Daiyi Yang created CASSANDRA-12623:
--------------------------------------
Summary: Performance impact for the big collection
Key: CASSANDRA-12623
URL: https://issues.apache.org/jira/browse/CASSANDRA-12623
Project: Cassandra
Issue Type: Bug
Reporter: Daiyi Yang
Fix For: 3.0.x
Hey there, we're recently seeing performance issues with rows with huge
collection of udts, we created a table that has one row per partition and the
biggest row has around 10M of data, which should be way lower than the expected
limitation. However we did see some performance impact when we're trying to
update rows with a big number of udts in its collection.
>From what we saw, whenever we're trying to write those rows, the garbage
>collection was very aggressive and the cpu was very high.
I'm wondering how the collection type is handled and if there's any suggested
limitation for it?
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
