[ https://issues.apache.org/jira/browse/HBASE-8806?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
rahul gidwani updated HBASE-8806: --------------------------------- Description: If we already have the lock in the doMiniBatchMutation we don't need to re-acquire it. The solution would be to keep a cache of the rowKeys already locked for a miniBatchMutation and If we already have the rowKey in the cache, we don't repeatedly try and acquire the lock. A fix to this problem would be to keep a set of rows we already locked and not try to acquire the lock for these rows. We have tested this fix in our production environment and has improved replication performance quite a bit. We saw a replication batch go from 3+ minutes to less than 10 seconds for batches with duplicate row keys. {code} static final int ACQUIRE_LOCK_COUNT = 0; @Test public void testRedundantRowKeys() throws Exception { final int batchSize = 100000; String tableName = getClass().getSimpleName(); Configuration conf = HBaseConfiguration.create(); conf.setClass(HConstants.REGION_IMPL, MockHRegion.class, HeapSize.class); MockHRegion region = (MockHRegion) TestHRegion.initHRegion(Bytes.toBytes(tableName), tableName, conf, Bytes.toBytes("a")); List<Pair<Mutation, Integer>> someBatch = Lists.newArrayList(); int i = 0; while (i < batchSize) { if (i % 2 == 0) { someBatch.add(new Pair<Mutation, Integer>(new Put(Bytes.toBytes(0)), null)); } else { someBatch.add(new Pair<Mutation, Integer>(new Put(Bytes.toBytes(1)), null)); } i++; } long startTime = System.currentTimeMillis(); region.batchMutate(someBatch.toArray(new Pair[0])); long endTime = System.currentTimeMillis(); long duration = endTime - startTime; System.out.println("duration: " + duration + " ms"); assertEquals(2, ACQUIRE_LOCK_COUNT); <--- should only try and acquire the lock twice. } @Override public Integer getLock(Integer lockid, byte[] row, boolean waitForLock) throws IOException { ACQUIRE_LOCK_COUNT++; return super.getLock(lockid, row, waitForLock); } {code} was: If we already have the lock in the doMiniBatchMutation we don't need to re-acquire it. The solution would be to keep a cache of the rowKeys already locked for a miniBatchMutation and If we already have the rowKey in the cache, we don't repeatedly try and acquire the lock. A fix to this problem would be to keep a set of rows we already locked and not try to acquire the lock for these rows. We have tested this fix in our production environment and has improved replication performance quite a bit. We saw a replication batch go from 3+ minutes to less than 10 seconds for batches with duplicate row keys. {code} static final int ACQUIRE_LOCK_COUNT = 0; @Test public void testRedundantRowKeys() throws Exception { final int batchSize = 100000; String tableName = getClass().getSimpleName(); Configuration conf = HBaseConfiguration.create(); conf.setClass(HConstants.REGION_IMPL, MockHRegion.class, HeapSize.class); MockHRegion region = (MockHRegion) TestHRegion.initHRegion(Bytes.toBytes(tableName), tableName, conf, Bytes.toBytes("a")); List<Pair<Mutation, Integer>> someBatch = Lists.newArrayList(); int i = 0; while (i < batchSize) { if (i % 2 == 0) { someBatch.add(new Pair<Mutation, Integer>(new Put(Bytes.toBytes(0)), null)); } else { someBatch.add(new Pair<Mutation, Integer>(new Put(Bytes.toBytes(1)), null)); } i++; } long startTime = System.currentTimeMillis(); region.batchMutate(someBatch.toArray(new Pair[0])); long endTime = System.currentTimeMillis(); long duration = endTime - startTime; System.out.println("duration: " + duration + " ms"); assertEquals(2, ACQUIRE_LOCK_COUNT); <--- should only try and acquire the lock twice. } @Override public Integer getLock(Integer lockid, byte[] row, boolean waitForLock) throws IOException { ACQUIRE_LOCK_COUNT++; return super.getLock(lockid, row, waitForLock); } {/code} > Row locks are acquired repeatedly in HRegion.doMiniBatchMutation for > duplicate rows. > ------------------------------------------------------------------------------------ > > Key: HBASE-8806 > URL: https://issues.apache.org/jira/browse/HBASE-8806 > Project: HBase > Issue Type: Bug > Components: regionserver > Affects Versions: 0.94.5 > Reporter: rahul gidwani > Fix For: 0.94.0, 0.98.0, 0.95.0 > > > If we already have the lock in the doMiniBatchMutation we don't need to > re-acquire it. The solution would be to keep a cache of the rowKeys already > locked for a miniBatchMutation and If we already have the > rowKey in the cache, we don't repeatedly try and acquire the lock. A fix to > this problem would be to keep a set of rows we already locked and not try to > acquire the lock for these rows. > We have tested this fix in our production environment and has improved > replication performance quite a bit. We saw a replication batch go from 3+ > minutes to less than 10 seconds for batches with duplicate row keys. > {code} > static final int ACQUIRE_LOCK_COUNT = 0; > @Test > public void testRedundantRowKeys() throws Exception { > final int batchSize = 100000; > > String tableName = getClass().getSimpleName(); > Configuration conf = HBaseConfiguration.create(); > conf.setClass(HConstants.REGION_IMPL, MockHRegion.class, HeapSize.class); > MockHRegion region = (MockHRegion) > TestHRegion.initHRegion(Bytes.toBytes(tableName), tableName, conf, > Bytes.toBytes("a")); > List<Pair<Mutation, Integer>> someBatch = Lists.newArrayList(); > int i = 0; > while (i < batchSize) { > if (i % 2 == 0) { > someBatch.add(new Pair<Mutation, Integer>(new Put(Bytes.toBytes(0)), > null)); > } else { > someBatch.add(new Pair<Mutation, Integer>(new Put(Bytes.toBytes(1)), > null)); > } > i++; > } > long startTime = System.currentTimeMillis(); > region.batchMutate(someBatch.toArray(new Pair[0])); > long endTime = System.currentTimeMillis(); > long duration = endTime - startTime; > System.out.println("duration: " + duration + " ms"); > assertEquals(2, ACQUIRE_LOCK_COUNT); <--- should only try and acquire the > lock twice. > } > @Override > public Integer getLock(Integer lockid, byte[] row, boolean waitForLock) > throws IOException { > ACQUIRE_LOCK_COUNT++; > return super.getLock(lockid, row, waitForLock); > } > {code} -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira