Replies: 1 comment
-
simonswine can you please help on this |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
We can see below values in config. Do we have api to check number of profile received and size like uncompressed_bytes in distributor and ingester component.
# Maximum size of a profile in bytes. This is based off the uncompressed size.
# 0 to disable.
# CLI flag: -validation.max-profile-size-bytes
[max_profile_size_bytes: | default = 4194304]
# Maximum number of samples in a profile. 0 to disable.
# CLI flag: -validation.max-profile-stacktrace-samples
[max_profile_stacktrace_samples: | default = 16000]
For java we are running example simple program below within aks cluster
https://github.com/grafana/pyroscope/blob/main/examples/java/simple/Main.java
Observation -
We are able to scale by increasing the replica count. But we are not able to achieve expected throughput.
Increasing X replica for Go application increases the load X times but for java application increasing X replica we can't achieve X times load
Replicas Samples in billion/sec(approx)
1 1
5 4
10 8
50 15
100 29
Beta Was this translation helpful? Give feedback.
All reactions