| Table of Contents |
|---|
...
- Tests showed the Lists App refresh of concurrent lists on 3 tenants are:
- 1.5 mins for 3 concurrent lists refresh test (1 list refresh on each tenant);
- 2.3 mins for 10 concurrent lists refresh test (3-4 lists refresh on each tenant).
- Load test for 30 lists (10 lists per tenant) failed due to DB overload (100% of refresh transactions failed). After the test end "isRefreshing" status remained "true" for each list. It was reset manually directly through the database.
- During the 10 lists test CPU utilization reached 200% for mod-fqm-manager and 111% for mod-lists. Also, mod-permissions' CPU utilization exceeded 100% during 30 lists test.
- Maximum DB CPU utilization reached 83% (writer instance) and 99% (reader instance) during the 30 lists test. In comparison with testing with R/W split disabled, RDS CPU utilization didn't decrease when DB R/W split was enabled.
- Memory utilization for mod-permissions increased from 48% to 76% during the tests. No memory leak is suspected for all the modules.
...
| Transaction | Duration, avg | Release | Tenants | Number of lists | R/W split | Other conditions |
|---|---|---|---|---|---|---|
Lists App refresh | 10 min 40 sec | [Orchid] | 1 tenant | 10 | disabled | |
| 8.5 min | [Poppy] | 1 tenant | 10 | disabled | ||
| 17.7 min | [Poppy] | 1 tenant | 10 | disabled | Testing in parallel with DI and CICO | |
| Lists App refresh current test results** | 1.5 min | [Poppy] | 3 tenants | 3 | enabled | |
| 2.3 min | [Poppy] | 3 tenants | 10 | enabled | ||
| error | [Poppy] | 3 tenants | 30 | enabled | 1 list refresh failed for the 1st tenant 8 list refreshes failed for the 3rd tenant*** |
...
**Query used in lists - "Item status != Available". List refresh result is about 200K records.
***After the test end "isRefreshing" status remained "true" for each of the failed lists. It was reset manually directly through the database. Details on the issue can be found [TBD]at Failed list refresh investigation part
Instance CPU Utilization
Service CPU Utilization
...
In order to investigate the issue there were conducted addtional tests for single tenant (30 lists in parallel) and multiple tenants (10 lists on each of three tenants in parallel).
| Test | Failed list refresh | |
|---|---|---|
1 tenant (30 lists in parallel) | 3 tenants (10 lists on each in parallel) | |
| 1 | 1 list | 2 lists for 1st tenant 10 lists for 3rd tenant |
| 2 | 1 list | 1 lists for 1st tenant 8 lists for 3rd tenant |
| 3 | 2 lists | 2 lists for 1st tenant 8 lists for 3rd tenant |
For the second tenant there were no failed list refreshes during all the tests.
...
Infrastructure
PTF -environment pcp1
- 10 m6i.2xlarge EC2 instances located in US East (N. Virginia)us-east-1
1 database instance, writer
Name API Name Memory GIB vCPUs max_connections R6G Extra Large db.r6g.xlarge 32 GiB 4 vCPUs 2731 - MSK tenant
- 4 m5.2xlarge brokers in 2 zones
Apache Kafka version 2.8.0
EBS storage volume per broker 300 GiB
- auto.create.topics.enable=true
- log.retention.minutes=480
- default.replication.factor=3
...