accumulo-notifications mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Keith Turner (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (ACCUMULO-2827) HeapIterator optimization
Date Wed, 18 Jun 2014 18:28:25 GMT

    [ https://issues.apache.org/jira/browse/ACCUMULO-2827?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14036092#comment-14036092
] 

Keith Turner commented on ACCUMULO-2827:
----------------------------------------

bq. The initial microbenchmarks showed a lot of promise (I think?) and the results from the
compact looked to fall far short of that.

I suspect this is because the compaction test used uniform random data.  CI generates random
rows w/ one column.  So the data in the tablets files is highly interleaved.  Its good to
see that it did not do worse in this case.  I suspect this case corresponds to X=1 in the
posted plots.  It would interesting to see the end-to-end experiment run with something that
generates random rows with multiple columns.   

> HeapIterator optimization
> -------------------------
>
>                 Key: ACCUMULO-2827
>                 URL: https://issues.apache.org/jira/browse/ACCUMULO-2827
>             Project: Accumulo
>          Issue Type: Improvement
>    Affects Versions: 1.5.1, 1.6.0
>            Reporter: Jonathan Park
>            Assignee: Jonathan Park
>            Priority: Minor
>             Fix For: 1.5.2, 1.6.1, 1.7.0
>
>         Attachments: ACCUMULO-2827.0.patch.txt, accumulo-2827.raw_data, new_heapiter.png,
old_heapiter.png, together.png
>
>
> We've been running a few performance tests of our iterator stack and noticed a decent
amount of time spent in the HeapIterator specifically related to add/removal into the heap.
> This may not be a general enough optimization but we thought we'd see what people thought.
Our assumption is that it's more probable that the current "top iterator" will supply the
next value in the iteration than not. The current implementation takes the other assumption
by always removing + inserting the minimum iterator back into the heap. With the implementation
of a binary heap that we're using, this can get costly if our assumption is wrong because
we pay the log penalty of percolating up the iterator in the heap upon insertion and again
when percolating down upon removal.
> We believe our assumption is a fair one to hold given that as major compactions create
a log distribution of file sizes, it's likely that we may see a long chain of consecutive
entries coming from 1 iterator. Understandably, taking this assumption comes at an additional
cost in the case that we're wrong. Therefore, we've run a few benchmarking tests to see how
much of a cost we pay as well as what kind of benefit we see. I've attached a potential patch
(which includes a test harness) + image that captures the results of our tests. The x-axis
represents # of repeated keys before switching to another iterator. The y-axis represents
iteration time. The sets of blue + red lines varies in # of iterators present in the heap.



--
This message was sent by Atlassian JIRA
(v6.2#6252)

Mime
View raw message