[
https://issues.apache.org/jira/browse/KUDU-463?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15494250#comment-15494250
]
Todd Lipcon commented on KUDU-463:
----------------------------------
I assumed that in the cfile-block checksums, the checksum would be in each
block, one per block. It's confusing here because we overload the term "block".
Perhaps we should call the little ones (--cfile_block_size) "pages" instead of
"blocks". These pages are already the unit of IO, so if we tack a checksum at
the end of it, it wouldn't cause amplification.
> Add checksumming to cfile and other on-disk formats
> ---------------------------------------------------
>
> Key: KUDU-463
> URL: https://issues.apache.org/jira/browse/KUDU-463
> Project: Kudu
> Issue Type: Sub-task
> Components: cfile, tablet
> Affects Versions: Private Beta
> Reporter: Todd Lipcon
> Assignee: Adar Dembo
> Labels: kudu-roadmap
>
> We should add CRC32C checksums to cfile blocks, metadata blocks, etc, to
> protect against silent disk corruption. We should probably do this prior to a
> public release, since it will likely have a negative performance impact, and
> we don't want to have a public regression.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
