We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Related #1578 (comment)
Consumer 在分配 partitions 時,除了得到負載分數外,還需注意 partition 不該與哪些 partitions 放在一起。否則會像 #1475 一樣,即使每個 consumer 分配了相同負載,吞吐量卻沒有得到改善
CostAware assignor 使用 NetworkIngressCost 時需要避免 同一個節點內流量差異過大的 partition 給同一個 consumer,故需要在 NetworkIngressCost 中實作反饋資訊供 assignor 分配時判斷,進而避免分配出負載平衡的 assignment 卻換來不穩定的吞吐量
NetworkIngressCost
The text was updated successfully, but these errors were encountered:
@chia7712 學長好,這幾天一直在想下面想討論的問題,不知道有沒有漏想或是怪怪的地方
所以想跟學長討論在 #1637 (comment) 中實作 feedback 時提到的 NetworkIngress cost 估算 upper bound 而非讓使用者介入實作
Upper bound 為一個邊界值,可搭配 traffic interval 來輔助 network ingress cost 產生 incompatibility 。
Upper bound
traffic interval
incompatibility
Sorry, something went wrong.
harryteng9527
Successfully merging a pull request may close this issue.
Related #1578 (comment)
Consumer 在分配 partitions 時,除了得到負載分數外,還需注意 partition 不該與哪些 partitions 放在一起。否則會像 #1475 一樣,即使每個 consumer 分配了相同負載,吞吐量卻沒有得到改善
CostAware assignor 使用
NetworkIngressCost
時需要避免 同一個節點內流量差異過大的 partition 給同一個 consumer,故需要在NetworkIngressCost
中實作反饋資訊供 assignor 分配時判斷,進而避免分配出負載平衡的 assignment 卻換來不穩定的吞吐量The text was updated successfully, but these errors were encountered: