[
https://issues.apache.org/jira/browse/ACCUMULO-2827?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14038166#comment-14038166
]
Keith Turner commented on ACCUMULO-2827:
----------------------------------------
I ran some test using the script in
{{ACCUMULO-2827-compaction-performance-test.patch}}. The table below shows
average compaction rates I observed. I threw away the numbers from the first
few compactions after the tserver started because the JIT was busy doing its
thing.
||files||rows per file||cols per row||rate w/o patch||rate w/ patch|| speedup||
|10|1000000|1|433,148|451,797|1.04|
|10|100000|10|557,307|684,984|1.23|
|10|10000|100|593,710|760,557|1.28|
These numbers show a nice speedup for the case where rows are interleaved but
have many columns. The rows in the files were randomly generated. Its nice
to see a significant difference in compaction speeds. These test were reading
and writing data. [~parkjsung] numbers show an even more dramatic difference
for only reading data.
> 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)
