-
Notifications
You must be signed in to change notification settings - Fork 1.1k
New issue
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
[dist-txns] CassandraSecondaryIndex write throughput drops gradually #368
Labels
kind/bug
This issue is a bug
Comments
In addition, there are some warnings logged in yb-tserver's log:
Also, after stopping the workload and rerunning it without recreating the table/index, the througput resumes at the same level as it was left off and continues the drop. |
yugabyte-ci
pushed a commit
that referenced
this issue
Jul 9, 2018
Summary: Transaction coordinator sends an apply request to participant in 2 cases: 1) Right after a transaction was committed. 2) Every 500ms, until it receives a response from the participant that the transaction was applied. That could cause "Apply of unknown transaction" error, because second request could be send right after the first one. Also in this scenario the participant tries to load this transaction from DB with lock acquired, so it slows down the whole performance. This fix prevents sending of first periodical retry after a commit. Test Plan: Create cluster of 3 n1-standard-16 nodes and run the following workload: java -jar ~/code/yugabyte/java/yb-loadtester/target/yb-sample-apps.jar --workload CassandraSecondaryIndex --nodes XXX:9042 --num_threads_read 0 --num_threads_write 64 --num_unique_keys 100000000 Reviewers: robert, mikhail Reviewed By: mikhail Subscribers: kannan, ybase Differential Revision: https://phabricator.dev.yugabyte.com/D5123
Fixed in add75f7 |
jasonyb
pushed a commit
that referenced
this issue
Jun 11, 2024
PG-602: Updated the README and added PG15
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Using commit 2ebadb8, write throughput of CassandraSecondaryIndex workload drops gradually over time.
The text was updated successfully, but these errors were encountered: