From 5aee5763a3afd88bfad6aace4aa9cf2dde1bb4c5 Mon Sep 17 00:00:00 2001 From: Grace Cai Date: Tue, 6 Jan 2026 11:02:58 +0800 Subject: [PATCH 01/12] Add temp.md --- temp.md | 1 + 1 file changed, 1 insertion(+) create mode 100644 temp.md diff --git a/temp.md b/temp.md new file mode 100644 index 0000000000000..af27ff4986a7b --- /dev/null +++ b/temp.md @@ -0,0 +1 @@ +This is a test file. \ No newline at end of file From 12b6d61710e9ed40f31519e95e73580e88acb45a Mon Sep 17 00:00:00 2001 From: Grace Cai Date: Tue, 6 Jan 2026 11:03:02 +0800 Subject: [PATCH 02/12] Delete temp.md --- temp.md | 1 - 1 file changed, 1 deletion(-) delete mode 100644 temp.md diff --git a/temp.md b/temp.md deleted file mode 100644 index af27ff4986a7b..0000000000000 --- a/temp.md +++ /dev/null @@ -1 +0,0 @@ -This is a test file. \ No newline at end of file From ed5e350129882dae3746bf68e4da3be77790ed91 Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Tue, 6 Jan 2026 03:04:48 +0000 Subject: [PATCH 03/12] Auto-sync: Update English docs from Chinese PR Synced from: https://github.com/pingcap/docs-cn/pull/21196 Target PR: https://github.com/pingcap/docs/pull/22269 AI Provider: gemini Co-authored-by: github-actions[bot] --- .../pd-scheduling-best-practices.md | 5 ++- pd-control.md | 40 ++++++++++++++++++- 2 files changed, 43 insertions(+), 2 deletions(-) diff --git a/best-practices/pd-scheduling-best-practices.md b/best-practices/pd-scheduling-best-practices.md index f9b2263a14f07..86facc4a54b92 100644 --- a/best-practices/pd-scheduling-best-practices.md +++ b/best-practices/pd-scheduling-best-practices.md @@ -296,8 +296,11 @@ If a TiKV node fails, PD defaults to setting the corresponding node to the **dow Practically, if a node failure is considered unrecoverable, you can immediately take it offline. This makes PD replenish replicas soon in another node and reduces the risk of data loss. In contrast, if a node is considered recoverable, but the recovery cannot be done in 30 minutes, you can temporarily adjust `max-store-down-time` to a larger value to avoid unnecessary replenishment of the replicas and resources waste after the timeout. -In TiDB v5.2.0, TiKV introduces the mechanism of slow TiKV node detection. By sampling the requests in TiKV, this mechanism works out a score ranging from 1 to 100. A TiKV node with a score higher than or equal to 80 is marked as slow. You can add [`evict-slow-store-scheduler`](/pd-control.md#scheduler-show--add--remove--pause--resume--config--describe) to detect and schedule slow nodes. If only one TiKV is detected as slow, and the slow score reaches the limit (80 by default), the Leader in this node will be evicted (similar to the effect of `evict-leader-scheduler`). +In TiDB v5.2.0, TiKV introduces the mechanism of **disk-based** slow TiKV node detection. By sampling the requests in TiKV, this mechanism works out a score ranging from 1 to 100. A TiKV node with a score higher than or equal to 80 is marked as slow. You can add [`evict-slow-store-scheduler`](/pd-control.md#scheduler-show--add--remove--pause--resume--config--describe) to schedule slow nodes. If only one TiKV is detected as slow, and the slow score reaches the limit (80 by default), the Leader in this node will be evicted (similar to the effect of `evict-leader-scheduler`). + +Starting from v8.5.5 and v9.0.0, TiKV introduces a network-based slow node detection mechanism. Similar to disk-based slow node detection, this mechanism detects network anomalies by probing network delays between TiKV nodes and calculating a score. You can enable this mechanism using [`enable-network-slow-store`](/pd-control.md#scheduler-config-evict-slow-store-scheduler). > **Note:** > > **Leader eviction** is accomplished by PD sending scheduling requests to TiKV slow nodes and then TiKV executing the received scheduling requests sequentially. Due to factors such as **slow I/O**, slow nodes might experience request accumulation, causing some Leaders to wait until the delayed requests are processed before handling **Leader eviction** requests. This results in an overall extended time for **Leader eviction**. Therefore, when you enable `evict-slow-store-scheduler`, it is recommended to enable [`store-io-pool-size`](/tikv-configuration-file.md#store-io-pool-size-new-in-v530) as well to mitigate this situation. + diff --git a/pd-control.md b/pd-control.md index 82bcd7fc6123c..2083b4c3d3113 100644 --- a/pd-control.md +++ b/pd-control.md @@ -940,7 +940,7 @@ Usage: >> scheduler config evict-leader-scheduler // Display the stores in which the scheduler is located since v4.0.0 >> scheduler config evict-leader-scheduler add-store 2 // Add leader eviction scheduling for store 2 >> scheduler config evict-leader-scheduler delete-store 2 // Remove leader eviction scheduling for store 2 ->> scheduler add evict-slow-store-scheduler // When there is one and only one slow store, evict all Region leaders of that store +>> scheduler add evict-slow-store-scheduler // Automatically detect disk or network slow stores and evict all Region leaders on that store when conditions are met >> scheduler remove grant-leader-scheduler-1 // Remove the corresponding scheduler, and `-1` corresponds to the store ID >> scheduler pause balance-region-scheduler 10 // Pause the balance-region scheduler for 10 seconds >> scheduler pause all 10 // Pause all schedulers for 10 seconds @@ -964,6 +964,44 @@ The state of the scheduler can be one of the following: - `pending`: the scheduler cannot generate scheduling operators. For a scheduler in the `pending` state, brief diagnostic information is returned. The brief information describes the state of stores and explains why these stores cannot be selected for scheduling. - `normal`: there is no need to generate scheduling operators. +### `scheduler config evict-slow-store-scheduler` + +The `evict-slow-store-scheduler` is used to limit PD from scheduling Leaders to abnormal TiKV nodes and actively evict Leaders when necessary, thereby reducing the impact of slow nodes on the cluster when TiKV nodes experience disk I/O or network jitters. + +#### Disk Slow Stores + +Since v6.2.0, TiKV reports the `SlowScore` in store heartbeats to PD. This score is calculated based on disk I/O conditions. The score ranges from 1 to 100, where a higher value indicates a greater possibility of disk performance anomalies on that node. + +For disk slow stores, TiKV-side detection and PD-side scheduling based on `evict-slow-store-scheduler` are enabled by default and require no additional configuration. + +#### Network Slow Stores + +Since v8.5.5 and v9.0.0, TiKV supports reporting `NetworkSlowScore` in store heartbeats. This score is calculated based on network probe results and is used to identify slow nodes caused by network jitters. The score ranges from 1 to 100, where a higher value indicates a greater possibility of network anomalies. + +For compatibility and resource consumption considerations, network slow store detection and scheduling are disabled by default. To enable them, you need to complete the following configurations simultaneously: + +1. Enable the scheduler to handle network slow stores on the PD side: + + ```bash + scheduler config evict-slow-store-scheduler set enable-network-slow-store true + ``` + +2. On the TiKV side, set the [`raftstore.inspect-network-interval`](/tikv-configuration-file.md#inspect-network-interval) configuration item to a value greater than `0` to enable network probing. + +#### Recovery Time Control + +You can control the time a slow node needs to remain stable before being considered recovered by using the `recovery-duration` parameter. + +Example: + +```bash +>> scheduler config evict-slow-store-scheduler +{ + "recovery-duration": "1800" // 30 minutes +} +>> scheduler config evict-slow-store-scheduler set recovery-duration 600 +``` + ### `scheduler config balance-leader-scheduler` Use this command to view and control the `balance-leader-scheduler` policy. From 0d2012c7e7d67904fac3cef26a7b2876f887c169 Mon Sep 17 00:00:00 2001 From: qiancai Date: Tue, 6 Jan 2026 17:52:04 +0800 Subject: [PATCH 04/12] revise translation --- .../pd-scheduling-best-practices.md | 3 +-- pd-control.md | 24 +++++++++---------- tikv-configuration-file.md | 7 ++++++ 3 files changed, 20 insertions(+), 14 deletions(-) diff --git a/best-practices/pd-scheduling-best-practices.md b/best-practices/pd-scheduling-best-practices.md index 86facc4a54b92..62a3eb19e43bb 100644 --- a/best-practices/pd-scheduling-best-practices.md +++ b/best-practices/pd-scheduling-best-practices.md @@ -296,9 +296,8 @@ If a TiKV node fails, PD defaults to setting the corresponding node to the **dow Practically, if a node failure is considered unrecoverable, you can immediately take it offline. This makes PD replenish replicas soon in another node and reduces the risk of data loss. In contrast, if a node is considered recoverable, but the recovery cannot be done in 30 minutes, you can temporarily adjust `max-store-down-time` to a larger value to avoid unnecessary replenishment of the replicas and resources waste after the timeout. -In TiDB v5.2.0, TiKV introduces the mechanism of **disk-based** slow TiKV node detection. By sampling the requests in TiKV, this mechanism works out a score ranging from 1 to 100. A TiKV node with a score higher than or equal to 80 is marked as slow. You can add [`evict-slow-store-scheduler`](/pd-control.md#scheduler-show--add--remove--pause--resume--config--describe) to schedule slow nodes. If only one TiKV is detected as slow, and the slow score reaches the limit (80 by default), the Leader in this node will be evicted (similar to the effect of `evict-leader-scheduler`). +Starting from TiDB v5.2.0, TiKV introduces a mechanism to detect slow-disk nodes. By sampling the requests in TiKV, this mechanism works out a score ranging from 1 to 100. A TiKV node with a score higher than or equal to 80 is marked as slow. You can add [`evict-slow-store-scheduler`](/pd-control.md#scheduler-show--add--remove--pause--resume--config--describe) to schedule slow nodes. If only one TiKV node is detected as slow, and its slow score reaches the limit (80 by default), the Leaders on that node will be evicted (similar to the effect of `evict-leader-scheduler`). -Starting from v8.5.5 and v9.0.0, TiKV introduces a network-based slow node detection mechanism. Similar to disk-based slow node detection, this mechanism detects network anomalies by probing network delays between TiKV nodes and calculating a score. You can enable this mechanism using [`enable-network-slow-store`](/pd-control.md#scheduler-config-evict-slow-store-scheduler). > **Note:** > diff --git a/pd-control.md b/pd-control.md index 2083b4c3d3113..23f24fde13a35 100644 --- a/pd-control.md +++ b/pd-control.md @@ -940,7 +940,7 @@ Usage: >> scheduler config evict-leader-scheduler // Display the stores in which the scheduler is located since v4.0.0 >> scheduler config evict-leader-scheduler add-store 2 // Add leader eviction scheduling for store 2 >> scheduler config evict-leader-scheduler delete-store 2 // Remove leader eviction scheduling for store 2 ->> scheduler add evict-slow-store-scheduler // Automatically detect disk or network slow stores and evict all Region leaders on that store when conditions are met +>> scheduler add evict-slow-store-scheduler // Automatically detect slow-disk or slow-network nodes and evict all Region leaders on that node when certain conditions are met >> scheduler remove grant-leader-scheduler-1 // Remove the corresponding scheduler, and `-1` corresponds to the store ID >> scheduler pause balance-region-scheduler 10 // Pause the balance-region scheduler for 10 seconds >> scheduler pause all 10 // Pause all schedulers for 10 seconds @@ -966,31 +966,31 @@ The state of the scheduler can be one of the following: ### `scheduler config evict-slow-store-scheduler` -The `evict-slow-store-scheduler` is used to limit PD from scheduling Leaders to abnormal TiKV nodes and actively evict Leaders when necessary, thereby reducing the impact of slow nodes on the cluster when TiKV nodes experience disk I/O or network jitters. +The `evict-slow-store-scheduler` limits PD from scheduling Leaders to abnormal TiKV nodes and actively evicts Leaders when necessary, thereby reducing the impact of slow nodes on the cluster when TiKV nodes experience disk I/O or network jitter. -#### Disk Slow Stores +#### Slow-disk nodes -Since v6.2.0, TiKV reports the `SlowScore` in store heartbeats to PD. This score is calculated based on disk I/O conditions. The score ranges from 1 to 100, where a higher value indicates a greater possibility of disk performance anomalies on that node. +Starting from v6.2.0, TiKV reports a `SlowScore` in store heartbeats to PD, calculated based on disk I/O conditions. The score ranges from 1 to 100, where a higher value indicates a higher possibility of disk performance anomalies on that node. -For disk slow stores, TiKV-side detection and PD-side scheduling based on `evict-slow-store-scheduler` are enabled by default and require no additional configuration. +For slow-disk nodes, the detection on TiKV and the scheduling via `evict-slow-store-scheduler` on PD are enabled by default, which means no additional configuration is required. -#### Network Slow Stores +#### Slow-network nodes -Since v8.5.5 and v9.0.0, TiKV supports reporting `NetworkSlowScore` in store heartbeats. This score is calculated based on network probe results and is used to identify slow nodes caused by network jitters. The score ranges from 1 to 100, where a higher value indicates a greater possibility of network anomalies. +Starting from v8.5.5 and v9.0.0, TiKV supports reporting a `NetworkSlowScore` in store heartbeats to PD. It is calculated based on network detection results and helps identify slow nodes experiencing network jitter. The score ranges from 1 to 100, where a higher value indicates a higher possibility of network anomalies. -For compatibility and resource consumption considerations, network slow store detection and scheduling are disabled by default. To enable them, you need to complete the following configurations simultaneously: +For compatibility and resource consumption considerations, the detection and scheduling of slow-network nodes are disabled by default. To enable them, configure both of the following: -1. Enable the scheduler to handle network slow stores on the PD side: +1. Enable the PD scheduler to handle slow-network nodes: ```bash scheduler config evict-slow-store-scheduler set enable-network-slow-store true ``` -2. On the TiKV side, set the [`raftstore.inspect-network-interval`](/tikv-configuration-file.md#inspect-network-interval) configuration item to a value greater than `0` to enable network probing. +2. On TiKV, set the [`raftstore.inspect-network-interval`](/tikv-configuration-file.md#inspect-network-interval) configuration item to a value greater than `0` to enable network detection. -#### Recovery Time Control +#### Recovery time control -You can control the time a slow node needs to remain stable before being considered recovered by using the `recovery-duration` parameter. +You can specify how long a slow node must remain stable before it is considered recovered by using the `recovery-duration` parameter. Example: diff --git a/tikv-configuration-file.md b/tikv-configuration-file.md index a2ea81b9af2f6..52051ceadeecf 100644 --- a/tikv-configuration-file.md +++ b/tikv-configuration-file.md @@ -288,6 +288,13 @@ This document only describes the parameters that are not included in command-lin + Sets the size of the connection pool for service and forwarding requests to the server. Setting it to too small a value affects the request latency and load balancing. + Default value: `4` +### `inspect-network-interval` New in v8.5.5 and v9.0.0 + ++ Controls the interval at which the TiKV HealthChecker actively performs network detection to PD and other TiKV nodes. TiKV calculates a `NetworkSlowScore` based on the network detection and reports the network status of slow nodes to PD. ++ Setting this value to `0` disables the network detection. Setting it to a smaller value increases the detection frequency, which helps detect network jitter more quickly, but it also consumes more network bandwidth and CPU resources. ++ Default value: `100ms` ++ Valid range: 0 or `[10ms, +∞)` + ## readpool.unified Configuration items related to the single thread pool serving read requests. This thread pool supersedes the original storage thread pool and coprocessor thread pool since the 4.0 version. From 02b59cf1e5fae9001ff9affcfe573902e04f1598 Mon Sep 17 00:00:00 2001 From: qiancai Date: Tue, 6 Jan 2026 17:52:14 +0800 Subject: [PATCH 05/12] Update pd-scheduling-best-practices.md --- best-practices/pd-scheduling-best-practices.md | 1 + 1 file changed, 1 insertion(+) diff --git a/best-practices/pd-scheduling-best-practices.md b/best-practices/pd-scheduling-best-practices.md index 62a3eb19e43bb..25e7cfe843823 100644 --- a/best-practices/pd-scheduling-best-practices.md +++ b/best-practices/pd-scheduling-best-practices.md @@ -298,6 +298,7 @@ Practically, if a node failure is considered unrecoverable, you can immediately Starting from TiDB v5.2.0, TiKV introduces a mechanism to detect slow-disk nodes. By sampling the requests in TiKV, this mechanism works out a score ranging from 1 to 100. A TiKV node with a score higher than or equal to 80 is marked as slow. You can add [`evict-slow-store-scheduler`](/pd-control.md#scheduler-show--add--remove--pause--resume--config--describe) to schedule slow nodes. If only one TiKV node is detected as slow, and its slow score reaches the limit (80 by default), the Leaders on that node will be evicted (similar to the effect of `evict-leader-scheduler`). +Starting from v8.5.5 and v9.0.0, TiKV introduces a mechanism to detect slow-network nodes. Similar to slow-disk node detection, this mechanism identifies slow nodes by probing network latency between TiKV nodes and calculating a score. You can enable this mechanism using [`enable-network-slow-store`](/pd-control.md#scheduler-config-evict-slow-store-scheduler). > **Note:** > From dca27132e3981c83f71a3a0556f3a1422f078961 Mon Sep 17 00:00:00 2001 From: Grace Cai Date: Wed, 7 Jan 2026 10:22:53 +0800 Subject: [PATCH 06/12] Update pd-control.md --- pd-control.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pd-control.md b/pd-control.md index 23f24fde13a35..bf78c77f4ff61 100644 --- a/pd-control.md +++ b/pd-control.md @@ -940,7 +940,7 @@ Usage: >> scheduler config evict-leader-scheduler // Display the stores in which the scheduler is located since v4.0.0 >> scheduler config evict-leader-scheduler add-store 2 // Add leader eviction scheduling for store 2 >> scheduler config evict-leader-scheduler delete-store 2 // Remove leader eviction scheduling for store 2 ->> scheduler add evict-slow-store-scheduler // Automatically detect slow-disk or slow-network nodes and evict all Region leaders on that node when certain conditions are met +>> scheduler add evict-slow-store-scheduler // Automatically detect slow-disk or slow-network nodes and evict all Region leaders from those nodes when certain conditions are met >> scheduler remove grant-leader-scheduler-1 // Remove the corresponding scheduler, and `-1` corresponds to the store ID >> scheduler pause balance-region-scheduler 10 // Pause the balance-region scheduler for 10 seconds >> scheduler pause all 10 // Pause all schedulers for 10 seconds From 4c0e8e98efa2d689c72b5a77cdabab88e12baf18 Mon Sep 17 00:00:00 2001 From: Grace Cai Date: Wed, 7 Jan 2026 10:25:02 +0800 Subject: [PATCH 07/12] Update tikv-configuration-file.md --- tikv-configuration-file.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tikv-configuration-file.md b/tikv-configuration-file.md index 52051ceadeecf..8a349b6f90b1d 100644 --- a/tikv-configuration-file.md +++ b/tikv-configuration-file.md @@ -293,7 +293,7 @@ This document only describes the parameters that are not included in command-lin + Controls the interval at which the TiKV HealthChecker actively performs network detection to PD and other TiKV nodes. TiKV calculates a `NetworkSlowScore` based on the network detection and reports the network status of slow nodes to PD. + Setting this value to `0` disables the network detection. Setting it to a smaller value increases the detection frequency, which helps detect network jitter more quickly, but it also consumes more network bandwidth and CPU resources. + Default value: `100ms` -+ Valid range: 0 or `[10ms, +∞)` ++ Value range: 0 or `[10ms, +∞)` ## readpool.unified From d2a24e570f64dd183a691c5489bac511ecad9f76 Mon Sep 17 00:00:00 2001 From: Grace Cai Date: Tue, 13 Jan 2026 09:37:37 +0800 Subject: [PATCH 08/12] Apply suggestions from code review Co-authored-by: Aolin --- pd-control.md | 4 ++-- tikv-configuration-file.md | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/pd-control.md b/pd-control.md index bf78c77f4ff61..a05c05ff50153 100644 --- a/pd-control.md +++ b/pd-control.md @@ -940,7 +940,7 @@ Usage: >> scheduler config evict-leader-scheduler // Display the stores in which the scheduler is located since v4.0.0 >> scheduler config evict-leader-scheduler add-store 2 // Add leader eviction scheduling for store 2 >> scheduler config evict-leader-scheduler delete-store 2 // Remove leader eviction scheduling for store 2 ->> scheduler add evict-slow-store-scheduler // Automatically detect slow-disk or slow-network nodes and evict all Region leaders from those nodes when certain conditions are met +>> scheduler add evict-slow-store-scheduler // Automatically detect slow-disk or slow-network nodes and evict all Region leaders from those nodes when specific conditions are met >> scheduler remove grant-leader-scheduler-1 // Remove the corresponding scheduler, and `-1` corresponds to the store ID >> scheduler pause balance-region-scheduler 10 // Pause the balance-region scheduler for 10 seconds >> scheduler pause all 10 // Pause all schedulers for 10 seconds @@ -970,7 +970,7 @@ The `evict-slow-store-scheduler` limits PD from scheduling Leaders to abnormal T #### Slow-disk nodes -Starting from v6.2.0, TiKV reports a `SlowScore` in store heartbeats to PD, calculated based on disk I/O conditions. The score ranges from 1 to 100, where a higher value indicates a higher possibility of disk performance anomalies on that node. +Starting from v6.2.0, TiKV reports a `SlowScore` in store heartbeats to PD. This score is calculated based on disk I/O conditions and ranges from 1 to 100. A higher value indicates a higher possibility of disk performance anomalies on that node. For slow-disk nodes, the detection on TiKV and the scheduling via `evict-slow-store-scheduler` on PD are enabled by default, which means no additional configuration is required. diff --git a/tikv-configuration-file.md b/tikv-configuration-file.md index 8a349b6f90b1d..02c89b0039d06 100644 --- a/tikv-configuration-file.md +++ b/tikv-configuration-file.md @@ -290,10 +290,10 @@ This document only describes the parameters that are not included in command-lin ### `inspect-network-interval` New in v8.5.5 and v9.0.0 -+ Controls the interval at which the TiKV HealthChecker actively performs network detection to PD and other TiKV nodes. TiKV calculates a `NetworkSlowScore` based on the network detection and reports the network status of slow nodes to PD. ++ Controls the interval at which the TiKV HealthChecker actively performs network detection to PD and other TiKV nodes. TiKV calculates a `NetworkSlowScore` based on the network detection results and reports the network status of slow nodes to PD. + Setting this value to `0` disables the network detection. Setting it to a smaller value increases the detection frequency, which helps detect network jitter more quickly, but it also consumes more network bandwidth and CPU resources. + Default value: `100ms` -+ Value range: 0 or `[10ms, +∞)` ++ Value range: `0` or `[10ms, +∞)` ## readpool.unified From 65a83650c6d8b36c8dfcc987beafd38e249d5c91 Mon Sep 17 00:00:00 2001 From: Grace Cai Date: Tue, 13 Jan 2026 09:41:12 +0800 Subject: [PATCH 09/12] Apply suggestions from code review --- best-practices/pd-scheduling-best-practices.md | 1 - 1 file changed, 1 deletion(-) diff --git a/best-practices/pd-scheduling-best-practices.md b/best-practices/pd-scheduling-best-practices.md index 25e7cfe843823..fbc57ec2142a8 100644 --- a/best-practices/pd-scheduling-best-practices.md +++ b/best-practices/pd-scheduling-best-practices.md @@ -303,4 +303,3 @@ Starting from v8.5.5 and v9.0.0, TiKV introduces a mechanism to detect slow-netw > **Note:** > > **Leader eviction** is accomplished by PD sending scheduling requests to TiKV slow nodes and then TiKV executing the received scheduling requests sequentially. Due to factors such as **slow I/O**, slow nodes might experience request accumulation, causing some Leaders to wait until the delayed requests are processed before handling **Leader eviction** requests. This results in an overall extended time for **Leader eviction**. Therefore, when you enable `evict-slow-store-scheduler`, it is recommended to enable [`store-io-pool-size`](/tikv-configuration-file.md#store-io-pool-size-new-in-v530) as well to mitigate this situation. - From a7109527b766e5c4aa68e121d04ceb9ac459524a Mon Sep 17 00:00:00 2001 From: Grace Cai Date: Tue, 13 Jan 2026 09:53:56 +0800 Subject: [PATCH 10/12] fix a broken link --- pd-control.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pd-control.md b/pd-control.md index a05c05ff50153..39603f7dc7ffc 100644 --- a/pd-control.md +++ b/pd-control.md @@ -986,7 +986,7 @@ For compatibility and resource consumption considerations, the detection and sch scheduler config evict-slow-store-scheduler set enable-network-slow-store true ``` -2. On TiKV, set the [`raftstore.inspect-network-interval`](/tikv-configuration-file.md#inspect-network-interval) configuration item to a value greater than `0` to enable network detection. +2. On TiKV, set the [`raftstore.inspect-network-interval`](/tikv-configuration-file.md#inspect-network-interval-new-in-v855-and-v900) configuration item to a value greater than `0` to enable network detection. #### Recovery time control From 5f196b94ea1b416ec67b5931caee44ae3e3be3f5 Mon Sep 17 00:00:00 2001 From: Grace Cai Date: Tue, 13 Jan 2026 10:09:42 +0800 Subject: [PATCH 11/12] remove the info about v9.0.0 --- best-practices/pd-scheduling-best-practices.md | 2 +- pd-control.md | 2 +- tikv-configuration-file.md | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/best-practices/pd-scheduling-best-practices.md b/best-practices/pd-scheduling-best-practices.md index fbc57ec2142a8..b81bd3217d9ba 100644 --- a/best-practices/pd-scheduling-best-practices.md +++ b/best-practices/pd-scheduling-best-practices.md @@ -298,7 +298,7 @@ Practically, if a node failure is considered unrecoverable, you can immediately Starting from TiDB v5.2.0, TiKV introduces a mechanism to detect slow-disk nodes. By sampling the requests in TiKV, this mechanism works out a score ranging from 1 to 100. A TiKV node with a score higher than or equal to 80 is marked as slow. You can add [`evict-slow-store-scheduler`](/pd-control.md#scheduler-show--add--remove--pause--resume--config--describe) to schedule slow nodes. If only one TiKV node is detected as slow, and its slow score reaches the limit (80 by default), the Leaders on that node will be evicted (similar to the effect of `evict-leader-scheduler`). -Starting from v8.5.5 and v9.0.0, TiKV introduces a mechanism to detect slow-network nodes. Similar to slow-disk node detection, this mechanism identifies slow nodes by probing network latency between TiKV nodes and calculating a score. You can enable this mechanism using [`enable-network-slow-store`](/pd-control.md#scheduler-config-evict-slow-store-scheduler). +Starting from v8.5.5, TiKV introduces a mechanism to detect slow-network nodes. Similar to slow-disk node detection, this mechanism identifies slow nodes by probing network latency between TiKV nodes and calculating a score. You can enable this mechanism using [`enable-network-slow-store`](/pd-control.md#scheduler-config-evict-slow-store-scheduler). > **Note:** > diff --git a/pd-control.md b/pd-control.md index 39603f7dc7ffc..4d3d6c09396cb 100644 --- a/pd-control.md +++ b/pd-control.md @@ -976,7 +976,7 @@ For slow-disk nodes, the detection on TiKV and the scheduling via `evict-slow-st #### Slow-network nodes -Starting from v8.5.5 and v9.0.0, TiKV supports reporting a `NetworkSlowScore` in store heartbeats to PD. It is calculated based on network detection results and helps identify slow nodes experiencing network jitter. The score ranges from 1 to 100, where a higher value indicates a higher possibility of network anomalies. +Starting from v8.5.5, TiKV supports reporting a `NetworkSlowScore` in store heartbeats to PD. It is calculated based on network detection results and helps identify slow nodes experiencing network jitter. The score ranges from 1 to 100, where a higher value indicates a higher possibility of network anomalies. For compatibility and resource consumption considerations, the detection and scheduling of slow-network nodes are disabled by default. To enable them, configure both of the following: diff --git a/tikv-configuration-file.md b/tikv-configuration-file.md index 02c89b0039d06..e94b7b51011e7 100644 --- a/tikv-configuration-file.md +++ b/tikv-configuration-file.md @@ -288,7 +288,7 @@ This document only describes the parameters that are not included in command-lin + Sets the size of the connection pool for service and forwarding requests to the server. Setting it to too small a value affects the request latency and load balancing. + Default value: `4` -### `inspect-network-interval` New in v8.5.5 and v9.0.0 +### `inspect-network-interval` New in v8.5.5 + Controls the interval at which the TiKV HealthChecker actively performs network detection to PD and other TiKV nodes. TiKV calculates a `NetworkSlowScore` based on the network detection results and reports the network status of slow nodes to PD. + Setting this value to `0` disables the network detection. Setting it to a smaller value increases the detection frequency, which helps detect network jitter more quickly, but it also consumes more network bandwidth and CPU resources. From 16fcef3654d01078f75fbc6ad4f3d740dd0ebd5b Mon Sep 17 00:00:00 2001 From: Grace Cai Date: Tue, 13 Jan 2026 10:10:28 +0800 Subject: [PATCH 12/12] fix a broken link --- pd-control.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pd-control.md b/pd-control.md index 4d3d6c09396cb..17e67dd39964f 100644 --- a/pd-control.md +++ b/pd-control.md @@ -986,7 +986,7 @@ For compatibility and resource consumption considerations, the detection and sch scheduler config evict-slow-store-scheduler set enable-network-slow-store true ``` -2. On TiKV, set the [`raftstore.inspect-network-interval`](/tikv-configuration-file.md#inspect-network-interval-new-in-v855-and-v900) configuration item to a value greater than `0` to enable network detection. +2. On TiKV, set the [`raftstore.inspect-network-interval`](/tikv-configuration-file.md#inspect-network-interval-new-in-v855) configuration item to a value greater than `0` to enable network detection. #### Recovery time control