monitoring : update metrics, small change in css/js of cockpit

monitoring/cockpit/castormon/staticfiles/css/base.css

@@ -239,6 +239,13 @@ div#home {
     box-shadow: 0 5px 10px rgba(0, 0, 0, 0.2);
 }
 
+div#home div.home-footer a {
+    border-bottom: none;
+}
+
+div#home div.home-footer img {
+    height: 32px;
+}
 
 /*****************************************************************************
 /*             FILTER AND OPTIONS 

monitoring/cockpit/castormon/staticfiles/js/scripts.js

@@ -912,6 +912,11 @@ $(document).ready(function () {
     $('body').on('click', '.popover-title button.close', function() {
         $('img.metric-info-button').popover('toggle');
     });
+    // tooltip on info button
+    var tooltipMetricDetailsOptions = {
+        title : 'Metric details (press to open/close)'
+    };
+    $('img.metric-info-button').tooltip(tooltipMetricDetailsOptions);
 
     /*****************************
      * Hide all series button    *

monitoring/cockpit/castormon/templates/cockpit/home.html

@@ -6,6 +6,11 @@
 <div id="home">
     <p><h1>CASTOR Cockpit</h1></p>
     <p>NB : this website heavily uses HTML5, CSS3 and AJAX/JavaScript. So you might observe poor performances/visual with IE and FF. If your browser is too slow when displaying charts, try to reduce the window size.</p>
+    <div class="home-footer">
+        <a href="http://www.python.org/"><img src="/static/img/python-powered-w.svg" title="Powered by Python." class="svg" /></a>
+        <a href="http://www.djangoproject.com/"><img src="/static/img/djangopowered126x54.gif" alt="Powered by Django." title="Powered by Django." /></a>
+        <img src="/static/img/HTML5_Badge.svg" title="This site uses HTML5 and CSS3." class="svg" />
+    </div>
 </div>
 {% endblock %}
 

monitoring/metrics/ATLASSRMFEDRequestType.metric

@@ -2,6 +2,8 @@
 
 <metric>
   name: ATLASSRMFEDRequestType
+  unit: Hz
+  category: ATLAS
   window: 60
   conditions: DAEMON=="srmfed" and INSTANCE=="c2atlas"
   groupbykeys: RequestType

monitoring/metrics/Alerts.metric

@@ -2,6 +2,8 @@
 
 <metric>
   name: Alerts
+  unit: count of alerts per minute
+  category: General
   window: 60
   conditions: LVL in ["Crit","Alert"]
   groupbykeys: INSTANCE, DAEMON

monitoring/metrics/CMSSRMFEDRequestType.metric

@@ -2,6 +2,8 @@
 
 <metric>
   name: CMSSRMFEDRequestType
+  unit: Hz
+  category: CMS
   window: 60
   conditions: DAEMON=="srmfed" and INSTANCE=="c2cms"
   groupbykeys: RequestType

monitoring/metrics/ClientVrsDistribution.metric

@@ -3,6 +3,8 @@
 
 <metric>
   name: ClientVrsDistribution  
+  unit: Hz
+  category: General
   window: 60
   conditions: MSG=="Reply sent to client" and DAEMON=="rhd"
   groupbykeys: ClientVersion

monitoring/metrics/CountByInstance.metric

 # Frequence of log msg arrival, broken down by instance
 
 <metric>
-name: CountByInstance
-window: 60
-conditions: NONE 
-groupbykeys: INSTANCE 
-data: CounterHz(COUNT)
-handle_unordered: time_threshold
-nbins: 1 
+    name: CountByInstance
+    unit: Hz
+    category: Monitoring
+    window: 60
+    conditions: NONE 
+    groupbykeys: INSTANCE 
+    data: CounterHz(COUNT)
+    handle_unordered: time_threshold
+    nbins: 1 
 </metric>

monitoring/metrics/CountMsgByHostPPS.metric

@@ -2,6 +2,8 @@
 
 <metric>
   name: CountMsgByHostC2PPS
+  unit: Hz
+  category: Monitoring
   window: 60
   conditions: INSTANCE == "c2pps"
   groupbykeys: HOSTNAME

monitoring/metrics/CountMsgOnHeadnodes.metric

-# Statistical information on the latency to access files on the disk cache 
-# broken down by request type, service class and protocol
+# Frequence of log msg from headnodes and central nodes
 
 <metric>
   name: CountMsgOnHeadnodes
+  unit: Hz
+  category: Monitoring
   window: 60
   conditions: "srv" in HOSTNAME
   groupbykeys: HOSTNAME

monitoring/metrics/CountTotal.metric

 # Frequence of log msg arrival
 
 <metric>
-name: CountTotal
-window: 60
-conditions: NONE 
-groupbykeys: NONE 
-data: CounterHz(COUNT)
-handle_unordered: time_threshold
-nbins: 1
+    name: CountTotal
+    unit: Hz
+    category: Monitoring
+    window: 60
+    conditions: NONE 
+    groupbykeys: NONE 
+    data: CounterHz(COUNT)
+    handle_unordered: time_threshold
+    nbins: 1
 </metric>

monitoring/metrics/Errors.metric

@@ -2,6 +2,8 @@
 
 <metric>
   name: Errors
+  unit: Count of errors
+  category: General
   window: 60
   conditions: LVL in ["Error"]
   groupbykeys: INSTANCE, DAEMON

monitoring/metrics/ErrorsRmnoded.metric

-# Count of error msg broken down by instance and daemon
+# Count of error from rmnoded
 
 <metric>
   name: ErrorsRmnoded
+  unit: Count of error from rmnoded
+  category: General
   window: 60
   conditions: LVL in ["Error"] and DAEMON in ["rmnoded"]
   groupbykeys: INSTANCE, HOSTNAME

monitoring/metrics/GCFileAgeAlice.metric

@@ -4,6 +4,8 @@
 
 <metric>
   name: GCFileAgeAlice 
+  unit: FileAge in seconds
+  category: ALICE
   window: 900
   conditions: DAEMON=="gcd" and INSTANCE=="c2alice" and GcType=="Automatic"
   groupbykeys: SvcClass

monitoring/metrics/GCFileAgeAtlas.metric

@@ -4,6 +4,8 @@
 
 <metric>
   name: GCFileAgeAtlas
+  unit: FileAge in seconds
+  category: ATLAS
   window: 900
   conditions: DAEMON=="gcd" and INSTANCE=="c2atlas" and GcType=="Automatic"
   groupbykeys: SvcClass

monitoring/metrics/GCFileAgeCms.metric

@@ -4,6 +4,8 @@
 
 <metric>
   name: GCFileAgeCms 
+  unit: FileAge in seconds
+  category: CMS
   window: 900
   conditions: DAEMON=="gcd" and INSTANCE=="c2cms" and GcType=="Automatic"
   groupbykeys: SvcClass

monitoring/metrics/GCFileAgeLhcb.metric

@@ -4,6 +4,8 @@
 
 <metric>
   name: GCFileAgeLhcb 
+  unit: FileAge in seconds
+  category: LHCb
   window: 900
   conditions: DAEMON=="gcd" and INSTANCE=="c2lhcb" and GcType=="Automatic"
   groupbykeys: SvcClass

monitoring/metrics/GCFileAgePublic.metric

@@ -4,6 +4,8 @@
 
 <metric>
   name: GCFileAgePublic 
+  unit: FileAge in seconds
+  category: Public
   window: 900
   conditions: DAEMON=="gcd" and INSTANCE=="c2public" and GcType=="Automatic"
   groupbykeys: SvcClass

monitoring/metrics/GCMigrationAtlas.metric

@@ -4,6 +4,8 @@
 
 <metric>
   name: GCMigrationAtlas
+  unit: FileSie in GB
+  category: ATLAS
   window: 60
   conditions: DAEMON=="tapegatewayd" and INSTANCE=="c2atlas" and MSG=="Worker: updating nameserver for migrated file"
   groupbykeys: NONE
@@ -14,6 +16,8 @@
 
 <metric>
   name: GCMigrationbyTpsrvAtlas
+  unit: FileSize in GB
+  category: ATLAS
   window: 60
   conditions: DAEMON=="tapegatewayd" and INSTANCE=="c2atlas" and MSG=="Worker: updating nameserver for migrated file"
   groupbykeys: HostName
@@ -24,6 +28,8 @@
 
 <metric>
   name: GCMigrationbyFclassAtlas
+  unit: FileSize in GB
+  category: ATLAS
   window: 60
   conditions: DAEMON=="tapegatewayd" and INSTANCE=="c2atlas" and MSG=="Worker: updating nameserver for migrated file"
   groupbykeys: fileClass

monitoring/metrics/GCMigrationCms.metric

@@ -4,6 +4,8 @@
 
 <metric>
   name: GCMigrationCms
+  unit: FileSize in GB
+  category: CMS
   window: 300
   conditions: DAEMON=="tapegatewayd" and INSTANCE=="c2cms" and MSG=="Worker: updating nameserver for migrated file"
   groupbykeys: NONE
@@ -14,6 +16,8 @@
 
 <metric>
   name: GCMigrationbyTpsrvCms
+  unit: FileSize in GB
+  category: CMS
   window: 300
   conditions: DAEMON=="tapegatewayd" and INSTANCE=="c2cms" and MSG=="Worker: updating nameserver for migrated file"
   groupbykeys: HostName
@@ -24,6 +28,8 @@
 
 <metric>
   name: GCMigrationbyFclassCms
+  unit: FileSize in GB
+  category: CMS
   window: 300
   conditions: DAEMON=="tapegatewayd" and INSTANCE=="c2cms" and MSG=="Worker: updating nameserver for migrated file"
   groupbykeys: fileClass
@@ -34,6 +40,8 @@
 
 <metric>
   name: GCMigrationbyTpPoolCms
+  unit: FileSize in GB
+  category: CMS
   window: 300
   conditions: DAEMON=="tapegatewayd" and INSTANCE=="c2cms" and MSG=="Worker: updating nameserver for migrated file"
   groupbykeys: tapePool