diff options
Diffstat (limited to '')
| -rw-r--r-- | health/health.d/httpcheck.conf | 62 |
1 files changed, 12 insertions, 50 deletions
diff --git a/health/health.d/httpcheck.conf b/health/health.d/httpcheck.conf index 599c47ac..2008b000 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: average ratio of successful HTTP requests over the last minute (at least 75%) + info: HTTP endpoint ${label:url} liveness status to: silent template: httpcheck_web_service_bad_content @@ -25,8 +25,7 @@ component: HTTP endpoint warn: $this >= 10 AND $this < 40 crit: $this >= 40 delay: down 5m multiplier 1.5 max 1h - info: average ratio of HTTP responses with unexpected content over the last 5 minutes - options: no-clear-notification + info: percentage of HTTP responses from ${label:url} with unexpected content in the last 5 minutes to: webmaster template: httpcheck_web_service_bad_status @@ -41,8 +40,7 @@ component: HTTP endpoint warn: $this >= 10 AND $this < 40 crit: $this >= 40 delay: down 5m multiplier 1.5 max 1h - info: average ratio of HTTP responses with unexpected status over the last 5 minutes - options: no-clear-notification + info: percentage of HTTP responses from ${label:url} with unexpected status in the last 5 minutes to: webmaster template: httpcheck_web_service_timeouts @@ -54,9 +52,13 @@ component: HTTP endpoint lookup: average -5m unaligned percentage of timeout every: 10s units: % - info: average ratio of HTTP request timeouts over the last 5 minutes + 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 ${label:url} in the last 5 minutes + to: webmaster - template: httpcheck_no_web_service_connections + template: httpcheck_web_service_no_connection families: * on: httpcheck.status class: Errors @@ -65,48 +67,8 @@ component: HTTP endpoint lookup: average -5m unaligned percentage of no_connection every: 10s units: % - info: average ratio of failed requests during the last 5 minutes - -# combined timeout & no connection alarm - template: httpcheck_web_service_unreachable - families: * - on: httpcheck.status - class: Errors - type: Web Server -component: HTTP endpoint - calc: ($httpcheck_no_web_service_connections >= $httpcheck_web_service_timeouts) ? ($httpcheck_no_web_service_connections) : ($httpcheck_web_service_timeouts) - units: % - every: 10s - warn: ($httpcheck_no_web_service_connections >= 10 OR $httpcheck_web_service_timeouts >= 10) AND ($httpcheck_no_web_service_connections < 40 OR $httpcheck_web_service_timeouts < 40) - crit: $httpcheck_no_web_service_connections >= 40 OR $httpcheck_web_service_timeouts >= 40 - delay: down 5m multiplier 1.5 max 1h - info: ratio of failed requests either due to timeouts or no connection over the last 5 minutes - options: no-clear-notification - to: webmaster - - template: httpcheck_1h_web_service_response_time - families: * - on: httpcheck.responsetime - class: Latency - type: Other -component: HTTP endpoint - lookup: average -1h unaligned of time - every: 30s - units: ms - info: average HTTP response time over the last hour - - template: httpcheck_web_service_slow - families: * - on: httpcheck.responsetime - class: Latency - type: Web Server -component: HTTP endpoint - lookup: average -3m unaligned of time - units: ms - every: 10s - warn: ($this > ($httpcheck_1h_web_service_response_time * 2) ) - crit: ($this > ($httpcheck_1h_web_service_response_time * 3) ) + warn: $this >= 10 AND $this < 40 + crit: $this >= 40 delay: down 5m multiplier 1.5 max 1h - info: average HTTP response time over the last 3 minutes, compared to the average over the last hour - options: no-clear-notification + info: percentage of failed HTTP requests to ${label:url} in the last 5 minutes to: webmaster |