[
https://issues.apache.org/jira/browse/HDFS-14402?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16842054#comment-16842054
]
Feilong He commented on HDFS-14402:
-----------------------------------
Thanks [~rakeshr] for your valuable comments.
The checksum logic for pmem cache is consistent with that for DRAM cache.
As you pointed, it looks more reasonable that the checksum should be executed
for cache data already on DRAM/Pmem, instead of for original data on disk. I
will consider your comment.
Upon making checksum configurable, I am thinking maybe to user, the cache read
performance is concerned mostly. The checksum is executed once when caching
data to DRAM/Pmem. It may be tolerable to user with checksum operation for data
verification. I think more discussions are required. I will open a separate
Jira common to DRAM and Pmem cache.
If DRAM and Pmem cache have respective checksum logic in our future impl,
#fileBuffer should be kept protected.
Thanks again!
> Use FileChannel.transferTo() method for transferring block to SCM cache
> -----------------------------------------------------------------------
>
> Key: HDFS-14402
> URL: https://issues.apache.org/jira/browse/HDFS-14402
> Project: Hadoop HDFS
> Issue Type: Sub-task
> Components: caching, datanode
> Reporter: Feilong He
> Assignee: Feilong He
> Priority: Major
> Attachments: HDFS-14402.000.patch, HFDS-14402.001.patch
>
>
> We will consider to use transferTo API to improve SCM's cach performace.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
