E-MapReduce (EMR) Serverless StarRocks provides the monitoring report feature that allows you to obtain and view the status and key performance metrics of EMR Serverless StarRocks instances in real time. This helps you identify issues in an efficient manner.
Limits
Only report data within the previous 30 days is retained. After the retention period expires, data is no longer retained.
Precautions
Some metrics are specific to the root account, such as the metric Queries per Minute. The root account is a dedicated account used to manage StarRocks instances. Users cannot view and use the root account.
Procedure
Go to the Instances tab of the E-MapReduce (EMR) console.
Log on to the EMR console.
In the left-side navigation pane, choose .
In the top navigation bar, select a region based on your business requirements.
On the Instances tab, find the EMR Serverless StarRocks instance that you want to manage and click its name.
On the instance details page, click the Monitoring and Alerting tab.
On the Monitoring Reports tab, filter metrics by resource group and time period.
You can view the monitoring data of the following resource groups:
default_wg: the default resource group of query tasks.
default_mv_wg: the default resource group of materialized views.
Metrics
Instance
Overview
Metric
Description
FE Availability
The availability of frontends (FEs).
FEs
The number of FEs.
FE Detection Status
The detection status of FEs. EMR Serverless StarRocks detects the status of FEs by sending HTTP requests. On indicates that the detection result is normal, and Off indicates that the detection fails.
BE or CN Availability
The availability of backends (BEs) or compute nodes (CNs).
BEs or CNs
The number of BEs or CNs.
BE or CN Detection Status
The detection status of BEs or CNs. EMR Serverless StarRocks detects the status of BEs or CNs by sending HTTP requests. On indicates that the detection result is normal, and Off indicates that the detection fails.
Disk Usage (Avg)
The average disk usage of all BEs in the cluster.
Compaction Score (Max)
The highest compaction score of all FEs.
Queries per Minute
The number of SELECT queries that are run per minute on each FE.
Storage Size
The total amount of data that can be stored. Unit: GiB.
NoteThis metric is applicable only to compute-storage separation scenarios. The latency of data updates is 1 hour.
Query
Metric
Description
Queries per Minute
The number of query tasks per minute.
Queries per Minute (Resource Group)
The number of query tasks per minute in the selected resource group.
Query Latency
The 99th percentile query latency.
Query Latency (Resource Group)
The 99th percentile query latency in the selected resource group.
Query Failures per Minute
The number of query failures per minute.
FE
Metric
Description
FE CPU Utilization
The CPU utilization of each FE.
FE CPU Load 1min
The average CPU load of each FE in the previous minute.
FE Memory Usage
The memory usage of each FE.
FE Available Memory
The size of available memory on each FE.
FE Connections
The number of active connections to each FE.
FE Transaction Status Statistics
The transaction status statistics per minute of each FE.
Materialized View
Metric
Description
Materialized View Status
The status of each materialized view. Valid values: 0 and 1. A value of 0 indicates that the materialized view is active, and a value of 1 indicates that the materialized view is inactive.
99th Percentile Refresh Duration
The amount of time required to refresh each materialized view.
Refresh Tasks
The total number of refresh tasks.
Successful Refresh Tasks
The number of successful refresh tasks.
Failed Refresh Tasks
The number of failed refresh tasks.
Empty Refresh Tasks
The number of refresh tasks that are canceled because no new data is available.
Running Refresh Tasks
The number of refresh tasks that are in progress.
Pending Refresh Tasks
The number of refresh tasks that wait to be run.
Query Rewritings
The number of queries that are rewritten on each materialized view, excluding the queries that are directly run on materialized views.
Queries
The number of queries that are rewritten on each materialized view, including the queries that are directly run on materialized views.
Database and Table Information
Metric
Description
Database Table Distribution
The distribution of tables across databases in the instance.
Tables
The number of tables in each database in the instance.
Tablets
The number of tablets on each BE in the instance.
Data Scanned from Tables
The total amount of data scanned from each non-system table. Unit: bytes.
Data Imported to Tables
The total amount of data imported to each non-system table. Unit: bytes.
Others
Metric
Description
Migration Tool: Table Migration Progress
The progress of table migration. This metric is applicable only to cluster migration scenarios.
Warehouse
Overview
Metric
Description
CPU Utilization (Avg)
The average CPU utilization of all BEs or CNs.
Memory Usage (Avg)
The average memory usage of all BEs or CNs.
Disk Usage (Max)
The maximum usage of multiple data disks of all BEs or CNs.
Compaction Score (Max)
The highest compaction score of all nodes. This value reflects the current compaction pressure.
Node Detection Status
The detection status of nodes. EMR Serverless StarRocks detects the status of nodes by sending HTTP requests. On indicates that the detection result is normal, and Off indicates that the detection fails.
Compaction
Metric
Description
Compacted Data per Minute
The amount of data that is compacted per minute during the base compaction and cumulative compaction process.
Compacted Rowsets per Minute
The number of rowsets that are compacted per minute during the base compaction and cumulative compaction process.
Maximum Compaction Score
The highest compaction score of all FEs.
Compaction Memory
The size of memory used by compaction tasks.
BE
Metric
Description
CPU Utilization
The CPU utilization of each BE.
BE CPU Load 1min
The average CPU load of each BE in the previous minute.
Scanned Data in Queries
The amount of data scanned during the queries on each BE.
Scanned Rows in Queries
The number of rows scanned during the queries on each BE.
Request Statistics
The total number of requests on BEs, including requests to create tables, publish versions, and clone tables.
Failed Request Statistics
The total number of failed requests on BEs, including requests to create tables, publish versions, and clone tables.
Transaction Phase Statistics
The statistics of transaction phases per minute.
BE Memory
Metric
Description
Memory Usage
The memory usage of each BE.
Process Memory
The size of memory used by each BE.
Available Memory
The size of available memory on each BE.
Memory Pie Chart {Selected nodes}
The items that consume memory on the selected nodes. You can use the pie chart to roughly view the proportion of memory used by each item.
Memory Stacked Chart {Selected nodes}
BE Disk
Metric
Description
Space Proportion
The disk space proportions of the following items: available space, cache files, data files, and others. Other items include trash and expired data.
Used Space
The total disk space occupied by the following items: available space, cache files, data files, and others. Other items include trash and expired data.
Used Space {Selected nodes}
The disk space occupied by each item on the selected BEs.
Available Space
The available disk space of each BE.
Available Space in Percentage
The percentage of the available space of each BE.
Used Space (Data)
The disk space occupied by data files on each BE.
Space Usage (Data)
The disk usage of data files on each BE.
Used Space (Cache)
The disk space occupied by cache files on each BE.
Space Usage (Cache)
The disk usage of cache files on each BE.
Used Space (Other)
The disk space occupied by other items on each BE. Other items include trash and expired data.
Space Usage (Other)
The disk usage of other items on each BE. Other items include trash and expired data.
Read Traffic (Sum)
The read traffic of all disks per second on each BE.
Read IOPS (Sum)
The number of read operations on all disks per second on each BE.
Read Latency (Avg)
The average read latency of all disks.
Write Traffic (Sum)
The write traffic of all disks per second on each BE.
Write IOPS (Sum)
The number of write operations on all disks per second on each BE.
Write Latency (Avg)
The average write latency of all disks.
BE Network
Metric
Description
Receive Rate
The amount of data that is received over the network per second on each BE.
Send Rate
The amount of data that is sent over the network per second on each BE.
TCP Connections
The number of TCP connections to each BE.
Cache
Metric
Description
FSLIB Cache Hit Ratio
The cache hit ratio per minute.
FSLIB Cache Hits
The number of cache hits per minute.
Fully Managed Storage
NoteThe metrics described in the following table are applicable only to fully managed storage in compute-storage separation scenarios.
Metric
Description
Storage Usage Trend
The amount of fully storage data. Unit: GiB.
Read and Write Traffic
The read and write traffic of fully managed storage.
Resource Group
Metric
Description
Used CPU Cores of Resource Group V3.1.x
The number of CPU cores used by the selected resource group. This value is an estimate, which is the average value within two consecutive sampling periods. This metric is applicable to EMR Serverless StarRocks instances of V3.1.4 and later.
CPU Utilization of Resource Group V2.x
The proportion of the CPU time consumed by the selected resource group to the total CPU time.
Used Memory of Resource Group
The size of memory used by the selected resource group.
Running Tasks in Resource Group
The number of query tasks that are in progress in the selected resource group.
Concurrency Limit Events in Resource Group
The number of queries that reach the concurrency limit in the selected resource group.
Large Query Limit Events in Resource Group
The number of times that the large query limit is reached in the selected resource group.
Query Latency in Resource Group
The 99th percentile and average query latency in the selected resource group.
Queries per Minute in Resource Group
The number of queries that are run per minute in the selected resource group.