[SOLR-6314] Facet counts duplicated in the response if specified more than once on the request. - ASF JIRA

Details

Type: Bug
Status: Resolved
Priority: Minor
Resolution: Fixed
Affects Version/s: 6.0
Fix Version/s: 4.10, 6.0
Component/s: SearchComponents - other, SolrCloud
Labels:
None

Description

I am trying to work with multi-threaded faceting on SolrCloud and in the process i was hit by some issues.

I am currently running the below upstream test on different SolrCloud configurations and i am getting a different result set per configuration.
https://github.com/apache/lucene-solr/blob/trunk/solr/core/src/test/org/apache/solr/request/TestFaceting.java#L654

Setup:

Indexed 50 docs into SolrCloud.

If the SolrCloud has only 1 shard, the facet field query has the below output (which matches with the expected upstream test output - # facet fields ~ 50).

$ curl  "http://localhost:8983/solr/collection1/select?facet=true&fl=id&indent=true&q=id%3A*&facet.limit=-1&facet.threads=1000&facet.field=f0_ws&facet.field=f0_ws&facet.field=f0_ws&facet.field=f0_ws&facet.field=f0_ws&facet.field=f1_ws&facet.field=f1_ws&facet.field=f1_ws&facet.field=f1_ws&facet.field=f1_ws&facet.field=f2_ws&facet.field=f2_ws&facet.field=f2_ws&facet.field=f2_ws&facet.field=f2_ws&facet.field=f3_ws&facet.field=f3_ws&facet.field=f3_ws&facet.field=f3_ws&facet.field=f3_ws&facet.field=f4_ws&facet.field=f4_ws&facet.field=f4_ws&facet.field=f4_ws&facet.field=f4_ws&facet.field=f5_ws&facet.field=f5_ws&facet.field=f5_ws&facet.field=f5_ws&facet.field=f5_ws&facet.field=f6_ws&facet.field=f6_ws&facet.field=f6_ws&facet.field=f6_ws&facet.field=f6_ws&facet.field=f7_ws&facet.field=f7_ws&facet.field=f7_ws&facet.field=f7_ws&facet.field=f7_ws&facet.field=f8_ws&facet.field=f8_ws&facet.field=f8_ws&facet.field=f8_ws&facet.field=f8_ws&facet.field=f9_ws&facet.field=f9_ws&facet.field=f9_ws&facet.field=f9_ws&facet.field=f9_ws&rows=1&wt=xml"

<?xml version="1.0" encoding="UTF-8"?>
<response>
<lst name="responseHeader">
  <int name="status">0</int>
  <int name="QTime">21</int>
  <lst name="params">
    <str name="facet">true</str>
    <str name="fl">id</str>
    <str name="indent">true</str>
    <str name="q">id:*</str>
    <str name="facet.limit">-1</str>
    <str name="facet.threads">1000</str>
    <arr name="facet.field">
      <str>f0_ws</str>
      <str>f0_ws</str>
      <str>f0_ws</str>
      <str>f0_ws</str>
      <str>f0_ws</str>
      <str>f1_ws</str>
      <str>f1_ws</str>
      <str>f1_ws</str>
      <str>f1_ws</str>
      <str>f1_ws</str>
      <str>f2_ws</str>
      <str>f2_ws</str>
      <str>f2_ws</str>
      <str>f2_ws</str>
      <str>f2_ws</str>
      <str>f3_ws</str>
      <str>f3_ws</str>
      <str>f3_ws</str>
      <str>f3_ws</str>
      <str>f3_ws</str>
      <str>f4_ws</str>
      <str>f4_ws</str>
      <str>f4_ws</str>
      <str>f4_ws</str>
      <str>f4_ws</str>
      <str>f5_ws</str>
      <str>f5_ws</str>
      <str>f5_ws</str>
      <str>f5_ws</str>
      <str>f5_ws</str>
      <str>f6_ws</str>
      <str>f6_ws</str>
      <str>f6_ws</str>
      <str>f6_ws</str>
      <str>f6_ws</str>
      <str>f7_ws</str>
      <str>f7_ws</str>
      <str>f7_ws</str>
      <str>f7_ws</str>
      <str>f7_ws</str>
      <str>f8_ws</str>
      <str>f8_ws</str>
      <str>f8_ws</str>
      <str>f8_ws</str>
      <str>f8_ws</str>
      <str>f9_ws</str>
      <str>f9_ws</str>
      <str>f9_ws</str>
      <str>f9_ws</str>
      <str>f9_ws</str>
    </arr>
    <str name="wt">xml</str>
    <str name="rows">1</str>
  </lst>
</lst>
<result name="response" numFound="50" start="0">
  <doc>
    <float name="id">0.0</float></doc>
</result>
<lst name="facet_counts">
  <lst name="facet_queries"/>
  <lst name="facet_fields">
    <lst name="f0_ws">
      <int name="zero_1">25</int>
      <int name="zero_2">25</int>
    </lst>
    <lst name="f0_ws">
      <int name="zero_1">25</int>
      <int name="zero_2">25</int>
    </lst>
    <lst name="f0_ws">
      <int name="zero_1">25</int>
      <int name="zero_2">25</int>
    </lst>
    <lst name="f0_ws">
      <int name="zero_1">25</int>
      <int name="zero_2">25</int>
    </lst>
    <lst name="f0_ws">
      <int name="zero_1">25</int>
      <int name="zero_2">25</int>
    </lst>
    <lst name="f1_ws">
      <int name="one_1">33</int>
      <int name="one_3">17</int>
    </lst>
    <lst name="f1_ws">
      <int name="one_1">33</int>
      <int name="one_3">17</int>
    </lst>
    <lst name="f1_ws">
      <int name="one_1">33</int>
      <int name="one_3">17</int>
    </lst>
    <lst name="f1_ws">
      <int name="one_1">33</int>
      <int name="one_3">17</int>
    </lst>
    <lst name="f1_ws">
      <int name="one_1">33</int>
      <int name="one_3">17</int>
    </lst>
    <lst name="f2_ws">
      <int name="two_1">37</int>
      <int name="two_4">13</int>
    </lst>
    <lst name="f2_ws">
      <int name="two_1">37</int>
      <int name="two_4">13</int>
    </lst>
    <lst name="f2_ws">
      <int name="two_1">37</int>
      <int name="two_4">13</int>
    </lst>
    <lst name="f2_ws">
      <int name="two_1">37</int>
      <int name="two_4">13</int>
    </lst>
    <lst name="f2_ws">
      <int name="two_1">37</int>
      <int name="two_4">13</int>
    </lst>
    <lst name="f3_ws">
      <int name="three_1">40</int>
      <int name="three_5">10</int>
    </lst>

    <lst name="f3_ws">
      <int name="three_1">40</int>
      <int name="three_5">10</int>
    </lst>
    <lst name="f3_ws">
      <int name="three_1">40</int>
      <int name="three_5">10</int>
    </lst>
    <lst name="f3_ws">
      <int name="three_1">40</int>
      <int name="three_5">10</int>
    </lst>
    <lst name="f3_ws">
      <int name="three_1">40</int>
      <int name="three_5">10</int>
    </lst>
    <lst name="f4_ws">
      <int name="four_1">41</int>
      <int name="four_6">9</int>
    </lst>
    <lst name="f4_ws">
      <int name="four_1">41</int>
      <int name="four_6">9</int>
    </lst>
    <lst name="f4_ws">
      <int name="four_1">41</int>
      <int name="four_6">9</int>
    </lst>
    <lst name="f4_ws">
      <int name="four_1">41</int>
      <int name="four_6">9</int>
    </lst>
    <lst name="f4_ws">
      <int name="four_1">41</int>
      <int name="four_6">9</int>
    </lst>
    <lst name="f5_ws">
      <int name="five_1">42</int>
      <int name="five_7">8</int>
    </lst>
    <lst name="f5_ws">
      <int name="five_1">42</int>
      <int name="five_7">8</int>
    </lst>
    <lst name="f5_ws">
      <int name="five_1">42</int>
      <int name="five_7">8</int>
    </lst>
    <lst name="f5_ws">
      <int name="five_1">42</int>
      <int name="five_7">8</int>
    </lst>
    <lst name="f5_ws">
      <int name="five_1">42</int>
      <int name="five_7">8</int>
    </lst>
    <lst name="f6_ws">
      <int name="six_1">43</int>
      <int name="six_8">7</int>

    </lst>
    <lst name="f6_ws">
      <int name="six_1">43</int>
      <int name="six_8">7</int>
    </lst>
    <lst name="f6_ws">
      <int name="six_1">43</int>
      <int name="six_8">7</int>
    </lst>
    <lst name="f6_ws">
      <int name="six_1">43</int>
      <int name="six_8">7</int>
    </lst>
    <lst name="f6_ws">
      <int name="six_1">43</int>
      <int name="six_8">7</int>
    </lst>
    <lst name="f7_ws">
      <int name="seven_1">44</int>
      <int name="seven_9">6</int>
    </lst>
    <lst name="f7_ws">
      <int name="seven_1">44</int>
      <int name="seven_9">6</int>
    </lst>
    <lst name="f7_ws">
      <int name="seven_1">44</int>
      <int name="seven_9">6</int>
    </lst>
    <lst name="f7_ws">
      <int name="seven_1">44</int>
      <int name="seven_9">6</int>
    </lst>
    <lst name="f7_ws">
      <int name="seven_1">44</int>
      <int name="seven_9">6</int>
    </lst>
    <lst name="f8_ws">
      <int name="eight_1">45</int>
      <int name="eight_10">5</int>
    </lst>
    <lst name="f8_ws">
      <int name="eight_1">45</int>
      <int name="eight_10">5</int>
    </lst>
    <lst name="f8_ws">
      <int name="eight_1">45</int>
      <int name="eight_10">5</int>
    </lst>
    <lst name="f8_ws">
      <int name="eight_1">45</int>
      <int name="eight_10">5</int>
    </lst>
    <lst name="f8_ws">
      <int name="eight_1">45</int>
      <int name="eight_10">5</int>
    </lst>
    <lst name="f9_ws">
      <int name="nine_1">45</int>
      <int name="nine_11">5</int>
    </lst>
    <lst name="f9_ws">
      <int name="nine_1">45</int>
      <int name="nine_11">5</int>
    </lst>

    <lst name="f9_ws">
      <int name="nine_1">45</int>
      <int name="nine_11">5</int>
    </lst>
    <lst name="f9_ws">
      <int name="nine_1">45</int>
      <int name="nine_11">5</int>
    </lst>
    <lst name="f9_ws">
      <int name="nine_1">45</int>
      <int name="nine_11">5</int>
    </lst>
  </lst>
  <lst name="facet_dates"/>
  <lst name="facet_ranges"/>
</lst>
</response>

Now, if a create a new collection with 2 shards (>1 shard SolrCloud), the same above query results in a different output. (# facet fields ~ 10 ; Expected 50)

$ curl  "http://localhost:8983/solr/collection1/select?facet=true&fl=id&indent=true&q=id%3A*&facet.limit=-1&facet.threads=1000&facet.field=f0_ws&facet.field=f0_ws&facet.field=f0_ws&facet.field=f0_ws&facet.field=f0_ws&facet.field=f1_ws&facet.field=f1_ws&facet.field=f1_ws&facet.field=f1_ws&facet.field=f1_ws&facet.field=f2_ws&facet.field=f2_ws&facet.field=f2_ws&facet.field=f2_ws&facet.field=f2_ws&facet.field=f3_ws&facet.field=f3_ws&facet.field=f3_ws&facet.field=f3_ws&facet.field=f3_ws&facet.field=f4_ws&facet.field=f4_ws&facet.field=f4_ws&facet.field=f4_ws&facet.field=f4_ws&facet.field=f5_ws&facet.field=f5_ws&facet.field=f5_ws&facet.field=f5_ws&facet.field=f5_ws&facet.field=f6_ws&facet.field=f6_ws&facet.field=f6_ws&facet.field=f6_ws&facet.field=f6_ws&facet.field=f7_ws&facet.field=f7_ws&facet.field=f7_ws&facet.field=f7_ws&facet.field=f7_ws&facet.field=f8_ws&facet.field=f8_ws&facet.field=f8_ws&facet.field=f8_ws&facet.field=f8_ws&facet.field=f9_ws&facet.field=f9_ws&facet.field=f9_ws&facet.field=f9_ws&facet.field=f9_ws&rows=1&wt=xml"
 
<?xml version="1.0" encoding="UTF-8"?>
<response>
<lst name="responseHeader">
  <int name="status">0</int>
  <int name="QTime">31</int>
  <lst name="params">
    <str name="facet">true</str>
    <str name="fl">id</str>
    <str name="indent">true</str>
    <str name="q">id:*</str>
    <str name="facet.limit">-1</str>
    <str name="facet.threads">1000</str>
    <arr name="facet.field">
      <str>f0_ws</str>
      <str>f0_ws</str>
      <str>f0_ws</str>
      <str>f0_ws</str>
      <str>f0_ws</str>
      <str>f1_ws</str>
      <str>f1_ws</str>
      <str>f1_ws</str>
      <str>f1_ws</str>
      <str>f1_ws</str>
      <str>f2_ws</str>
      <str>f2_ws</str>
      <str>f2_ws</str>
      <str>f2_ws</str>
      <str>f2_ws</str>
      <str>f3_ws</str>
      <str>f3_ws</str>
      <str>f3_ws</str>
      <str>f3_ws</str>
      <str>f3_ws</str>
      <str>f4_ws</str>
      <str>f4_ws</str>
      <str>f4_ws</str>
      <str>f4_ws</str>
      <str>f4_ws</str>
      <str>f5_ws</str>
      <str>f5_ws</str>
      <str>f5_ws</str>
      <str>f5_ws</str>
      <str>f5_ws</str>
      <str>f6_ws</str>
      <str>f6_ws</str>
      <str>f6_ws</str>
      <str>f6_ws</str>
      <str>f6_ws</str>
      <str>f7_ws</str>
      <str>f7_ws</str>
      <str>f7_ws</str>
      <str>f7_ws</str>
      <str>f7_ws</str>
      <str>f8_ws</str>
      <str>f8_ws</str>
      <str>f8_ws</str>
      <str>f8_ws</str>
      <str>f8_ws</str>
      <str>f9_ws</str>
      <str>f9_ws</str>
      <str>f9_ws</str>
      <str>f9_ws</str>
      <str>f9_ws</str>
    </arr>
    <str name="wt">xml</str>
    <str name="rows">1</str>
  </lst>
</lst>
<result name="response" numFound="50" start="0" maxScore="1.0">
  <doc>
    <float name="id">2.0</float></doc>
</result>
<lst name="facet_counts">
  <lst name="facet_queries"/>
  <lst name="facet_fields">
    <lst name="f0_ws">
      <int name="zero_1">25</int>
      <int name="zero_2">25</int>
    </lst>
    <lst name="f1_ws">
      <int name="one_1">33</int>
      <int name="one_3">17</int>
    </lst>
    <lst name="f2_ws">
      <int name="two_1">37</int>
      <int name="two_4">13</int>
    </lst>
    <lst name="f3_ws">
      <int name="three_1">40</int>
      <int name="three_5">10</int>
    </lst>
    <lst name="f4_ws">
      <int name="four_1">41</int>
      <int name="four_6">9</int>
    </lst>
    <lst name="f5_ws">
      <int name="five_1">42</int>
      <int name="five_7">8</int>
    </lst>
    <lst name="f6_ws">
      <int name="six_1">43</int>
      <int name="six_8">7</int>
    </lst>
    <lst name="f7_ws">
      <int name="seven_1">44</int>
      <int name="seven_9">6</int>
    </lst>
    <lst name="f8_ws">
      <int name="eight_1">45</int>
      <int name="eight_10">5</int>
    </lst>
    <lst name="f9_ws">
      <int name="nine_1">45</int>
      <int name="nine_11">5</int>
    </lst>
  </lst>
  <lst name="facet_dates"/>
  <lst name="facet_ranges"/>
</lst>
</response>

This behavior is quite strange as it is being dependent on the number of shards in SolrCloud. It would be great if someone can shed some light on this?

Attachments

SOLR-6314.patch
08/Aug/14 08:42
8 kB
Erick Erickson
SOLR-6314.patch
15/Aug/14 09:06
9 kB
Erick Erickson
SOLR-6314.patch
19/Aug/14 00:11
7 kB
Erick Erickson

Issue Links

Add Link

relates to

SOLR-6386 make secondary ordering of facet.field values (and facet.pivot?) consistently deterministic

Open

Delete this link

Activity

Comment

This comment will be Viewable by All Users Viewable by All Users

Cancel

Facet counts duplicated in the response if specified more than once on the request.

Details

Description

Attachments

Attachments

Issue Links

Activity

People

Dates

Agile

Slack

Issue deployment