[
https://issues.apache.org/jira/browse/CASSANDRA-8160?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14334219#comment-14334219
]
Benedict commented on CASSANDRA-8160:
-------------------------------------
bq. Can it be done in a platform independent way that doesn't involve actually
reading the files via the JVM and materializing objects on the heap?
Yes, just read the contents into a small byte[] that we repeatedly overwrite.
bq. This was with DSE > 4.0 so the 1.2 bug where we were gratuitously
invalidating the buffer cache shouldn't have been in effect.
Invalidating the buffer cache on flush is the default behaviour until 2.1 and
CASSANDRA-6916. You need to set populate_io_cache_on_flush: true in your yaml
to change this.
> CF level option to call posix_fadvise for sstables on creation and startup
> --------------------------------------------------------------------------
>
> Key: CASSANDRA-8160
> URL: https://issues.apache.org/jira/browse/CASSANDRA-8160
> Project: Cassandra
> Issue Type: New Feature
> Components: Core
> Reporter: Matt Stump
> Assignee: Branimir Lambov
> Priority: Minor
> Fix For: 2.1.4
>
> Attachments: trunk-8160.txt
>
>
> We should have a CF level configuration with will result in posix_fadvise
> being called for sstables for that CF. It should be called on node startup
> and for new sstables. This should be configurable per CF to allow for some
> CFs to be prioritized above others. Not sure if we should use
> POSIX_FADV_SEQUENTIAL or POSIX_FADV_WILLNEED.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
