apoorvmittal10 commented on PR #19928:
URL: https://github.com/apache/kafka/pull/19928#issuecomment-2957255489

   > @apoorvmittal10 : Thanks for the experimental results. For Local log 
fetch, could you run multiple groups on the same topic? Could you also measure 
the CPU usage on the broker?
   
   Please find the details below:
   
   #### Message size 1024 Bytes, 5 share groups, no parallel produce, read 
2Million records each (2 GB bytes read)
   
   ```
   ➜  kafka git:(KAFKA-19389) ✗ bin/kafka-share-consumer-perf-test.sh 
--bootstrap-server localhost:9092 --topic T2 
   --messages 2000000 --timeout 300000 --group share-group-local1
   start.time, end.time, data.consumed.in.MB, MB.sec, nMsg.sec, 
data.consumed.in.nMsg, fetch.time.ms
   [2025-06-10 00:05:56,619] WARN Share groups and KafkaShareConsumer are part 
of a preview feature introduced by KIP-932, and are not recommended for use in 
production. 
(org.apache.kafka.clients.consumer.internals.ShareConsumerDelegateCreator)
   2025-06-10 00:05:56:646, 2025-06-10 00:08:04:118, 1953.3984, 15.3241, 
15691.9167, 2000280, 127472
   ```
   
   ```
   ➜  kafka git:(KAFKA-19389) ✗ bin/kafka-share-consumer-perf-test.sh 
--bootstrap-server localhost:9092 --topic T2
    --messages 2000000 --timeout 300000 --group share-group-local2
   start.time, end.time, data.consumed.in.MB, MB.sec, nMsg.sec, 
data.consumed.in.nMsg, fetch.time.ms
   [2025-06-10 00:05:57,676] WARN Share groups and KafkaShareConsumer are part 
of a preview feature introduced by KIP-932, and are not recommended for use in 
production. 
(org.apache.kafka.clients.consumer.internals.ShareConsumerDelegateCreator)
   2025-06-10 00:05:57:705, 2025-06-10 00:08:07:343, 1953.3984, 15.0681, 
15429.7351, 2000280, 129638
   ```
   
   ```
   ➜  kafka git:(KAFKA-19389) ✗ bin/kafka-share-consumer-perf-test.sh 
--bootstrap-server localhost:9092 --topic T2 
   --messages 2000000 --timeout 300000 --group share-group-local3
   start.time, end.time, data.consumed.in.MB, MB.sec, nMsg.sec, 
data.consumed.in.nMsg, fetch.time.ms
   [2025-06-10 00:05:58,849] WARN Share groups and KafkaShareConsumer are part 
of a preview feature introduced by KIP-932, and are not recommended for use in 
production. 
(org.apache.kafka.clients.consumer.internals.ShareConsumerDelegateCreator)
   2025-06-10 00:05:58:877, 2025-06-10 00:08:09:053, 1953.3984, 15.0058, 
15365.9661, 2000280, 130176
   ```
   
   ```
   ➜  kafka git:(KAFKA-19389) ✗ bin/kafka-share-consumer-perf-test.sh 
--bootstrap-server localhost:9092 --topic T2 
   --messages 2000000 --timeout 300000 --group share-group-local4
   start.time, end.time, data.consumed.in.MB, MB.sec, nMsg.sec, 
data.consumed.in.nMsg, fetch.time.ms
   [2025-06-10 00:06:00,081] WARN Share groups and KafkaShareConsumer are part 
of a preview feature introduced by KIP-932, and are not recommended for use in 
production. 
(org.apache.kafka.clients.consumer.internals.ShareConsumerDelegateCreator)
   2025-06-10 00:06:00:109, 2025-06-10 00:08:09:869, 1953.3984, 15.0539, 
15415.2281, 2000280, 129760
   ```
   
   ```
   ➜  kafka git:(KAFKA-19389) ✗ bin/kafka-share-consumer-perf-test.sh 
--bootstrap-server localhost:9092 --topic T2
    --messages 2000000 --timeout 300000 --group share-group-local5
   start.time, end.time, data.consumed.in.MB, MB.sec, nMsg.sec, 
data.consumed.in.nMsg, fetch.time.ms
   [2025-06-10 00:06:01,475] WARN Share groups and KafkaShareConsumer are part 
of a preview feature introduced by KIP-932, and are not recommended for use in 
production. 
(org.apache.kafka.clients.consumer.internals.ShareConsumerDelegateCreator)
   2025-06-10 00:06:01:503, 2025-06-10 00:08:10:307, 1953.3984, 15.1657, 
15529.6419, 2000280, 128804
   ```
   
   #### Memory Usage:
   
   ![Screenshot 2025-06-10 at 00 10 
53](https://github.com/user-attachments/assets/f93c6805-7776-4587-baf9-9243c88d6f2f)
   
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: jira-unsubscr...@kafka.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org

Reply via email to