980a26a..b90455a58 100644
--- a/health/health.d/mdstat.conf
+++ b/health/health.d/mdstat.conf
@@ -29,7 +29,7 @@ component: RAID
class: Errors
type: System
component: RAID
- families: !*(raid1) !*(raid10) *
+chart labels: raid_level=!raid1 !raid10 *
units: unsynchronized blocks
calc: $count
every: 60s
diff --git a/health/health.d/net.conf b/health/health.d/net.conf
index a0723f303..08a4eecb4 100644
--- a/health/health.d/net.conf
+++ b/health/health.d/net.conf
@@ -11,7 +11,6 @@
component: Network
os: *
hosts: *
- families: *
calc: ( $nic_speed_max > 0 ) ? ( $nic_speed_max) : ( nan )
units: Mbit
every: 10s
@@ -24,7 +23,6 @@ component: Network
component: Network
os: linux
hosts: *
- families: *
lookup: average -1m unaligned absolute of received
calc: ($interface_speed > 0) ? ($this * 100 / ($interface_speed)) : ( nan )
units: %
@@ -41,7 +39,6 @@ component: Network
component: Network
os: linux
hosts: *
- families: *
lookup: average -1m unaligned absolute of sent
calc: ($interface_speed > 0) ? ($this * 100 / ($interface_speed)) : ( nan )
units: %
@@ -68,7 +65,6 @@ component: Network
component: Network
os: linux
hosts: *
- families: *
lookup: sum -10m unaligned absolute of inbound
units: packets
every: 1m
@@ -81,7 +77,6 @@ component: Network
component: Network
os: linux
hosts: *
- families: *
lookup: sum -10m unaligned absolute of outbound
units: packets
every: 1m
@@ -94,7 +89,7 @@ component: Network
component: Network
os: linux
hosts: *
- families: !wl* *
+chart labels: device=!wl* *
lookup: sum -10m unaligned absolute of received
calc: (($inbound_packets_dropped != nan AND $this > 10000) ? ($inbound_packets_dropped * 100 / $this) : (0))
units: %
@@ -111,7 +106,7 @@ component: Network
component: Network
os: linux
hosts: *
- families: !wl* *
+chart labels: device=!wl* *
lookup: sum -10m unaligned absolute of sent
calc: (($outbound_packets_dropped != nan AND $this > 1000) ? ($outbound_packets_dropped * 100 / $this) : (0))
units: %
@@ -128,7 +123,7 @@ component: Network
component: Network
os: linux
hosts: *
- families: wl*
+chart labels: device=wl*
lookup: sum -10m unaligned absolute of received
calc: (($inbound_packets_dropped != nan AND $this > 10000) ? ($inbound_packets_dropped * 100 / $this) : (0))
units: %
@@ -145,7 +140,7 @@ component: Network
component: Network
os: linux
hosts: *
- families: wl*
+chart labels: device=wl*
lookup: sum -10m unaligned absolute of sent
calc: (($outbound_packets_dropped != nan AND $this > 1000) ? ($outbound_packets_dropped * 100 / $this) : (0))
units: %
@@ -165,7 +160,6 @@ component: Network
component: Network
os: freebsd
hosts: *
- families: *
lookup: sum -10m unaligned absolute of inbound
units: errors
every: 1m
@@ -181,7 +175,6 @@ component: Network
component: Network
os: freebsd
hosts: *
- families: *
lookup: sum -10m unaligned absolute of outbound
units: errors
every: 1m
@@ -205,7 +198,6 @@ component: Network
component: Network
os: linux
hosts: *
- families: *
lookup: sum -10m unaligned absolute
units: errors
every: 1m
@@ -230,7 +222,6 @@ component: Network
component: Network
os: linux freebsd
hosts: *
- families: *
lookup: average -1m unaligned of received
units: packets
every: 10s
@@ -243,7 +234,6 @@ component: Network
component: Network
os: linux freebsd
hosts: *
- families: *
lookup: average -10s unaligned of received
calc: $this * 100 / (($1m_received_packets_rate < 1000)?(1000):($1m_received_packets_rate))
every: 10s
diff --git a/health/health.d/nvme.conf b/health/health.d/nvme.conf
index b7c0e6fd4..742ffbc93 100644
--- a/health/health.d/nvme.conf
+++ b/health/health.d/nvme.conf
@@ -1,7 +1,6 @@
# you can disable an alarm notification by setting the 'to' line to: silent
template: nvme_device_critical_warnings_state
- families: *
on: nvme.device_critical_warnings_state
class: Errors
type: System
diff --git a/health/health.d/ping.conf b/health/health.d/ping.conf
index fa8213ad3..b8d39bbad 100644
--- a/health/health.d/ping.conf
+++ b/health/health.d/ping.conf
@@ -1,7 +1,6 @@
# you can disable an alarm notification by setting the 'to' line to: silent
template: ping_host_reachable
- families: *
on: ping.host_packet_loss
class: Errors
type: Other
@@ -16,7 +15,6 @@ component: Network
to: sysadmin
template: ping_packet_loss
- families: *
on: ping.host_packet_loss
class: Errors
type: Other
@@ -33,7 +31,6 @@ component: Network
to: sysadmin
template: ping_host_latency
- families: *
on: ping.host_rtt
class: Latency
type: Other
diff --git a/health/health.d/plugin.conf b/health/health.d/plugin.conf
new file mode 100644
index 000000000..0a891db79
--- /dev/null
+++ b/health/health.d/plugin.conf
@@ -0,0 +1,11 @@
+ template: plugin_availability_status
+ on: netdata.plugin_availability_status
+ class: Errors
+ type: Netdata
+ calc: $now - $last_collected_t
+ units: seconds ago
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? ($update_every) : (20 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: the amount of time that ${label:_collect_plugin} did not report its availability status
+ to: sysadmin
diff --git a/health/health.d/portcheck.conf b/health/health.d/portcheck.conf
index e8908404c..34550ea02 100644
--- a/health/health.d/portcheck.conf
+++ b/health/health.d/portcheck.conf
@@ -1,7 +1,6 @@
# This is a fast-reacting no-notification alarm ideal for custom dashboards or badges
template: portcheck_service_reachable
- families: *
on: portcheck.status
class: Workload
type: Other
@@ -14,7 +13,6 @@ component: TCP endpoint
to: silent
template: portcheck_connection_timeouts
- families: *
on: portcheck.status
class: Errors
type: Other
@@ -29,7 +27,6 @@ component: TCP endpoint
to: sysadmin
template: portcheck_connection_fails
- families: *
on: portcheck.status
class: Errors
type: Other
diff --git a/health/health.d/redis.conf b/health/health.d/redis.conf
index 34d00b5df..a58fa34d1 100644
--- a/health/health.d/redis.conf
+++ b/health/health.d/redis.conf
@@ -1,7 +1,6 @@
# you can disable an alarm notification by setting the 'to' line to: silent
template: redis_connections_rejected
- families: *
on: redis.connections
class: Errors
type: KV Storage
@@ -15,7 +14,6 @@ component: Redis
to: dba
template: redis_bgsave_broken
- families: *
on: redis.bgsave_health
class: Errors
type: KV Storage
@@ -28,7 +26,6 @@ component: Redis
to: dba
template: redis_bgsave_slow
- families: *
on: redis.bgsave_now
class: Latency
type: KV Storage
@@ -43,7 +40,6 @@ component: Redis
to: dba
template: redis_master_link_down
- families: *
on: redis.master_link_down_since_time
class: Errors
type: KV Storage
diff --git a/health/health.d/vsphere.conf b/health/health.d/vsphere.conf
index d8fc899b9..1d8be6cb5 100644
--- a/health/health.d/vsphere.conf
+++ b/health/health.d/vsphere.conf
@@ -43,7 +43,6 @@ component: Memory
type: Virtual Machine
component: Network
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of rx
units: packets
every: 1m
@@ -55,7 +54,6 @@ component: Network
type: Virtual Machine
component: Network
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of tx
units: packets
every: 1m
@@ -69,7 +67,6 @@ component: Network
type: Virtual Machine
component: Network
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of rx
calc: (($vsphere_inbound_packets_errors != nan AND $this > 1000) ? ($vsphere_inbound_packets_errors * 100 / $this) : (0))
units: %
@@ -85,7 +82,6 @@ component: Network
type: Virtual Machine
component: Network
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of tx
calc: (($vsphere_outbound_packets_errors != nan AND $this > 1000) ? ($vsphere_outbound_packets_errors * 100 / $this) : (0))
units: %
@@ -121,7 +117,6 @@ component: CPU
type: Virtual Machine
component: Network
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of rx
units: packets
every: 1m
@@ -133,7 +128,6 @@ component: Network
type: Virtual Machine
component: Network
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of tx
units: packets
every: 1m
@@ -147,7 +141,6 @@ component: Network
type: Virtual Machine
component: Network
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of rx
calc: (($vsphere_inbound_packets_dropped != nan AND $this > 1000) ? ($vsphere_inbound_packets_dropped * 100 / $this) : (0))
units: %
@@ -163,7 +156,6 @@ component: Network
type: Virtual Machine
component: Network
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of tx
calc: (($vsphere_outbound_packets_dropped != nan AND $this > 1000) ? ($vsphere_outbound_packets_dropped * 100 / $this) : (0))
units: %
diff --git a/health/health.d/web_log.conf b/health/health.d/web_log.conf
index c33c4664c..3fd01831b 100644
--- a/health/health.d/web_log.conf
+++ b/health/health.d/web_log.conf
@@ -13,7 +13,6 @@
class: Workload
type: Web Server
component: Web log
- families: *
lookup: sum -1m unaligned
calc: ($this == 0)?(1):($this)
units: requests
@@ -25,7 +24,6 @@ component: Web log
class: Errors
type: Web Server
component: Web log
- families: *
lookup: sum -1m unaligned of unmatched
calc: $this * 100 / $web_log_1m_total_requests
units: %
@@ -50,7 +48,6 @@ component: Web log
class: Workload
type: Web Server
component: Web log
- families: *
lookup: sum -1m unaligned
calc: ($this == 0)?(1):($this)
units: requests
@@ -62,7 +59,6 @@ component: Web log
class: Workload
type: Web Server
component: Web log
- families: *
lookup: sum -1m unaligned of success
calc: $this * 100 / $web_log_1m_requests
units: %
@@ -78,7 +74,6 @@ component: Web log
class: Workload
type: Web Server
component: Web log
- families: *
lookup: sum -1m unaligned of redirect
calc: $this * 100 / $web_log_1m_requests
units: %
@@ -93,7 +88,6 @@ component: Web log
class: Errors
type: Web Server
component: Web log
- families: *
lookup: sum -1m unaligned of bad
calc: $this * 100 / $web_log_1m_requests
units: %
@@ -108,7 +102,6 @@ component: Web log
class: Errors
type: Web Server
component: Web log
- families: *
lookup: sum -1m unaligned of error
calc: $this * 100 / $web_log_1m_requests
units: %
@@ -134,7 +127,6 @@ component: Web log
class: Latency
type: System
component: Web log
- families: *
lookup: average -10m unaligned of avg
units: ms
every: 30s
@@ -145,7 +137,6 @@ component: Web log
class: Latency
type: Web Server
component: Web log
- families: *
lookup: average -1m unaligned of avg
units: ms
every: 10s
@@ -174,7 +165,6 @@ component: Web log
class: Workload
type: Web Server
component: Web log
- families: *
lookup: average -5m at -5m unaligned of success
units: requests/s
every: 30s
@@ -185,7 +175,6 @@ component: Web log
class: Workload
type: Web Server
component: Web log
- families: *
lookup: average -5m unaligned of success
units: requests/s
every: 30s
@@ -196,7 +185,6 @@ component: Web log
class: Workload
type: Web Server
component: Web log
- families: *
calc: ($web_log_5m_successful_old > 0)?($web_log_5m_successful * 100 / $web_log_5m_successful_old):(100)
units: %
every: 30s
diff --git a/health/health.d/windows.conf b/health/health.d/windows.conf
index d678ac3ae..d4bc7639c 100644
--- a/health/health.d/windows.conf
+++ b/health/health.d/windows.conf
@@ -62,7 +62,6 @@ component: Memory
component: Network
os: linux
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of inbound
units: packets
every: 1m
@@ -78,7 +77,6 @@ component: Network
component: Network
os: linux
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of outbound
units: packets
every: 1m
@@ -94,7 +92,6 @@ component: Network
component: Network
os: linux
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of inbound
units: packets
every: 1m
@@ -110,7 +107,6 @@ component: Network
component: Network
os: linux
hosts: *
- families: *
lookup: sum -10m unaligned absolute match-names of outbound
units: packets
every: 1m
diff --git a/health/health.h b/health/health.h
index 902e36c62..c36aabac7 100644
--- a/health/health.h
+++ b/health/health.h
@@ -41,7 +41,6 @@ void health_reload(void);
void health_aggregate_alarms(RRDHOST *host, BUFFER *wb, BUFFER* context, RRDCALC_STATUS status);
void health_alarms2json(RRDHOST *host, BUFFER *wb, int all);
void health_alarms_values2json(RRDHOST *host, BUFFER *wb, int all);
-void health_alarm_log2json(RRDHOST *host, BUFFER *wb, uint32_t after, char *chart);
void health_api_v1_chart_variables2json(RRDSET *st, BUFFER *buf);
void health_api_v1_chart_custom_variables2json(RRDSET *st, BUFFER *buf);
@@ -87,11 +86,10 @@ void health_alarm_log_free_one_nochecks_nounlink(ALARM_ENTRY *ae);
void *health_cmdapi_thread(void *ptr);
-void health_label_log_save(RRDHOST *host);
-
char *health_edit_command_from_source(const char *source);
void sql_refresh_hashes(void);
void health_add_host_labels(void);
+void health_string2json(BUFFER *wb, const char *prefix, const char *label, const char *value, const char *suffix);
#endif //NETDATA_HEALTH_H
diff --git a/health/health_config.c b/health/health_config.c
index 38857fc9a..a11fd51cd 100644
--- a/health/health_config.c
+++ b/health/health_config.c
@@ -32,6 +32,7 @@
#define HEALTH_REPEAT_KEY "repeat"
#define HEALTH_HOST_LABEL_KEY "host labels"
#define HEALTH_FOREACH_KEY "foreach"
+#define HEALTH_CHART_LABEL_KEY "chart labels"
static inline int health_parse_delay(
size_t line, const char *filename, char *string,
@@ -192,6 +193,50 @@ static inline int isvariableterm(const char s) {
return 1;
}
+// If needed, add a prefix key to all possible values in the range
+static inline char *health_config_add_key_to_values(char *value) {
+ BUFFER *wb = buffer_create(HEALTH_CONF_MAX_LINE + 1, NULL);
+ char key[HEALTH_CONF_MAX_LINE + 1];
+ char data[HEALTH_CONF_MAX_LINE + 1];
+
+ char *s = value;
+ size_t i = 0;
+
+ key[0] = '\0';
+ while(*s) {
+ if (*s == '=') {
+ //hold the key
+ data[i]='\0';
+ strncpyz(key, data, HEALTH_CONF_MAX_LINE);
+ i=0;
+ } else if (*s == ' ') {
+ data[i]='\0';
+ if (data[0]=='!')
+ buffer_snprintf(wb, HEALTH_CONF_MAX_LINE, "!%s=%s ", key, data + 1);
+ else
+ buffer_snprintf(wb, HEALTH_CONF_MAX_LINE, "%s=%s ", key, data);
+ i=0;
+ } else {
+ data[i++] = *s;
+ }
+ s++;
+ }
+
+ data[i]='\0';
+ if (data[0]) {
+ if (data[0]=='!')
+ buffer_snprintf(wb, HEALTH_CONF_MAX_LINE, "!%s=%s ", key, data + 1);
+ else
+ buffer_snprintf(wb, HEALTH_CONF_MAX_LINE, "%s=%s ", key, data);
+ }
+
+ char *final = mallocz(HEALTH_CONF_MAX_LINE + 1);
+ strncpyz(final, buffer_tostring(wb), HEALTH_CONF_MAX_LINE);
+ buffer_free(wb);
+
+ return final;
+}
+
static inline void parse_variables_and_store_in_health_rrdvars(char *value, size_t len) {
const char *s = value;
char buffer[RRDVAR_MAX_LENGTH];
@@ -453,6 +498,7 @@ static inline void alert_config_free(struct alert_config *cfg)
string_freez(cfg->host_labels);
string_freez(cfg->p_db_lookup_dimensions);
string_freez(cfg->p_db_lookup_method);
+ string_freez(cfg->chart_labels);
freez(cfg);
}
@@ -489,7 +535,8 @@ static int health_readfile(const char *filename, void *data) {
hash_delay = 0,
hash_options = 0,
hash_repeat = 0,
- hash_host_label = 0;
+ hash_host_label = 0,
+ hash_chart_label = 0;
char buffer[HEALTH_CONF_MAX_LINE + 1];
@@ -521,6 +568,7 @@ static int health_readfile(const char *filename, void *data) {
hash_options = simple_uhash(HEALTH_OPTIONS_KEY);
hash_repeat = simple_uhash(HEALTH_REPEAT_KEY);
hash_host_label = simple_uhash(HEALTH_HOST_LABEL_KEY);
+ hash_chart_label = simple_uhash(HEALTH_CHART_LABEL_KEY);
}
FILE *fp = fopen(filename, "r");
@@ -937,6 +985,27 @@ static int health_readfile(const char *filename, void *data) {
rc->module_match = string_strdupz(value);
rc->module_pattern = simple_pattern_create(rrdcalc_module_match(rc), NULL, SIMPLE_PATTERN_EXACT, true);
}
+ else if(hash == hash_chart_label && !strcasecmp(key, HEALTH_CHART_LABEL_KEY)) {
+ alert_cfg->chart_labels = string_strdupz(value);
+ if(rc->chart_labels) {
+ if(strcmp(rrdcalc_chart_labels(rc), value) != 0)
+ error("Health configuration at line %zu of file '%s' for alarm '%s' has key '%s' twice, once with value '%s' and later with value '%s'.",
+ line, filename, rrdcalc_name(rc), key, value, value);
+
+ string_freez(rc->chart_labels);
+ simple_pattern_free(rc->chart_labels_pattern);
+ }
+
+ {
+ char *tmp = simple_pattern_trim_around_equal(value);
+ char *tmp_2 = health_config_add_key_to_values(tmp);
+ rc->chart_labels = string_strdupz(tmp_2);
+ freez(tmp);
+ freez(tmp_2);
+ }
+ rc->chart_labels_pattern = simple_pattern_create(rrdcalc_chart_labels(rc), NULL, SIMPLE_PATTERN_EXACT,
+ true);
+ }
else {
error("Health configuration at line %zu of file '%s' for alarm '%s' has unknown key '%s'.",
line, filename, rrdcalc_name(rc), key);
@@ -1186,9 +1255,31 @@ static int health_readfile(const char *filename, void *data) {
rt->host_labels = string_strdupz(tmp);
freez(tmp);
}
+
rt->host_labels_pattern = simple_pattern_create(rrdcalctemplate_host_labels(rt), NULL,
SIMPLE_PATTERN_EXACT, true);
}
+ else if(hash == hash_chart_label && !strcasecmp(key, HEALTH_CHART_LABEL_KEY)) {
+ alert_cfg->chart_labels = string_strdupz(value);
+ if(rt->chart_labels) {
+ if(strcmp(rrdcalctemplate_chart_labels(rt), value) != 0)
+ error("Health configuration at line %zu of file '%s' for template '%s' has key '%s' twice, once with value '%s' and later with value '%s'. Using ('%s').",
+ line, filename, rrdcalctemplate_name(rt), key, rrdcalctemplate_chart_labels(rt), value, value);
+
+ string_freez(rt->chart_labels);
+ simple_pattern_free(rt->chart_labels_pattern);
+ }
+
+ {
+ char *tmp = simple_pattern_trim_around_equal(value);
+ char *tmp_2 = health_config_add_key_to_values(tmp);
+ rt->chart_labels = string_strdupz(tmp_2);
+ freez(tmp);
+ freez(tmp_2);
+ }
+ rt->chart_labels_pattern = simple_pattern_create(rrdcalctemplate_chart_labels(rt), NULL,
+ SIMPLE_PATTERN_EXACT, true);
+ }
else {
error("Health configuration at line %zu of file '%s' for template '%s' has unknown key '%s'.",
line, filename, rrdcalctemplate_name(rt), key);
diff --git a/health/health_json.c b/health/health_json.c
index ba18bddba..4f81998f0 100644
--- a/health/health_json.c
+++ b/health/health_json.c
@@ -13,136 +13,6 @@ void health_string2json(BUFFER *wb, const char *prefix, const char *label, const
buffer_sprintf(wb, "%s\"%s\":null%s", prefix, label, suffix);
}
-void health_alarm_entry2json_nolock(BUFFER *wb, ALARM_ENTRY *ae, RRDHOST *host) {
- char *edit_command = ae->source ? health_edit_command_from_source(ae_source(ae)) : strdupz("UNKNOWN=0=UNKNOWN");
- char config_hash_id[GUID_LEN + 1];
- uuid_unparse_lower(ae->config_hash_id, config_hash_id);
-
- buffer_sprintf(wb,
- "\n\t{\n"
- "\t\t\"hostname\": \"%s\",\n"
- "\t\t\"utc_offset\": %d,\n"
- "\t\t\"timezone\": \"%s\",\n"
- "\t\t\"unique_id\": %u,\n"
- "\t\t\"alarm_id\": %u,\n"
- "\t\t\"alarm_event_id\": %u,\n"
- "\t\t\"config_hash_id\": \"%s\",\n"
- "\t\t\"name\": \"%s\",\n"
- "\t\t\"chart\": \"%s\",\n"
- "\t\t\"context\": \"%s\",\n"
- "\t\t\"family\": \"%s\",\n"
- "\t\t\"class\": \"%s\",\n"
- "\t\t\"component\": \"%s\",\n"
- "\t\t\"type\": \"%s\",\n"
- "\t\t\"processed\": %s,\n"
- "\t\t\"updated\": %s,\n"
- "\t\t\"exec_run\": %lu,\n"
- "\t\t\"exec_failed\": %s,\n"
- "\t\t\"exec\": \"%s\",\n"
- "\t\t\"recipient\": \"%s\",\n"
- "\t\t\"exec_code\": %d,\n"
- "\t\t\"source\": \"%s\",\n"
- "\t\t\"command\": \"%s\",\n"
- "\t\t\"units\": \"%s\",\n"
- "\t\t\"when\": %lu,\n"
- "\t\t\"duration\": %lu,\n"
- "\t\t\"non_clear_duration\": %lu,\n"
- "\t\t\"status\": \"%s\",\n"
- "\t\t\"old_status\": \"%s\",\n"
- "\t\t\"delay\": %d,\n"
- "\t\t\"delay_up_to_timestamp\": %lu,\n"
- "\t\t\"updated_by_id\": %u,\n"
- "\t\t\"updates_id\": %u,\n"
- "\t\t\"value_string\": \"%s\",\n"
- "\t\t\"old_value_string\": \"%s\",\n"
- "\t\t\"last_repeat\": \"%lu\",\n"
- "\t\t\"silenced\": \"%s\",\n"
- , rrdhost_hostname(host)
- , host->utc_offset
- , rrdhost_abbrev_timezone(host)
- , ae->unique_id
- , ae->alarm_id
- , ae->alarm_event_id
- , config_hash_id
- , ae_name(ae)
- , ae_chart_name(ae)
- , ae_chart_context(ae)
- , ae_family(ae)
- , ae->classification?ae_classification(ae):"Unknown"
- , ae->component?ae_component(ae):"Unknown"
- , ae->type?ae_type(ae):"Unknown"
- , (ae->flags & HEALTH_ENTRY_FLAG_PROCESSED)?"true":"false"
- , (ae->flags & HEALTH_ENTRY_FLAG_UPDATED)?"true":"false"
- , (unsigned long)ae->exec_run_timestamp
- , (ae->flags & HEALTH_ENTRY_FLAG_EXEC_FAILED)?"true":"false"
- , ae->exec?ae_exec(ae):string2str(host->health.health_default_exec)
- , ae->recipient?ae_recipient(ae):string2str(host->health.health_default_recipient)
- , ae->exec_code
- , ae_source(ae)
- , edit_command
- , ae_units(ae)
- , (unsigned long)ae->when
- , (unsigned long)ae->duration
- , (unsigned long)ae->non_clear_duration
- , rrdcalc_status2string(ae->new_status)
- , rrdcalc_status2string(ae->old_status)
- , ae->delay
- , (unsigned long)ae->delay_up_to_timestamp
- , ae->updated_by_id
- , ae->updates_id
- , ae_new_value_string(ae)
- , ae_old_value_string(ae)
- , (unsigned long)ae->last_repeat
- , (ae->flags & HEALTH_ENTRY_FLAG_SILENCED)?"true":"false"
- );
-
- health_string2json(wb, "\t\t", "info", ae->info ? ae_info(ae) : "", ",\n");
-
- if(unlikely(ae->flags & HEALTH_ENTRY_FLAG_NO_CLEAR_NOTIFICATION)) {
- buffer_strcat(wb, "\t\t\"no_clear_notification\": true,\n");
- }
-
- buffer_strcat(wb, "\t\t\"value\":");
- buffer_print_netdata_double(wb, ae->new_value);
- buffer_strcat(wb, ",\n");
-
- buffer_strcat(wb, "\t\t\"old_value\":");
- buffer_print_netdata_double(wb, ae->old_value);
- buffer_strcat(wb, "\n");
-
- buffer_strcat(wb, "\t}");
-
- freez(edit_command);
-}
-
-void health_alarm_log2json(RRDHOST *host, BUFFER *wb, uint32_t after, char *chart) {
-
- buffer_strcat(wb, "[");
-
- unsigned int max = host->health_log.max;
- unsigned int count = 0;
-
- STRING *chart_string = string_strdupz(chart);
-
- netdata_rwlock_rdlock(&host->health_log.alarm_log_rwlock);
-
- ALARM_ENTRY *ae;
- for (ae = host->health_log.alarms; ae && count < max; ae = ae->next) {
- if ((ae->unique_id > after) && (!chart || chart_string == ae->chart)) {
- if (likely(count))
- buffer_strcat(wb, ",");
- health_alarm_entry2json_nolock(wb, ae, host);
- count++;
- }
- }
-
- netdata_rwlock_unlock(&host->health_log.alarm_log_rwlock);
-
- string_freez(chart_string);
-
- buffer_strcat(wb, "\n]\n");
-}
-
static inline void health_rrdcalc_values2json_nolock(RRDHOST *host, BUFFER *wb, RRDCALC *rc) {
(void)host;
buffer_sprintf(wb,
@@ -397,43 +267,3 @@ void health_alarms_values2json(RRDHOST *host, BUFFER *wb, int all) {
buffer_strcat(wb, "\n\t}\n}\n");
}
-static int have_recent_alarm(RRDHOST *host, uint32_t alarm_id, uint32_t mark)
-{
- ALARM_ENTRY *ae = host->health_log.alarms;
-
- while(ae) {
- if (ae->alarm_id == alarm_id && ae->unique_id > mark &&
- (ae->new_status != RRDCALC_STATUS_WARNING && ae->new_status != RRDCALC_STATUS_CRITICAL))
- return 1;
- ae = ae->next;
- }
- return 0;
-}
-
-void health_active_log_alarms_2json(RRDHOST *host, BUFFER *wb) {
- netdata_rwlock_rdlock(&host->health_log.alarm_log_rwlock);
-
- buffer_sprintf(wb, "[\n");
-
- unsigned int max = host->health_log.max;
- unsigned int count = 0;
- ALARM_ENTRY *ae;
- for(ae = host->health_log.alarms; ae && count < max ; ae = ae->next) {
- if (!ae->updated_by_id &&
- ((ae->new_status == RRDCALC_STATUS_WARNING || ae->new_status == RRDCALC_STATUS_CRITICAL) ||
- ((ae->old_status == RRDCALC_STATUS_WARNING || ae->old_status == RRDCALC_STATUS_CRITICAL) &&
- ae->new_status == RRDCALC_STATUS_REMOVED))) {
-
- if (have_recent_alarm(host, ae->alarm_id, ae->unique_id))
- continue;
-
- if (likely(count))
- buffer_strcat(wb, ",");
- health_alarm_entry2json_nolock(wb, ae, host);
- count++;
- }
- }
- buffer_strcat(wb, "]");
-
- netdata_rwlock_unlock(&host->health_log.alarm_log_rwlock);
-}
diff --git a/health/health_log.c b/health/health_log.c
index b1f59a1a5..b62e0ace4 100644
--- a/health/health_log.c
+++ b/health/health_log.c
@@ -5,14 +5,7 @@
// ----------------------------------------------------------------------------
inline void health_alarm_log_save(RRDHOST *host, ALARM_ENTRY *ae) {
-
sql_health_alarm_log_save(host, ae);
-
-#ifdef ENABLE_ACLK
- if (netdata_cloud_setting) {
- sql_queue_alarm_to_aclk(host, ae, 0);
- }
-#endif
}
// ----------------------------------------------------------------------------
@@ -53,6 +46,8 @@ inline ALARM_ENTRY* health_create_alarm_entry(
uuid_copy(ae->config_hash_id, *((uuid_t *) config_hash_id));
+ uuid_generate_random(ae->transition_id);
+
ae->family = string_dup(family);
ae->classification = string_dup(class);
ae->component = string_dup(component);