web_log fixes and improvements

diff --git a/conf.d/health.d/web_log.conf b/conf.d/health.d/web_log.conf
index b6d2d537f9a811e16d9aae59937bb1bacfeba450..c8d0c112a6afe84c7a2c912759f1e3d4ba228f2c 100644 (file)
--- a/conf.d/health.d/web_log.conf
+++ b/conf.d/health.d/web_log.conf
@@ -13,9 +13,17 @@ families: *
     info: number of seconds since the last successful data collection
       to: webmaster
 
+
 # -----------------------------------------------------------------------------
 # high level response code alarms
 
+# the following alarms trigger only when there are enough data.
+# we assume there are enough data when:
+#
+#  $1m_requests > 120
+#
+# i.e. when there are at least 120 requests during the last minute
+
 template: 1m_requests
       on: web_log.response_codes
 families: *
@@ -40,58 +48,62 @@ families: *
     calc: $1m_2xx * 100 / $1m_requests
    units: %
    every: 10s
-    warn: ($1m_requests > 30) ? ($this < (($status >= $WARNING ) ? ( 98 ) : ( 95 )) ) : ( 0 )
-    crit: ($1m_requests > 30) ? ($this < (($status == $CRITICAL) ? ( 95 ) : ( 90 )) ) : ( 0 )
+    warn: ($1m_requests > 120) ? ($this < (($status >= $WARNING ) ? ( 98 ) : ( 95 )) ) : ( 0 )
+    crit: ($1m_requests > 120) ? ($this < (($status == $CRITICAL) ? ( 95 ) : ( 90 )) ) : ( 0 )
    delay: down 15m multiplier 1.5 max 1h
-    info: the ratio of HTTP redirects (3xx) vs the successful requests, \
-          over the last minute
+    info: the ratio of successful HTTP responses (2xx) over the last minute
       to: webmaster
 
 template: 1m_redirects
       on: web_log.detailed_response_codes
 families: *
   lookup: sum -1m unaligned of 301,303,307,308
-    calc: $this * 100 / ( $1m_2xx + $this )
+    calc: $this * 100 / $1m_requests
    units: %
    every: 10s
-    warn: ($1m_requests > 30) ? ($this > (($status >= $WARNING ) ? ( 1 ) : ( 2 )) ) : ( 0 )
-    crit: ($1m_requests > 30) ? ($this > (($status == $CRITICAL) ? ( 2 ) : ( 5 )) ) : ( 0 )
+    warn: ($1m_requests > 120) ? ($this > (($status >= $WARNING ) ? ( 1 ) : ( 2 )) ) : ( 0 )
+    crit: ($1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 2 ) : ( 5 )) ) : ( 0 )
    delay: down 15m multiplier 1.5 max 1h
-    info: the ratio of HTTP redirects (301, 303, 307, 308) vs the successful requests, \
-          over the last minute
+    info: the ratio of HTTP redirects (301, 303, 307, 308) over the last minute
       to: webmaster
 
 template: 1m_bad_requests
       on: web_log.response_codes
 families: *
   lookup: sum -1m unaligned of 4xx
-    calc: $this * 100 / ( $1m_2xx + $this )
+    calc: $this * 100 / $1m_requests
    units: %
    every: 10s
-    warn: ($1m_requests > 30) ? ($this > (($status >= $WARNING)  ? ( 1 ) : (  5 )) ) : ( 0 )
-    crit: ($1m_requests > 30) ? ($this > (($status == $CRITICAL) ? ( 5 ) : ( 10 )) ) : ( 0 )
+    warn: ($1m_requests > 120) ? ($this > (($status >= $WARNING)  ? ( 1 ) : (  5 )) ) : ( 0 )
+    crit: ($1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 5 ) : ( 10 )) ) : ( 0 )
    delay: down 15m multiplier 1.5 max 1h
-    info: the ratio of HTTP bad requests (4xx) vs the successful requests, \
-          over the last minute
+    info: the ratio of HTTP bad requests (4xx) over the last minute
       to: webmaster
 
 template: 1m_internal_errors
       on: web_log.response_codes
 families: *
   lookup: sum -1m unaligned of 5xx
-    calc: $this * 100 / ( $1m_2xx + $this )
+    calc: $this * 100 / $1m_requests
    units: %
    every: 10s
-    warn: ($1m_requests > 30) ? ($this > (($status >= $WARNING)  ? ( 1 ) : ( 2 )) ) : ( 0 )
-    crit: ($1m_requests > 30) ? ($this > (($status == $CRITICAL) ? ( 2 ) : ( 5 )) ) : ( 0 )
+    warn: ($1m_requests > 120) ? ($this > (($status >= $WARNING)  ? ( 1 ) : ( 2 )) ) : ( 0 )
+    crit: ($1m_requests > 120) ? ($this > (($status == $CRITICAL) ? ( 2 ) : ( 5 )) ) : ( 0 )
    delay: down 15m multiplier 1.5 max 1h
-    info: the ratio of HTTP internal server errors (5xx) vs the successful \
-          requests, over the last minute
+    info: the ratio of HTTP internal server errors (5xx), over the last minute
       to: webmaster
 
+
 # -----------------------------------------------------------------------------
 # web slow
 
+# the following alarms trigger only when there are enough data.
+# we assume there are enough data when:
+#
+#  $1m_requests > 120
+#
+# i.e. when there are at least 120 requests during the last minute
+
 template: 10m_response_time
       on: web_log.response_time
 families: *
@@ -108,8 +120,8 @@ families: *
    every: 10s
    green: 500
      red: 1000
-    warn: ($1m_requests > 30) ? ($this > $green && $this > ($10m_response_time * 2) ) : ( 0 )
-    crit: ($1m_requests > 30) ? ($this > $red   && $this > ($10m_response_time * 4) ) : ( 0 )
+    warn: ($1m_requests > 120) ? ($this > $green && $this > ($10m_response_time * 2) ) : ( 0 )
+    crit: ($1m_requests > 120) ? ($this > $red   && $this > ($10m_response_time * 4) ) : ( 0 )
    delay: down 15m multiplier 1.5 max 1h
     info: the average time to respond to HTTP requests, over the last 1 minute
       to: webmaster
@@ -117,6 +129,14 @@ families: *
 # -----------------------------------------------------------------------------
 # web too many or too few requests
 
+# the following alarms trigger only when there are enough data.
+# we assume there are enough data when:
+#
+#  $5m_2xx_last > 120
+#
+# i.e. when there were at least 120 requests during the 5 minutes starting
+#      at -10m and ending at -5m
+
 template: 5m_2xx_last
       on: web_log.response_codes
 families: *
@@ -139,11 +159,11 @@ families: *
     calc: ($5m_2xx_last > 0)?($5m_2xx_now * 100 / $5m_2xx_last):(100)
    units: %
    every: 30s
-    warn: ($1m_requests > 30) ? (($5m_2xx_last > 30) ? ($this > 200 OR $this < 50) : (0) ) : ( 0 )
-    crit: ($1m_requests > 30) ? (($5m_2xx_last > 30) ? ($this > 400 OR $this < 25) : (0) ) : ( 0 )
+    warn: ($5m_2xx_last > 120) ? ($this > 200 OR $this < 50) : (0)
+    crit: ($5m_2xx_last > 120) ? ($this > 400 OR $this < 25) : (0)
    delay: down 15m multiplier 1.5 max 1h
 options: no-clear-notification
     info: the percentage of web requests over the last 5 minutes, \
-          compared with the previous 15 minutes
+          compared with the previous 5 minutes
       to: webmaster
 

diff --git a/web/dashboard_info.js b/web/dashboard_info.js
index 7da621ef10eae5b0ee80008faec771d4c4773eea..4eca27e078991be37199b9d144519d54eac01727 100644 (file)
--- a/web/dashboard_info.js
+++ b/web/dashboard_info.js
@@ -857,7 +857,7 @@ netdataDashboard.context = {
                     + ' data-dimensions="2xx"'
                     + ' data-chart-library="gauge"'
                     + ' data-title="Successful"'
-                    + ' data-units="requests"'
+                    + ' data-units="requests/s"'
                     + ' data-gauge-adjust="width"'
                     + ' data-width="12%"'
                     + ' data-before="0"'
@@ -865,6 +865,7 @@ netdataDashboard.context = {
                     + ' data-points="CHART_DURATION"'
                     + ' data-common-max="' + id + '"'
                     + ' data-colors="' + NETDATA.colors[0] + '"'
+                    + ' data-decimal-digits="0"'
                     + ' role="application"></div>';
             },
 
@@ -874,7 +875,7 @@ netdataDashboard.context = {
                     + ' data-dimensions="3xx"'
                     + ' data-chart-library="gauge"'
                     + ' data-title="Redirects"'
-                    + ' data-units="requests"'
+                    + ' data-units="requests/s"'
                     + ' data-gauge-adjust="width"'
                     + ' data-width="12%"'
                     + ' data-before="0"'
@@ -882,6 +883,7 @@ netdataDashboard.context = {
                     + ' data-points="CHART_DURATION"'
                     + ' data-common-max="' + id + '"'
                     + ' data-colors="' + NETDATA.colors[2] + '"'
+                    + ' data-decimal-digits="0"'
                     + ' role="application"></div>';
             },
 
@@ -891,7 +893,7 @@ netdataDashboard.context = {
                     + ' data-dimensions="4xx"'
                     + ' data-chart-library="gauge"'
                     + ' data-title="Bad Requests"'
-                    + ' data-units="requests"'
+                    + ' data-units="requests/s"'
                     + ' data-gauge-adjust="width"'
                     + ' data-width="12%"'
                     + ' data-before="0"'
@@ -899,6 +901,7 @@ netdataDashboard.context = {
                     + ' data-points="CHART_DURATION"'
                     + ' data-common-max="' + id + '"'
                     + ' data-colors="' + NETDATA.colors[3] + '"'
+                    + ' data-decimal-digits="0"'
                     + ' role="application"></div>';
             },
 
@@ -908,7 +911,7 @@ netdataDashboard.context = {
                     + ' data-dimensions="5xx"'
                     + ' data-chart-library="gauge"'
                     + ' data-title="Server Errors"'
-                    + ' data-units="requests"'
+                    + ' data-units="requests/s"'
                     + ' data-gauge-adjust="width"'
                     + ' data-width="12%"'
                     + ' data-before="0"'
@@ -916,6 +919,7 @@ netdataDashboard.context = {
                     + ' data-points="CHART_DURATION"'
                     + ' data-common-max="' + id + '"'
                     + ' data-colors="' + NETDATA.colors[1] + '"'
+                    + ' data-decimal-digits="0"'
                     + ' role="application"></div>';
             }
         ]
@@ -928,7 +932,7 @@ netdataDashboard.context = {
                 return  '<div data-netdata="' + id + '"'
                     + ' data-dimensions="avg"'
                     + ' data-chart-library="gauge"'
-                    + ' data-title="Average Response"'
+                    + ' data-title="Average Response Time"'
                     + ' data-units="milliseconds"'
                     + ' data-gauge-adjust="width"'
                     + ' data-width="12%"'
@@ -936,6 +940,7 @@ netdataDashboard.context = {
                     + ' data-after="-CHART_DURATION"'
                     + ' data-points="CHART_DURATION"'
                     + ' data-colors="' + NETDATA.colors[4] + '"'
+                    + ' data-decimal-digits="2"'
                     + ' role="application"></div>';
             }
         ]

diff --git a/web/index.html b/web/index.html
index b21998bdc0e08e8b43c0afe33ea9307a2f3abaf5..e8e821f43193fbba30f396a505bfacf2d00c0c3e 100644 (file)
--- a/web/index.html
+++ b/web/index.html
@@ -2800,7 +2800,7 @@
             });
 
             NETDATA.requiredJs.push({
-                url: NETDATA.serverDefault + 'dashboard_info.js?v20170211-19',
+                url: NETDATA.serverDefault + 'dashboard_info.js?v20170211-20',
                 async: false,
                 isAlreadyLoaded: function() { return false; }
             });