[
https://issues.apache.org/jira/browse/HBASE-3725?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jonathan Gray updated HBASE-3725:
---------------------------------
Attachment: HBASE-3725-v3.patch
This fixes the problem in the only simple way I could think of.
A new configuration option is added "hbase.hregion.increment.supportdeletes"
which defaults to true (because it is required for "correctness").
When this option is true, then when the scan against StoreFiles is done, it
will also include the MemStore. This should ensure correctness for cases where
delete markers are present in the MemStore that need to apply to KVs in the
StoreFiles.
I made this a configuration option because it makes increment operations less
optimal, so for increment workloads that do not need to support deletes, they
can keep the option turned off and avoid the double scan of the MemStore.
A potential optimal and correct solution to this could be to use the old Get
delete tracker which would retain delete information across files (for in-order
file processing rather than one mega merge). Some work is going into
re-integrating those, so if they do make it back in the HBase, we could utilize
them here.
This should suffice for now.
> HBase increments from old value after delete and write to disk
> --------------------------------------------------------------
>
> Key: HBASE-3725
> URL: https://issues.apache.org/jira/browse/HBASE-3725
> Project: HBase
> Issue Type: Bug
> Components: io, regionserver
> Affects Versions: 0.90.1
> Reporter: Nathaniel Cook
> Attachments: HBASE-3725-Test-v1.patch, HBASE-3725-v3.patch,
> HBASE-3725.patch
>
>
> Deleted row values are sometimes used for starting points on new increments.
> To reproduce:
> Create a row "r". Set column "x" to some default value.
> Force hbase to write that value to the file system (such as restarting the
> cluster).
> Delete the row.
> Call table.incrementColumnValue with "some_value"
> Get the row.
> The returned value in the column was incremented from the old value before
> the row was deleted instead of being initialized to "some_value".
> Code to reproduce:
> {code}
> import java.io.IOException;
> import org.apache.hadoop.conf.Configuration;
> import org.apache.hadoop.hbase.HBaseConfiguration;
> import org.apache.hadoop.hbase.HColumnDescriptor;
> import org.apache.hadoop.hbase.HTableDescriptor;
> import org.apache.hadoop.hbase.client.Delete;
> import org.apache.hadoop.hbase.client.Get;
> import org.apache.hadoop.hbase.client.HBaseAdmin;
> import org.apache.hadoop.hbase.client.HTableInterface;
> import org.apache.hadoop.hbase.client.HTablePool;
> import org.apache.hadoop.hbase.client.Increment;
> import org.apache.hadoop.hbase.client.Result;
> import org.apache.hadoop.hbase.util.Bytes;
> public class HBaseTestIncrement
> {
> static String tableName = "testIncrement";
> static byte[] infoCF = Bytes.toBytes("info");
> static byte[] rowKey = Bytes.toBytes("test-rowKey");
> static byte[] newInc = Bytes.toBytes("new");
> static byte[] oldInc = Bytes.toBytes("old");
> /**
> * This code reproduces a bug with increment column values in hbase
> * Usage: First run part one by passing '1' as the first arg
> * Then restart the hbase cluster so it writes everything to disk
> * Run part two by passing '2' as the first arg
> *
> * This will result in the old deleted data being found and used for
> the increment calls
> *
> * @param args
> * @throws IOException
> */
> public static void main(String[] args) throws IOException
> {
> if("1".equals(args[0]))
> partOne();
> if("2".equals(args[0]))
> partTwo();
> if ("both".equals(args[0]))
> {
> partOne();
> partTwo();
> }
> }
> /**
> * Creates a table and increments a column value 10 times by 10 each
> time.
> * Results in a value of 100 for the column
> *
> * @throws IOException
> */
> static void partOne()throws IOException
> {
> Configuration conf = HBaseConfiguration.create();
> HBaseAdmin admin = new HBaseAdmin(conf);
> HTableDescriptor tableDesc = new HTableDescriptor(tableName);
> tableDesc.addFamily(new HColumnDescriptor(infoCF));
> if(admin.tableExists(tableName))
> {
> admin.disableTable(tableName);
> admin.deleteTable(tableName);
> }
> admin.createTable(tableDesc);
> HTablePool pool = new HTablePool(conf, Integer.MAX_VALUE);
> HTableInterface table = pool.getTable(Bytes.toBytes(tableName));
> //Increment unitialized column
> for (int j = 0; j < 10; j++)
> {
> table.incrementColumnValue(rowKey, infoCF, oldInc,
> (long)10);
> Increment inc = new Increment(rowKey);
> inc.addColumn(infoCF, newInc, (long)10);
> table.increment(inc);
> }
> Get get = new Get(rowKey);
> Result r = table.get(get);
> System.out.println("initial values: new " +
> Bytes.toLong(r.getValue(infoCF, newInc)) + " old " +
> Bytes.toLong(r.getValue(infoCF, oldInc)));
> }
> /**
> * First deletes the data then increments the column 10 times by 1 each
> time
> *
> * Should result in a value of 10 but it doesn't, it results in a
> values of 110
> *
> * @throws IOException
> */
> static void partTwo()throws IOException
> {
> Configuration conf = HBaseConfiguration.create();
> HTablePool pool = new HTablePool(conf, Integer.MAX_VALUE);
> HTableInterface table = pool.getTable(Bytes.toBytes(tableName));
>
> Delete delete = new Delete(rowKey);
> table.delete(delete);
> //Increment columns
> for (int j = 0; j < 10; j++)
> {
> table.incrementColumnValue(rowKey, infoCF, oldInc,
> (long)1);
> Increment inc = new Increment(rowKey);
> inc.addColumn(infoCF, newInc, (long)1);
> table.increment(inc);
> }
> Get get = new Get(rowKey);
> Result r = table.get(get);
> System.out.println("after delete values: new " +
> Bytes.toLong(r.getValue(infoCF, newInc)) + " old " +
> Bytes.toLong(r.getValue(infoCF, oldInc)));
> }
> }
> {code}
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
