diff options
-rw-r--r-- | database/rrdcalc.c | 14 | ||||
-rw-r--r-- | database/rrdcalc.h | 4 | ||||
-rw-r--r-- | health/REFERENCE.md | 8 | ||||
-rw-r--r-- | health/health.d/cgroups.conf | 8 | ||||
-rw-r--r-- | health/health.d/consul.conf | 22 | ||||
-rw-r--r-- | health/health.d/disks.conf | 8 | ||||
-rw-r--r-- | health/health.d/dns_query.conf | 2 | ||||
-rw-r--r-- | health/health.d/httpcheck.conf | 10 | ||||
-rw-r--r-- | health/health.d/mdstat.conf | 4 | ||||
-rw-r--r-- | health/health.d/net.conf | 28 | ||||
-rw-r--r-- | health/health.d/nvme.conf | 2 | ||||
-rw-r--r-- | health/health.d/ping.conf | 6 | ||||
-rw-r--r-- | health/health.d/portcheck.conf | 6 | ||||
-rw-r--r-- | health/health.d/postgres.conf | 22 | ||||
-rw-r--r-- | health/health.d/zfs.conf | 4 |
15 files changed, 75 insertions, 73 deletions
diff --git a/database/rrdcalc.c b/database/rrdcalc.c index aad945a907..45338a8260 100644 --- a/database/rrdcalc.c +++ b/database/rrdcalc.c @@ -74,18 +74,16 @@ static STRING *rrdcalc_replace_variables_with_rrdset_labels(const char *line, RR char var[RRDCALC_VAR_MAX]; char *m, *lbl_value = NULL; - while ((m = strchr(temp + pos, '$'))) { + while ((m = strchr(temp + pos, '$')) && *(m+1) == '{') { int i = 0; char *e = m; while (*e) { + var[i++] = *e; - if (*e == ' ' || i == RRDCALC_VAR_MAX - 1) + if (*e == '}' || i == RRDCALC_VAR_MAX - 1) break; - else - var[i] = *e; e++; - i++; } var[i] = '\0'; @@ -97,8 +95,12 @@ static STRING *rrdcalc_replace_variables_with_rrdset_labels(const char *line, RR temp = buf; } else if (!strncmp(var, RRDCALC_VAR_LABEL, RRDCALC_VAR_LABEL_LEN)) { + char label_val[RRDCALC_VAR_MAX + 1] = { 0 }; + strcpy(label_val, var+RRDCALC_VAR_LABEL_LEN); + label_val[i - RRDCALC_VAR_LABEL_LEN - 1] = '\0'; + if(likely(rc->rrdset && rc->rrdset->rrdlabels)) { - rrdlabels_get_value_to_char_or_null(rc->rrdset->rrdlabels, &lbl_value, var+RRDCALC_VAR_LABEL_LEN); + rrdlabels_get_value_to_char_or_null(rc->rrdset->rrdlabels, &lbl_value, label_val); if (lbl_value) { char *buf = find_and_replace(temp, var, lbl_value, m); freez(temp); diff --git a/database/rrdcalc.h b/database/rrdcalc.h index a25c05cc6e..08d8beee20 100644 --- a/database/rrdcalc.h +++ b/database/rrdcalc.h @@ -251,8 +251,8 @@ void rrdcalc_rrdhost_index_init(RRDHOST *host); void rrdcalc_rrdhost_index_destroy(RRDHOST *host); #define RRDCALC_VAR_MAX 100 -#define RRDCALC_VAR_FAMILY "$family" -#define RRDCALC_VAR_LABEL "$label:" +#define RRDCALC_VAR_FAMILY "${family}" +#define RRDCALC_VAR_LABEL "${label:" #define RRDCALC_VAR_LABEL_LEN (sizeof(RRDCALC_VAR_LABEL)-1) #endif //NETDATA_RRDCALC_H diff --git a/health/REFERENCE.md b/health/REFERENCE.md index 90da4102a9..c92d697299 100644 --- a/health/REFERENCE.md +++ b/health/REFERENCE.md @@ -548,13 +548,13 @@ alert information. Current variables supported are: | variable | description | | ---------| ----------- | -| $family | Will be replaced by the family instance for the alert (e.g. eth0) | -| $label: | Followed by a chart label name, this will replace the variable with the chart label's value | +| ${family} | Will be replaced by the family instance for the alert (e.g. eth0) | +| ${label:LABEL_NAME} | The variable will be replaced with the value of the label | For example, an info field like the following: ```yaml -info: average inbound utilization for the network interface $family over the last minute +info: average inbound utilization for the network interface ${family} over the last minute ``` 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 can be enriched as follows: ```yaml -info: average ratio of HTTP responses with unexpected status over the last 5 minutes for the site $label:target +info: average ratio of HTTP responses with unexpected status over the last 5 minutes for the site ${label:target} ``` Will become: diff --git a/health/health.d/cgroups.conf b/health/health.d/cgroups.conf index 7bdd6d6b36..08260ff6d9 100644 --- a/health/health.d/cgroups.conf +++ b/health/health.d/cgroups.conf @@ -51,7 +51,7 @@ component: Network lookup: average -1m unaligned of received units: packets every: 10s - info: average number of packets received by the network interface $label:device over the last minute + info: average number of packets received by the network interface ${label:device} over the last minute template: cgroup_10s_received_packets_storm on: cgroup.net_packets @@ -66,7 +66,7 @@ component: Network warn: $this > (($status >= $WARNING)?(200):(5000)) crit: $this > (($status == $CRITICAL)?(5000):(6000)) options: no-clear-notification - info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \ + info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \ compared to the rate over the last minute to: sysadmin @@ -121,7 +121,7 @@ component: Network lookup: average -1m unaligned of received units: packets every: 10s - info: average number of packets received by the network interface $label:device over the last minute + info: average number of packets received by the network interface ${label:device} over the last minute template: k8s_cgroup_10s_received_packets_storm on: k8s.cgroup.net_packets @@ -136,6 +136,6 @@ component: Network warn: $this > (($status >= $WARNING)?(200):(5000)) crit: $this > (($status == $CRITICAL)?(5000):(6000)) options: no-clear-notification - info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \ + info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \ compared to the rate over the last minute to: sysadmin diff --git a/health/health.d/consul.conf b/health/health.d/consul.conf index b591558f4c..8621134dd2 100644 --- a/health/health.d/consul.conf +++ b/health/health.d/consul.conf @@ -10,7 +10,7 @@ component: Consul units: status warn: $this == 1 delay: down 5m multiplier 1.5 max 1h - info: datacenter $label:datacenter cluster is unhealthy as reported by server $label:node_name + info: datacenter ${label:datacenter} cluster is unhealthy as reported by server ${label:node_name} to: sysadmin template: consul_autopilot_server_health_status @@ -23,7 +23,7 @@ component: Consul units: status warn: $this == 1 delay: down 5m multiplier 1.5 max 1h - info: server $label:node_name from datacenter $label:datacenter is unhealthy + info: server ${label:node_name} from datacenter ${label:datacenter} is unhealthy to: sysadmin template: consul_raft_leader_last_contact_time @@ -37,7 +37,7 @@ component: Consul warn: $this > (($status >= $WARNING) ? (150) : (200)) crit: $this > (($status == $CRITICAL) ? (200) : (500)) delay: down 5m multiplier 1.5 max 1h - info: median time elapsed since leader server $label:node_name datacenter $label:datacenter was last able to contact the follower nodes + info: median time elapsed since leader server ${label:node_name} datacenter ${label:datacenter} was last able to contact the follower nodes to: sysadmin template: consul_raft_leadership_transitions @@ -50,7 +50,7 @@ component: Consul units: percentage warn: $this > 0 delay: down 5m multiplier 1.5 max 1h - info: there has been a leadership change and server $label:node_name datacenter $label:datacenter has become the leader + info: there has been a leadership change and server ${label:node_name} datacenter ${label:datacenter} has become the leader to: sysadmin template: consul_raft_thread_main_saturation @@ -63,7 +63,7 @@ component: Consul units: percentage warn: $this > (($status >= $WARNING) ? (40) : (50)) delay: down 5m multiplier 1.5 max 1h - info: average saturation of the main Raft goroutine on server $label:node_name datacenter $label:datacenter + info: average saturation of the main Raft goroutine on server ${label:node_name} datacenter ${label:datacenter} to: sysadmin template: consul_raft_thread_fsm_saturation @@ -76,7 +76,7 @@ component: Consul units: milliseconds warn: $this > (($status >= $WARNING) ? (40) : (50)) delay: down 5m multiplier 1.5 max 1h - info: average saturation of the FSM Raft goroutine on server $label:node_name datacenter $label:datacenter + info: average saturation of the FSM Raft goroutine on server ${label:node_name} datacenter ${label:datacenter} to: sysadmin template: consul_client_rpc_requests_exceeded @@ -89,7 +89,7 @@ component: Consul units: requests warn: $this > (($status >= $WARNING) ? (0) : (5)) delay: down 5m multiplier 1.5 max 1h - info: number of rate-limited RPC requests made by server $label:node_name datacenter $label:datacenter + info: number of rate-limited RPC requests made by server ${label:node_name} datacenter ${label:datacenter} to: sysadmin template: consul_client_rpc_requests_failed @@ -102,7 +102,7 @@ component: Consul units: requests warn: $this > (($status >= $WARNING) ? (0) : (5)) delay: down 5m multiplier 1.5 max 1h - info: number of failed RPC requests made by server $label:node_name datacenter $label:datacenter + info: number of failed RPC requests made by server ${label:node_name} datacenter ${label:datacenter} to: sysadmin template: consul_node_health_check_status @@ -115,7 +115,7 @@ component: Consul units: status warn: $this != nan AND $this != 0 delay: down 5m multiplier 1.5 max 1h - info: node health check $label:check_name has failed on server $label:node_name datacenter $label:datacenter + info: node health check ${label:check_name} has failed on server ${label:node_name} datacenter ${label:datacenter} to: sysadmin template: consul_service_health_check_status @@ -128,7 +128,7 @@ component: Consul units: status warn: $this == 1 delay: down 5m multiplier 1.5 max 1h - info: service health check $label:check_name for service $label:service_name has failed on server $label:node_name datacenter $label:datacenter + info: service health check ${label:check_name} for service ${label:service_name} has failed on server ${label:node_name} datacenter ${label:datacenter} to: sysadmin template: consul_gc_pause_time @@ -142,5 +142,5 @@ component: Consul warn: $this > (($status >= $WARNING) ? (1) : (2)) crit: $this > (($status >= $WARNING) ? (2) : (5)) delay: down 5m multiplier 1.5 max 1h - info: time spent in stop-the-world garbage collection pauses on server $label:node_name datacenter $label:datacenter + info: time spent in stop-the-world garbage collection pauses on server ${label:node_name} datacenter ${label:datacenter} to: sysadmin diff --git a/health/health.d/disks.conf b/health/health.d/disks.conf index dc5f3d4f9a..fd207fbc14 100644 --- a/health/health.d/disks.conf +++ b/health/health.d/disks.conf @@ -23,7 +23,7 @@ component: Disk warn: $this > (($status >= $WARNING ) ? (80) : (90)) crit: $this > (($status == $CRITICAL) ? (90) : (98)) delay: up 1m down 15m multiplier 1.5 max 1h - info: disk $label:mount_point space utilization + info: disk ${label:mount_point} space utilization to: sysadmin template: disk_inode_usage @@ -40,7 +40,7 @@ component: Disk warn: $this > (($status >= $WARNING) ? (80) : (90)) crit: $this > (($status == $CRITICAL) ? (90) : (98)) delay: up 1m down 15m multiplier 1.5 max 1h - info: disk $label:mount_point inode utilization + info: disk ${label:mount_point} inode utilization to: sysadmin @@ -147,7 +147,7 @@ component: Disk every: 1m warn: $this > 98 * (($status >= $WARNING) ? (0.7) : (1)) delay: down 15m multiplier 1.2 max 1h - info: average percentage of time $label:device disk was busy over the last 10 minutes + info: average percentage of time ${label:device} disk was busy over the last 10 minutes to: silent @@ -169,5 +169,5 @@ component: Disk every: 1m warn: $this > 5000 * (($status >= $WARNING) ? (0.7) : (1)) delay: down 15m multiplier 1.2 max 1h - info: average backlog size of the $label:device disk over the last 10 minutes + info: average backlog size of the ${label:device} disk over the last 10 minutes to: silent diff --git a/health/health.d/dns_query.conf b/health/health.d/dns_query.conf index b9d6c2374b..bf9397d858 100644 --- a/health/health.d/dns_query.conf +++ b/health/health.d/dns_query.conf @@ -10,5 +10,5 @@ component: DNS every: 10s warn: $this != nan && $this != 1 delay: up 30s down 5m multiplier 1.5 max 1h - info: DNS request type $label:record_type to server $label:server is unsuccessful + info: DNS request type ${label:record_type} to server ${label:server} is unsuccessful to: sysadmin diff --git a/health/health.d/httpcheck.conf b/health/health.d/httpcheck.conf index 9523a4b5ad..2008b000d8 100644 --- a/health/health.d/httpcheck.conf +++ b/health/health.d/httpcheck.conf @@ -10,7 +10,7 @@ component: HTTP endpoint calc: ($this < 75) ? (0) : ($this) every: 5s units: up/down - info: HTTP endpoint $label:url liveness status + info: HTTP endpoint ${label:url} liveness status to: silent template: httpcheck_web_service_bad_content @@ -25,7 +25,7 @@ component: HTTP endpoint warn: $this >= 10 AND $this < 40 crit: $this >= 40 delay: down 5m multiplier 1.5 max 1h - info: percentage of HTTP responses from $label:url with unexpected content in the last 5 minutes + info: percentage of HTTP responses from ${label:url} with unexpected content in the last 5 minutes to: webmaster template: httpcheck_web_service_bad_status @@ -40,7 +40,7 @@ component: HTTP endpoint warn: $this >= 10 AND $this < 40 crit: $this >= 40 delay: down 5m multiplier 1.5 max 1h - info: percentage of HTTP responses from $label:url with unexpected status in the last 5 minutes + info: percentage of HTTP responses from ${label:url} with unexpected status in the last 5 minutes to: webmaster template: httpcheck_web_service_timeouts @@ -55,7 +55,7 @@ component: HTTP endpoint warn: $this >= 10 AND $this < 40 crit: $this >= 40 delay: down 5m multiplier 1.5 max 1h - info: percentage of timed-out HTTP requests to $label:url in the last 5 minutes + info: percentage of timed-out HTTP requests to ${label:url} in the last 5 minutes to: webmaster template: httpcheck_web_service_no_connection @@ -70,5 +70,5 @@ component: HTTP endpoint warn: $this >= 10 AND $this < 40 crit: $this >= 40 delay: down 5m multiplier 1.5 max 1h - info: percentage of failed HTTP requests to $label:url in the last 5 minutes + info: percentage of failed HTTP requests to ${label:url} in the last 5 minutes to: webmaster diff --git a/health/health.d/mdstat.conf b/health/health.d/mdstat.conf index 3594cd043c..ed980a26a9 100644 --- a/health/health.d/mdstat.conf +++ b/health/health.d/mdstat.conf @@ -20,7 +20,7 @@ component: RAID every: 10s calc: $down crit: $this > 0 - info: number of devices in the down state for the $label:device $label:raid_level array. \ + info: number of devices in the down state for the ${label:device} ${label:raid_level} array. \ Any number > 0 indicates that the array is degraded. to: sysadmin @@ -35,7 +35,7 @@ component: RAID every: 60s warn: $this > 1024 delay: up 30m - info: number of unsynchronized blocks for the $label:device $label:raid_level array + info: number of unsynchronized blocks for the ${label:device} ${label:raid_level} array to: sysadmin template: mdstat_nonredundant_last_collected diff --git a/health/health.d/net.conf b/health/health.d/net.conf index 28aa617b9b..a0723f3030 100644 --- a/health/health.d/net.conf +++ b/health/health.d/net.conf @@ -15,7 +15,7 @@ component: Network calc: ( $nic_speed_max > 0 ) ? ( $nic_speed_max) : ( nan ) units: Mbit every: 10s - info: network interface $label:device current speed + info: network interface ${label:device} current speed template: 1m_received_traffic_overflow on: net.net @@ -31,7 +31,7 @@ component: Network every: 10s warn: $this > (($status >= $WARNING) ? (85) : (90)) delay: up 1m down 1m multiplier 1.5 max 1h - info: average inbound utilization for the network interface $label:device over the last minute + info: average inbound utilization for the network interface ${label:device} over the last minute to: sysadmin template: 1m_sent_traffic_overflow @@ -48,7 +48,7 @@ component: Network every: 10s warn: $this > (($status >= $WARNING) ? (85) : (90)) delay: up 1m down 1m multiplier 1.5 max 1h - info: average outbound utilization for the network interface $label:device over the last minute + info: average outbound utilization for the network interface ${label:device} over the last minute to: sysadmin # ----------------------------------------------------------------------------- @@ -72,7 +72,7 @@ component: Network lookup: sum -10m unaligned absolute of inbound units: packets every: 1m - info: number of inbound dropped packets for the network interface $label:device in the last 10 minutes + info: number of inbound dropped packets for the network interface ${label:device} in the last 10 minutes template: outbound_packets_dropped on: net.drops @@ -85,7 +85,7 @@ component: Network lookup: sum -10m unaligned absolute of outbound units: packets every: 1m - info: number of outbound dropped packets for the network interface $label:device in the last 10 minutes + info: number of outbound dropped packets for the network interface ${label:device} in the last 10 minutes template: inbound_packets_dropped_ratio on: net.packets @@ -101,7 +101,7 @@ component: Network every: 1m warn: $this >= 2 delay: up 1m down 1h multiplier 1.5 max 2h - info: ratio of inbound dropped packets for the network interface $label:device over the last 10 minutes + info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes to: sysadmin template: outbound_packets_dropped_ratio @@ -118,7 +118,7 @@ component: Network every: 1m warn: $this >= 2 delay: up 1m down 1h multiplier 1.5 max 2h - info: ratio of outbound dropped packets for the network interface $label:device over the last 10 minutes + info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes to: sysadmin template: wifi_inbound_packets_dropped_ratio @@ -135,7 +135,7 @@ component: Network every: 1m warn: $this >= 10 delay: up 1m down 1h multiplier 1.5 max 2h - info: ratio of inbound dropped packets for the network interface $label:device over the last 10 minutes + info: ratio of inbound dropped packets for the network interface ${label:device} over the last 10 minutes to: sysadmin template: wifi_outbound_packets_dropped_ratio @@ -152,7 +152,7 @@ component: Network every: 1m warn: $this >= 10 delay: up 1m down 1h multiplier 1.5 max 2h - info: ratio of outbound dropped packets for the network interface $label:device over the last 10 minutes + info: ratio of outbound dropped packets for the network interface ${label:device} over the last 10 minutes to: sysadmin # ----------------------------------------------------------------------------- @@ -171,7 +171,7 @@ component: Network every: 1m warn: $this >= 5 delay: down 1h multiplier 1.5 max 2h - info: number of inbound errors for the network interface $label:device in the last 10 minutes + info: number of inbound errors for the network interface ${label:device} in the last 10 minutes to: sysadmin template: interface_outbound_errors @@ -187,7 +187,7 @@ component: Network every: 1m warn: $this >= 5 delay: down 1h multiplier 1.5 max 2h - info: number of outbound errors for the network interface $label:device in the last 10 minutes + info: number of outbound errors for the network interface ${label:device} in the last 10 minutes to: sysadmin # ----------------------------------------------------------------------------- @@ -211,7 +211,7 @@ component: Network every: 1m warn: $this > 0 delay: down 1h multiplier 1.5 max 2h - info: number of FIFO errors for the network interface $label:device in the last 10 minutes + info: number of FIFO errors for the network interface ${label:device} in the last 10 minutes to: sysadmin # ----------------------------------------------------------------------------- @@ -234,7 +234,7 @@ component: Network lookup: average -1m unaligned of received units: packets every: 10s - info: average number of packets received by the network interface $label:device over the last minute + info: average number of packets received by the network interface ${label:device} over the last minute template: 10s_received_packets_storm on: net.packets @@ -251,6 +251,6 @@ component: Network warn: $this > (($status >= $WARNING)?(200):(5000)) crit: $this > (($status == $CRITICAL)?(5000):(6000)) options: no-clear-notification - info: ratio of average number of received packets for the network interface $label:device over the last 10 seconds, \ + info: ratio of average number of received packets for the network interface ${label:device} over the last 10 seconds, \ compared to the rate over the last minute to: sysadmin diff --git a/health/health.d/nvme.conf b/health/health.d/nvme.conf index 5f729d52bc..b7c0e6fd45 100644 --- a/health/health.d/nvme.conf +++ b/health/health.d/nvme.conf @@ -11,5 +11,5 @@ component: Disk every: 10s crit: $this != nan AND $this != 0 delay: down 5m multiplier 1.5 max 2h - info: NVMe device $label:device has critical warnings + info: NVMe device ${label:device} has critical warnings to: sysadmin diff --git a/health/health.d/ping.conf b/health/health.d/ping.conf index cbe7c30c9d..fa8213ad34 100644 --- a/health/health.d/ping.conf +++ b/health/health.d/ping.conf @@ -12,7 +12,7 @@ component: Network every: 10s crit: $this == 0 delay: down 30m multiplier 1.5 max 2h - info: network host $label:host reachability status + info: network host ${label:host} reachability status to: sysadmin template: ping_packet_loss @@ -29,7 +29,7 @@ component: Network warn: $this > $green crit: $this > $red delay: down 30m multiplier 1.5 max 2h - info: packet loss percentage to the network host $label:host over the last 10 minutes + info: packet loss percentage to the network host ${label:host} over the last 10 minutes to: sysadmin template: ping_host_latency @@ -46,5 +46,5 @@ component: Network warn: $this > $green OR $max > $red crit: $this > $red delay: down 30m multiplier 1.5 max 2h - info: average latency to the network host $label:host over the last 10 seconds + info: average latency to the network host ${label:host} over the last 10 seconds to: sysadmin diff --git a/health/health.d/portcheck.conf b/health/health.d/portcheck.conf index 653c373e11..e8908404c3 100644 --- a/health/health.d/portcheck.conf +++ b/health/health.d/portcheck.conf @@ -10,7 +10,7 @@ component: TCP endpoint calc: ($this < 75) ? (0) : ($this) every: 5s units: up/down - info: TCP host $label:host port $label:port liveness status + info: TCP host ${label:host} port ${label:port} liveness status to: silent template: portcheck_connection_timeouts @@ -25,7 +25,7 @@ component: TCP endpoint warn: $this >= 10 AND $this < 40 crit: $this >= 40 delay: down 5m multiplier 1.5 max 1h - info: percentage of timed-out TCP connections to host $label:host port $label:port in the last 5 minutes + info: percentage of timed-out TCP connections to host ${label:host} port ${label:port} in the last 5 minutes to: sysadmin template: portcheck_connection_fails @@ -40,5 +40,5 @@ component: TCP endpoint warn: $this >= 10 AND $this < 40 crit: $this >= 40 delay: down 5m multiplier 1.5 max 1h - info: percentage of failed TCP connections to host $label:host port $label:port in the last 5 minutes + info: percentage of failed TCP connections to host ${label:host} port ${label:port} in the last 5 minutes to: sysadmin diff --git a/health/health.d/postgres.conf b/health/health.d/postgres.conf index 66d034cfe5..6c04ef13f4 100644 --- a/health/health.d/postgres.conf +++ b/health/health.d/postgres.conf @@ -58,7 +58,7 @@ component: PostgreSQL warn: $this < (($status >= $WARNING) ? (70) : (60)) crit: $this < (($status == $CRITICAL) ? (60) : (50)) delay: down 15m multiplier 1.5 max 1h - info: average cache hit ratio in db $label:database over the last minute + info: average cache hit ratio in db ${label:database} over the last minute to: dba template: postgres_db_transactions_rollback_ratio @@ -72,7 +72,7 @@ component: PostgreSQL every: 1m warn: $this > (($status >= $WARNING) ? (0) : (2)) delay: down 15m multiplier 1.5 max 1h - info: average aborted transactions percentage in db $label:database over the last five minutes + info: average aborted transactions percentage in db ${label:database} over the last five minutes to: dba template: postgres_db_deadlocks_rate @@ -86,7 +86,7 @@ component: PostgreSQL every: 1m warn: $this > (($status >= $WARNING) ? (0) : (10)) delay: down 15m multiplier 1.5 max 1h - info: number of deadlocks detected in db $label:database in the last minute + info: number of deadlocks detected in db ${label:database} in the last minute to: dba # Table alarms @@ -104,7 +104,7 @@ component: PostgreSQL warn: $this < (($status >= $WARNING) ? (70) : (60)) crit: $this < (($status == $CRITICAL) ? (60) : (50)) delay: down 15m multiplier 1.5 max 1h - info: average cache hit ratio in db $label:database table $label:table over the last minute + info: average cache hit ratio in db ${label:database} table ${label:table} over the last minute to: dba template: postgres_table_index_cache_io_ratio @@ -120,7 +120,7 @@ component: PostgreSQL warn: $this < (($status >= $WARNING) ? (70) : (60)) crit: $this < (($status == $CRITICAL) ? (60) : (50)) delay: down 15m multiplier 1.5 max 1h - info: average index cache hit ratio in db $label:database table $label:table over the last minute + info: average index cache hit ratio in db ${label:database} table ${label:table} over the last minute to: dba template: postgres_table_toast_cache_io_ratio @@ -136,7 +136,7 @@ component: PostgreSQL warn: $this < (($status >= $WARNING) ? (70) : (60)) crit: $this < (($status == $CRITICAL) ? (60) : (50)) delay: down 15m multiplier 1.5 max 1h - info: average TOAST hit ratio in db $label:database table $label:table over the last minute + info: average TOAST hit ratio in db ${label:database} table ${label:table} over the last minute to: dba template: postgres_table_toast_index_cache_io_ratio @@ -152,7 +152,7 @@ component: PostgreSQL warn: $this < (($status >= $WARNING) ? (70) : (60)) crit: $this < (($status == $CRITICAL) ? (60) : (50)) delay: down 15m multiplier 1.5 max 1h - info: average index TOAST hit ratio in db $label:database table $label:table over the last minute + info: average index TOAST hit ratio in db ${label:database} table ${label:table} over the last minute to: dba template: postgres_table_bloat_size_perc @@ -167,7 +167,7 @@ component: PostgreSQL warn: $this > (($status >= $WARNING) ? (60) : (70)) crit: $this > (($status == $CRITICAL) ? (70) : (80)) delay: down 15m multiplier 1.5 max 1h - info: bloat size percentage in db $label:database table $label:table + info: bloat size percentage in db ${label:database} table ${label:table} to: dba template: postgres_table_last_autovacuum_time @@ -180,7 +180,7 @@ component: PostgreSQL units: seconds every: 1m warn: $this != nan AND $this > (60 * 60 * 24 * 7) - info: time elapsed since db $label:database table $label:table was vacuumed by the autovacuum daemon + info: time elapsed since db ${label:database} table ${label:table} was vacuumed by the autovacuum daemon to: dba template: postgres_table_last_autoanalyze_time @@ -193,7 +193,7 @@ component: PostgreSQL units: seconds every: 1m warn: $this != nan AND $this > (60 * 60 * 24 * 7) - info: time elapsed since db $label:database table $label:table was analyzed by the autovacuum daemon + info: time elapsed since db ${label:database} table ${label:table} was analyzed by the autovacuum daemon to: dba # Index alarms @@ -210,5 +210,5 @@ component: PostgreSQL warn: $this > (($status >= $WARNING) ? (60) : (70)) crit: $this > (($status == $CRITICAL) ? (70) : (80)) delay: down 15m multiplier 1.5 max 1h - info: bloat size percentage in db $label:database table $label:table index $label:index + info: bloat size percentage in db ${label:database} table ${label:table} index ${label:index} to: dba diff --git a/health/health.d/zfs.conf b/health/health.d/zfs.conf index c53f8032ea..7f8ea2793a 100644 --- a/health/health.d/zfs.conf +++ b/health/health.d/zfs.conf @@ -24,7 +24,7 @@ component: File system every: 10s warn: $this > 0 delay: down 1m multiplier 1.5 max 1h - info: ZFS pool $label:pool state is degraded + info: ZFS pool ${label:pool} state is degraded to: sysadmin template: zfs_pool_state_crit @@ -37,5 +37,5 @@ component: File system every: 10s crit: $this > 0 delay: down 1m multiplier 1.5 max 1h - info: ZFS pool $label:pool state is faulted or unavail + info: ZFS pool ${label:pool} state is faulted or unavail to: sysadmin |