You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@iotdb.apache.org by qi...@apache.org on 2022/11/29 11:44:25 UTC
[iotdb] branch rel/1.0 updated: [To rel/1.0][IOTDB-5079] Update the doc of dashboard and fix some minor problem (#8248)
This is an automated email from the ASF dual-hosted git repository.
qiaojialin pushed a commit to branch rel/1.0
in repository https://gitbox.apache.org/repos/asf/iotdb.git
The following commit(s) were added to refs/heads/rel/1.0 by this push:
new 7b67bbe689 [To rel/1.0][IOTDB-5079] Update the doc of dashboard and fix some minor problem (#8248)
7b67bbe689 is described below
commit 7b67bbe6890cc5382adb52365059b23da1250b4e
Author: ZhangHongYin <46...@users.noreply.github.com>
AuthorDate: Tue Nov 29 19:44:19 2022 +0800
[To rel/1.0][IOTDB-5079] Update the doc of dashboard and fix some minor problem (#8248)
---
docs/UserGuide/Monitor-Alert/Metric-Tool.md | 220 +++++++++++----------
docs/zh/UserGuide/Monitor-Alert/Metric-Tool.md | 139 ++++++-------
.../Apache IoTDB ConfigNode Dashboard.json | 113 +++++++++--
.../Apache IoTDB DataNode Dashboard.json | 123 ++++++++++--
.../db/mpp/plan/analyze/cache/PartitionCache.java | 2 +-
5 files changed, 377 insertions(+), 220 deletions(-)
diff --git a/docs/UserGuide/Monitor-Alert/Metric-Tool.md b/docs/UserGuide/Monitor-Alert/Metric-Tool.md
index 49200d21c5..8bf78c2797 100644
--- a/docs/UserGuide/Monitor-Alert/Metric-Tool.md
+++ b/docs/UserGuide/Monitor-Alert/Metric-Tool.md
@@ -132,15 +132,15 @@ Core-level metrics are enabled by default during system operation. The addition
| ------------ | -------------------------------------------------------------------------------------------- | --------- | --------------------------------------------------------------------- |
| mutli_leader | name="logDispatcher-{{IP}}:{{Port}}", region="{{region}}", type="currentSyncIndex" | AutoGauge | The sync index of synchronization thread in replica group |
| mutli_leader | name="logDispatcher-{{IP}}:{{Port}}", region="{{region}}", type="cachedRequestInMemoryQueue" | AutoGauge | The size of cache requests of synchronization thread in replica group |
-| mutli_leader | name="IoTConsensusServerImpl", region="{{region}}", type="searchIndex" | AutoGauge | The write process of main process in replica group |
-| mutli_leader | name="IoTConsensusServerImpl", region="{{region}}", type="safeIndex" | AutoGauge | The sync index of replica group |
-| stage | name="iot_consensus", region="{{region}}", type="getStateMachineLock" | Histogram | The time consumed to get statemachine lock in main process |
-| stage | name="iot_consensus", region="{{region}}", type="checkingBeforeWrite" | Histogram | The time consumed to precheck before write in main process |
-| stage | name="iot_consensus", region="{{region}}", type="writeStateMachine" | Histogram | The time consumed to write statemachine in main process |
-| stage | name="iot_consensus", region="{{region}}", type="offerRequestToQueue" | Histogram | The time consumed to try to offer request to queue in main process |
-| stage | name="iot_consensus", region="{{region}}", type="consensusWrite" | Histogram | The time consumed to the whole write in main process |
-| stage | name="iot_consensus", region="{{region}}", type="constructBatch" | Histogram | The time consumed to construct batch in synchronization thread |
-| stage | name="iot_consensus", region="{{region}}", type="syncLogTimePerRequest" | Histogram | The time consumed to sync log in asynchronous callback process |
+| mutli_leader | name="IoTConsensusServerImpl", region="{{region}}", type="searchIndex" | AutoGauge | The write process of main process in replica group |
+| mutli_leader | name="IoTConsensusServerImpl", region="{{region}}", type="safeIndex" | AutoGauge | The sync index of replica group |
+| stage | name="iot_consensus", region="{{region}}", type="getStateMachineLock" | Histogram | The time consumed to get statemachine lock in main process |
+| stage | name="iot_consensus", region="{{region}}", type="checkingBeforeWrite" | Histogram | The time consumed to precheck before write in main process |
+| stage | name="iot_consensus", region="{{region}}", type="writeStateMachine" | Histogram | The time consumed to write statemachine in main process |
+| stage | name="iot_consensus", region="{{region}}", type="offerRequestToQueue" | Histogram | The time consumed to try to offer request to queue in main process |
+| stage | name="iot_consensus", region="{{region}}", type="consensusWrite" | Histogram | The time consumed to the whole write in main process |
+| stage | name="iot_consensus", region="{{region}}", type="constructBatch" | Histogram | The time consumed to construct batch in synchronization thread |
+| stage | name="iot_consensus", region="{{region}}", type="syncLogTimePerRequest" | Histogram | The time consumed to sync log in asynchronous callback process |
### 4.2.4. Cache
| Metric | Tags | Type | Description |
@@ -149,8 +149,8 @@ Core-level metrics are enabled by default during system operation. The addition
| cache_hit | name="schema" | AutoGauge | The cache hit ratio of SchemaCache, Unit: % |
| cache_hit | name="timeSeriesMeta" | AutoGauge | The cache hit ratio of TimeseriesMetadataCache, Unit: % |
| cache_hit | name="bloomFilter" | AutoGauge | The interception rate of bloomFilter in TimeseriesMetadataCache, Unit: % |
-| cache | name="StorageGroup", type="hit" | Counter | The hit number of StorageGroup Cache |
-| cache | name="StorageGroup", type="all" | Counter | The access number of StorageGroup Cache |
+| cache | name="Database", type="hit" | Counter | The hit number of Database Cache |
+| cache | name="Database", type="all" | Counter | The access number of Database Cache |
| cache | name="SchemaPartition", type="hit" | Counter | The hit number of SchemaPartition Cache |
| cache | name="SchemaPartition", type="all" | Counter | The access number of SSchemaPartition Cache |
| cache | name="DataPartition", type="hit" | Counter | The hit number of DataPartition Cache |
@@ -175,7 +175,7 @@ Core-level metrics are enabled by default during system operation. The addition
| ------ | ----------------------------- | --------- | ------------------------------------------------------------------ |
| mem | name="database_{{name}}" | AutoGauge | The memory usage of DataRegion in DataNode, Unit: byte |
| mem | name="chunkMetaData_{{name}}" | AutoGauge | The memory usage of chunkMetaData when writting TsFile, Unit: byte |
-| mem | name="IoTConsensus" | AutoGauge | The memory usage of IoTConsensus, Unit: byte |
+| mem | name="IoTConsensus" | AutoGauge | The memory usage of IoTConsensus, Unit: byte |
### 4.2.7. Task
| Metric | Tags | Type | Description |
@@ -264,10 +264,10 @@ Core-level metrics are enabled by default during system operation. The addition
## 4.3. Normal level Metrics
### 4.3.1. Cluster
-| Metric | Tags | Type | Description |
-| ------ | ------------------------------------------------------------------ | --------- | ------------------------------------------------------------------ |
-| region | name="{{storageGroupName}}",type="SchemaRegion/DataRegion" | AutoGauge | The number of DataRegion/SchemaRegion of database in specific node |
-| slot | name="{{storageGroupName}}",type="schemaSlotNumber/dataSlotNumber" | AutoGauge | The number of DataSlot/SchemaSlot of database in specific node |
+| Metric | Tags | Type | Description |
+| ------ | -------------------------------------------------------------- | --------- | ------------------------------------------------------------------ |
+| region | name="{{DatabaseName}}",type="SchemaRegion/DataRegion" | AutoGauge | The number of DataRegion/SchemaRegion of database in specific node |
+| slot | name="{{DatabaseName}}",type="schemaSlotNumber/dataSlotNumber" | AutoGauge | The number of DataSlot/SchemaSlot of database in specific node |
## 4.4. All Metric
Currently there is no All level metrics, and it will continue to be added in the future.
@@ -384,99 +384,103 @@ We provide the Apache IoTDB Dashboard, and the rendering shown in Grafana is as
When creating Grafana, you can select the json file you just downloaded to `Import` and select the corresponding target data source for Apache IoTDB Dashboard.
-#### 5.2.4.2. Apache IoTDB StandaAlone Dashboard Instructions
+#### 5.2.4.2. Apache IoTDB ConfigNode Dashboard Instructions
> Except for the metrics specified specially, the following metrics are guaranteed to be available in the monitoring framework at the Important levels.
-1. `Overview`:
- 1. `The number of entity`: The number of entities, currently including the number of timeseries
- 2. `write point per minute`: the cumulative number of write points per minute
- 3. `database used memory`: The memory size used by each database
-2. `Interface`:
- 1. `The QPS of Interface`: The number of times the system interface is accessed per second
- 2. `The time consumed of Interface`: The average time consumed by the system interface
- 3. `Cache hit rate`: Cache hit rate
-3. `Engine`:
- 1. `Task number (pending and active)`: The number of tasks in different states in the system
- 2. `The time consumed of tasking (pending and active)`: The time consumption of tasks in different states in the system
-4. `System`:
- 1. `The size of file`: The size of files related to the IoTDB system, including the total file size under wal, the total size of tsfile files under seq, and the total size of tsfile files under unseq
- 2. `The number of file`: The number of files related to the IoTDB system, including the number of files under wal, the number of tsfile files under seq, and the number of tsfile files under unseq
- 3. `The number of GC (per minute)`: The number of GC per minute of IoTDB, including Young GC and Full GC
- 4. `The time consumed of GC (per minute)`: IoTDB's average GC time per minute, including Young GC and Full GC
- 5. `Heap Memory`: The heap memory of IoTDB
- 6. `Off-heap Memory`: The off-heap memory of IoTDB
- 7. `The number of Java Thread`: The number of threads in different states of IoTDB
-
-#### 5.2.4.3. Apache IoTDB ConfigNode Dashboard Instructions
+- `Overview`: system overview
+ - `Registered Node`: The number of registered ConfigNode/DataNode
+ - `DataNode`: The status of the cluster DataNode, including Online and Unknown.
+ - `ConfigNode`: The status of the cluster ConfigNode, including Online and Unknown.
+ - `The Status Of Node`: The status of specific nodes in the cluster, including Online and Unknown.
+- `Region`: Region overview
+ - `Region Number`: the number of Regions, including the total number, the number of DataRegions and the number of SchemaRegions.
+ - `Leadership distribution`: Cluster leader distribution, which refers to the number of Leaders corresponding to the Region on each node.
+ - `Total Region in Node`: The total number of Regions of different Nodes.
+ - `Region in Node`: the number of SchemaRegions/DataRegions of different Nodes.
+ - `Region in Database` (Normal level): the number of Regions in different Databases, including SchemaRegion and DataRegion.
+ - `Slot in Database` (Normal level): The number of Slots in different Databases, including the number of DataSlots and SchemaSlots.
+- `System`: system
+ - `CPU Core`: the number of CPU cores in the system.
+ - `CPU Load`: system CPU load, progress CPU load.
+ - `CPU Time Per Minute`: The process takes up the system CPU time per minute on average. Note: multi-core will cause this value to exceed 1 minute.
+ - `System Memory`: the physical memory size of the system, the physical memory size used by the system, and the memory size submitted by the virtual machine.
+ - `System Swap Size`: the total size of the system swap area, the size used by the system swap area.
+ - `Process Memory`: the maximum total memory size of the IoTDB process, the total memory size of the IoTDB process, and the memory size used by the IoTDB process.
+ - `The Number of GC Per Minute`: The average number of GC per minute.
+ - `The Time Consumed Of GC Per Minute`: Average GC time spent per minute.
+ - `The Number Of Java Thread`: The number of threads in different states of the IoTDB process.
+ - `Heap Memory`: the heap memory of the IoTDB process
+ - `Off Heap Memory`: the off-heap memory of the IoTDB process
+ - `Log Number Per Minute`: the average number of logs per minute of the IoTDB process
+ - `The Time Consumed of Compliation Per Minute`: average compilation time per minute
+ - `The Number Of Class`: The number of classes loaded and unloaded by the JVM
+
+#### 5.2.4.3. Apache IoTDB DataNode Dashboard Instructions
> Except for the metrics specified specially, the following metrics are guaranteed to be available in the monitoring framework at the Important levels.
-1. `Overview`:
- 1. `Online ConfigNode`：The number of online confignode
- 2. `Registered ConfigNode`：The number of registered confignode
- 3. `Unknown ConfigNode`：The number of unknown confignode
- 4. `Online DataNode`：The number of online datanode
- 5. `Registered DataNode`：The number of registered datanode
- 6. `Unknown DataNode`：The number of unknown datanode
- 7. `TotalRegion`：The number of region
- 8. `DataRegion`：The number of data region
- 9. `SchemaRegion`：The number of schema region
-2. `Node Info`
- 1. `The status of cluster node`：The status of cluster node
- 2. `Leadership distribution`：The distribution of leaderShip
-3. `Region`:
- 1. `Total Region in Node`: The total number of Regions in different Nodes
- 2. `Region in Node`: The number of Regions in different Nodes, including SchemaRegion, DataRegion
- 3. `Region in Database` (Normal level): The number of Regions in different databases, including SchemaRegion, DataRegion
- 4. `Slot in Database` (Normal level): The number of Slots in different databases, including the number of DataSlots and the number of SchemaSlots
-4. `System`:
- 1. `The number of GC(per minute)`: The number of GCs per minute of IoTDB, including Young GC and Full GC.
- 2. `The time consumed of GC (per minute)`: IoTDB's average GC time per minute, including Young GC and Full GC.
- 3. `Heap Memory`: The heap memory of IoTDB.
- 4. `Off-heap Memory`: The off-heap memory of IoTDB.
- 5. `The number of Java Thread`: The number of threads in different states of IoTDB.
- 6. `The time consumed of Interface`: The average time consumed by the system interface
- 7. `CPU Load`：The load of cpu
- 8. `Memory`：The size of system memory and used system memory
-
-#### 5.2.4.4. Apache IoTDB DataNode Dashboard Instructions
-> Except for the metrics specified specially, the following metrics are guaranteed to be available in the monitoring framework at the Important levels.
-
-1. `Overview`:
- 1. `The number of entity`: The number of entities, currently including the number of timeseries
- 2. `write point per minute`: the cumulative number of write points per minute
- 3. `database used memory`: The memory size used by each database
- 4. `Memory`：The size of system memory and used system memory
-2. `Interface`:
- 1. `The QPS of Interface`: The number of times the system interface is accessed per second
- 2. `The time consumed of Interface`: The average time consumed by the system interface
- 3. `Cache hit rate`: Cache hit rate
-3. `Engine`:
- 1. `Task number (pending and active)`: The number of tasks in different states in the system
- 2. `The time consumed of tasking (pending and active)`: The time consumption of tasks in different states in the system
-4. `IoTConsensus`：
- 1. `IoTConsensus Used Memory`：The size of the memory used by IoTConsensus consensus
- 2. `IoTConsensus Sync Index`：the searchIndex and safeIndex of region
- 3. `IoTConsensus Overview`：The total sync lag and total size of buffered requests of node
- 4. `The time consumed of different stages(50%)`：The median of the time consumed of different stages
- 5. `The time consumed of different stages(75%)`：The upper quartile of the time consumed of different stages
- 6. `The time consumed of different stages(100%)`：The max of the time consumed of different stages
- 7. `IoTConsensus Search Index Rate`：The increasing rate of searchIndex of region
- 8. `IoTConsensus Safe Index Rate`：The increasing rate of safeIndex of region
- 9. `IoTConsensus LogDispatcher Request Size`：The number of requests buffered in logDispatcher
- 10. `Sync Lag`：The sync lag of region
- 11. `Min Peer Sync Lag`：The sync lag between the searchIndex of IoTConsensusServerImpl and the max currentSyncIndex of LogDispatcher
- 12. `Sync speed diff of Peers`：The sync lag between the max currentSyncIndex of LogDispatcher and the min currentSyncIndex of LogDispatcher
-5. `CPU`:
- 1. `CPU Load`：The load of CPU
- 2. `Process CPU Load`：The cpu load of iotdb process
-6. `File System`：
- 1. `The size of file`: The size of files related to the IoTDB system, including the total file size under wal, the total size of tsfile files under seq, and the total size of tsfile files under unseq
- 2. `The number of file`: The number of files related to the IoTDB system, including the number of files under wal, the number of tsfile files under seq, and the number of tsfile files under unseq
- 3. `Disk Space`：The total size and remaining size of the disk mounted by the current data directory
-7. `JVM`：
- 1. `The number of GC (per minute)`: The number of GC per minute of IoTDB, including Young GC and Full GC
- 2. `The time consumed of GC (per minute)`: IoTDB's average GC time per minute, including Young GC and Full GC
- 3. `Heap Memory`: The heap memory of IoTDB
- 4. `Off-heap Memory`: The off-heap memory of IoTDB
- 5. `The number of Java Thread`: The number of threads in different states of IoTDB
-
+- `Overview`: system overview
+ - `The Number Of Entity`: the number of entities, including time series, etc.
+ - `Write Point Per Minute`: the average number of system write points per minute
+ - `Database Used Memory`: the memory size used by each Database
+- `Interface`: interface
+ - `The Time Consumed Of Operation(50%)`: Median time spent by different client operations
+ - `The Time Consumed Of Operation(75%)`: The upper quartile of the time consumed by different client operations
+ - `The Time Consumed Of Operation(100%)`: The maximum time spent by different client operations
+ - `The QPS of Interface`: system interface visits per second
+ - `The Time Consumed Of Interface`: the average time consumed by the system interface
+ - `Cache Hit Rate`: cache hit rate
+ - `Thrift Connection`: the number of Thrift connections established
+ - `Thrift Active Thread`: The number of active Thrift connections established
+- `Engine`:
+ - `Task Number`: the number of tasks in different states in the system
+ - `The Time Consumed Of Tasking`: Time consumption of tasks in different states in the system
+ - `Compaction Read And Write Per Minute`: the average amount of combined read and write data per minute
+ - `Compaction R/W Ratio Per Minute`: The average ratio of combined read and write data per minute
+ - `Compaction Number Per Minute`: the average number of different types of consolidation tasks per minute
+- `IoTConsensus`：
+ - `IoTConsensus Used Memory`：The size of the memory used by IoTConsensus consensus
+ - `IoTConsensus Sync Index`：the searchIndex and safeIndex of region
+ - `IoTConsensus Overview`：The total sync lag and total size of buffered requests of node
+ - `The time consumed of different stages(50%)`：The median of the time consumed of different stages
+ - `The time consumed of different stages(75%)`：The upper quartile of the time consumed of different stages
+ - `The time consumed of different stages(100%)`：The max of the time consumed of different stages
+ - `IoTConsensus Search Index Rate`：The increasing rate of searchIndex of region
+ - `IoTConsensus Safe Index Rate`：The increasing rate of safeIndex of region
+ - `IoTConsensus LogDispatcher Request Size`：The number of requests buffered in logDispatcher
+ - `Sync Lag`：The sync lag of region
+ - `Min Peer Sync Lag`：The sync lag between the searchIndex of IoTConsensusServerImpl and the max currentSyncIndex of LogDispatcher
+ - `Sync speed diff of Peers`：The sync lag between the max currentSyncIndex of LogDispatcher and the min currentSyncIndex of LogDispatcher
+- `System`: system
+ - `CPU Core`: the number of CPU cores in the system.
+ - `CPU Load`: system CPU load, progress CPU load.
+ - `CPU Time Per Minute`: The process takes up the system CPU time per minute on average. Note: multi-core will cause this value to exceed 1 minute.
+ - `System Memory`: the physical memory size of the system, the physical memory size used by the system, and the memory size submitted by the virtual machine.
+ - `System Swap Size`: the total size of the system swap area, the size used by the system swap area.
+ - `Process Memory`: the maximum total memory size of the IoTDB process, the total memory size of the IoTDB process, and the memory size used by the IoTDB process.
+ - `The Size Of File`: IoTDB system-related file size, including the total file size under wal, the total size of tsfile files under seq, and the total size of tsfile files under unseq
+ - `The Number Of File`: the number of files related to the IoTDB system, including the number of files under wal, the number of tsfile files under seq, and the number of tsfile files under unseq
+ - `The Space Of Disk`: the total size and remaining size of the disk mounted in the current data directory
+ - `The Number of GC Per Minute`: The average number of GC per minute.
+ - `The Time Consumed Of GC Per Minute`: Average GC time spent per minute.
+ - `The Number Of Java Thread`: The number of threads in different states of the IoTDB process.
+ - `Heap Memory`: the heap memory of the IoTDB process
+ - `Off Heap Memory`: the off-heap memory of the IoTDB process
+ - `Log Number Per Minute`: the average number of logs per minute of the IoTDB process
+ - `The Time Consumed of Compliation Per Minute`: average compilation time per minute
+ - `The Number Of Class`: The number of classes loaded and unloaded by the JVM
+
+## 5.3. IoTDB
+
+### 5.3.1. IoTDB mapping relationship of metrics
+> For metrics whose Metric Name is name and Tags are K1=V1, ..., Kn=Vn, the mapping is as follows, taking root.__system.metric as an example by default
+
+| Metric Type | Mapping [...]
+| ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- [...]
+| Counter | root.__system.metric.name.`K1=V1`...`Kn=Vn`.value [...]
+| AutoGauge、Gauge | root.__system.metric.name.`K1=V1`...`Kn=Vn`.value [...]
+| Histogram | root.__system.metric.name.`K1=V1`...`Kn=Vn`.count <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.max <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.sum <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p0 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p25 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p50 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p75 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p100 [...]
+| Rate | root.__system.metric.name.`K1=V1`...`Kn=Vn`.count <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.mean <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.m1 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.m5 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.m15 [...]
+| Timer | root.__system.metric.name.`K1=V1`...`Kn=Vn`.count <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.max <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.mean <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.sum <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p0 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p25 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p50 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p75 <br> root.__system.metric.name.`K1=V1`...`Kn=Vn`.p [...]
+
+### 5.3.2. Obtain metrics
+According to the above mapping relationship, related IoTDB query statements can be formed to obtain metrics
\ No newline at end of file
diff --git a/docs/zh/UserGuide/Monitor-Alert/Metric-Tool.md b/docs/zh/UserGuide/Monitor-Alert/Metric-Tool.md
index d6e2ed976c..c48f48dadb 100644
--- a/docs/zh/UserGuide/Monitor-Alert/Metric-Tool.md
+++ b/docs/zh/UserGuide/Monitor-Alert/Metric-Tool.md
@@ -152,8 +152,8 @@ Core 级别的监控指标在系统运行中默认开启，每一个 Core 级别
| cache_hit | name="schema" | AutoGauge | SchemaCache的命中率，单位为% |
| cache_hit | name="timeSeriesMeta" | AutoGauge | TimeseriesMetadataCache的命中率，单位为% |
| cache_hit | name="bloomFilter" | AutoGauge | TimeseriesMetadataCache中的bloomFilter的拦截率，单位为% |
-| cache | name="StorageGroup", type="hit" | Counter | StorageGroup Cache 的命中次数 |
-| cache | name="StorageGroup", type="all" | Counter | StorageGroup Cache 的访问次数 |
+| cache | name="Database", type="hit" | Counter | Database Cache 的命中次数 |
+| cache | name="Database", type="all" | Counter | Database Cache 的访问次数 |
| cache | name="SchemaPartition", type="hit" | Counter | SchemaPartition Cache 的命中次数 |
| cache | name="SchemaPartition", type="all" | Counter | SchemaPartition Cache 的访问次数 |
| cache | name="DataPartition", type="hit" | Counter | DataPartition Cache 的命中次数 |
@@ -377,75 +377,59 @@ static_configs:
在创建Grafana时，您可以选择Import刚刚下载的json文件，并为Apache IoTDB Dashboard选择对应目标数据源。
-#### 5.2.4.2. Apache IoTDB StandAlone Dashboard 说明
+#### 5.2.4.2. Apache IoTDB ConfigNode Dashboard 说明
> 除特殊说明的监控项以外，以下监控项均保证在Important级别的监控框架中可用。
- `Overview`：系统概述
- - `The number of entity`：实体数量，目前包含时间序列的数量
- - `write point per minute`：每分钟系统累计写入点数
- - `database used memory`：每个 database 使用的内存大小
-- `Interface`：接口
- - `The QPS of Interface`：系统接口每秒钟访问次数
- - `The time consumed of Interface`：系统接口的平均耗时
- - `Cache hit rate`：缓存命中率
-- `Engine`：引擎
- - `Task number(pending and active)`：系统中不同状态的任务个数
- - `The time consumed of tasking(pending and active)`：系统中不同状态的任务的耗时
-- `System`：系统
- - `The size of file`：IoTDB系统相关的文件大小，包括wal下的文件总大小、seq下的tsfile文件总大小、unseq下的tsfile文件总大小
- - `The number of file`：IoTDB系统相关的文件个数，包括wal下的文件个数、seq下的tsfile文件个数、unseq下的tsfile文件个数
- - `The number of GC(per minute)`：IoTDB每分钟的GC数量，包括Young GC和Full GC
- - `The time consumed of GC(per minute)`：IoTDB的每分钟平均GC耗时，包括Young GC和Full GC
- - `Heap Memory`：IoTDB的堆内存
- - `Off-heap Memory`：IoTDB的堆外内存
- - `The number of Java Thread`：IoTDB的不同状态线程数
-
-#### 5.2.4.3. Apache IoTDB ConfigNode Dashboard 说明
-> 除特殊说明的监控项以外，以下监控项均保证在Important级别的监控框架中可用。
-
-- `Overview`：系统概述
- - `Online ConfigNode`：正常运行ConfigNode个数
- - `Registered ConfigNode`：注册ConfigNode个数
- - `Unknown ConfigNode`：状态未知ConfigNode个数
- - `Online DataNode`：正常运行DataNode个数
- - `Registered DataNode`：注册DataNode个数
- - `Unknown DataNode`：状态未知DataNode个数
- - `TotalRegion`：Region总数量
- - `DataRegion`：DataRegion总数量
- - `SchemaRegion`：SchemaRegion总数量
-- `Node Info`：节点信息
- - `The status of cluster node`：集群节点状态
- - `Leadership distribution`：Leader分布情况
-- `Region`：Region分布情况
- - `Total Region in Node`：不同Node的Region总数量
- - `Region in Node`：不同Node的Region数量，包括SchemaRegion、DataRegion
- - `Region in Database`(Normal级别)：不同数据库的Region数量，包括SchemaRegion、DataRegion
- - `Slot in Database`(Normal级别)：不同数据库的Slot数量，包括DataSlot数量和SchemaSlot数量
-- `System`：系统
- - `The number of GC(per minute)`：IoTDB每分钟的GC数量，包括Young GC和Full GC
- - `The time consumed of GC(per minute)`：IoTDB的每分钟平均GC耗时，包括Young GC和Full GC
- - `Heap Memory`：IoTDB的堆内存
- - `Off-heap Memory`：IoTDB的堆外内存
- - `The number of Java Thread`：IoTDB的不同状态线程数
- - `The time consumed of Interface`：系统接口的平均耗时
- - `CPU Load`：当前处理器的总负载
- - `Memory`：系统内存大小和已经使用的大小
-
-#### 5.2.4.4. Apache IoTDB DataNode Dashboard 说明
+ - `Registered Node`：注册的ConfigNode/DataNode个数
+ - `DataNode`：集群DataNode的存活状态，包括Online和Unknown两种。
+ - `ConfigNode`：集群ConfigNode的存活状态，包括Online和Unknown两种。
+ - `The Status Of Node`：集群具体节点运行状态，包括Online和Unkown两种。
+- `Region`：Region概述
+ - `Region Number`：Region个数，包括总个数，DataRegion 个数和 SchemaRegion 个数。
+ - `Leadership distribution`：集群 Leader 分布情况，指每个节点上对应 Region 的 Leader 的个数。
+ - `Total Region in Node`：不同 Node 的 Region 总数量。
+ - `Region in Node`：不同 Node 的 SchemaRegion/DataRegion 数量。
+ - `Region in Database`（Normal级别）：不同 Database 的 Region 数量，包括 SchemaRegion、DataRegion。
+ - `Slot in Database`(Normal级别)：不同 Database 的Slot数量，包括 DataSlot 数量和 SchemaSlot 数量。
+- `System`：系统
+ - `CPU Core`：系统 CPU 核数情况。
+ - `CPU Load`：系统 CPU 负载情况、进度 CPU 负载情况。
+ - `CPU Time Per Minute`：进程平均每分钟占用系统 CPU 时间，注意：多核会导致该值超过1分钟。
+ - `System Memory`：系统物理内存大小、系统使用物理内存大小、虚拟机提交的内存大小。
+ - `System Swap Size`：系统交换区总大小、系统交换区使用大小。
+ - `Process Memory`：IoTDB 进程最大内存总大小、IoTDB 进程总内存大小、IoTDB 进程使用内存大小。
+ - `The Number of GC Per Minute`：平均每分钟 GC 次数。
+ - `The Time Consumed Of GC Per Minute`：平均每分钟 GC 耗时。
+ - `The Number Of Java Thread`：IoTDB 进程的不同状态的线程数。
+ - `Heap Memory`：IoTDB 进程的堆内存
+ - `Off Heap Memory`：IoTDB 进程的堆外内存
+ - `Log Number Per Minute`：IoTDB 进程平均每分钟日志数
+ - `The Time Consumed of Compliation Per Minute`：平均每分钟编译耗时
+ - `The Number Of Class`：JVM 加载和卸载的类数量
+
+#### 5.2.4.3. Apache IoTDB DataNode Dashboard 说明
> 除特殊说明的监控项以外，以下监控项均保证在Important级别的监控框架中可用。
- `Overview`：系统概述
- - `The number of entity`：实体数量，目前包含时间序列的数量
- - `write point per minute`：每分钟系统累计写入点数
- - `database used memory`：每个 database 使用的内存大小
- - `Memory`：系统内存大小和已经使用的大小
+ - `The Number Of Entity`：实体数量，包含时间序列等
+ - `Write Point Per Minute`：每分钟系统平均写入点数
+ - `Database Used Memory`：每个 Database 使用的内存大小
- `Interface`：接口
+ - `The Time Consumed Of Operation(50%)`：不同客户端操作耗时的中位数
+ - `The Time Consumed Of Operation(75%)`：不同客户端操作耗时的上四分位数
+ - `The Time Consumed Of Operation(100%)`：不同客户端操作耗时的最大值
- `The QPS of Interface`：系统接口每秒钟访问次数
- - `The time consumed of Interface`：系统接口的平均耗时
- - `Cache hit Rate`：缓存命中率
+ - `The Time Consumed Of Interface`：系统接口的平均耗时
+ - `Cache Hit Rate`：缓存命中率
+ - `Thrift Connection`：建立的 Thrift 连接个数
+ - `Thrift Active Thread`：建立的活跃的 Thrift 连接的个数
- `Engine`：引擎
- - `Task number(pending and active)`：系统中不同状态的任务个数
- - `The time consumed of tasking(pending and active)`：系统中不同状态的任务的耗时
+ - `Task Number`：系统中不同状态的任务个数
+ - `The Time Consumed Of Tasking`：系统中不同状态的任务的耗时
+ - `Compaction Read And Write Per Minute`：平均每分钟合并读取和写入数据量
+ - `Compaction R/W Ratio Per Minute`：平均每分钟合并读取和写入数据比
+ - `Compaction Number Per Minute`：平均每分钟不同类型的合并任务数量
- `IoTConsensus`：IoT共识协议
- `IoTConsensus Used Memory`：IoT共识层使用的内存大小
- `IoTConsensus Sync Index`：不同的Region的写入Index和同步Index
@@ -459,19 +443,24 @@ static_configs:
- `Sync Lag`：每个region的同步index差距
- `Min Peer Sync Lag`：每个region的写入index和同步最快的LogDispatcherThread的同步index之间的差距
- `Sync speed diff of Peers`：每个region中同步最快的LogDispatcherThread与同步最慢的LogDispatcherThread之间的同步index差距
-- `CPU`：处理器
- - `CPU Load`：当前处理器的总负载
- - `Process CPU Load`：IoTDB进程占用处理器的负载
-- `File System`：文件系统
- - `The size of file`：IoTDB系统相关的文件大小，包括wal下的文件总大小、seq下的tsfile文件总大小、unseq下的tsfile文件总大小
- - `The number of file`：IoTDB系统相关的文件个数，包括wal下的文件个数、seq下的tsfile文件个数、unseq下的tsfile文件个数
- - `Disk Space`：当前data目录所挂载的磁盘总大小和剩余大小
-- `JVM`：系统
- - `The number of GC(per minute)`：IoTDB每分钟的GC数量，包括Young GC和Full GC
- - `The time consumed of GC(per minute)`：IoTDB的每分钟平均GC耗时，包括Young GC和Full GC
- - `Heap Memory`：IoTDB的堆内存
- - `Off-heap Memory`：IoTDB的堆外内存
- - `The number of Java Thread`：IoTDB的不同状态线程数
+- `System`：系统
+ - `CPU Core`：系统 CPU 核数情况。
+ - `CPU Load`：系统 CPU 负载情况、进度 CPU 负载情况。
+ - `CPU Time Per Minute`：进程平均每分钟占用系统 CPU 时间，注意：多核会导致该值超过1分钟。
+ - `System Memory`：系统物理内存大小、系统使用物理内存大小、虚拟机提交的内存大小。
+ - `System Swap Size`：系统交换区总大小、系统交换区使用大小。
+ - `Process Memory`：IoTDB 进程最大内存总大小、IoTDB 进程总内存大小、IoTDB 进程使用内存大小。
+ - `The Size Of File`：IoTDB系统相关的文件大小，包括wal下的文件总大小、seq下的tsfile文件总大小、unseq下的tsfile文件总大小
+ - `The Number Of File`：IoTDB系统相关的文件个数，包括wal下的文件个数、seq下的tsfile文件个数、unseq下的tsfile文件个数
+ - `The Space Of Disk`：当前data目录所挂载的磁盘总大小和剩余大小
+ - `The Number of GC Per Minute`：平均每分钟 GC 次数。
+ - `The Time Consumed Of GC Per Minute`：平均每分钟 GC 耗时。
+ - `The Number Of Java Thread`：IoTDB 进程的不同状态的线程数。
+ - `Heap Memory`：IoTDB 进程的堆内存
+ - `Off Heap Memory`：IoTDB 进程的堆外内存
+ - `Log Number Per Minute`：IoTDB 进程平均每分钟日志数
+ - `The Time Consumed of Compliation Per Minute`：平均每分钟编译耗时
+ - `The Number Of Class`：JVM 加载和卸载的类数量
## 5.3. 使用 IoTDB 方式
diff --git a/grafana-metrics-example/cluster/Apache IoTDB ConfigNode Dashboard.json b/grafana-metrics-example/Apache IoTDB ConfigNode Dashboard.json
similarity index 96%
rename from grafana-metrics-example/cluster/Apache IoTDB ConfigNode Dashboard.json
rename to grafana-metrics-example/Apache IoTDB ConfigNode Dashboard.json
index de3e48ad15..4e9a208684 100644
--- a/grafana-metrics-example/cluster/Apache IoTDB ConfigNode Dashboard.json
+++ b/grafana-metrics-example/Apache IoTDB ConfigNode Dashboard.json
@@ -15,7 +15,7 @@
"type": "grafana",
"id": "grafana",
"name": "Grafana",
- "version": "8.4.2"
+ "version": "8.4.6"
},
{
"type": "panel",
@@ -69,7 +69,7 @@
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
- "iteration": 1669566467252,
+ "iteration": 1669709013871,
"links": [],
"liveNow": false,
"panels": [
@@ -134,7 +134,7 @@
},
"textMode": "auto"
},
- "pluginVersion": "8.4.2",
+ "pluginVersion": "8.4.6",
"targets": [
{
"datasource": {
@@ -473,7 +473,7 @@
},
"textMode": "auto"
},
- "pluginVersion": "8.4.2",
+ "pluginVersion": "8.4.6",
"targets": [
{
"datasource": {
@@ -551,7 +551,7 @@
},
"textMode": "auto"
},
- "pluginVersion": "8.4.2",
+ "pluginVersion": "8.4.6",
"targets": [
{
"datasource": {
@@ -825,7 +825,7 @@
"refId": "A"
}
],
- "title": "Region in StorageGroup",
+ "title": "Region in Database",
"type": "timeseries"
},
{
@@ -911,7 +911,7 @@
"refId": "A"
}
],
- "title": "Slot In Storage Group",
+ "title": "Slot In Database",
"type": "timeseries"
},
{
@@ -989,7 +989,7 @@
},
"textMode": "auto"
},
- "pluginVersion": "8.4.2",
+ "pluginVersion": "8.4.6",
"targets": [
{
"datasource": {
@@ -1365,7 +1365,38 @@
},
"unit": "bytes"
},
- "overrides": []
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Total Swap Size"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "green",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "Used Swap Size"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "yellow",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
},
"gridPos": {
"h": 8,
@@ -1488,8 +1519,8 @@
"showLegend": true
},
"tooltip": {
- "mode": "single",
- "sort": "none"
+ "mode": "multi",
+ "sort": "desc"
}
},
"targets": [
@@ -2058,6 +2089,10 @@
"type": "timeseries"
},
{
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
"fieldConfig": {
"defaults": {
"color": {
@@ -2103,7 +2138,53 @@
},
"unit": "none"
},
- "overrides": []
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "warn"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "trace"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "purple",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "error"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
},
"gridPos": {
"h": 8,
@@ -2230,7 +2311,7 @@
"refId": "A"
}
],
- "title": "Time Time Consumed of Compilation Per Minute",
+ "title": "The Time Consumed of Compilation Per Minute",
"type": "timeseries"
},
{
@@ -2342,7 +2423,7 @@
"tags": [
"Apache-IoTDB",
"ConfigNode",
- "0.14.0"
+ "v1.0"
],
"templating": {
"list": [
@@ -2408,7 +2489,7 @@
},
"timezone": "browser",
"title": "Apache IoTDB ConfigNode Dashboard",
- "uid": "TbEVYRw7g",
- "version": 1,
+ "uid": "TbEVYRw7T",
+ "version": 8,
"weekStart": ""
}
\ No newline at end of file
diff --git a/grafana-metrics-example/cluster/Apache IoTDB DataNode Dashboard.json b/grafana-metrics-example/Apache IoTDB DataNode Dashboard.json
similarity index 97%
rename from grafana-metrics-example/cluster/Apache IoTDB DataNode Dashboard.json
rename to grafana-metrics-example/Apache IoTDB DataNode Dashboard.json
index 247057b1aa..a065285d37 100644
--- a/grafana-metrics-example/cluster/Apache IoTDB DataNode Dashboard.json
+++ b/grafana-metrics-example/Apache IoTDB DataNode Dashboard.json
@@ -15,7 +15,7 @@
"type": "grafana",
"id": "grafana",
"name": "Grafana",
- "version": "8.4.2"
+ "version": "8.4.6"
},
{
"type": "datasource",
@@ -63,7 +63,7 @@
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
- "iteration": 1669566440584,
+ "iteration": 1669708594135,
"links": [],
"liveNow": false,
"panels": [
@@ -182,6 +182,10 @@
"type": "timeseries"
},
{
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
"fieldConfig": {
"defaults": {
"color": {
@@ -257,7 +261,7 @@
"exemplar": true,
"expr": "rate(quantity_total{instance=~\"$instance\"}[1m])",
"interval": "1m",
- "legendFormat": "{{instance}} write point per second",
+ "legendFormat": "write point per second",
"range": true,
"refId": "A"
}
@@ -892,7 +896,7 @@
},
"tooltip": {
"mode": "multi",
- "sort": "none"
+ "sort": "desc"
}
},
"pluginVersion": "8.4.2",
@@ -1196,7 +1200,7 @@
},
"tooltip": {
"mode": "multi",
- "sort": "none"
+ "sort": "desc"
}
},
"targets": [
@@ -1296,9 +1300,9 @@
},
"editorMode": "code",
"exemplar": true,
- "expr": "rate(cost_task_seconds_sum{}[1m])/rate(cost_task_seconds_count{}[1m])",
+ "expr": "rate(cost_task_seconds_sum{instance=~\"$instance\"}[1m])/rate(cost_task_seconds_count{instance=~\"$instance\"}[1m])",
"interval": "",
- "legendFormat": "{{instance}}-{{name}}",
+ "legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
@@ -1714,9 +1718,9 @@
},
"editorMode": "code",
"exemplar": true,
- "expr": "mem{name=\"IoTConsensus\"}",
+ "expr": "mem{instance=\"$instance\", name=\"IoTConsensus\"}",
"interval": "",
- "legendFormat": "{{instance}}",
+ "legendFormat": "{{name}}",
"range": true,
"refId": "A"
}
@@ -2153,7 +2157,32 @@
},
"unit": "ms"
},
- "overrides": []
+ "overrides": [
+ {
+ "__systemRef": "hideSeriesFrom",
+ "matcher": {
+ "id": "byNames",
+ "options": {
+ "mode": "exclude",
+ "names": [
+ "checkingBeforeWrite"
+ ],
+ "prefix": "All except:",
+ "readOnly": true
+ }
+ },
+ "properties": [
+ {
+ "id": "custom.hideFrom",
+ "value": {
+ "legend": false,
+ "tooltip": false,
+ "viz": true
+ }
+ }
+ ]
+ }
+ ]
},
"gridPos": {
"h": 8,
@@ -2816,7 +2845,7 @@
},
"textMode": "auto"
},
- "pluginVersion": "8.4.2",
+ "pluginVersion": "8.4.6",
"targets": [
{
"datasource": {
@@ -2905,7 +2934,7 @@
},
"tooltip": {
"mode": "multi",
- "sort": "none"
+ "sort": "desc"
}
},
"targets": [
@@ -3099,7 +3128,7 @@
},
"tooltip": {
"mode": "multi",
- "sort": "none"
+ "sort": "desc"
}
},
"targets": [
@@ -3214,7 +3243,7 @@
},
"tooltip": {
"mode": "multi",
- "sort": "none"
+ "sort": "desc"
}
},
"targets": [
@@ -3317,7 +3346,7 @@
},
"tooltip": {
"mode": "multi",
- "sort": "none"
+ "sort": "desc"
}
},
"targets": [
@@ -4096,6 +4125,10 @@
"type": "timeseries"
},
{
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
"fieldConfig": {
"defaults": {
"color": {
@@ -4179,6 +4212,10 @@
"type": "timeseries"
},
{
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${DS_PROMETHEUS}"
+ },
"fieldConfig": {
"defaults": {
"color": {
@@ -4224,7 +4261,53 @@
},
"unit": "none"
},
- "overrides": []
+ "overrides": [
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "warn"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "orange",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "trace"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "purple",
+ "mode": "fixed"
+ }
+ }
+ ]
+ },
+ {
+ "matcher": {
+ "id": "byName",
+ "options": "error"
+ },
+ "properties": [
+ {
+ "id": "color",
+ "value": {
+ "fixedColor": "red",
+ "mode": "fixed"
+ }
+ }
+ ]
+ }
+ ]
},
"gridPos": {
"h": 8,
@@ -4456,13 +4539,13 @@
"type": "timeseries"
}
],
- "refresh": "15s",
+ "refresh": false,
"schemaVersion": 35,
"style": "dark",
"tags": [
"Apache-IoTDB",
"DataNode",
- "0.14.0"
+ "v1.0"
],
"templating": {
"list": [
@@ -4528,7 +4611,7 @@
},
"timezone": "browser",
"title": "Apache IoTDB DataNode Dashboard",
- "uid": "TbEVYRw7m",
- "version": 1,
+ "uid": "TbEVYRw7A",
+ "version": 18,
"weekStart": ""
}
\ No newline at end of file
diff --git a/server/src/main/java/org/apache/iotdb/db/mpp/plan/analyze/cache/PartitionCache.java b/server/src/main/java/org/apache/iotdb/db/mpp/plan/analyze/cache/PartitionCache.java
index 33ace6aa1f..3b5b25967f 100644
--- a/server/src/main/java/org/apache/iotdb/db/mpp/plan/analyze/cache/PartitionCache.java
+++ b/server/src/main/java/org/apache/iotdb/db/mpp/plan/analyze/cache/PartitionCache.java
@@ -73,7 +73,7 @@ public class PartitionCache {
private static final Logger logger = LoggerFactory.getLogger(PartitionCache.class);
private static final IoTDBConfig config = IoTDBDescriptor.getInstance().getConfig();
private static final List<String> ROOT_PATH = Arrays.asList("root", "**");
- private static final String STORAGE_GROUP_CACHE_NAME = "StorageGroup";
+ private static final String STORAGE_GROUP_CACHE_NAME = "Database";
private static final String SCHEMA_PARTITION_CACHE_NAME = "SchemaPartition";
private static final String DATA_PARTITION_CACHE_NAME = "DataPartition";