Kafka Zookeeper Mode vs KRaft Mode MSK - instance type comparison
Overview
This document contains the comparison results of testing workflows Check-in/Check-out and Data Import for MARC Bibliographic records in the Quesnelia release with different instance types: kafka.m7g.2xlarge zookeeper mode against kafka.m7g.2xlarge KRaft mode.
Tickets: 
Summary
Comparing kafka.m7g.2xlarge zookeeper metadata mode against kafka.m7g.2xlarge KRaft metadata mode
No difference in MSK resource utilization (CPU and Disk) comparing two MSK clusters
In KRaft mode services utilized less memory in mod-inventory-b on 11%, mod-source-record-storage-b on 9%, and more memory in mod-data-import-b on 14%. For the rest modules the difference was less than 7%
No significant difference in service CPU utilization:
Service CPU utilization in Zookeeper mode: mod-inventory-b - 136%, mod-quick-marc-b - 96%, mod-di-converter-storage-b - 100%, nginx-okapi - 88% the rest of modules utilized less than 50%
Service CPU utilization in KRaft mode: mod-inventory-b - 133%, mod-quick-marc-b - 75%, mod-di-converter-storage-b - 103%, nginx-okapi - 75% the rest of modules utilized less than 50%
No difference in Check-in/Check-out response time
Data import durations fluctuate from test to test but work stable without issues
Test Runs
Test # | MSK instance type | Scenario | Load level |
|---|---|---|---|
1 | kafka.m7g.2xlarge zookeeper mode | CICO + DI MARC Bib Create | 8 users + 5K, 25K sequentially |
2 | DI MARC Bib Create | 5K, 25K sequentially | |
3 | CICO + DI MARC Bib Update | 8 users + 5K, 25K sequentially | |
4 | DI MARC Bib Update | 5K, 25K sequentially | |
5 | kafka.m7g.2xlarge KRaft mode | CICO + DI MARC Bib Create | 8 users + 5K, 25K sequentially |
6 | DI MARC Bib Create | 5K, 25K sequentially | |
7 | CICO + DI MARC Bib Update | 8 users + 5K, 25K sequentially | |
8 | DI MARC Bib Update | 5K, 25K sequentially |
Test Results
This table shows results of Check-In/Check-out and Data Import create and update jobs.
MSK instance: kafka.m7g.2xlarge, metadata mode - ZooKeeper | |||||
|---|---|---|---|---|---|
Job profile | File size | DI Duration without CI/CO | DI Duration with CI/CO | CI with DI Average sec | CO with DI Average sec |
PTF - Create 2 | 5k | 00:03:05 | 00:02:39 | 0.707 | 1.104 |
| 25k | 00:12:03 | 00:12:08 | 0.718 | 1.129 |
PTF - Updates Success - 6 | 5k | 00:03:36 | 00:03:34 | 0.742 | 1.124 |
| 25k | 00:17:05 | 00:17:33 | 0.756 | 1.148 |
MSK instance: kafka.m7g.2xlarge, metadata mode - KRaft | |||||
Job profile | File size | DI Duration without CI/CO | DI Duration with CI/CO | CI with DI Average sec | CO with DI Average sec |
PTF - Create 2 | 5k | 00:02:49 | 00:02:39 | 0.765 | 1.118 |
| 25k | 00:13:31 | 00:12:04 | 0.777 | 1.186 |
PTF - Updates Success - 6 | 5k | 00:04:36 | 00:04:31 | 0.706 | 1.095 |
| 25k | 00:24:07 | 00:21:50 | 0.74 | 1.16 |
Check-in/Check-out without DI
Scenario | Load level | Request | Response time, sec | Response time, sec KRaft mode | ||
|---|---|---|---|---|---|---|
95 perc | average | 95 perc | average | |||
Circulation Check-in/Check-out (without Data import) | 8 users | Check-in | 0.72 | 0.606 | 0.695 | 0.583 |
Check-out | 1.241 | 0.969 | 1.151 | 0.944 | ||
Comparison
Data Import durations and Check-In/Check-Out response time comparison
Response times of CI/CO with Data import do not differ in both MSK clusters
Job Profile | File size | DELTA, DI without CI/CO | DELTA, DI+CI/CO | DELTA, CI with DI | DELTA, CO with DI |
|---|---|---|---|---|---|
PTF - Create 2 | 5k | 00:00:16 | 00:00:00 | -0.058 | -0.014 |
25k | -00:01:28 | 00:00:04 | -0.059 | -0.057 | |
PTF - Updates Success - 6 | 5k | -00:01:00 | -00:00:57 | 0.036 | 0.029 |
25k | -00:07:02 | -00:04:17 | 0.016 | -0.012 |
Check-in/Check-out without DI
Check-in/Check-out perform the same in both MSK clusters. The difference of response times is so small that it can be neglected.
Scenario | Load level | Request | Response time, sec instance: kafka.m7g.2xlarge Zookeeper mode | Response time, sec instance: kafka.m7g.2xlarge KRaft mode
| Delta | ||
|---|---|---|---|---|---|---|---|
95 perc | average | 95 perc | average | Average | |||
Circulation Check-in/Check-out (without Data import) | 8 users | Check-in | 0.72 | 0.606 | 0.695 | 0.583 | -0.023 |
Check-out | 1.241 | 0.969 | 1.151 | 0.944 | -0.025 | ||
MSK resource utilization (CPU)
Load scenario | Brokers | MSK instance: kafka.m7g.2xlarge Zookeeper mode | MSK instance: kafka.m7g.2xlarge KRaft mode | Delta, % |
|---|---|---|---|---|
CICO | 1 | 10 | 9 | -1 |
2 | 10 | 9 | -1 | |
CICO+DI | 1 | 31 | 32 | 1 |
2 | 32 | 30 | -2 |
Response time
MSK instance: kafka.m7g.2xlarge Zookeeper mode
MSK instance: kafka.m7g.2xlarge Kraft mode
Service CPU Utilization
CPU utilization table