Update: We can see the same behavior with acks=all as well. After running for sometime, throughput drops a lot.
What can I monitor to debug this issue? ________________________________ From: Prateek Kohli <prateek.ko...@ericsson.com> Sent: Monday, August 21, 2023 8:05:00 pm To: users@kafka.apache.org <users@kafka.apache.org> Subject: RE: Sudden performance dip with acks=1 Attaching Grafana graphs for reference. Network and I/O threads are more than 60% idle. From: Prateek Kohli <prateek.ko...@ericsson.com.INVALID> Sent: 21 August 2023 19:56 To: users@kafka.apache.org Subject: Sudden performance dip with acks=1 Hi, I am trying to test Kafka performance in my setup using kafka-perf scripts provided by Kafka. I see a behavior in my Kafka cluster in case of acks=1, which I am unable to understand. My run works as expected for sometime, but after that suddenly “fetcher lag” starts to increase exponentially and Producer/consumer throughput decreases significantly. CPU consumption of broker also comes down a lot. Any suggestions what could be the culprit here, is it because of the fetcher lag? If yes, why does fetcher lag starts increasing suddenly after sometime? [cid:image001.png@01D9D468.F27FCF50] Regards, Prateek Kohli