Fixed the logic that prevents all cluster slot requests sent to specific instances

[petpetg]

Fixed the logic that prevents all cluster slot requests sent to specific instances when jedis is initialized on many processes(such as storm with a lot of works).
It can cause high CPU and the impact of many slow queries.

Please review.
thanks.

[petpetg]

When the amount of requests is large, it will result in high CPU and a lot of slow queries.

[petpetg]

When a storm application with 200 workers is started, the CPU utilization of one instance exceeds 20%, while that of the other instances is only 2%. At the same time, there will be a lot of requests blocked and slow queries.

[sazzad16]

Replace each tab with two spaces.

[petpetg]

Hi @sazzad16
This changed was fixed the logic that prevents all cluster slot requests sent to specific instances when jedis is initialized on many processes(such as storm with a lot of works). It can cause high CPU and the impact of many slow queries.
When a storm application with 200 workers is started, the CPU utilization of one instance exceeds 20%, while that of the other instances is only 2%. At the same time, there will be a lot of requests blocked and slow queries.

Please review.
thanks.

[sazzad16]

@petpetg I understand and I already reviewed. Please address what was said in the review. Thx!

[petpetg]

@sazzad16 Done. Thx!

[gkorland]

It feels like shuffle might be a too "heavy" solution for this, should we just let each client randomly start to iterate the node from a different place?