hbase - Select with limit and offset loses many rows in phoenix -


we have on 300m records in phoenix table.

create table if not exists secure.transaction ( salt varchar(4) not null, transaction_id varchar not null, ins_date timestamp, 

... transaction_date timestamp, ... constraint pk primary key (salt, transaction_id) ) immutable_rows=true,"keyprefixregionsplitpolicy.prefix_length"=4,split_policy='org.apache.hadoop.hbase.regionserver.keyprefixregionsplitpolicy' ...;

when query

select transaction_date, transaction_id secure.transaction      salt = '1234' , transaction_id '12345%'  order transaction_date limit 100 offset 100; 

i see huge gap in middle of result set. looks different hbase regions sorted , sliced data separately.

if ommit offset clause sorting looks correct.

the execution plan query

    | client 2-chunk 371724 rows 314572847 bytes parallel 2-way range scan on secure.transaction ['8077','0000001019011232'] - ['8077','0000001019011233']  |     |     server top 20 rows sorted [transaction_date desc]                                                                                                |     | client merge sort                                                 | | client offset 10 

is bug in phoenix 4.8.1 or sql query?


Comments

Popular posts from this blog

javascript - Confirm a form & display message if form is valid with JQuery -

Retrieving ETA (estimated time of arrival) with Google Distance Matrix API and public transit as transport mode -

ionic framework - Meteor - Error: Failed to execute 'insertBefore' on 'Node' -