[GitHub] [incubator-doris] morningman commented on a change in pull request #3808: [Doc] Add docs to OLAP_SCAN_NODE query profile

[GitBox <gi...@apache.org>]

morningman commented on a change in pull request #3808:
URL: https://github.com/apache/incubator-doris/pull/3808#discussion_r439251334



##########
File path: docs/zh-CN/administrator-guide/running-profile.md
##########
@@ -130,22 +133,105 @@ BE端收集的统计信息较多，下面列出了各个参数的对应含义：
   - HashProbe:  HashTable查询的次数
   - HashTravelLength:  HashTable查询时移动的步数
 
-#### OLAP_SCAN_NODE:
- - RowsProduced: 生成结果的行数
- - BytesRead: scan node 扫描数据的总量
- - TotalReadThroughput：吞吐量
- - TabletCount: tablet 的数目
- - RowsPushedCondFiltered：下推的过滤器
- - RawRowsRead: 实际读取的行数
- - RowsReturned: 该节点返回的行数
- - RowsReturnedRate: 返回行数的速率
- - PeakMemoryUsage 内存使用的峰值  
-
-#### Buffer pool:
+#### `OLAP_SCAN_NODE`
+
+`OLAP_SCAN_NODE` 节点负责具体的数据扫描任务。一个 `OLAP_SCAN_NODE` 会生成一个或多个 `OlapScanner` 线程。每个 Scanner 线程负责扫描部分数据。
+
+查询中的部分或全部谓词条件会推送给 `OLAP_SCAN_NODE`。这些谓词条件中一部分会继续下推给存储引擎，以便利用存储引擎的索引进行数据过滤。另一部分会保留在 `OLAP_SCAN_NODE` 中，用于过滤从存储引擎中返回的数据。
+
+一个典型的 `OLAP_SCAN_NODE` 节点的 Profile 如下。部分指标会因存储格式的不同（V1 或 V2）而有不同含义。
+
+```
+OLAP_SCAN_NODE (id=0):(Active: 4.050ms, non-child: 35.68%)
+   - BitmapIndexFilterCount: 0  # 利用 bitmap 索引过滤掉的行数。

Review comment:
       ok

##########
File path: docs/en/administrator-guide/running-profile.md
##########
@@ -127,21 +127,105 @@ There are many statistical information collected at BE.  so we list the correspo
   - HashProbe:  Number of hashtable probe
   - HashTravelLength:  The number of steps moved when hashtable queries
 
-#### OLAP_SCAN_NODE:
- - BytesRead: Total data
- - TotalReadThroughput：Throughput = BytesRead / Time
- - TabletCount: Number of scanned tablets
- - RowsPushedCondFiltered：Number of filters pushed down
- - RawRowsRead: Number of rows read
- - RowsReturned: Number of rows returned by the node
- - RowsReturnedRate: Rate of rows returned
- - PeakMemoryUsage: Peak memory usage of the node
-
-#### Buffer pool:
+#### `OLAP_SCAN_NODE`
+
+The `OLAP_SCAN_NODE` is responsible for specific data scanning tasks. One `OLAP_SCAN_NODE` will generate one or more `OlapScanner` threads. Each Scanner thread is responsible for scanning part of the data.
+
+Some or all of the predicate conditions in the query will be pushed to `OLAP_SCAN_NODE`. Some of these predicate conditions will continue to be pushed down to the storage engine in order to use the storage engine's index for data filtering. The other part will be kept in `OLAP_SCAN_NODE` to filter the data returned from the storage engine.
+
+The profile of a typical `OLAP_SCAN_NODE` is as follows. Some indicators will have different meanings depending on the storage format (V1 or V2).
+
+```
+OLAP_SCAN_NODE (id=0): (Active: 4.050ms, non-child: 35.68%)
+   -BitmapIndexFilterCount: 0   # Number of rows filtered by bitmap index

Review comment:
       ok




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@doris.apache.org
For additional commands, e-mail: commits-help@doris.apache.org