@cryptotaxi247 / netdata-1 / commits / 6898558b7

Use brackets around info variables (#14206)

* use brackets around vars * update doc * change doc * try fix codacy * fix 2

Emmanuel Vasilakis committed Jan 5, 2023 at 15:42 UTC 6898558b7278fa6ac80a2c91b2854d08b0360fe3
15 files changed +75 -73
database/rrdcalc.c
+8 -6
@@ -74,18 +74,16 @@ static STRING *rrdcalc_replace_variables_with_rrdset_labels(const char *line, RR
74 char var[RRDCALC_VAR_MAX];
75 char *m, *lbl_value = NULL;
76
77 - while ((m = strchr(temp + pos, '$'))) {
77 + while ((m = strchr(temp + pos, '$')) && *(m+1) == '{') {
78 int i = 0;
79 char *e = m;
80 while (*e) {
81 + var[i++] = *e;
82
82 - if (*e == ' ' || i == RRDCALC_VAR_MAX - 1)
83 + if (*e == '}' || i == RRDCALC_VAR_MAX - 1)
84 break;
84 - else
85 - var[i] = *e;
85
86 e++;
88 - i++;
87 }
88
89 var[i] = '\0';
@@ -97,8 +95,12 @@ static STRING *rrdcalc_replace_variables_with_rrdset_labels(const char *line, RR
95 temp = buf;
96 }
97 else if (!strncmp(var, RRDCALC_VAR_LABEL, RRDCALC_VAR_LABEL_LEN)) {
98 + char label_val[RRDCALC_VAR_MAX + 1] = { 0 };
99 + strcpy(label_val, var+RRDCALC_VAR_LABEL_LEN);
100 + label_val[i - RRDCALC_VAR_LABEL_LEN - 1] = '\0';
101 +
102 if(likely(rc->rrdset && rc->rrdset->rrdlabels)) {
101 - rrdlabels_get_value_to_char_or_null(rc->rrdset->rrdlabels, &lbl_value, var+RRDCALC_VAR_LABEL_LEN);
103 + rrdlabels_get_value_to_char_or_null(rc->rrdset->rrdlabels, &lbl_value, label_val);
104 if (lbl_value) {
105 char *buf = find_and_replace(temp, var, lbl_value, m);
106 freez(temp);
database/rrdcalc.h
+2 -2
@@ -251,8 +251,8 @@ void rrdcalc_rrdhost_index_init(RRDHOST *host);
251 void rrdcalc_rrdhost_index_destroy(RRDHOST *host);
252
253 #define RRDCALC_VAR_MAX 100
254 -#define RRDCALC_VAR_FAMILY "$family"
255 -#define RRDCALC_VAR_LABEL "$label:"
254 +#define RRDCALC_VAR_FAMILY "${family}"
255 +#define RRDCALC_VAR_LABEL "${label:"
256 #define RRDCALC_VAR_LABEL_LEN (sizeof(RRDCALC_VAR_LABEL)-1)
257
258 #endif //NETDATA_RRDCALC_H
health/REFERENCE.md
+4 -4
@@ -548,13 +548,13 @@ alert information. Current variables supported are:
548
549 | variable | description |
550 | ---------| ----------- |
551 -| $family | Will be replaced by the family instance for the alert (e.g. eth0) |
552 -| $label: | Followed by a chart label name, this will replace the variable with the chart label's value |
551 +| ${family} | Will be replaced by the family instance for the alert (e.g. eth0) |
552 +| ${label:LABEL_NAME} | The variable will be replaced with the value of the label |
553
554 For example, an info field like the following:
555
556 ```yaml
557 -info: average inbound utilization for the network interface $family over the last minute
557 +info: average inbound utilization for the network interface ${family} over the last minute
558 ```
559
560 Will be rendered on the alert acting on interface `eth0` as:
@@ -567,7 +567,7 @@ An alert acting on a chart that has a chart label named e.g. `target`, with a va
567 can be enriched as follows:
568
569 ```yaml
570 -info: average ratio of HTTP responses with unexpected status over the last 5 minutes for the site $label:target
570 +info: average ratio of HTTP responses with unexpected status over the last 5 minutes for the site ${label:target}
571 ```
572
573 Will become:
health/health.d/cgroups.conf
+4 -4
@@ -51,7 +51,7 @@ component: Network
51 lookup: average -1m unaligned of received
52 units: packets
53 every: 10s
54 - info: average number of packets received by the network interface $label:device over the last minute
54 + info: average number of packets received by the network interface ${label:device} over the last minute
55
56 template: cgroup_10s_received_packets_storm
57 on: cgroup.net_packets
@@ -66,7 +66,7 @@ component: Network
66 warn: $this > (($status >= $WARNING)?(200):(5000))
67 crit: $this > (($status == $CRITICAL)?(5000):(6000))
68 options: no-clear-notification
69 - info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \
69 + info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \
70 compared to the rate over the last minute
71 to: sysadmin
72
@@ -121,7 +121,7 @@ component: Network
121 lookup: average -1m unaligned of received
122 units: packets
123 every: 10s
124 - info: average number of packets received by the network interface $label:device over the last minute
124 + info: average number of packets received by the network interface ${label:device} over the last minute
125
126 template: k8s_cgroup_10s_received_packets_storm
127 on: k8s.cgroup.net_packets
@@ -136,6 +136,6 @@ component: Network
136 warn: $this > (($status >= $WARNING)?(200):(5000))
137 crit: $this > (($status == $CRITICAL)?(5000):(6000))
138 options: no-clear-notification
139 - info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \
139 + info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \
140 compared to the rate over the last minute
141 to: sysadmin
health/health.d/consul.conf
+11 -11
@@ -10,7 +10,7 @@ component: Consul
10 units: status
11 warn: $this == 1
12 delay: down 5m multiplier 1.5 max 1h
13 - info: datacenter $label:datacenter cluster is unhealthy as reported by server $label:node_name
13 + info: datacenter ${label:datacenter} cluster is unhealthy as reported by server ${label:node_name}
14 to: sysadmin
15
16 template: consul_autopilot_server_health_status
@@ -23,7 +23,7 @@ component: Consul
23 units: status
24 warn: $this == 1
25 delay: down 5m multiplier 1.5 max 1h
26 - info: server $label:node_name from datacenter $label:datacenter is unhealthy
26 + info: server ${label:node_name} from datacenter ${label:datacenter} is unhealthy
27 to: sysadmin
28
29 template: consul_raft_leader_last_contact_time
@@ -37,7 +37,7 @@ component: Consul
37 warn: $this > (($status >= $WARNING) ? (150) : (200))
38 crit: $this > (($status == $CRITICAL) ? (200) : (500))
39 delay: down 5m multiplier 1.5 max 1h
40 - info: median time elapsed since leader server $label:node_name datacenter $label:datacenter was last able to contact the follower nodes
40 + info: median time elapsed since leader server ${label:node_name} datacenter ${label:datacenter} was last able to contact the follower nodes
41 to: sysadmin
42
43 template: consul_raft_leadership_transitions
@@ -50,7 +50,7 @@ component: Consul
50 units: percentage
51 warn: $this > 0
52 delay: down 5m multiplier 1.5 max 1h
53 - info: there has been a leadership change and server $label:node_name datacenter $label:datacenter has become the leader
53 + info: there has been a leadership change and server ${label:node_name} datacenter ${label:datacenter} has become the leader
54 to: sysadmin
55
56 template: consul_raft_thread_main_saturation
@@ -63,7 +63,7 @@ component: Consul
63 units: percentage
64 warn: $this > (($status >= $WARNING) ? (40) : (50))
65 delay: down 5m multiplier 1.5 max 1h
66 - info: average saturation of the main Raft goroutine on server $label:node_name datacenter $label:datacenter
66 + info: average saturation of the main Raft goroutine on server ${label:node_name} datacenter ${label:datacenter}
67 to: sysadmin
68
69 template: consul_raft_thread_fsm_saturation
@@ -76,7 +76,7 @@ component: Consul
76 units: milliseconds
77 warn: $this > (($status >= $WARNING) ? (40) : (50))
78 delay: down 5m multiplier 1.5 max 1h
79 - info: average saturation of the FSM Raft goroutine on server $label:node_name datacenter $label:datacenter
79 + info: average saturation of the FSM Raft goroutine on server ${label:node_name} datacenter ${label:datacenter}
80 to: sysadmin
81
82 template: consul_client_rpc_requests_exceeded
@@ -89,7 +89,7 @@ component: Consul
89 units: requests
90 warn: $this > (($status >= $WARNING) ? (0) : (5))
91 delay: down 5m multiplier 1.5 max 1h
92 - info: number of rate-limited RPC requests made by server $label:node_name datacenter $label:datacenter
92 + info: number of rate-limited RPC requests made by server ${label:node_name} datacenter ${label:datacenter}
93 to: sysadmin
94
95 template: consul_client_rpc_requests_failed
@@ -102,7 +102,7 @@ component: Consul
102 units: requests
103 warn: $this > (($status >= $WARNING) ? (0) : (5))
104 delay: down 5m multiplier 1.5 max 1h
105 - info: number of failed RPC requests made by server $label:node_name datacenter $label:datacenter
105 + info: number of failed RPC requests made by server ${label:node_name} datacenter ${label:datacenter}
106 to: sysadmin
107
108 template: consul_node_health_check_status
@@ -115,7 +115,7 @@ component: Consul
115 units: status
116 warn: $this != nan AND $this != 0
117 delay: down 5m multiplier 1.5 max 1h
118 - info: node health check $label:check_name has failed on server $label:node_name datacenter $label:datacenter
118 + info: node health check ${label:check_name} has failed on server ${label:node_name} datacenter ${label:datacenter}
119 to: sysadmin
120
121 template: consul_service_health_check_status
@@ -128,7 +128,7 @@ component: Consul
128 units: status
129 warn: $this == 1
130 delay: down 5m multiplier 1.5 max 1h
131 - info: service health check $label:check_name for service $label:service_name has failed on server $label:node_name datacenter $label:datacenter
131 + info: service health check ${label:check_name} for service ${label:service_name} has failed on server ${label:node_name} datacenter ${label:datacenter}
132 to: sysadmin
133
134 template: consul_gc_pause_time
@@ -142,5 +142,5 @@ component: Consul
142 warn: $this > (($status >= $WARNING) ? (1) : (2))
143 crit: $this > (($status >= $WARNING) ? (2) : (5))
144 delay: down 5m multiplier 1.5 max 1h
145 - info: time spent in stop-the-world garbage collection pauses on server $label:node_name datacenter $label:datacenter
145 + info: time spent in stop-the-world garbage collection pauses on server ${label:node_name} datacenter ${label:datacenter}
146 to: sysadmin
health/health.d/disks.conf
+4 -4
@@ -23,7 +23,7 @@ component: Disk
23 warn: $this > (($status >= $WARNING ) ? (80) : (90))
24 crit: $this > (($status == $CRITICAL) ? (90) : (98))
25 delay: up 1m down 15m multiplier 1.5 max 1h
26 - info: disk $label:mount_point space utilization
26 + info: disk ${label:mount_point} space utilization
27 to: sysadmin
28
29 template: disk_inode_usage
@@ -40,7 +40,7 @@ component: Disk
40 warn: $this > (($status >= $WARNING) ? (80) : (90))
41 crit: $this > (($status == $CRITICAL) ? (90) : (98))
42 delay: up 1m down 15m multiplier 1.5 max 1h
43 - info: disk $label:mount_point inode utilization
43 + info: disk ${label:mount_point} inode utilization
44 to: sysadmin
45
46
@@ -147,7 +147,7 @@ component: Disk
147 every: 1m
148 warn: $this > 98 * (($status >= $WARNING) ? (0.7) : (1))
149 delay: down 15m multiplier 1.2 max 1h
150 - info: average percentage of time $label:device disk was busy over the last 10 minutes
150 + info: average percentage of time ${label:device} disk was busy over the last 10 minutes
151 to: silent
152
153
@@ -169,5 +169,5 @@ component: Disk
169 every: 1m
170 warn: $this > 5000 * (($status >= $WARNING) ? (0.7) : (1))
171 delay: down 15m multiplier 1.2 max 1h
172 - info: average backlog size of the $label:device disk over the last 10 minutes
172 + info: average backlog size of the ${label:device} disk over the last 10 minutes
173 to: silent
health/health.d/dns_query.conf
+1 -1
@@ -10,5 +10,5 @@ component: DNS
10 every: 10s
11 warn: $this != nan && $this != 1
12 delay: up 30s down 5m multiplier 1.5 max 1h
13 - info: DNS request type $label:record_type to server $label:server is unsuccessful
13 + info: DNS request type ${label:record_type} to server ${label:server} is unsuccessful
14 to: sysadmin
health/health.d/httpcheck.conf
+5 -5
@@ -10,7 +10,7 @@ component: HTTP endpoint
10 calc: ($this < 75) ? (0) : ($this)
11 every: 5s
12 units: up/down
13 - info: HTTP endpoint $label:url liveness status
13 + info: HTTP endpoint ${label:url} liveness status
14 to: silent
15
16 template: httpcheck_web_service_bad_content
@@ -25,7 +25,7 @@ component: HTTP endpoint
25 warn: $this >= 10 AND $this < 40
26 crit: $this >= 40
27 delay: down 5m multiplier 1.5 max 1h
28 - info: percentage of HTTP responses from $label:url with unexpected content in the last 5 minutes
28 + info: percentage of HTTP responses from ${label:url} with unexpected content in the last 5 minutes
29 to: webmaster
30
31 template: httpcheck_web_service_bad_status
@@ -40,7 +40,7 @@ component: HTTP endpoint
40 warn: $this >= 10 AND $this < 40
41 crit: $this >= 40
42 delay: down 5m multiplier 1.5 max 1h
43 - info: percentage of HTTP responses from $label:url with unexpected status in the last 5 minutes
43 + info: percentage of HTTP responses from ${label:url} with unexpected status in the last 5 minutes
44 to: webmaster
45
46 template: httpcheck_web_service_timeouts
@@ -55,7 +55,7 @@ component: HTTP endpoint
55 warn: $this >= 10 AND $this < 40
56 crit: $this >= 40
57 delay: down 5m multiplier 1.5 max 1h
58 - info: percentage of timed-out HTTP requests to $label:url in the last 5 minutes
58 + info: percentage of timed-out HTTP requests to ${label:url} in the last 5 minutes
59 to: webmaster
60
61 template: httpcheck_web_service_no_connection
@@ -70,5 +70,5 @@ component: HTTP endpoint
70 warn: $this >= 10 AND $this < 40
71 crit: $this >= 40
72 delay: down 5m multiplier 1.5 max 1h
73 - info: percentage of failed HTTP requests to $label:url in the last 5 minutes
73 + info: percentage of failed HTTP requests to ${label:url} in the last 5 minutes
74 to: webmaster
health/health.d/mdstat.conf
+2 -2
@@ -20,7 +20,7 @@ component: RAID
20 every: 10s
21 calc: $down
22 crit: $this > 0
23 - info: number of devices in the down state for the $label:device $label:raid_level array. \
23 + info: number of devices in the down state for the ${label:device} ${label:raid_level} array. \
24 Any number > 0 indicates that the array is degraded.
25 to: sysadmin
26
@@ -35,7 +35,7 @@ component: RAID
35 every: 60s
36 warn: $this > 1024
37 delay: up 30m
38 - info: number of unsynchronized blocks for the $label:device $label:raid_level array
38 + info: number of unsynchronized blocks for the ${label:device} ${label:raid_level} array
39 to: sysadmin
40
41 template: mdstat_nonredundant_last_collected
health/health.d/net.conf
+14 -14
@@ -15,7 +15,7 @@ component: Network
15 calc: ( $nic_speed_max > 0 ) ? ( $nic_speed_max) : ( nan )
16 units: Mbit
17 every: 10s
18 - info: network interface $label:device current speed
18 + info: network interface ${label:device} current speed
19
20 template: 1m_received_traffic_overflow
21 on: net.net
@@ -31,7 +31,7 @@ component: Network
31 every: 10s
32 warn: $this > (($status >= $WARNING) ? (85) : (90))
33 delay: up 1m down 1m multiplier 1.5 max 1h
34 - info: average inbound utilization for the network interface $label:device over the last minute
34 + info: average inbound utilization for the network interface ${label:device} over the last minute
35 to: sysadmin
36
37 template: 1m_sent_traffic_overflow
@@ -48,7 +48,7 @@ component: Network
48 every: 10s
49 warn: $this > (($status >= $WARNING) ? (85) : (90))
50 delay: up 1m down 1m multiplier 1.5 max 1h
51 - info: average outbound utilization for the network interface $label:device over the last minute
51 + info: average outbound utilization for the network interface ${label:device} over the last minute
52 to: sysadmin
53
54 # -----------------------------------------------------------------------------
@@ -72,7 +72,7 @@ component: Network
72 lookup: sum -10m unaligned absolute of inbound
73 units: packets
74 every: 1m
75 - info: number of inbound dropped packets for the network interface $label:device in the last 10 minutes
75 + info: number of inbound dropped packets for the network interface ${label:device} in the last 10 minutes
76
77 template: outbound_packets_dropped
78 on: net.drops
@@ -85,7 +85,7 @@ component: Network
85 lookup: sum -10m unaligned absolute of outbound
86 units: packets
87 every: 1m
88 - info: number of outbound dropped packets for the network interface $label:device in the last 10 minutes
88 + info: number of outbound dropped packets for the network interface ${label:device} in the last 10 minutes
89
90 template: inbound_packets_dropped_ratio
91 on: net.packets
@@ -101,7 +101,7 @@ component: Network
101 every: 1m
102 warn: $this >= 2
103 delay: up 1m down 1h multiplier 1.5 max 2h
104 - info: ratio of inbound dropped packets for the network interface $label:device over the last 10 minutes
104 + info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
105 to: sysadmin
106
107 template: outbound_packets_dropped_ratio
@@ -118,7 +118,7 @@ component: Network
118 every: 1m
119 warn: $this >= 2
120 delay: up 1m down 1h multiplier 1.5 max 2h
121 - info: ratio of outbound dropped packets for the network interface $label:device over the last 10 minutes
121 + info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
122 to: sysadmin
123
124 template: wifi_inbound_packets_dropped_ratio
@@ -135,7 +135,7 @@ component: Network
135 every: 1m
136 warn: $this >= 10
137 delay: up 1m down 1h multiplier 1.5 max 2h
138 - info: ratio of inbound dropped packets for the network interface $label:device over the last 10 minutes
138 + info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes
139 to: sysadmin
140
141 template: wifi_outbound_packets_dropped_ratio
@@ -152,7 +152,7 @@ component: Network
152 every: 1m
153 warn: $this >= 10
154 delay: up 1m down 1h multiplier 1.5 max 2h
155 - info: ratio of outbound dropped packets for the network interface $label:device over the last 10 minutes
155 + info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes
156 to: sysadmin
157
158 # -----------------------------------------------------------------------------
@@ -171,7 +171,7 @@ component: Network
171 every: 1m
172 warn: $this >= 5
173 delay: down 1h multiplier 1.5 max 2h
174 - info: number of inbound errors for the network interface $label:device in the last 10 minutes
174 + info: number of inbound errors for the network interface ${label:device} in the last 10 minutes
175 to: sysadmin
176
177 template: interface_outbound_errors
@@ -187,7 +187,7 @@ component: Network
187 every: 1m
188 warn: $this >= 5
189 delay: down 1h multiplier 1.5 max 2h
190 - info: number of outbound errors for the network interface $label:device in the last 10 minutes
190 + info: number of outbound errors for the network interface ${label:device} in the last 10 minutes
191 to: sysadmin
192
193 # -----------------------------------------------------------------------------
@@ -211,7 +211,7 @@ component: Network
211 every: 1m
212 warn: $this > 0
213 delay: down 1h multiplier 1.5 max 2h
214 - info: number of FIFO errors for the network interface $label:device in the last 10 minutes
214 + info: number of FIFO errors for the network interface ${label:device} in the last 10 minutes
215 to: sysadmin
216
217 # -----------------------------------------------------------------------------
@@ -234,7 +234,7 @@ component: Network
234 lookup: average -1m unaligned of received
235 units: packets
236 every: 10s
237 - info: average number of packets received by the network interface $label:device over the last minute
237 + info: average number of packets received by the network interface ${label:device} over the last minute
238
239 template: 10s_received_packets_storm
240 on: net.packets
@@ -251,6 +251,6 @@ component: Network
251 warn: $this > (($status >= $WARNING)?(200):(5000))
252 crit: $this > (($status == $CRITICAL)?(5000):(6000))
253 options: no-clear-notification
254 - info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \
254 + info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \
255 compared to the rate over the last minute
256 to: sysadmin
health/health.d/nvme.conf
+1 -1
@@ -11,5 +11,5 @@ component: Disk
11 every: 10s
12 crit: $this != nan AND $this != 0
13 delay: down 5m multiplier 1.5 max 2h
14 - info: NVMe device $label:device has critical warnings
14 + info: NVMe device ${label:device} has critical warnings
15 to: sysadmin
health/health.d/ping.conf
+3 -3
@@ -12,7 +12,7 @@ component: Network
12 every: 10s
13 crit: $this == 0
14 delay: down 30m multiplier 1.5 max 2h
15 - info: network host $label:host reachability status
15 + info: network host ${label:host} reachability status
16 to: sysadmin
17
18 template: ping_packet_loss
@@ -29,7 +29,7 @@ component: Network
29 warn: $this > $green
30 crit: $this > $red
31 delay: down 30m multiplier 1.5 max 2h
32 - info: packet loss percentage to the network host $label:host over the last 10 minutes
32 + info: packet loss percentage to the network host ${label:host} over the last 10 minutes
33 to: sysadmin
34
35 template: ping_host_latency
@@ -46,5 +46,5 @@ component: Network
46 warn: $this > $green OR $max > $red
47 crit: $this > $red
48 delay: down 30m multiplier 1.5 max 2h
49 - info: average latency to the network host $label:host over the last 10 seconds
49 + info: average latency to the network host ${label:host} over the last 10 seconds
50 to: sysadmin
health/health.d/portcheck.conf
+3 -3
@@ -10,7 +10,7 @@ component: TCP endpoint
10 calc: ($this < 75) ? (0) : ($this)
11 every: 5s
12 units: up/down
13 - info: TCP host $label:host port $label:port liveness status
13 + info: TCP host ${label:host} port ${label:port} liveness status
14 to: silent
15
16 template: portcheck_connection_timeouts
@@ -25,7 +25,7 @@ component: TCP endpoint
25 warn: $this >= 10 AND $this < 40
26 crit: $this >= 40
27 delay: down 5m multiplier 1.5 max 1h
28 - info: percentage of timed-out TCP connections to host $label:host port $label:port in the last 5 minutes
28 + info: percentage of timed-out TCP connections to host ${label:host} port ${label:port} in the last 5 minutes
29 to: sysadmin
30
31 template: portcheck_connection_fails
@@ -40,5 +40,5 @@ component: TCP endpoint
40 warn: $this >= 10 AND $this < 40
41 crit: $this >= 40
42 delay: down 5m multiplier 1.5 max 1h
43 - info: percentage of failed TCP connections to host $label:host port $label:port in the last 5 minutes
43 + info: percentage of failed TCP connections to host ${label:host} port ${label:port} in the last 5 minutes
44 to: sysadmin
health/health.d/postgres.conf
+11 -11
@@ -58,7 +58,7 @@ component: PostgreSQL
58 warn: $this < (($status >= $WARNING) ? (70) : (60))
59 crit: $this < (($status == $CRITICAL) ? (60) : (50))
60 delay: down 15m multiplier 1.5 max 1h
61 - info: average cache hit ratio in db $label:database over the last minute
61 + info: average cache hit ratio in db ${label:database} over the last minute
62 to: dba
63
64 template: postgres_db_transactions_rollback_ratio
@@ -72,7 +72,7 @@ component: PostgreSQL
72 every: 1m
73 warn: $this > (($status >= $WARNING) ? (0) : (2))
74 delay: down 15m multiplier 1.5 max 1h
75 - info: average aborted transactions percentage in db $label:database over the last five minutes
75 + info: average aborted transactions percentage in db ${label:database} over the last five minutes
76 to: dba
77
78 template: postgres_db_deadlocks_rate
@@ -86,7 +86,7 @@ component: PostgreSQL
86 every: 1m
87 warn: $this > (($status >= $WARNING) ? (0) : (10))
88 delay: down 15m multiplier 1.5 max 1h
89 - info: number of deadlocks detected in db $label:database in the last minute
89 + info: number of deadlocks detected in db ${label:database} in the last minute
90 to: dba
91
92 # Table alarms
@@ -104,7 +104,7 @@ component: PostgreSQL
104 warn: $this < (($status >= $WARNING) ? (70) : (60))
105 crit: $this < (($status == $CRITICAL) ? (60) : (50))
106 delay: down 15m multiplier 1.5 max 1h
107 - info: average cache hit ratio in db $label:database table $label:table over the last minute
107 + info: average cache hit ratio in db ${label:database} table ${label:table} over the last minute
108 to: dba
109
110 template: postgres_table_index_cache_io_ratio
@@ -120,7 +120,7 @@ component: PostgreSQL
120 warn: $this < (($status >= $WARNING) ? (70) : (60))
121 crit: $this < (($status == $CRITICAL) ? (60) : (50))
122 delay: down 15m multiplier 1.5 max 1h
123 - info: average index cache hit ratio in db $label:database table $label:table over the last minute
123 + info: average index cache hit ratio in db ${label:database} table ${label:table} over the last minute
124 to: dba
125
126 template: postgres_table_toast_cache_io_ratio
@@ -136,7 +136,7 @@ component: PostgreSQL
136 warn: $this < (($status >= $WARNING) ? (70) : (60))
137 crit: $this < (($status == $CRITICAL) ? (60) : (50))
138 delay: down 15m multiplier 1.5 max 1h
139 - info: average TOAST hit ratio in db $label:database table $label:table over the last minute
139 + info: average TOAST hit ratio in db ${label:database} table ${label:table} over the last minute
140 to: dba
141
142 template: postgres_table_toast_index_cache_io_ratio
@@ -152,7 +152,7 @@ component: PostgreSQL
152 warn: $this < (($status >= $WARNING) ? (70) : (60))
153 crit: $this < (($status == $CRITICAL) ? (60) : (50))
154 delay: down 15m multiplier 1.5 max 1h
155 - info: average index TOAST hit ratio in db $label:database table $label:table over the last minute
155 + info: average index TOAST hit ratio in db ${label:database} table ${label:table} over the last minute
156 to: dba
157
158 template: postgres_table_bloat_size_perc
@@ -167,7 +167,7 @@ component: PostgreSQL
167 warn: $this > (($status >= $WARNING) ? (60) : (70))
168 crit: $this > (($status == $CRITICAL) ? (70) : (80))
169 delay: down 15m multiplier 1.5 max 1h
170 - info: bloat size percentage in db $label:database table $label:table
170 + info: bloat size percentage in db ${label:database} table ${label:table}
171 to: dba
172
173 template: postgres_table_last_autovacuum_time
@@ -180,7 +180,7 @@ component: PostgreSQL
180 units: seconds
181 every: 1m
182 warn: $this != nan AND $this > (60 * 60 * 24 * 7)
183 - info: time elapsed since db $label:database table $label:table was vacuumed by the autovacuum daemon
183 + info: time elapsed since db ${label:database} table ${label:table} was vacuumed by the autovacuum daemon
184 to: dba
185
186 template: postgres_table_last_autoanalyze_time
@@ -193,7 +193,7 @@ component: PostgreSQL
193 units: seconds
194 every: 1m
195 warn: $this != nan AND $this > (60 * 60 * 24 * 7)
196 - info: time elapsed since db $label:database table $label:table was analyzed by the autovacuum daemon
196 + info: time elapsed since db ${label:database} table ${label:table} was analyzed by the autovacuum daemon
197 to: dba
198
199 # Index alarms
@@ -210,5 +210,5 @@ component: PostgreSQL
210 warn: $this > (($status >= $WARNING) ? (60) : (70))
211 crit: $this > (($status == $CRITICAL) ? (70) : (80))
212 delay: down 15m multiplier 1.5 max 1h
213 - info: bloat size percentage in db $label:database table $label:table index $label:index
213 + info: bloat size percentage in db ${label:database} table ${label:table} index ${label:index}
214 to: dba
health/health.d/zfs.conf
+2 -2
@@ -24,7 +24,7 @@ component: File system
24 every: 10s
25 warn: $this > 0
26 delay: down 1m multiplier 1.5 max 1h
27 - info: ZFS pool $label:pool state is degraded
27 + info: ZFS pool ${label:pool} state is degraded
28 to: sysadmin
29
30 template: zfs_pool_state_crit
@@ -37,5 +37,5 @@ component: File system
37 every: 10s
38 crit: $this > 0
39 delay: down 1m multiplier 1.5 max 1h
40 - info: ZFS pool $label:pool state is faulted or unavail
40 + info: ZFS pool ${label:pool} state is faulted or unavail
41 to: sysadmin