Dan Hecht has posted comments on this change.

Change subject: IMPALA-3286: Prefetching for PHJ probing.
......................................................................


Patch Set 7:

(1 comment)

http://gerrit.cloudera.org:8080/#/c/2959/7/be/src/exec/hash-table.h
File be/src/exec/hash-table.h:

Line 230: Resets the iterators and end pointers to the start before writing
> This is not strictly true. The content in theory is still in the cache as w
The contents are physically still in the cache but logically they have been 
reset. My point is that you aren't allowed to access the contents after calling 
Reset() and so therefore it's safe to free the local allocations that the cache 
referenced (even though, yes, the cache wasn't physically cleared).

It's analogous to calling free() on a piece of memory that contains pointers. 
free() doesn't (necessarily) clear the memory, but you still consider those 
references to be dead at that point.


-- 
To view, visit http://gerrit.cloudera.org:8080/2959
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings

Gerrit-MessageType: comment
Gerrit-Change-Id: Ib42b93d99d09c833571e39d20d58c11ef73f3cc0
Gerrit-PatchSet: 7
Gerrit-Project: Impala
Gerrit-Branch: cdh5-trunk
Gerrit-Owner: Michael Ho <[email protected]>
Gerrit-Reviewer: Dan Hecht <[email protected]>
Gerrit-Reviewer: Huaisi Xu <[email protected]>
Gerrit-Reviewer: Michael Ho <[email protected]>
Gerrit-Reviewer: Mostafa Mokhtar <[email protected]>
Gerrit-Reviewer: Tim Armstrong <[email protected]>
Gerrit-HasComments: Yes

Reply via email to