Add set of standard alarms to logback.xml

This is a "working" typology which I consider open to additions or modifications.  

Target: trunk
Patch: http://rb.dcache.org/r/5176
Merge: 2.5
Require-book: yes
Require-notes: yes
Acked-by: Dmitry

Tested deployed dCache as far as feasible to ensure that the various types were recognized and displayed on the alarms page.

RELEASE NOTES:

The following alarm definitions are now included with the standard dCache distribution:

           TYPE                          [SEVERITY]
--------------------------------------------------------------------------------------
           SERVICE_CREATION_FAILURE      [CRITICAL]
           DB_OUT_OF_CONNECTIONS         [CRITICAL]
           DB_UNAVAILABLE                [CRITICAL]
           JVM_OUT_OF_MEMORY             [CRITICAL]
           OUT_OF_FILE_DESCRIPTORS       [CRITICAL]
           IO_ERROR                      [HIGH]
           HSM_READ_FAILURE              [HIGH]
           HSM_WRITE_FAILURE             [HIGH]
           LOCATION_MANAGER_UNAVAILABLE  [HIGH]
           POOL_MANAGER_UNAVAILABLE      [HIGH]
           POOL_DISABLED                 [MODERATE]
           CHECKSUM                      [MODERATE]

Their full definitions may be inspected in the logback.xml file found in /etc/dcache.

Author: alrossi

skel/etc/logback.xml

@@ -122,13 +122,93 @@
           to its embedded child appender(s)
       -->
       <filter class="org.dcache.alarms.logback.AlarmDefinitionFilter">
+            <alarmType>
+                regex:"(.+) from ac_create",
+                type:SERVICE_CREATION_FAILURE,
+                level:ERROR,
+                severity:CRITICAL,
+                include-in-key:group1 type host domain service
+            </alarmType>
+            <alarmType>
+                regex:"Failed to acquire connection.+Attempts left: 0",
+                type:DB_OUT_OF_CONNECTIONS,
+                level:ERROR,
+                severity:CRITICAL,
+                include-in-key:type host
+            </alarmType>
+            <alarmType>
+                regex:"Unable to open a test connection to the given database|Connections could not be acquired from the underlying database",
+                match-exception:true,
+                depth:1,
+                type:DB_UNAVAILABLE,
+                level:ERROR,
+                severity:CRITICAL,
+                include-in-key:type host
+            </alarmType>
+            <alarmType>
+                regex:"OutOfMemory",
+                type:JVM_OUT_OF_MEMORY,
+                level:ERROR,
+                severity:CRITICAL,
+                include-in-key:type host domain
+            </alarmType>
+            <alarmType>
+                regex:"[Tt]oo many open files",
+                type:OUT_OF_FILE_DESCRIPTORS,
+                match-exception:true,
+                level:ERROR,
+                severity:CRITICAL,
+                include-in-key:type host domain
+            </alarmType>
+            <alarmType>
+                regex:"I/O.*failed(.+)|I/O error occur.*ed(.+)",
+                type:IO_ERROR,
+                level:WARN,
+                severity:HIGH,
+                include-in-key:group1 type host service domain
+            </alarmType>
+            <alarmType>
+                regex:"Fetch failed: HSM script failed",
+                type:HSM_READ_FAILURE,
+                level:WARN,
+                severity:HIGH,
+                include-in-key:type host service domain
+            </alarmType>
+            <alarmType>
+                regex:"Store failed: HSM script failed",
+                type:HSM_WRITE_FAILURE,
+                level:WARN,
+                severity:HIGH,
+                include-in-key:type host service domain
+            </alarmType>
+            <alarmType>
+                regex:"Timeout querying location manager",
+                type:LOCATION_MANAGER_UNAVAILABLE,
+                level:WARN,
+                severity:HIGH,
+                include-in-key:type host service domain
+            </alarmType>
+            <alarmType>
+                regex:"PoolManager.+not found",
+                type:POOL_MANAGER_UNAVAILABLE,
+                level:WARN,
+                severity:HIGH,
+                include-in-key:type host service domain
+            </alarmType>
+            <alarmType>
+                regex:"Pool mode changed to disabled",
+                type:POOL_DISABLED,
+                level:WARN,
+                severity:MODERATE,
+                include-in-key:type host service domain
+            </alarmType>
             <alarmType>
                 logger:org.dcache.pool.classic.ChecksumScanner,
-                regex:"Checksum mismatch",
+                regex:"Checksum mismatch detected for (.+) - marking as BROKEN",
                 type:CHECKSUM,
                 level:ERROR,
                 severity:MODERATE,
-                include-in-key:message type host service domain
+                include-in-key:group1 type host service domain
             </alarmType>
       </filter>
       <appender-ref ref="remote"/>