-
Notifications
You must be signed in to change notification settings - Fork 3.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Fixed the logic that prevents all cluster slot requests sent to specific instances #1928
Conversation
…fic 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 the amount of requests is large, it will result in high CPU and a lot of 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. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Replace each tab with two spaces.
Hi @sazzad16 Please review. |
@petpetg I understand and I already reviewed. Please address what was said in the review. Thx! |
@sazzad16 Done. Thx! |
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? |
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.