Update system-variables.md

.github/workflows/sync-docs-cn-to-en.yml

@@ -0,0 +1,163 @@
+name: Sync Docs Changes from ZH PR to EN PR
+
+on:
+  workflow_dispatch:
+    inputs:
+      source_pr_url:
+        description: 'Source PR URL (Chinese docs repository)'
+        required: true
+        type: string
+        default: ''
+      target_pr_url:
+        description: 'Target PR URL (English docs repository)'
+        required: true
+        type: string
+        default: ''
+      ai_provider:
+        description: 'AI Provider to use for translation'
+        required: false
+        type: choice
+        options:
+          - deepseek
+          - gemini
+        default: 'gemini'
+
+jobs:
+  sync-docs:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout current repository
+        uses: actions/checkout@v4
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          fetch-depth: 0
+
+      - name: Checkout ai-pr-translator repository
+        uses: actions/checkout@v4
+        with:
+          repository: "qiancai/ai-pr-translator"
+          ref: "main"
+          path: "ai-pr-translator"
+
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.9'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r ai-pr-translator/scripts/requirements.txt
+
+      - name: Extract PR information
+        id: extract_info
+        run: |
+          # Extract source repo info
+          SOURCE_URL="${{ github.event.inputs.source_pr_url }}"
+          SOURCE_OWNER=$(echo $SOURCE_URL | cut -d'/' -f4)
+          SOURCE_REPO=$(echo $SOURCE_URL | cut -d'/' -f5)
+          SOURCE_PR=$(echo $SOURCE_URL | cut -d'/' -f7)
+
+          # Extract target repo info
+          TARGET_URL="${{ github.event.inputs.target_pr_url }}"
+          TARGET_OWNER=$(echo $TARGET_URL | cut -d'/' -f4)
+          TARGET_REPO=$(echo $TARGET_URL | cut -d'/' -f5)
+          TARGET_PR=$(echo $TARGET_URL | cut -d'/' -f7)
+
+          echo "source_owner=${SOURCE_OWNER}" >> $GITHUB_OUTPUT
+          echo "source_repo=${SOURCE_REPO}" >> $GITHUB_OUTPUT
+          echo "source_pr=${SOURCE_PR}" >> $GITHUB_OUTPUT
+          echo "target_owner=${TARGET_OWNER}" >> $GITHUB_OUTPUT
+          echo "target_repo=${TARGET_REPO}" >> $GITHUB_OUTPUT
+          echo "target_pr=${TARGET_PR}" >> $GITHUB_OUTPUT
+
+          echo "Source: ${SOURCE_OWNER}/${SOURCE_REPO}#${SOURCE_PR}"
+          echo "Target: ${TARGET_OWNER}/${TARGET_REPO}#${TARGET_PR}"
+
+      - name: Get target PR branch info
+        id: target_branch
+        run: |
+          # Get target PR branch name
+          TARGET_BRANCH=$(curl -s \
+            -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/${{ steps.extract_info.outputs.target_owner }}/${{ steps.extract_info.outputs.target_repo }}/pulls/${{ steps.extract_info.outputs.target_pr }}" \
+            | jq -r '.head.ref')
+
+          echo "target_branch=${TARGET_BRANCH}" >> $GITHUB_OUTPUT
+          echo "Target branch: ${TARGET_BRANCH}"
+
+      - name: Clone target repository
+        run: |
+          # Clone target repository with the PR branch
+          git clone https://x-access-token:${{ secrets.GITHUB_TOKEN }}@github.com/${{ steps.extract_info.outputs.target_owner }}/${{ steps.extract_info.outputs.target_repo }}.git target_repo
+          cd target_repo
+          git checkout ${{ steps.target_branch.outputs.target_branch }}
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+
+      - name: Run sync script
+        id: sync_script
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          DEEPSEEK_API_TOKEN: ${{ secrets.DEEPSEEK_API_TOKEN }}
+          GEMINI_API_TOKEN: ${{ secrets.GEMINI_API_TOKEN }}
+          SOURCE_PR_URL: ${{ github.event.inputs.source_pr_url }}
+          TARGET_PR_URL: ${{ github.event.inputs.target_pr_url }}
+          AI_PROVIDER: ${{ github.event.inputs.ai_provider }}
+          TARGET_REPO_PATH: ${{ github.workspace }}/target_repo
+        run: |
+          cd ai-pr-translator/scripts
+          if python main_workflow.py; then
+            echo "sync_success=true" >> $GITHUB_OUTPUT
+            echo "✅ Sync script completed successfully"
+          else
+            echo "sync_success=false" >> $GITHUB_OUTPUT
+            echo "❌ Sync script failed"
+            exit 1
+          fi
+
+      - name: Commit and push changes
+        if: steps.sync_script.outputs.sync_success == 'true'
+        run: |
+          cd target_repo
+          git add .
+          if git diff --staged --quiet; then
+            echo "No changes to commit"
+          else
+            git commit -m "Auto-sync: Update English docs from Chinese PR ${{ github.event.inputs.source_pr_url }}
+
+            Synced from: ${{ github.event.inputs.source_pr_url }}
+            Target PR: ${{ github.event.inputs.target_pr_url }}
+            AI Provider: ${{ github.event.inputs.ai_provider }}
+
+            Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>"
+
+            git push origin ${{ steps.target_branch.outputs.target_branch }}
+            echo "Changes pushed to target PR branch: ${{ steps.target_branch.outputs.target_branch }}"
+          fi
+
+      - name: Add success comment to target PR
+        if: steps.sync_script.outputs.sync_success == 'true'
+        run: |
+          # Add a comment to the target PR about the sync success
+          curl -X POST \
+            -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/${{ steps.extract_info.outputs.target_owner }}/${{ steps.extract_info.outputs.target_repo }}/issues/${{ steps.extract_info.outputs.target_pr }}/comments" \
+            -d "{
+              \"body\": \"🤖 **Auto-sync completed successfully**\\n\\n📥 **Source PR**: ${{ github.event.inputs.source_pr_url }}\\n🎯 **Target PR**: ${{ github.event.inputs.target_pr_url }}\\n✅ English documentation has been updated based on Chinese documentation changes.\\n\\n_This comment was generated automatically by the sync workflow._\"
+            }"
+
+      - name: Add failure comment to target PR
+        if: steps.sync_script.outputs.sync_success == 'false'
+        run: |
+          # Add a comment to the target PR about the sync failure
+          curl -X POST \
+            -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/${{ steps.extract_info.outputs.target_owner }}/${{ steps.extract_info.outputs.target_repo }}/issues/${{ steps.extract_info.outputs.target_pr }}/comments" \
+            -d "{
+              \"body\": \"🤖 **Auto-sync failed**\\n\\n📥 **Source PR**: ${{ github.event.inputs.source_pr_url }}\\n🎯 **Target PR**: ${{ github.event.inputs.target_pr_url }}\\n❌ The sync process encountered an error. Please check the workflow logs for details.\\n\\n_This comment was generated automatically by the sync workflow._\"
+            }"

scripts/sync-en-cloud-toc-changes-to-zh.py

@@ -17,7 +17,7 @@
 from urllib.error import URLError, HTTPError
 from google import genai
 
-REPO_OWNER = "pingcap"
+REPO_OWNER = "qiancai"
 REPO_NAME = "docs"
 EN_BRANCH = "release-8.5"
 ZH_BRANCH = "i18n-zh-release-8.5"

system-variables.md

@@ -1727,7 +1727,6 @@ mysql> SELECT job_info FROM mysql.analyze_jobs ORDER BY end_time DESC LIMIT 1;
     - If `tidb_ddl_enable_fast_reorg` is set to `OFF`, `ADD INDEX` is executed as a transaction. If there are many update operations such as `UPDATE` and `REPLACE` in the target columns during the `ADD INDEX` execution, a larger batch size indicates a larger probability of transaction conflicts. In this case, it is recommended that you set the batch size to a smaller value. The minimum value is 32.
     - If the transaction conflict does not exist, or if `tidb_ddl_enable_fast_reorg` is set to `ON`, you can set the batch size to a large value. This makes data backfilling faster but also increases the write pressure on TiKV. For a proper batch size, you also need to refer to the value of `tidb_ddl_reorg_worker_cnt`. See [Interaction Test on Online Workloads and `ADD INDEX` Operations](https://docs.pingcap.com/tidb/dev/online-workloads-and-add-index-operations) for reference.
     - Starting from v8.3.0, this parameter is supported at the SESSION level. Modifying the parameter at the GLOBAL level will not impact currently running DDL statements. It will only apply to DDLs submitted in new sessions.
-    - Starting from v8.5.0, you can modify this parameter for a running DDL job by executing `ADMIN ALTER DDL JOBS <job_id> BATCH_SIZE = <new_batch_size>;`. Note that this operation is not supported for `ADD INDEX` DDL when [`tidb_enable_dist_task`](/system-variables.md#tidb_enable_dist_task-new-in-v710) is enabled. For details, see [`ADMIN ALTER DDL JOBS`](/sql-statements/sql-statement-admin-alter-ddl.md).
 
 ### tidb_ddl_reorg_priority
 
@@ -1779,7 +1778,6 @@ Assume that you have a cluster with 4 TiDB nodes and multiple TiKV nodes. In thi
 - Unit: Threads
 - This variable is used to set the concurrency of the DDL operation in the `re-organize` phase.
 - Starting from v8.3.0, this parameter is supported at the SESSION level. Modifying the parameter at the GLOBAL level will not impact currently running DDL statements. It will only apply to DDLs submitted in new sessions.
-- Starting from v8.5.0, you can modify this parameter for a running DDL job by executing `ADMIN ALTER DDL JOBS <job_id> THREAD = <new_thread_count>;`. Note that this operation is not supported for `ADD INDEX` DDL when [`tidb_enable_dist_task`](/system-variables.md#tidb_enable_dist_task-new-in-v710) is enabled. For details, see [`ADMIN ALTER DDL JOBS`](/sql-statements/sql-statement-admin-alter-ddl.md).
 
 ### `tidb_enable_fast_create_table` <span class="version-mark">New in v8.0.0</span>
 
@@ -1793,6 +1791,16 @@ Assume that you have a cluster with 4 TiDB nodes and multiple TiKV nodes. In thi
 - This variable is renamed from the variable [`tidb_ddl_version`](https://docs-archive.pingcap.com/tidb/v7.6/system-variables#tidb_ddl_version-new-in-v760) that is introduced in v7.6.0. Starting from v8.0.0, `tidb_ddl_version` no longer takes effect.
 - Starting from TiDB v8.5.0, the accelerated table creation feature is enabled by default for newly created clusters, with `tidb_enable_fast_create_table` set to `ON`. For clusters upgraded from v8.4.0 or earlier versions, the default value of `tidb_enable_fast_create_table` remains unchanged.
 
+### `tidb_opt_selectivity_factor` <span class="version-mark">Introduced in v9.0.0</span>
+
+- Scope: SESSION | GLOBAL
+- Is persisted to the cluster: Yes
+- Is controlled by the Hint [SET_VAR](/optimizer-hints.md#set_varvar_namevar_value): Yes
+- Type: Floating-point number
+- Value range: `[0, 1]`
+- Default value: `0.8`
+- This variable is used to specify the default selectivity of the TiDB optimizer. In some cases, when the optimizer cannot derive the predicate selectivity based on statistics, the optimizer uses this default selectivity as an alternative value. **It is not recommended** to modify this value.
+
 ### tidb_default_string_match_selectivity <span class="version-mark">New in v6.2.0</span>
 
 - Scope: SESSION | GLOBAL

ticdc/ticdc-faq.md

@@ -407,7 +407,7 @@ If the downstream is a TiDB cluster or MySQL instance, it is recommended that yo
 
 ## Replication of a single table can only be run on a single TiCDC node. Will it be possible to use multiple TiCDC nodes to replicate data of multiple tables?
 
-Starting from v7.1.0, TiCDC supports the MQ sink to replicate data change logs at the granularity of TiKV Regions, which achieves scalable processing capability and allows TiCDC to replicate a single table with a large number of Regions. To enable this feature, you can configure the following parameter in the [TiCDC changefeed configuration file](/ticdc/ticdc-changefeed-config.md):
+Starting from v7.1.0, TiCDC supports the MQ sink to replicate data change logs at the granularity of TiKV Regions, which achieves scalable processing capability and allows TiCDC to replicate a single table with a large number of Regions. To enable this feature, you can configure the following parameter in the [TiCDC configuration file](/ticdc/ticdc-changefeed-config.md):
 
 ```toml
 [scheduler]

tikv-configuration-file.md

@@ -2709,8 +2709,8 @@ TiKV MVCC in-memory engine (IME) configuration items related to the storage laye
 > + After the in-memory engine is enabled, `block-cache.capacity` automatically decreases by 10%.
 > + If you manually configure `capacity`, `block-cache.capacity` does not automatically decrease. In this case, you need to manually adjust its value to avoid OOM.
 
-+ Controls the maximum memory size that the [TiKV MVCC in-memory engine](/tikv-in-memory-engine.md) can use. The memory capacity determines the number of Regions that can be cached. When the capacity is full, the in-memory engine loads new Regions and evicts cached Regions based on the redundancy of Region MVCC.
-+ Default value: `min(10% of the total system memory, 5 GiB)`
++ Controls the maximum memory size that the in-memory engine can use. The maximum value is 5 GiB. You can manually configure it to use more memory.
++ Default value: 10% of the system memory.
 
 ### `gc-run-interval` <span class="version-mark">New in v8.5.0</span>