From 96afa7adeb2914284af0e93eec3793145e896ba3 Mon Sep 17 00:00:00 2001
From: Viacheslav Mitrofanov <unflag@ymail.com>
Date: Sun, 22 Oct 2023 11:33:34 +0100
Subject: [PATCH] Raw query tip and README.md updated

---
 README.md           | 37 ++++++++++++++++++++++++++++++++++++-
 src/QueryEditor.tsx | 18 +++++++++++-------
 2 files changed, 47 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index 9e03b6c..42f4e07 100644
--- a/README.md
+++ b/README.md
@@ -167,7 +167,7 @@ Note that `PER PARTITION LIMIT 1` used instead of `LIMIT 1` to query one row for
 
 ### Alerting
 Alerting is supported, however it has some limitations. Grafana does not support long(narrow) series in alerting, 
-so query result must be converted to wide series before hading it over to grafana. Datasource performs it in pretty
+so query result must be converted to wide series before handing it over to grafana. Datasource performs it in pretty
 simple way - it creates labels using all the non-timeseries field and then removes that fields from response.
 Basically, this query(using example table)
 ```
@@ -210,6 +210,41 @@ AND registered_at > $__unixEpochFrom AND registered_at < $__unixEpochTo
   * `dateOf(maxTimeuuid(registered_at*1000))` used to convert seconds to milliseconds(`registered_at*1000`) and then to convert milliseconds to `timestamp` type, which is handed over to grafana.
   * `$__unixEpochFrom` and `$__unixEpochTo` are variables with unix time in the seconds format that are used to fill out conditions part of the query.
 
+#### Cassandra fat partitions
+Cassandra stores data in `partitions` which are minimal storage units for the DB. It means that using the example table
+```
+CREATE TABLE IF NOT EXISTS temperature (
+    sensor_id uuid,
+    registered_at timestamp,
+    temperature int,
+    PRIMARY KEY ((sensor_id), registered_at)
+);
+```
+will lead to partitions bloating and performance degradation, because all the data for all time for specific `sensor_id` is stored in just one partition(first part of `PRIMARY KEY` is `PARTITION KEY`).
+To avoid that there is a technique called `bucketing`, which basically means that partitions are split up into smaller pieces.
+For instance, we can split that example table partitions by time: year, month, day, or even hour and less. What to choose depends on how
+much data stored in each partition. To achieve that the example table has to be modified like this:
+```
+CREATE TABLE IF NOT EXISTS temperature (
+    sensor_id uuid,
+    date date,
+    registered_at timestamp,
+    temperature int,
+    PRIMARY KEY ((sensor_id, date), registered_at)
+);
+```
+After that change the database schema became more effective because of bucketing by date, and queries will have a form of
+```
+SELECT sensor_id, temperature, registered_at
+FROM temperature
+WHERE sensor_id IN (99051fe9-6a9c-46c2-b949-38ef78858dd1, 99051fe9-6a9c-46c2-b949-38ef78858dd0) 
+AND date = '${__from:date:YYYY-MM-DD}'
+AND registered_at > $__timeFrom 
+AND registered_at < $__timeTo
+```
+Note that `$__from`/`$__to` variables are used. They are [grafana built-in variables](https://grafana.com/docs/grafana/latest/dashboards/variables/add-template-variables/#__from-and-__to), and they have formatting capabilities which are perfect for our case.
+In case when time range includes more than one day, each day has to be added into `AND date IN (...)` predicate. Another way to make it more convenient is to consider using larger buckets, e.g. month instead of day-size.
+
 ## Development
 
 [Developer documentation](https://github.com/HadesArchitect/GrafanaCassandraDatasource/wiki/Developer-Guide)
diff --git a/src/QueryEditor.tsx b/src/QueryEditor.tsx
index d00dad6..fac9e5a 100644
--- a/src/QueryEditor.tsx
+++ b/src/QueryEditor.tsx
@@ -1,8 +1,8 @@
-import React, { ChangeEvent, PureComponent, FormEvent } from 'react';
-import { Button, InlineField, InlineFieldRow, Input, InlineSwitch, Select, TextArea } from '@grafana/ui';
-import { QueryEditorProps, SelectableValue } from '@grafana/data';
-import { CassandraDatasource, CassandraDataSourceOptions } from './datasource';
-import { CassandraQuery } from './models';
+import React, {ChangeEvent, FormEvent, PureComponent} from 'react';
+import {Button, InlineField, InlineFieldRow, InlineSwitch, Input, Select, TextArea} from '@grafana/ui';
+import {CoreApp, QueryEditorProps, SelectableValue} from '@grafana/data';
+import {CassandraDatasource, CassandraDataSourceOptions} from './datasource';
+import {CassandraQuery} from './models';
 
 type Props = QueryEditorProps<CassandraDatasource, CassandraQuery, CassandraDataSourceOptions>;
 
@@ -42,6 +42,10 @@ export class QueryEditor extends PureComponent<Props> {
       props.query.valueId &&
       props.query.valueId !== ''
     ) {
+      // @ts-ignore
+      this.props.queries.forEach(function (value) {
+        console.log("TYPE: %s", value.queryType)
+      })
       this.props.onRunQuery();
     }
   }
@@ -150,7 +154,7 @@ export class QueryEditor extends PureComponent<Props> {
     const options = this.props;
 
     this.props.query.queryType = 'query';
-    if (this.props.app === 'unified-alerting') {
+    if (this.props.app !== undefined && this.props.app === CoreApp.UnifiedAlerting) {
       this.props.query.queryType = 'alert';
     }
 
@@ -162,7 +166,7 @@ export class QueryEditor extends PureComponent<Props> {
               <InlineField
                 label="Cassandra CQL Query"
                 labelWidth={30}
-                tooltip="Enter Cassandra CQL query. You can use $__timeFrom/$__timeTo and $__unixEpochFrom/$__unixEpochTo variables, they will be replaced by chosen range"
+                tooltip="Enter Cassandra CQL query. There are $__timeFrom/$__timeTo, $__unixEpochFrom/$__unixEpochTo and $__from/$__to variables to dynamically limit time range in queries. You should always use them to avoid excessive data fetching from DB."
                 grow
               >
                 <TextArea