[
https://issues.apache.org/jira/browse/CALCITE-4522?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17298888#comment-17298888
]
Vladimir Sitnikov commented on CALCITE-4522:
--------------------------------------------
{quote}You should multiply by constant + row_bytes, not row_bytes. You cannot
sort 4-byte rows 25 types faster than 100-byte rows. There is a per-row
overhead.{quote}
per-row overhead is caused by the comparison which is not related with the row
size.
I suggest we use {{collation.getFieldCollations().size()}} as an estimate of
the per-tuple comparison cost.
A slightly better estimate would be {{sum of datatype widths of all the fields
in the collation oclumns}}
> Sort cost should account for the number of columns in collation
> ---------------------------------------------------------------
>
> Key: CALCITE-4522
> URL: https://issues.apache.org/jira/browse/CALCITE-4522
> Project: Calcite
> Issue Type: Improvement
> Components: core
> Reporter: hqx
> Priority: Minor
> Labels: pull-request-available
> Time Spent: 9h
> Remaining Estimate: 0h
>
> The old method to compute the cost of sort has some problem.
> # When the RelCollation is empty, there is no need to sort, but it still
> compute the cpu cost of sort.
> # use n * log\(n) * row_byte to estimate the cpu cost may be inaccurate,
> where n means the output row count of the sort operator, and row_byte means
> the average bytes of one row .
> Instead, I give follow suggestion.
> # the cpu cost is zero if the RelCollation is empty.
> # let heap_size be min\(offset + output_count, input_count), and use
> input_count * log\(heap_size)* row_byte to compute the cpu cost.
> When fetch is zero, I found the output_count is 1 not 0. This conveniently
> ensure the log\(heap_size) no less than zero
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
