Edit D:\app\Administrator\product\11.2.0\dbhome_1\sysman\admin\default_collection\osm_instance.xml
<!-- $Header: emdb/sysman/admin/default_collection/osm_instance.xml /st_emdbsa_11.2/9 2009/03/13 10:02:56 mpawelko Exp $ MODIFIED (MM/DD/YY) mpawelko 03/09/09 - 8316983: change ofs_performance_metrics to 1 hr mpawelko 02/20/09 - 6996096: split performance metrics into 2 collections fagonzal 02/18/09 - Adding checker failures alert ajdsouza 02/17/09 - added resource_name and ishasmanaged metric collections mnihalan 09/08/08 - Change 11gR1TB to 11gR1 mnihalan 08/29/08 - Fix bug 7342407 yozhang 08/11/08 - Name change OFS to ACFS asubba 07/29/08 - diskgroup size alert enhancemnt mnihalan 04/17/08 - Fix alert message for OFS dchakumk 03/10/08 - XbranchMerge dchakumk_6752_xbmsrc from st_emdbsa_11.1 mnihalan 02/11/08 - Add collection for Volume Performance metrics mnihalan 01/25/08 - Change OFS alerts mnihalan 01/23/08 - Fix OFS bug 6754205 fagonzal 12/06/07 - Adding/updating alert log metrics asubba 09/25/07 - XbranchMerge asubba_ui_improvements from main mpawelko 08/30/07 - XbranchMerge mpawelko_bug-6266985 from main jsoule 08/07/07 - collect ADR alert metrics qsong 07/02/07 - bug 6165631 - combine all the diskgroup metrics (which has 15 minutes as default time interval) into one collection item mpawelko 04/18/07 - bug 6003984: fix failure group unavailable; add review changes mpawelko 03/14/07 - add new imbalance and failure group metrics mpawelko 03/14/07 - add new imbalance and failure group metrics mpawelko 03/14/07 - add new imbalance and failure group metrics qsong 03/06/07 - remove dg rebalance metric qsong 10/23/06 - bug 5619037, combine all the disk/diskgroup related metrics to one collection item qsong 11/03/06 - chanchan 10/13/06 - qsong 03/23/06 - qsong 10/23/06 - bug 5619037, combine all the disk/diskgroup related metrics to one collection item mnihalan 08/02/06 - Fix bug 5406081 qsong 07/11/06 - ajdsouza 07/27/05 - collect disk_path once a day rajeshar 05/11/05 - bug 4350509 rajeshar 04/07/05 - bug 4094328 rajeshar 03/14/05 - bug 4191804 jochen 12/21/04 - Fix NLS resources rajeshar 12/08/04 - Changing the collection time for 10gR1 and 10gR2 bug 3590905 jochen 11/04/04 - Alert on percent used for 10.2 jochen 07/29/04 - Add failure reason to response alert ychan 07/12/04 - Remove 10gBeta jochen 06/25/04 - Use asm_disk_stat and asm_diskgroup_stat jochen 06/24/04 - Add mode_status=offline alert jochen 06/21/04 - Add media failures rreilly 06/07/04 - add asm ( osm ) policies sbadrina 05/10/04 - jochen 03/31/04 - Fix read_write_err alert lhan - Multiple edits spanchum 10/14/02 - Initial file creation for 10gR1 --> <TargetCollection TYPE="osm_instance" LEVEL="Oracle Recommended"> <CollectionLevel NAME="Minimum"/> <CollectionLevel NAME="Oracle Recommended"/> <CollectionItem NAME="Response"> <Schedule> <IntervalSchedule INTERVAL="5" TIME_UNIT="Min"/> </Schedule> <Condition COLUMN_NAME="Status" CRITICAL="0" OPERATOR="EQ" MESSAGE="Failed to connect to ASM instance. %oraerr%" MESSAGE_NLSID="Response_Status_alertmessage" /> </CollectionItem> <!-- ================================================================== == DiskGroup_Usage - 10.2+ ================================================================== --> <!-- We are alerting on both percent_used and safe_percent_used because in the case that this 10.2 agent is talking to a 10.1 OMS, the Disk Groups Space page (link from host home page) displays status based on the percent_used threshold values. If these threshold values don't exist, the status comes up empty. If we decide not to support the 10.1 OMS, remove the percent_used, since it has the side effect of causing 2 alerts for basically the same thing, and safe_percent_used should supersede percent_used - Bug #3972557 Due to bug 4350509 merging borh collection into one and it will work for 10gR1 and 10gR2 --> <CollectionItem NAME="diskgroup_space_usage"> <Schedule> <IntervalSchedule INTERVAL="15" TIME_UNIT="Min"/> </Schedule> <MetricColl NAME="DiskGroup_Usage"> <Condition COLUMN_NAME="percent_used" CRITICAL="90" WARNING="75" OPERATOR="GT" MESSAGE="Disk Group %dg_name% is %value%%% used." MESSAGE_NLSID="DiskGroup_Usage_alertmessage"/> <Condition COLUMN_NAME="safe_percent_used" CRITICAL="90" WARNING="75" OPERATOR="GT" MESSAGE="Disk group %dg_name% has used %value%%% of safely usable free space (space that can be allocated while still having enough space to recover from failure group failures)." MESSAGE_NLSID="DiskGroup_102_usage_alertmessage"/> <Condition COLUMN_NAME="free_mb" CRITICAL="NotDefined" WARNING="NotDefined" OPERATOR="LE" MESSAGE="Total free size for Disk Group %dg_name% has fallen to %value% (MB)." MESSAGE_NLSID="Diskgroup_Free_Size_alertmessage"/> <Condition COLUMN_NAME="usable_file_mb" CRITICAL="NotDefined" WARNING="NotDefined" OPERATOR="LE" MESSAGE="Usable free size for Disk Group %dg_name% has fallen to %value% (MB)." MESSAGE_NLSID="Diskgroup_Usable_Free_Size_alertmessage"/> </MetricColl> <MetricColl NAME="Database_DiskGroup_Usage"/> <MetricColl NAME="Volumes_Summary"/> <MetricColl NAME="Single_Instance_OFS_Summary"> <Condition COLUMN_NAME="ofs_corrupted_state" CRITICAL="TRUE" OPERATOR="EQ" MESSAGE="The ASM Cluster File System using volume device %ofs_volume_device% has sections that are corrupt. Run check and repair operation on the file system to fix the issue." MESSAGE_NLSID="OFS_Response_Corrupted_alertmessage" CLEAR_MESSAGE="CLEARED - The ASM Cluster File System using volume device %ofs_volume_device% has sections that are corrupt." CLEAR_MESSAGE_NLSID="OFS_Response_Corrupted_alertmessage_clear"/> <Condition COLUMN_NAME="ofs_used_pct" CRITICAL="97" WARNING="85" OPERATOR="GT" MESSAGE="The ASM Cluster File System using volume device %ofs_volume_device% is %ofs_used_pct%%% full. Resize the file system to add more space." MESSAGE_NLSID="OFS_Space_Usage_alertmessage" CLEAR_MESSAGE="CLEARED - The ASM Cluster File System using volume device %ofs_volume_device% is %ofs_used_pct%%% full." CLEAR_MESSAGE_NLSID="OFS_Space_Usage_alertmessage_clear"/> </MetricColl> </CollectionItem> <CollectionItem NAME="Disk_Path"> <ValidIf> <CategoryProp NAME="VersionCategory" CHOICES="10gR2;11gR1;11gR2"/> </ValidIf> <Schedule> <IntervalSchedule INTERVAL="24" TIME_UNIT="Hr"/> </Schedule> </CollectionItem> <!-- ====================================================================== == Note: Collection time for single-instance Instance_Disk_Performance, == Instance_DiskGroup_Performance, and Single_Instance_DiskGroup_Performance == metrics. ====================================================================== --> <CollectionItem NAME="performance_metrics" COLLECT_WHEN_ALTSKIP="TRUE"> <Schedule> <IntervalSchedule INTERVAL="15" TIME_UNIT="Min"/> </Schedule> <MetricColl NAME="Instance_Disk_Performance"> <Condition COLUMN_NAME="read_write_errs" CRITICAL="0" OPERATOR="GT" MESSAGE="Disk %dg_name%.%disk_name% has %value% Read/Write errors." MESSAGE_NLSID="Disk_ReadWrite_alertmessage"/> </MetricColl> <MetricColl NAME="Instance_DiskGroup_Performance"/> <MetricColl NAME="Single_Instance_DiskGroup_Performance"/> </CollectionItem> <!-- ====================================================================== == Note: Collection time for cluster-wide Disk_Performance and == DiskGroup_Performance metrics. Collection time is 60 minutes to == reduce load on cluster since each agent for each instance collects == this data. (bug 6996096) ====================================================================== --> <CollectionItem NAME="cluster_performance_metrics" COLLECT_WHEN_ALTSKIP="TRUE"> <Schedule> <IntervalSchedule INTERVAL="1" TIME_UNIT="Hr"/> </Schedule> <MetricColl NAME="Disk_Performance"/> <MetricColl NAME="DiskGroup_Performance"/> </CollectionItem> <CollectionItem NAME="ofs_performance_metrics" COLLECT_WHEN_ALTSKIP="TRUE"> <Schedule> <IntervalSchedule INTERVAL="1" TIME_UNIT="Hr"/> </Schedule> <MetricColl NAME="Instance_Volume_Performance"/> <MetricColl NAME="Volume_Performance"/> </CollectionItem> <!-- ====================================================================== == Group: alert_log_rollup ====================================================================== --> <CollectionItem NAME="alert_log_rollup" COLLECT_WHEN_ALTSKIP="TRUE"> <ValidIf> <CategoryProp NAME="VersionCategory" CHOICES="10gR1;10gR2"/> </ValidIf> <Schedule> <IntervalSchedule INTERVAL="5" TIME_UNIT="Min"/> </Schedule> <!-- ==================================================================== == Category: Alert Log == Fetchlet: Perl == (NB: An alert log error stack never contributes to more than one == event.) == User Properties: ignorePattern - Perl regular expression used to == suppress specific ORA-errors ==================================================================== --> <MetricColl NAME="alertLog"> <!-- ================================================================== == User Property: pattern to ignore ================================================================== --> <ItemProperty NAME="ignorePattern">.*ORA-0*(54|1142|1146)\D.*</ItemProperty> <!-- ================================================================== == Alert: Alert Log Error Stack ================================================================== --> <Condition COLUMN_NAME="genericErrStack" WARNING="ORA-0*(600?|7445|4[0-9][0-9][0-9])[^0-9]" OPERATOR="MATCH" MESSAGE="ORA-error stack (%errCodes%) logged in %alertLogName%." MESSAGE_NLSID="alertLog_genericErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE" /> <!-- ================================================================== == Alert: Archiver Hung Error Stack ================================================================== --> <Condition COLUMN_NAME="archiveHungErrStack" CRITICAL="ORA-" OPERATOR="CONTAINS" MESSAGE="The archiver hung at time/line number: %timeLine%." MESSAGE_NLSID="alertLog_archiveHungErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE" /> <!-- ================================================================== == Alert: Data Block Corruption Error Stack ================================================================== --> <Condition COLUMN_NAME="blockCorruptErrStack" CRITICAL="ORA-" OPERATOR="CONTAINS" MESSAGE="A data block was corrupted at time/line number: %timeLine%." MESSAGE_NLSID="alertLog_blockCorruptErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE" /> <!-- ================================================================== == Alert: Session Terminated Error Stack ================================================================== --> <Condition COLUMN_NAME="sessTerminateErrStack" WARNING="ORA-" OPERATOR="CONTAINS" MESSAGE="A session was terminated at time/line number: %timeLine%." MESSAGE_NLSID="alertLog_sessTerminateErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE" /> <!-- ================================================================== == Alert: Media Failure Error Stack ================================================================== --> <Condition COLUMN_NAME="mediaFailureErrStack" CRITICAL="ORA-" OPERATOR="CONTAINS" MESSAGE="Media failure was detected at time/line number: %timeLine%." MESSAGE_NLSID="alertLog_mediaFailureErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE" /> </MetricColl> <!-- ==================================================================== == Category: Alert Log Error Status == Fetchlet: Aggregation ==================================================================== --> <MetricColl NAME="alertLogStatus"> <!-- ================================================================== == User Property: pattern to ignore ================================================================== --> <ItemProperty NAME="ignorePattern">.*ORA-0*(54|1142|1146)\D.*</ItemProperty> <!-- ================================================================== == Alert: Generic Alert Log Errors ================================================================== --> <Condition COLUMN_NAME="genericErrors" WARNING="0" OPERATOR="GT" MESSAGE="%value% distinct types of ORA- errors have been found in the alert log." MESSAGE_NLSID="alertLogStatus_genericErrors_alertmessage" /> <!-- ================================================================== == Alert: Archiver Hung Errors ================================================================== --> <Condition COLUMN_NAME="archiveHungErrors" WARNING="0" OPERATOR="GT" MESSAGE="Archiver hung errors have been found in the alert log." MESSAGE_NLSID="alertLogStatus_archiveHungErrors_alertmessage" /> <!-- ================================================================== == Alert: Data Block Corruption Errors ================================================================== --> <Condition COLUMN_NAME="blockCorruptErrors" WARNING="0" OPERATOR="GT" MESSAGE="Data block corruption errors have been found in the alert log." MESSAGE_NLSID="alertLogStatus_blockCorruptErrors_alertmessage" /> <!-- ==================================================================== == Alert: Session Terminated Error Stack ==================================================================== --> <Condition COLUMN_NAME="sessTerminateErrors" WARNING="0" OPERATOR="GT" MESSAGE="Session terminations have been found in the alert log." MESSAGE_NLSID="alertLogStatus_sessTerminateErrors_alertmessage" /> <!-- ================================================================== == Alert: Media Failure Errors ================================================================== --> <Condition COLUMN_NAME="mediaFailureErrors" WARNING="0" OPERATOR="GT" MESSAGE="Media failure errors have been found in the alert log." MESSAGE_NLSID="alertLogStatus_mediaFailureErrors_alertmessage" /> </MetricColl> </CollectionItem> <!-- ==================================================================== == Collection Item: ASM Policies == Collection Interval: Once every 7 Days ==================================================================== --> <CollectionItem NAME="oracle_osm" UPLOAD_ON_FETCH="TRUE" CONFIG="TRUE"> <Schedule> <IntervalSchedule INTERVAL = "7" TIME_UNIT = "Day"/> </Schedule> <MetricColl NAME="osm_diskGroupPolicies"/> </CollectionItem> <!-- ====================================================================== == Fetchlet: SQL == due to bug 4350509 we have to keep the conservation interval of 15 minutes == for Grid Control it will be 15 minutes as it can run agaisnt 10gR1 target == where performance of query is bad due to bug 4365041 == for 10.2SA it will be 3 minutes as it run against 10.2ASM where no performance issue ====================================================================== --> <CollectionItem NAME="disk_status"> <Schedule> <IntervalSchedule INTERVAL="15" TIME_UNIT="Min" /> </Schedule> <!-- ==================================================================== == Metric disk_status == Alert: disk mode_status OFFLINE for each offline disk ==================================================================== --> <MetricColl NAME="disk_status" TRANSIENT="TRUE"> <Condition COLUMN_NAME="mode_status" CRITICAL="OFFLINE" OPERATOR="EQ" MESSAGE="Disk %dg_name%.%disk_name% is offline." MESSAGE_NLSID="modeStatusErr_alertmessage" /> </MetricColl> <!-- ==================================================================== == Metric disk_status_rollup == Alert: Count of all disks offline ==================================================================== --> <MetricColl NAME="disk_status_rollup"> <!-- ========== To avoid flooding the repository with data, we only send the offline disk count if it is different than it was the last sample. ========== --> <Filter COLUMN_NAME="delta_offline" OPERATOR="NE" AFTER_SEVERITY_CHECKING="TRUE"> </Filter> <Condition COLUMN_NAME="offline_count" CRITICAL="0" OPERATOR="GT" UPLOAD_IF_SEVERITY="CHANGE_ONLY" MESSAGE="%offline_count% disks are offline." MESSAGE_NLSID="modeStatusCount_alertmessage" /> </MetricColl> </CollectionItem> <!-- ================================================================== == OFS related Metrics ================================================================== --> <CollectionItem NAME="ofs_collections"> <Schedule> <IntervalSchedule INTERVAL="5" TIME_UNIT="Min" /> </Schedule> <MetricColl NAME="OFS_State"> <Condition COLUMN_NAME="ofs_availability" CRITICAL="NOT AVAILABLE" OPERATOR="EQ" MESSAGE="The ASM Cluster File System %ofs_mount_point% is not available on host %ofs_host%." MESSAGE_NLSID="OFS_Response_Status_alertmessage" CLEAR_MESSAGE="CLEARED - The ASM Cluster File System %ofs_mount_point% is not available on host %ofs_host%." CLEAR_MESSAGE_NLSID="OFS_Response_Status_alertmessage_clear"/> <Condition COLUMN_NAME="ofs_mount_state" WARNING="DISMOUNTED" OPERATOR="EQ" MESSAGE="The volume device %volume_device% is dismounted on host %ofs_host%" MESSAGE_NLSID="OFS_Mount_State_alertmessage" CLEAR_MESSAGE="CLEARED - The volume device %volume_device% is dismounted on host %ofs_host%" CLEAR_MESSAGE_NLSID="OFS_Mount_State_alertmessage_clear"/> </MetricColl> </CollectionItem> <!-- ================================================================== == diskgroup_failgroup_checks (3 metrics) == == 1. diskgroup_fg_imbalance (ASM failure group imbalance) == Purpose: For NORMAL or HIGH redundancy, alert on partner count == (different number of disks) and/or partner space (disks of == different sizes) imbalance == == 2.diskgroup_imbalance (ASM disk group imbalance) == Purpose: Alert when disk group requires rebalance, disk group == requires configuration change (e.g. increase storage) and == when a rebalance in progress requires a power boost. == == 3. unavailable_failure_group (ASM unavailable failure group) == Purpose: Alert on failure groups with all member disks offline ================================================================== --> <CollectionItem NAME="diskgroup_failgroup_checks"> <Schedule> <IntervalSchedule INTERVAL="15" TIME_UNIT="Min" /> </Schedule> <MetricColl NAME="diskgroup_fg_imbalance"> <Condition COLUMN_NAME="pImbalance" WARNING="2" OPERATOR="GE" CLEAR_MESSAGE="CLEARED - Disk Group %diskGroup% has failure groups with different numbers of disks which may lead to suboptimal space usage. Changing the configuration may alleviate this problem." CLEAR_MESSAGE_NLSID="diskGroupFGPImbalanceRebalance_alertmessage_clear" MESSAGE="Disk Group %diskGroup% has failure groups with different numbers of disks which may lead to suboptimal space usage. Changing the configuration may alleviate this problem." MESSAGE_NLSID="diskGroupFGPImbalance_alertmessage" /> <Condition COLUMN_NAME="sImbalance" WARNING="10" OPERATOR="GT" CLEAR_MESSAGE="CLEARED - Disk Group %diskGroup% has failure groups with disks of different sizes which may lead to suboptimal space usage. Changing the configuration may alleviate this problem." CLEAR_MESSAGE_NLSID="diskGroupFGSImbalance_alertmessage_clear" MESSAGE="Disk Group %diskGroup% has failure groups with disks of different sizes which may lead to suboptimal space usage. Changing the configuration may alleviate this problem." MESSAGE_NLSID="diskGroupFGSImbalance_alertmessage" /> </MetricColl> <MetricColl NAME="diskgroup_imbalance"> <Condition COLUMN_NAME="computedImbalance" WARNING="10" OPERATOR="GT" CLEAR_MESSAGE="CLEARED - Disk Group %diskGroup% requires rebalance because the space usage imbalance between disks is high." CLEAR_MESSAGE_NLSID="diskGroupRebalance_alertmessage_clear" MESSAGE="Disk Group %diskGroup% requires rebalance because the space usage imbalance between disks is high." MESSAGE_NLSID="diskGroupRebalance_alertmessage" /> <Condition COLUMN_NAME="computedMinFree" WARNING="20" CRITICAL="10" OPERATOR="LT" CLEAR_MESSAGE="CLEARED - Disk Group %diskGroup% requires rebalance because at least one disk is low on space." CLEAR_MESSAGE_NLSID="diskGroupRebalance2_alertmessage_clear" MESSAGE="Disk Group %diskGroup% requires rebalance because at least one disk is low on space." MESSAGE_NLSID="diskGroupRebalance2_alertmessage" /> <Condition COLUMN_NAME="computedMaxUsed" CRITICAL="95" OPERATOR="GT" CLEAR_MESSAGE="CLEARED - Increase the rebalance power for Disk Group %diskGroup% because at least one disk is critically low on space." CLEAR_MESSAGE_NLSID="diskGroupRebalanceInProg_alertmessage_clear" MESSAGE="Increase the rebalance power for Disk Group %diskGroup% because at least one disk is critically low on space." MESSAGE_NLSID="diskGroupRebalanceInProg_alertmessage" /> </MetricColl> <MetricColl NAME="unavailable_failure_group"> <Condition COLUMN_NAME="fgAlertDiskCount" CRITICAL="0" OPERATOR="EQ" CLEAR_MESSAGE="CLEARED - Failure Group %diskGroup%.%failureGroup% is offline." CLEAR_MESSAGE_NLSID="failureGroupUnavailable_alertmessage_clear" MESSAGE="Failure Group %diskGroup%.%failureGroup% is offline." MESSAGE_NLSID="failureGroupUnavailable_alertmessage" /> </MetricColl> </CollectionItem> <!-- ====================================================================== == Group: Incident Meter ====================================================================== --> <CollectionItem NAME="incident_meter"> <Schedule> <IntervalSchedule INTERVAL="5" TIME_UNIT="Min"/> </Schedule> <!-- ====================================================================== == Category: Collect Incident Meter == Fetchlet: SQL ====================================================================== --> <MetricColl NAME="incident_meter"/> </CollectionItem> <!-- ====================================================================== == Group: adr_alert_log_rollup ====================================================================== --> <CollectionItem NAME="adr_alert_log_rollup" COLLECT_WHEN_ALTSKIP="TRUE" COLLECT_WHEN_DOWN="TRUE"> <ValidIf> <CategoryProp NAME="VersionCategory" CHOICES="11gR1;11gR2"/> </ValidIf> <Schedule> <IntervalSchedule INTERVAL="5" TIME_UNIT="Min"/> </Schedule> <MetricColl NAME="adrAlertLogError"> </MetricColl> <!-- ==================================================================== == Category: ADR Alert Log Incident Error == Fetchlet: Perl == (NB: An alert log error stack never contributes to more than one == event.) ==================================================================== --> <MetricColl NAME="adrAlertLogIncidentError"> <!-- ================================================================== == Alert: Generic Incident Error Stack ================================================================== --> <Condition COLUMN_NAME="genericIncidentErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="Incident (%errCodes%) detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_genericIncidentErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Generic Internal Error Stack ================================================================== --> <Condition COLUMN_NAME="genericInternalErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="Internal error (%errCodes%) detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_genericInternalErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Session Terminated Error Stack ================================================================== --> <Condition COLUMN_NAME="sessTerminateErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="A session termination detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_sessTerminateErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Internal SQL Error Stack ================================================================== --> <Condition COLUMN_NAME="internalSqlErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="An internal SQL error detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_internalSqlErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Access Violation Error Stack ================================================================== --> <Condition COLUMN_NAME="accessViolationErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="An access violation detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_accessViolationErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: File Access Error Stack ================================================================== --> <Condition COLUMN_NAME="fileAccessErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="A file access error detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_fileAccessErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Out of Memory Error Stack ================================================================== --> <Condition COLUMN_NAME="outOfMemoryErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="Out of memory detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_outOfMemoryErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Cluster Error Stack ================================================================== --> <Condition COLUMN_NAME="clusterErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="A cluster error detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_clusterErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Deadlock Error Stack ================================================================== --> <Condition COLUMN_NAME="deadlockErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="A deadlock error detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_deadlockErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: ASM Block Corruption Error Stack ================================================================== --> <Condition COLUMN_NAME="asmBlockCorruptionErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="An ASM data block was corrupted at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_asmBlockCorruptionErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Redo Log Corruption Error Stack ================================================================== --> <Condition COLUMN_NAME="redoLogCorruptionErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="A data block was corrupted at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_redoLogCorruptionErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> </MetricColl> <!-- ==================================================================== == Category: ADR Alert Log Operational Error == Fetchlet: Perl == (NB: An alert log error stack never contributes to more than one == event.) ==================================================================== --> <MetricColl NAME="adrAlertLogOperationalError"> <!-- ================================================================== == Alert: Generic Operational Error Stack ================================================================== --> <Condition COLUMN_NAME="genericOperationalErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="Operational error (%errCodes%) detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_genericOperationalErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Data Block Corruption Error Stack ================================================================== --> <Condition COLUMN_NAME="dataBlockCorruptionErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="A data block was corrupted at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_dataBlockCorruptionErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> <!-- ================================================================== == Alert: Media Failure Error Stack ================================================================== --> <Condition COLUMN_NAME="mediaFailureErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="Media failure detected in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_mediaFailureErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> </MetricColl> <!-- ==================================================================== == Category: ADR Alert Log Checker Failure == Fetchlet: Perl == (NB: An alert log error stack never contributes to more than one == event.) ==================================================================== --> <MetricColl NAME="adrAlertLogCheckerFailure"> <!-- ================================================================== == Alert: Data Failure Error Stack ================================================================== --> <Condition COLUMN_NAME="genericCheckerFailureErrStack" CRITICAL=".*" OPERATOR="MATCH" MESSAGE="Health checker runs found %numberOfFailures% new failures in %alertLogName% at time/line number: %timeLine%." MESSAGE_NLSID="adrAlertLog_genericCheckerFailureErrStack_alertmessage" NO_CLEAR_ON_NULL="TRUE"/> </MetricColl> <!-- ==================================================================== == Category: ADR Alert Log Incident Error Status == Fetchlet: Aggregation ==================================================================== --> <MetricColl NAME="adrAlertLogIncidentErrorStatus"> <!-- ================================================================== == Alert: Generic Incident Errors ================================================================== --> <Condition COLUMN_NAME="genericIncidentErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="%value% distinct types of incidents have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_genericIncidentErrors_alertmessage"/> <!-- ================================================================== == Alert: Generic Internal Errors ================================================================== --> <Condition COLUMN_NAME="genericInternalErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Generic internal errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_genericInternalErrors_alertmessage"/> <!-- ==================================================================== == Alert: Session Terminated Errors ==================================================================== --> <Condition COLUMN_NAME="sessTerminateErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Session terminations have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_sessTerminateErrors_alertmessage"/> <!-- ==================================================================== == Alert: Internal SQL Errors ==================================================================== --> <Condition COLUMN_NAME="internalSqlErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Internal SQL errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_internalErrors_alertmessage"/> <!-- ==================================================================== == Alert: Access Violation Errors ==================================================================== --> <Condition COLUMN_NAME="accessViolationErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Access violation errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_accessViolationErrors_alertmessage"/> <!-- ==================================================================== == Alert: File Access Errors ==================================================================== --> <Condition COLUMN_NAME="fileAccessErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="File access errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_fileAccessErrors_alertmessage"/> <!-- ==================================================================== == Alert: Out of Memory Errors ==================================================================== --> <Condition COLUMN_NAME="outOfMemoryErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Out of memory errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_outOfMemoryErrors_alertmessage"/> <!-- ==================================================================== == Alert: Cluster Errors ==================================================================== --> <Condition COLUMN_NAME="clusterErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Cluster errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_clusterErrors_alertmessage"/> <!-- ==================================================================== == Alert: Deadlock Errors ==================================================================== --> <Condition COLUMN_NAME="deadlockErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Deadlock errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_deadlockErrors_alertmessage"/> <!-- ================================================================== == Alert: ASM Data Block Corruption Errors ================================================================== --> <Condition COLUMN_NAME="asmBlockCorruptionErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="ASM data block corruption errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_asmBlockCorruptionErrors_alertmessage"/> <!-- ================================================================== == Alert: Redo Log Corruption Errors ================================================================== --> <Condition COLUMN_NAME="redoLogCorruptionErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Redo log corruption errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_redoLogCorruptionErrors_alertmessage"/> </MetricColl> <!-- ==================================================================== == Category: ADR Alert Log Operational Error Status == Fetchlet: Aggregation ==================================================================== --> <MetricColl NAME="adrAlertLogOperationalErrorStatus"> <!-- ================================================================== == Alert: Generic Operational Errors ================================================================== --> <Condition COLUMN_NAME="genericOperationalErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="%value% distinct types of operational errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_genericOperationalErrors_alertmessage"/> <!-- ================================================================== == Alert: Data Block Corruption Errors ================================================================== --> <Condition COLUMN_NAME="dataBlockCorruptionErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Data block corruption errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_dataBlockCorruptionErrors_alertmessage" /> <!-- ================================================================== == Alert: Media Failure Errors ================================================================== --> <Condition COLUMN_NAME="mediaFailureErrors" CRITICAL="0" OPERATOR="GT" MESSAGE="Media failure errors have been found in the alert log." MESSAGE_NLSID="adrAlertLogStatus_mediaFailureErrors_alertmessage" /> </MetricColl> </CollectionItem> <!-- ====================================================================== == collection cluster_resource_name ====================================================================== --> <CollectionItem NAME="cluster_resource_name" UPLOAD_ON_FETCH="TRUE" > <Schedule OFFSET_TYPE="INCREMENTAL"> <IntervalSchedule INTERVAL="6" TIME_UNIT="Hr"/> </Schedule> <MetricColl NAME="cluster_resource_name"/> </CollectionItem> </TargetCollection>
Ms-Dos/Windows
Unix
Write backup
jsp File Browser version 1.2 by
www.vonloesch.de