What is the difference between the two parameters: TiKV readpool.storage and readpool.coprocessor?

Note:
This topic has been translated from a Chinese forum by GPT and might contain errors.

Original topic: TiKV readpool.storage和readpool.coprocessor 两个参数有什么区别

| username: 超7成网友

As per the topic, what is the difference between these two parameters? I see that the documentation states they both handle read requests.

| username: xfworld | Original post link

One controls disk reading,
the other controls the number of logical parallelisms.

This is the difference: one is physical reading, the other is logical reading.

| username: TiDBer_jYQINSnf | Original post link

Your version is a bit old.

TiKV read requests are divided into two categories:

One category is simple queries that specify querying one or a few rows, which run in the Storage Read Pool.
The other category is complex aggregation calculations and range queries, which run in the Coprocessor Read Pool.

In simple terms, the coprocessor read pool is the thread pool that handles compute pushdown. Generally, those scan-related requests.
In the explain SQL, tikv(cop) refers to the coprocessor, while tikv refers to the storage read pool.

| username: MrSylar | Original post link

Refer to this image. Essentially, they all serve the purpose of reading; it’s just that TiDB categorizes the read operations.

| username: TIDB-Learner | Original post link

Such an old version, what scenarios are using it? A patch released in 2020. Back then, I hadn’t even heard of TiDB.

| username: dba远航 | Original post link

Now we are uniformly using the UnifyReadPool thread pool.

| username: system | Original post link

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.