-
Notifications
You must be signed in to change notification settings - Fork 209
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
key pool can cause memtier to hang when there are multiple shards and request count is bellow pool size #204
Closed
Comments
YaacovHazan
added a commit
to YaacovHazan/memtier_benchmark
that referenced
this issue
May 17, 2023
In cluster mode, where there are few requests with many shards, some of the shards might not send any requests. Currently, the memtier-benchmark is hang, because the connections to these shards are not disabling their read/write events
YaacovHazan
added a commit
that referenced
this issue
May 17, 2023
Co-authored-by: YaacovHazan <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
this can be easily reproduced with master ( or any previous stable version ) and more than 1 shards scenario on OSS cluster.
with a simple > 1 shard scenario:
you can see that there is no assurance that the 4 requests generated are for the connections that is sending the requests ( given we have 3 connections ).
this is due to the following codition
and https://github.com/RedisLabs/memtier_benchmark/blob/master/cluster_client.cpp#L352
This can be solved by avoiding pushing to other pools if we don't have enough requests to fill all pools of all shards.
The text was updated successfully, but these errors were encountered: