[
https://issues.apache.org/jira/browse/PHOENIX-1074?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
jay wong updated PHOENIX-1074:
------------------------------
Description:
create a table
{code}
create table if not exists table1(
gmt VARCHAR NOT NULL,
spm_type VARCHAR NOT NULL,
spm VARCHAR NOT NULL,
A.int_a INTEGER,
B.int_b INTEGER,
B.int_c INTEGER
CONSTRAINT pk PRIMARY KEY (gmt, spm_type, spm)) SALT_BUCKETS = 4,
bloomfilter='ROW';
{code}
and made the table 29 partitions as this.
|startrow|endrow|
| |\x0020140201|
|\x0020140201|\x0020140202|
|\x0020140202|\x0020140203|
|\x0020140203|\x0020140204|
|\x0020140204|\x0020140205|
|\x0020140205|\x0020140206|
|\x0020140206|\x0020140207|
|\x0020140207|\x0120140201|
|\x0120140201|\x0120140202|
|\x0120140202|\x0120140203|
|\x0120140203|\x0120140204|
|\x0120140204|\x0120140205|
|\x0120140205|\x0120140206|
|\x0120140206|\x0120140207|
|\x0120140207|\x0220140201|
|\x0220140201|\x0220140202|
|\x0220140202|\x0220140203|
|\x0220140203|\x0220140204|
|\x0220140204|\x0220140205|
|\x0220140205|\x0220140206|
|\x0220140206|\x0220140207|
|\x0220140207|\x0320140201|
|\x0320140201|\x0320140202|
|\x0320140202|\x0320140203|
|\x0320140203|\x0320140204|
|\x0320140204|\x0320140205|
|\x0320140205|\x0320140206|
|\x0320140206|\x0320140207|
|\x0320140207| |
Then insert some data;
| GMT | SPM_TYPE | SPM | INT_A | INT_B | INT_C |
| 20140201 | 1 | 1.2.3.4546 | 218 | 218 | null |
| 20140201 | 1 | 1.2.44545 | 190 | 190 | null |
| 20140201 | 1 | 1.353451312 | 246 | 246 | null |
| 20140201 | 2 | 1.2.3.6775 | 183 | 183 | null |
|...|...|...|...|...|...|
| 20140207 | 3 | 1.2.3.4546 | 224 | 224 | null |
| 20140207 | 3 | 1.2.44545 | 196 | 196 | null |
| 20140207 | 3 | 1.353451312 | 168 | 168 | null |
| 20140207 | 4 | 1.2.3.6775 | 189 | 189 | null |
| 20140207 | 4 | 1.23.345345 | 217 | 217 | null |
| 20140207 | 4 | 1.23234234234 | 245 | 245 | null
|
print a log like this
{code}
public class ParallelIterators extends ExplainTable implements ResultIterators {
....
@Override
public List<PeekingResultIterator> getIterators() throws SQLException {
boolean success = false;
final ConnectionQueryServices services =
context.getConnection().getQueryServices();
ReadOnlyProps props = services.getProps();
int numSplits = splits.size();
List<PeekingResultIterator> iterators = new
ArrayList<PeekingResultIterator>(numSplits);
List<Pair<byte[],Future<PeekingResultIterator>>> futures = new
ArrayList<Pair<byte[],Future<PeekingResultIterator>>>(numSplits);
final UUID scanId = UUID.randomUUID();
try {
ExecutorService executor = services.getExecutor();
System.out.println("the split size is " + numSplits);
....
}
}
{code}
then execute some sql
{code}
select * from table1 where gmt > '20140202' and gmt < '20140207' and spm_type =
'2' and spm like '1.%'
the split size is 31
select * from table1 where gmt > '20140202' and gmt < '20140207' and spm_type =
'2'
the split size is 31
select * from table1 where gmt > '20140202' and gmt < '20140207'
the split size is 27
select * from table1 where gmt > '20140202' and gmt < '20140204' and spm_type =
'2' and spm like '1.%'
the split size is 28
select * from table1 where gmt > '20140202' and gmt < '20140204' and spm_type =
'2'
the split size is 28
select * from table1 where gmt > '20140202' and gmt < '20140204'
the split size is 12
{code}
but I think
{code}
select * from table1 where gmt > '20140202' and gmt < '20140207' and spm_type =
'2' and spm like '1.%'
{code}
and
{code}
select * from table1 where gmt > '20140202' and gmt < '20140207'
{code}
the two sql will has the same split , but why not?
was:
create a table
{code}
create table if not exists table1(
gmt VARCHAR NOT NULL,
spm_type VARCHAR NOT NULL,
spm VARCHAR NOT NULL,
A.int_a INTEGER,
B.int_b INTEGER,
B.int_c INTEGER
CONSTRAINT pk PRIMARY KEY (gmt, spm_type, spm)) SALT_BUCKETS = 4,
bloomfilter='ROW';
{code}
and made the table partition as this.
|startrow|endrow|
| |\x0020140201|
|\x0020140201|\x0020140202|
|\x0020140202|\x0020140203|
|\x0020140203|\x0020140204|
|\x0020140204|\x0020140205|
|\x0020140205|\x0020140206|
|\x0020140206|\x0020140207|
|\x0020140207|\x0120140201|
|\x0120140201|\x0120140202|
|\x0120140202|\x0120140203|
|\x0120140203|\x0120140204|
|\x0120140204|\x0120140205|
|\x0120140205|\x0120140206|
|\x0120140206|\x0120140207|
|\x0120140207|\x0220140201|
|\x0220140201|\x0220140202|
|\x0220140202|\x0220140203|
|\x0220140203|\x0220140204|
|\x0220140204|\x0220140205|
|\x0220140205|\x0220140206|
|\x0220140206|\x0220140207|
|\x0220140207|\x0320140201|
|\x0320140201|\x0320140202|
|\x0320140202|\x0320140203|
|\x0320140203|\x0320140204|
|\x0320140204|\x0320140205|
|\x0320140205|\x0320140206|
|\x0320140206|\x0320140207|
|\x0320140207| |
Then insert some data;
| GMT | SPM_TYPE | SPM | INT_A | INT_B | INT_C |
| 20140201 | 1 | 1.2.3.4546 | 218 | 218 | null |
| 20140201 | 1 | 1.2.44545 | 190 | 190 | null |
| 20140201 | 1 | 1.353451312 | 246 | 246 | null |
| 20140201 | 2 | 1.2.3.6775 | 183 | 183 | null |
|...|...|...|...|...|...|
| 20140207 | 3 | 1.2.3.4546 | 224 | 224 | null |
| 20140207 | 3 | 1.2.44545 | 196 | 196 | null |
| 20140207 | 3 | 1.353451312 | 168 | 168 | null |
| 20140207 | 4 | 1.2.3.6775 | 189 | 189 | null |
| 20140207 | 4 | 1.23.345345 | 217 | 217 | null |
| 20140207 | 4 | 1.23234234234 | 245 | 245 | null
|
print a log like this
{code}
public class ParallelIterators extends ExplainTable implements ResultIterators {
....
@Override
public List<PeekingResultIterator> getIterators() throws SQLException {
boolean success = false;
final ConnectionQueryServices services =
context.getConnection().getQueryServices();
ReadOnlyProps props = services.getProps();
int numSplits = splits.size();
List<PeekingResultIterator> iterators = new
ArrayList<PeekingResultIterator>(numSplits);
List<Pair<byte[],Future<PeekingResultIterator>>> futures = new
ArrayList<Pair<byte[],Future<PeekingResultIterator>>>(numSplits);
final UUID scanId = UUID.randomUUID();
try {
ExecutorService executor = services.getExecutor();
System.out.println("the split size is " + numSplits);
....
}
}
{code}
then execute some sql
{code}
select * from table1 where gmt > '20140202' and gmt < '20140207' and spm_type =
'2' and spm like '1.%'
the split size is 31
select * from table1 where gmt > '20140202' and gmt < '20140207' and spm_type =
'2'
the split size is 31
select * from table1 where gmt > '20140202' and gmt < '20140207'
the split size is 27
select * from table1 where gmt > '20140202' and gmt < '20140204' and spm_type =
'2' and spm like '1.%'
the split size is 28
select * from table1 where gmt > '20140202' and gmt < '20140204' and spm_type =
'2'
the split size is 28
select * from table1 where gmt > '20140202' and gmt < '20140204'
the split size is 12
{code}
but I think
{code}
select * from table1 where gmt > '20140202' and gmt < '20140207' and spm_type =
'2' and spm like '1.%'
{code}
and
{code}
select * from table1 where gmt > '20140202' and gmt < '20140207'
{code}
the two sql will has the same split , but why not?
> ParallelIteratorRegionSplitterFactory get Splits is not rational
> ----------------------------------------------------------------
>
> Key: PHOENIX-1074
> URL: https://issues.apache.org/jira/browse/PHOENIX-1074
> Project: Phoenix
> Issue Type: Wish
> Reporter: jay wong
>
> create a table
> {code}
> create table if not exists table1(
> gmt VARCHAR NOT NULL,
> spm_type VARCHAR NOT NULL,
> spm VARCHAR NOT NULL,
> A.int_a INTEGER,
> B.int_b INTEGER,
> B.int_c INTEGER
> CONSTRAINT pk PRIMARY KEY (gmt, spm_type, spm)) SALT_BUCKETS = 4,
> bloomfilter='ROW';
> {code}
> and made the table 29 partitions as this.
> |startrow|endrow|
> | |\x0020140201|
> |\x0020140201|\x0020140202|
> |\x0020140202|\x0020140203|
> |\x0020140203|\x0020140204|
> |\x0020140204|\x0020140205|
> |\x0020140205|\x0020140206|
> |\x0020140206|\x0020140207|
> |\x0020140207|\x0120140201|
> |\x0120140201|\x0120140202|
> |\x0120140202|\x0120140203|
> |\x0120140203|\x0120140204|
> |\x0120140204|\x0120140205|
> |\x0120140205|\x0120140206|
> |\x0120140206|\x0120140207|
> |\x0120140207|\x0220140201|
> |\x0220140201|\x0220140202|
> |\x0220140202|\x0220140203|
> |\x0220140203|\x0220140204|
> |\x0220140204|\x0220140205|
> |\x0220140205|\x0220140206|
> |\x0220140206|\x0220140207|
> |\x0220140207|\x0320140201|
> |\x0320140201|\x0320140202|
> |\x0320140202|\x0320140203|
> |\x0320140203|\x0320140204|
> |\x0320140204|\x0320140205|
> |\x0320140205|\x0320140206|
> |\x0320140206|\x0320140207|
> |\x0320140207| |
> Then insert some data;
> | GMT | SPM_TYPE | SPM | INT_A | INT_B | INT_C
> |
> | 20140201 | 1 | 1.2.3.4546 | 218 | 218 | null
> |
> | 20140201 | 1 | 1.2.44545 | 190 | 190 | null
> |
> | 20140201 | 1 | 1.353451312 | 246 | 246 | null
> |
> | 20140201 | 2 | 1.2.3.6775 | 183 | 183 | null
> |
> |...|...|...|...|...|...|
> | 20140207 | 3 | 1.2.3.4546 | 224 | 224 | null
> |
> | 20140207 | 3 | 1.2.44545 | 196 | 196 | null
> |
> | 20140207 | 3 | 1.353451312 | 168 | 168 | null
> |
> | 20140207 | 4 | 1.2.3.6775 | 189 | 189 | null
> |
> | 20140207 | 4 | 1.23.345345 | 217 | 217 | null
> |
> | 20140207 | 4 | 1.23234234234 | 245 | 245 | null
> |
> print a log like this
> {code}
> public class ParallelIterators extends ExplainTable implements
> ResultIterators {
> ....
> @Override
> public List<PeekingResultIterator> getIterators() throws SQLException {
> boolean success = false;
> final ConnectionQueryServices services =
> context.getConnection().getQueryServices();
> ReadOnlyProps props = services.getProps();
> int numSplits = splits.size();
> List<PeekingResultIterator> iterators = new
> ArrayList<PeekingResultIterator>(numSplits);
> List<Pair<byte[],Future<PeekingResultIterator>>> futures = new
> ArrayList<Pair<byte[],Future<PeekingResultIterator>>>(numSplits);
> final UUID scanId = UUID.randomUUID();
> try {
> ExecutorService executor = services.getExecutor();
> System.out.println("the split size is " + numSplits);
> ....
> }
> }
> {code}
> then execute some sql
> {code}
> select * from table1 where gmt > '20140202' and gmt < '20140207' and spm_type
> = '2' and spm like '1.%'
> the split size is 31
> select * from table1 where gmt > '20140202' and gmt < '20140207' and spm_type
> = '2'
> the split size is 31
> select * from table1 where gmt > '20140202' and gmt < '20140207'
> the split size is 27
> select * from table1 where gmt > '20140202' and gmt < '20140204' and spm_type
> = '2' and spm like '1.%'
> the split size is 28
> select * from table1 where gmt > '20140202' and gmt < '20140204' and spm_type
> = '2'
> the split size is 28
> select * from table1 where gmt > '20140202' and gmt < '20140204'
> the split size is 12
> {code}
> but I think
> {code}
> select * from table1 where gmt > '20140202' and gmt < '20140207' and spm_type
> = '2' and spm like '1.%'
> {code}
> and
> {code}
> select * from table1 where gmt > '20140202' and gmt < '20140207'
> {code}
> the two sql will has the same split , but why not?
--
This message was sent by Atlassian JIRA
(v6.2#6252)
