Github user a-roberts commented on the pull request:
https://github.com/apache/spark/pull/12327#issuecomment-211999755
Hi, with this new test I'm seeing large deviations using IBM JDKs and
different platforms, for example:
`java.lang.AssertionError: assertion failed: deviation too large:
0.25359712230215825, first size: 26688, second size: 19920`
Is the 20% deviation particularly important? Why this number?
FYI here's the comparison between different Java vendors and architectures:
- OpenJDK on Intel (passes), cacheSize1: 180392 and cacheSize2: 187896
(4.07%)
- IBM JDK with SUSE on zSystems (fails): cacheSize1: 26688 and cacheSize2:
19920 (29%)
- IBM JDK with Ubuntu 14 04 on Power 8 LE (fails): cacheSize1: 26688 and
cacheSize2: 19920 (29%)
- IBM JDK with Ubuntu 14 04 on Intel (fails): cacheSize1: 354692 and
cacheSize2: 263800 (29.3%)
I'll look into this, interesting that with IBM Java it's always a very
similar and much larger percentage
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
