Github user wulei-bj-cn commented on the pull request:
https://github.com/apache/spark/pull/8533#issuecomment-149078255
And furthermore, this always being 'ANY' issue in Spark will cause Tachyon
to keep re-caching remote memory blocks via networks from remote Tachyon
workers, which introduces way too much unnecessary network I/Os, and what is
even worse, more memory space is wasted due to this re-caching, since more than
one copy of the file blocks are cached in the ram-disks. More details for this
Spark + Tachyon issue could be found :
https://groups.google.com/forum/#!topic/tachyon-users/HJ9xQH2AJxE .
---
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]
