You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hbase.apache.org by "Duo Zhang (JIRA)" <ji...@apache.org> on 2019/08/14 02:25:00 UTC
[jira] [Updated] (HBASE-22496) UnsafeAccess.unsafeCopy should not
copy more than UNSAFE_COPY_THRESHOLD on each iteration
[ https://issues.apache.org/jira/browse/HBASE-22496?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Duo Zhang updated HBASE-22496:
------------------------------
Fix Version/s: (was: 2.1.5)
2.1.6
> UnsafeAccess.unsafeCopy should not copy more than UNSAFE_COPY_THRESHOLD on each iteration
> -----------------------------------------------------------------------------------------
>
> Key: HBASE-22496
> URL: https://issues.apache.org/jira/browse/HBASE-22496
> Project: HBase
> Issue Type: Improvement
> Reporter: Wellington Chevreuil
> Assignee: Wellington Chevreuil
> Priority: Major
> Fix For: 3.0.0, 1.5.0, 2.2.0, 1.4.10, 2.0.6, 1.3.5, 2.1.6
>
> Attachments: HBASE-22496.master.001.patch
>
>
> In *UnsafeAccess.unsafeCopy*, we calculate a _size_ __ to be read, no greater than UNSAFE_COPY_THRESHOLD, if total _len_ is larger than UNSAFE_COPY_THRESHOLD:
> {noformat}
> long size = (len > UNSAFE_COPY_THRESHOLD) ? UNSAFE_COPY_THRESHOLD : len;
> {noformat}
> But then we simply read the whole len anyway:
> {noformat}
> theUnsafe.copyMemory(src, srcAddr, dst, destAddr, len);
> {noformat}
> I believe the real intention here is to copy chunks of _size_ bytes, the current code is already copying everything on the first iteration, then performing additional chunked copies.
--
This message was sent by Atlassian JIRA
(v7.6.14#76016)