[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450801959 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { +logResult(result); +if (msckInfo.getResFile() != null) { + success = writeResultToFile(msckInfo, result, repairOutput, partitionExpirySeconds) && success; } } - LOG.info("Tables not in metastore: {}", result.getTablesNotInMs()); - LOG.info("Tables missing on filesystem: {}", result.getTablesNotOnFs()); - LOG.info("Partitions not in metastore: {}", result.getPartitionsNotInMs()); - LOG.info("Partitions missing from filesystem: {}", result.getPartitionsNotOnFs()); - LOG.info("Expired partitions: {}", result.getExpiredPartitions()); - if (acquireLock && txnId > 0) { - if (success) { -try { - LOG.info("txnId: {} succeeded. Committing..", txnId); - getMsc().commitTxn(txnId); -} catch (Exception e) { - LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } else { -try { - LOG.info("txnId: {} failed. Aborting..", txnId); - getMsc().abortTxns(Lists.newArrayList(txnId)); -} catch (Exception e) { - LOG.warn("Error while aborting txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } + if (txnId > 0) { +success = closeTxn(qualifiedTableName, success, txnId) && success; } if (getMsc() != null) { getMsc().close(); msc = null; } } +return success ? 0 : 1; + } + private boolean closeTxn(String qualifiedTableName, boolean success, long txnId) { +boolean ret = true; +if (success) { + try { +LOG.info("txnId: {} succeeded. Committing..", txnId); +getMsc().commitTxn(txnId); + } catch (Exception e) { +LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); +ret = false; + } +} else { + try { +LOG.info("txnId: {} failed. Aborting.."
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450793830 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/txn/TxnHandler.java ## @@ -2032,28 +2077,61 @@ public void seedWriteIdOnAcidConversion(InitializeTableWriteIdsRequest rqst) // The initial value for write id should be 1 and hence we add 1 with number of write ids // allocated here String s = "INSERT INTO \"NEXT_WRITE_ID\" (\"NWI_DATABASE\", \"NWI_TABLE\", \"NWI_NEXT\") VALUES (?, ?, " -+ Long.toString(rqst.getSeeWriteId() + 1) + ")"; -pst = sqlGenerator.prepareStmtWithParameters(dbConn, s, Arrays.asList(rqst.getDbName(), rqst.getTblName())); ++ Long.toString(rqst.getSeedWriteId() + 1) + ")"; +pst = sqlGenerator.prepareStmtWithParameters(dbConn, s, Arrays.asList(rqst.getDbName(), rqst.getTableName())); LOG.debug("Going to execute insert <" + s.replaceAll("\\?", "{}") + ">", -quoteString(rqst.getDbName()), quoteString(rqst.getTblName())); +quoteString(rqst.getDbName()), quoteString(rqst.getTableName())); pst.execute(); LOG.debug("Going to commit"); dbConn.commit(); } catch (SQLException e) { -LOG.debug("Going to rollback"); rollbackDBConn(dbConn); -checkRetryable(dbConn, e, "seedWriteIdOnAcidConversion(" + rqst + ")"); -throw new MetaException("Unable to update transaction database " -+ StringUtils.stringifyException(e)); +checkRetryable(dbConn, e, "seedWriteId(" + rqst + ")"); +throw new MetaException("Unable to update transaction database " + StringUtils.stringifyException(e)); } finally { close(null, pst, dbConn); unlockInternal(); } } catch (RetryException e) { - seedWriteIdOnAcidConversion(rqst); + seedWriteId(rqst); } + } + + @Override + public void seedTxnId(SeedTxnIdRequest rqst) throws MetaException { +try { + Connection dbConn = null; + Statement stmt = null; + try { +lockInternal(); +dbConn = getDbConn(Connection.TRANSACTION_READ_COMMITTED); +stmt = dbConn.createStatement(); +/* + * Locking the txnLock an exclusive way, we do not want to set the txnId backward accidentally + * if there are concurrent open transactions + */ +acquireTxnLock(stmt, false); +long highWaterMark = getHighWaterMark(stmt); +if (highWaterMark >= rqst.getSeedTxnId()) { Review comment: This is not about the writeIds, it is about the txnId. If you have a data from a database where there were high amount of transaction and the compaction run on the table, you will have some high txnId in the visibilityTxnId in the name of the compacted folder. If you then move this data to a cluster with less transaction (ex. a test cluster) and you run the msck repair, you have to skip the txnId forward so the next query will read the compacted folder. Here the race condition is, that somehow the txnId sequence gets ahead of you between the check and the seeding the value, in that case we throw this exception to not to set the sequence backward. Anyway, in this case if you run the msck repair again it will succeed, since the txnid will be high enough. The writeId race condition won't cause a problem I think, since if some other transaction allocated the first writeId the seedWriteId will fail on the unique constraint on the table This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450789075 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/txn/TxnHandler.java ## @@ -2032,28 +2077,61 @@ public void seedWriteIdOnAcidConversion(InitializeTableWriteIdsRequest rqst) // The initial value for write id should be 1 and hence we add 1 with number of write ids // allocated here String s = "INSERT INTO \"NEXT_WRITE_ID\" (\"NWI_DATABASE\", \"NWI_TABLE\", \"NWI_NEXT\") VALUES (?, ?, " -+ Long.toString(rqst.getSeeWriteId() + 1) + ")"; -pst = sqlGenerator.prepareStmtWithParameters(dbConn, s, Arrays.asList(rqst.getDbName(), rqst.getTblName())); ++ Long.toString(rqst.getSeedWriteId() + 1) + ")"; +pst = sqlGenerator.prepareStmtWithParameters(dbConn, s, Arrays.asList(rqst.getDbName(), rqst.getTableName())); LOG.debug("Going to execute insert <" + s.replaceAll("\\?", "{}") + ">", -quoteString(rqst.getDbName()), quoteString(rqst.getTblName())); +quoteString(rqst.getDbName()), quoteString(rqst.getTableName())); pst.execute(); LOG.debug("Going to commit"); dbConn.commit(); } catch (SQLException e) { -LOG.debug("Going to rollback"); rollbackDBConn(dbConn); -checkRetryable(dbConn, e, "seedWriteIdOnAcidConversion(" + rqst + ")"); -throw new MetaException("Unable to update transaction database " -+ StringUtils.stringifyException(e)); +checkRetryable(dbConn, e, "seedWriteId(" + rqst + ")"); +throw new MetaException("Unable to update transaction database " + StringUtils.stringifyException(e)); } finally { close(null, pst, dbConn); unlockInternal(); Review comment: fixed, the unique key on NEXT_WRITE_ID is enough This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450787844 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/txn/TxnHandler.java ## @@ -2015,8 +2019,49 @@ public AllocateTableWriteIdsResponse allocateTableWriteIds(AllocateTableWriteIds return allocateTableWriteIds(rqst); } } + + @Override + public MaxAllocatedTableWriteIdResponse getMaxAllocatedTableWrited(MaxAllocatedTableWriteIdRequest rqst) throws MetaException { +String dbName = rqst.getDbName(); +String tableName = rqst.getTableName(); +try { + Connection dbConn = null; + PreparedStatement pStmt = null; + ResultSet rs = null; + try { +lockInternal(); +dbConn = getDbConn(Connection.TRANSACTION_READ_COMMITTED); +List params = Arrays.asList(dbName, tableName); +String query = "SELECT \"NWI_NEXT\" FROM \"NEXT_WRITE_ID\" WHERE \"NWI_DATABASE\" = ? AND \"NWI_TABLE\" = ?"; +pStmt = sqlGenerator.prepareStmtWithParameters(dbConn, query, params); Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450786917 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/txn/TxnHandler.java ## @@ -2015,8 +2019,49 @@ public AllocateTableWriteIdsResponse allocateTableWriteIds(AllocateTableWriteIds return allocateTableWriteIds(rqst); } } + + @Override + public MaxAllocatedTableWriteIdResponse getMaxAllocatedTableWrited(MaxAllocatedTableWriteIdRequest rqst) throws MetaException { +String dbName = rqst.getDbName(); +String tableName = rqst.getTableName(); +try { + Connection dbConn = null; + PreparedStatement pStmt = null; + ResultSet rs = null; + try { +lockInternal(); +dbConn = getDbConn(Connection.TRANSACTION_READ_COMMITTED); Review comment: most of Txnhandler uses this pattern, instead of using three nested try-with for dbconn, statement and resultset This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450785863 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/txn/TxnHandler.java ## @@ -2015,8 +2019,49 @@ public AllocateTableWriteIdsResponse allocateTableWriteIds(AllocateTableWriteIds return allocateTableWriteIds(rqst); } } + + @Override + public MaxAllocatedTableWriteIdResponse getMaxAllocatedTableWrited(MaxAllocatedTableWriteIdRequest rqst) throws MetaException { +String dbName = rqst.getDbName(); +String tableName = rqst.getTableName(); +try { + Connection dbConn = null; + PreparedStatement pStmt = null; + ResultSet rs = null; + try { +lockInternal(); Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450785738 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/txn/TxnHandler.java ## @@ -2015,8 +2019,49 @@ public AllocateTableWriteIdsResponse allocateTableWriteIds(AllocateTableWriteIds return allocateTableWriteIds(rqst); } } + + @Override + public MaxAllocatedTableWriteIdResponse getMaxAllocatedTableWrited(MaxAllocatedTableWriteIdRequest rqst) throws MetaException { +String dbName = rqst.getDbName(); +String tableName = rqst.getTableName(); +try { + Connection dbConn = null; + PreparedStatement pStmt = null; + ResultSet rs = null; + try { +lockInternal(); +dbConn = getDbConn(Connection.TRANSACTION_READ_COMMITTED); +List params = Arrays.asList(dbName, tableName); +String query = "SELECT \"NWI_NEXT\" FROM \"NEXT_WRITE_ID\" WHERE \"NWI_DATABASE\" = ? AND \"NWI_TABLE\" = ?"; Review comment: fixed ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/txn/TxnHandler.java ## @@ -2015,8 +2019,49 @@ public AllocateTableWriteIdsResponse allocateTableWriteIds(AllocateTableWriteIds return allocateTableWriteIds(rqst); } } + + @Override + public MaxAllocatedTableWriteIdResponse getMaxAllocatedTableWrited(MaxAllocatedTableWriteIdRequest rqst) throws MetaException { +String dbName = rqst.getDbName(); +String tableName = rqst.getTableName(); +try { + Connection dbConn = null; + PreparedStatement pStmt = null; + ResultSet rs = null; + try { +lockInternal(); +dbConn = getDbConn(Connection.TRANSACTION_READ_COMMITTED); +List params = Arrays.asList(dbName, tableName); +String query = "SELECT \"NWI_NEXT\" FROM \"NEXT_WRITE_ID\" WHERE \"NWI_DATABASE\" = ? AND \"NWI_TABLE\" = ?"; +pStmt = sqlGenerator.prepareStmtWithParameters(dbConn, query, params); +LOG.debug("Going to execute query <" + query.replaceAll("\\?", "{}") + ">", quoteString(dbName), +quoteString(tableName)); +rs = pStmt.executeQuery(); +// If there is no record, we never allocated anything +long maxWriteId = 0l; +if (rs.next()) { + // The row contains the nextId not the previously allocated + maxWriteId = rs.getLong(1) - 1; +} +return new MaxAllocatedTableWriteIdResponse(maxWriteId); + } catch (SQLException e) { +LOG.error( +"Exception during reading the max allocated writeId for dbName={}, tableName={}. Will retry if possible.", +dbName, tableName, e); +rollbackDBConn(dbConn); Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r45058 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/txn/TxnDbUtil.java ## @@ -313,6 +313,41 @@ private static void resetTxnSequence(Connection conn, Statement stmt) throws SQL } } + /** + * Restarts the txnId sequence with the given seed value. + * It is the responsibility of the caller to not set the sequence backward. + * @param conn database connection + * @param stmt sql statement + * @param seedTxnId the seed value for the sequence + * @throws SQLException ex + */ + public static void seedTxnSequence(Connection conn, Statement stmt, long seedTxnId) throws SQLException { +String dbProduct = conn.getMetaData().getDatabaseProductName(); +DatabaseProduct databaseProduct = determineDatabaseProduct(dbProduct); +switch (databaseProduct) { + +case DERBY: Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450765905 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -383,6 +475,7 @@ public Void execute(int size) throws MetastoreException { partsToAdd.add(partition); lastBatch.add(part); addMsgs.add(String.format(addMsgFormat, part.getPartitionName())); + LOG.debug(String.format(addMsgFormat, part.getPartitionName())); Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450760163 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { +logResult(result); +if (msckInfo.getResFile() != null) { + success = writeResultToFile(msckInfo, result, repairOutput, partitionExpirySeconds) && success; } } - LOG.info("Tables not in metastore: {}", result.getTablesNotInMs()); - LOG.info("Tables missing on filesystem: {}", result.getTablesNotOnFs()); - LOG.info("Partitions not in metastore: {}", result.getPartitionsNotInMs()); - LOG.info("Partitions missing from filesystem: {}", result.getPartitionsNotOnFs()); - LOG.info("Expired partitions: {}", result.getExpiredPartitions()); - if (acquireLock && txnId > 0) { - if (success) { -try { - LOG.info("txnId: {} succeeded. Committing..", txnId); - getMsc().commitTxn(txnId); -} catch (Exception e) { - LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } else { -try { - LOG.info("txnId: {} failed. Aborting..", txnId); - getMsc().abortTxns(Lists.newArrayList(txnId)); -} catch (Exception e) { - LOG.warn("Error while aborting txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } + if (txnId > 0) { +success = closeTxn(qualifiedTableName, success, txnId) && success; } if (getMsc() != null) { getMsc().close(); msc = null; } } +return success ? 0 : 1; + } + private boolean closeTxn(String qualifiedTableName, boolean success, long txnId) { +boolean ret = true; +if (success) { + try { +LOG.info("txnId: {} succeeded. Committing..", txnId); +getMsc().commitTxn(txnId); + } catch (Exception e) { +LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); +ret = false; + } +} else { + try { +LOG.info("txnId: {} failed. Aborting.."
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450756822 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { +logResult(result); +if (msckInfo.getResFile() != null) { + success = writeResultToFile(msckInfo, result, repairOutput, partitionExpirySeconds) && success; } } - LOG.info("Tables not in metastore: {}", result.getTablesNotInMs()); - LOG.info("Tables missing on filesystem: {}", result.getTablesNotOnFs()); - LOG.info("Partitions not in metastore: {}", result.getPartitionsNotInMs()); - LOG.info("Partitions missing from filesystem: {}", result.getPartitionsNotOnFs()); - LOG.info("Expired partitions: {}", result.getExpiredPartitions()); - if (acquireLock && txnId > 0) { - if (success) { -try { - LOG.info("txnId: {} succeeded. Committing..", txnId); - getMsc().commitTxn(txnId); -} catch (Exception e) { - LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } else { -try { - LOG.info("txnId: {} failed. Aborting..", txnId); - getMsc().abortTxns(Lists.newArrayList(txnId)); -} catch (Exception e) { - LOG.warn("Error while aborting txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } + if (txnId > 0) { +success = closeTxn(qualifiedTableName, success, txnId) && success; } if (getMsc() != null) { getMsc().close(); msc = null; } } +return success ? 0 : 1; + } + private boolean closeTxn(String qualifiedTableName, boolean success, long txnId) { +boolean ret = true; +if (success) { + try { +LOG.info("txnId: {} succeeded. Committing..", txnId); +getMsc().commitTxn(txnId); + } catch (Exception e) { +LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); +ret = false; + } +} else { + try { +LOG.info("txnId: {} failed. Aborting.."
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450754328 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { +logResult(result); +if (msckInfo.getResFile() != null) { + success = writeResultToFile(msckInfo, result, repairOutput, partitionExpirySeconds) && success; } } - LOG.info("Tables not in metastore: {}", result.getTablesNotInMs()); - LOG.info("Tables missing on filesystem: {}", result.getTablesNotOnFs()); - LOG.info("Partitions not in metastore: {}", result.getPartitionsNotInMs()); - LOG.info("Partitions missing from filesystem: {}", result.getPartitionsNotOnFs()); - LOG.info("Expired partitions: {}", result.getExpiredPartitions()); - if (acquireLock && txnId > 0) { - if (success) { -try { - LOG.info("txnId: {} succeeded. Committing..", txnId); - getMsc().commitTxn(txnId); -} catch (Exception e) { - LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } else { -try { - LOG.info("txnId: {} failed. Aborting..", txnId); - getMsc().abortTxns(Lists.newArrayList(txnId)); -} catch (Exception e) { - LOG.warn("Error while aborting txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } + if (txnId > 0) { +success = closeTxn(qualifiedTableName, success, txnId) && success; } if (getMsc() != null) { getMsc().close(); msc = null; } } +return success ? 0 : 1; + } + private boolean closeTxn(String qualifiedTableName, boolean success, long txnId) { +boolean ret = true; +if (success) { + try { +LOG.info("txnId: {} succeeded. Committing..", txnId); +getMsc().commitTxn(txnId); + } catch (Exception e) { +LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); +ret = false; + } +} else { + try { +LOG.info("txnId: {} failed. Aborting.."
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450754040 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { +logResult(result); +if (msckInfo.getResFile() != null) { + success = writeResultToFile(msckInfo, result, repairOutput, partitionExpirySeconds) && success; } } - LOG.info("Tables not in metastore: {}", result.getTablesNotInMs()); - LOG.info("Tables missing on filesystem: {}", result.getTablesNotOnFs()); - LOG.info("Partitions not in metastore: {}", result.getPartitionsNotInMs()); - LOG.info("Partitions missing from filesystem: {}", result.getPartitionsNotOnFs()); - LOG.info("Expired partitions: {}", result.getExpiredPartitions()); - if (acquireLock && txnId > 0) { - if (success) { -try { - LOG.info("txnId: {} succeeded. Committing..", txnId); - getMsc().commitTxn(txnId); -} catch (Exception e) { - LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } else { -try { - LOG.info("txnId: {} failed. Aborting..", txnId); - getMsc().abortTxns(Lists.newArrayList(txnId)); -} catch (Exception e) { - LOG.warn("Error while aborting txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } + if (txnId > 0) { +success = closeTxn(qualifiedTableName, success, txnId) && success; } if (getMsc() != null) { getMsc().close(); msc = null; } } +return success ? 0 : 1; + } + private boolean closeTxn(String qualifiedTableName, boolean success, long txnId) { +boolean ret = true; +if (success) { + try { +LOG.info("txnId: {} succeeded. Committing..", txnId); +getMsc().commitTxn(txnId); + } catch (Exception e) { +LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); +ret = false; + } +} else { + try { +LOG.info("txnId: {} failed. Aborting.."
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450753396 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { +logResult(result); +if (msckInfo.getResFile() != null) { + success = writeResultToFile(msckInfo, result, repairOutput, partitionExpirySeconds) && success; } } - LOG.info("Tables not in metastore: {}", result.getTablesNotInMs()); - LOG.info("Tables missing on filesystem: {}", result.getTablesNotOnFs()); - LOG.info("Partitions not in metastore: {}", result.getPartitionsNotInMs()); - LOG.info("Partitions missing from filesystem: {}", result.getPartitionsNotOnFs()); - LOG.info("Expired partitions: {}", result.getExpiredPartitions()); - if (acquireLock && txnId > 0) { - if (success) { -try { - LOG.info("txnId: {} succeeded. Committing..", txnId); - getMsc().commitTxn(txnId); -} catch (Exception e) { - LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } else { -try { - LOG.info("txnId: {} failed. Aborting..", txnId); - getMsc().abortTxns(Lists.newArrayList(txnId)); -} catch (Exception e) { - LOG.warn("Error while aborting txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } + if (txnId > 0) { +success = closeTxn(qualifiedTableName, success, txnId) && success; } if (getMsc() != null) { getMsc().close(); msc = null; } } +return success ? 0 : 1; + } + private boolean closeTxn(String qualifiedTableName, boolean success, long txnId) { +boolean ret = true; +if (success) { + try { +LOG.info("txnId: {} succeeded. Committing..", txnId); +getMsc().commitTxn(txnId); + } catch (Exception e) { +LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); +ret = false; + } +} else { + try { +LOG.info("txnId: {} failed. Aborting.."
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450362382 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { +logResult(result); +if (msckInfo.getResFile() != null) { + success = writeResultToFile(msckInfo, result, repairOutput, partitionExpirySeconds) && success; } } - LOG.info("Tables not in metastore: {}", result.getTablesNotInMs()); - LOG.info("Tables missing on filesystem: {}", result.getTablesNotOnFs()); - LOG.info("Partitions not in metastore: {}", result.getPartitionsNotInMs()); - LOG.info("Partitions missing from filesystem: {}", result.getPartitionsNotOnFs()); - LOG.info("Expired partitions: {}", result.getExpiredPartitions()); - if (acquireLock && txnId > 0) { - if (success) { -try { - LOG.info("txnId: {} succeeded. Committing..", txnId); - getMsc().commitTxn(txnId); -} catch (Exception e) { - LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } else { -try { - LOG.info("txnId: {} failed. Aborting..", txnId); - getMsc().abortTxns(Lists.newArrayList(txnId)); -} catch (Exception e) { - LOG.warn("Error while aborting txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } + if (txnId > 0) { +success = closeTxn(qualifiedTableName, success, txnId) && success; } if (getMsc() != null) { getMsc().close(); msc = null; } } +return success ? 0 : 1; + } + private boolean closeTxn(String qualifiedTableName, boolean success, long txnId) { +boolean ret = true; +if (success) { + try { +LOG.info("txnId: {} succeeded. Committing..", txnId); +getMsc().commitTxn(txnId); + } catch (Exception e) { +LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); Review comment: fixed ## File path: standalone-metastore/metastore-server/src/main/java/
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450361883 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { +logResult(result); +if (msckInfo.getResFile() != null) { + success = writeResultToFile(msckInfo, result, repairOutput, partitionExpirySeconds) && success; } } - LOG.info("Tables not in metastore: {}", result.getTablesNotInMs()); - LOG.info("Tables missing on filesystem: {}", result.getTablesNotOnFs()); - LOG.info("Partitions not in metastore: {}", result.getPartitionsNotInMs()); - LOG.info("Partitions missing from filesystem: {}", result.getPartitionsNotOnFs()); - LOG.info("Expired partitions: {}", result.getExpiredPartitions()); - if (acquireLock && txnId > 0) { - if (success) { -try { - LOG.info("txnId: {} succeeded. Committing..", txnId); - getMsc().commitTxn(txnId); -} catch (Exception e) { - LOG.warn("Error while committing txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } else { -try { - LOG.info("txnId: {} failed. Aborting..", txnId); - getMsc().abortTxns(Lists.newArrayList(txnId)); -} catch (Exception e) { - LOG.warn("Error while aborting txnId: {} for table: {}", txnId, qualifiedTableName, e); - ret = 1; -} - } + if (txnId > 0) { +success = closeTxn(qualifiedTableName, success, txnId) && success; Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450361792 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { +logResult(result); +if (msckInfo.getResFile() != null) { + success = writeResultToFile(msckInfo, result, repairOutput, partitionExpirySeconds) && success; Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450361266 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { +if (txnId < 0) { + // We need the txnId to check against even if we didn't do the locking + txnId = getMsc().openTxn(getUserName()); +} + +validateAndAddMaxTxnIdAndWriteId(result.getMaxWriteId(), result.getMaxTxnId(), +table.getDbName(), table.getTableName(), txnId); + } +} } success = true; } catch (Exception e) { LOG.warn("Failed to run metacheck: ", e); success = false; - ret = 1; } finally { - if (msckInfo.getResFile() != null) { -BufferedWriter resultOut = null; -try { - Path resFile = new Path(msckInfo.getResFile()); - FileSystem fs = resFile.getFileSystem(getConf()); - resultOut = new BufferedWriter(new OutputStreamWriter(fs.create(resFile))); - - boolean firstWritten = false; - firstWritten |= writeMsckResult(result.getTablesNotInMs(), -"Tables not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getTablesNotOnFs(), -"Tables missing on filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotInMs(), -"Partitions not in metastore:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getPartitionsNotOnFs(), -"Partitions missing from filesystem:", resultOut, firstWritten); - firstWritten |= writeMsckResult(result.getExpiredPartitions(), -"Expired partitions (retention period: " + partitionExpirySeconds + "s) :", resultOut, firstWritten); - // sorting to stabilize qfile output (msck_repair_drop.q) - Collections.sort(repairOutput); - for (String rout : repairOutput) { -if (firstWritten) { - resultOut.write(terminator); -} else { - firstWritten = true; -} -resultOut.write(rout); - } -} catch (IOException e) { - LOG.warn("Failed to save metacheck output: ", e); - ret = 1; -} finally { - if (resultOut != null) { -try { - resultOut.close(); -} catch (IOException e) { - LOG.warn("Failed to close output file: ", e); - ret = 1; -} - } + if (result!=null) { Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450360969 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/Msck.java ## @@ -229,102 +239,168 @@ public int repair(MsckInfo msckInfo) { throw new MetastoreException(e); } } +if (transactionalTable && !MetaStoreServerUtils.isPartitioned(table)) { + if (result.getMaxWriteId() > 0) { Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450360016 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/HiveMetaStoreChecker.java ## @@ -429,6 +451,75 @@ void findUnknownPartitions(Table table, Set partPaths, LOG.debug("Number of partitions not in metastore : " + result.getPartitionsNotInMs().size()); } + /** + * Calculate the maximum seen writeId from the acid directory structure + * @param partPath Path of the partition directory + * @param res Partition result to write the max ids + * @throws IOException ex + */ + private void setMaxTxnAndWriteIdFromPartition(Path partPath, CheckResult.PartitionResult res) throws IOException { +FileSystem fs = partPath.getFileSystem(conf); +FileStatus[] deltaOrBaseFiles = fs.listStatus(partPath, HIDDEN_FILES_PATH_FILTER); + +// Read the writeIds from every base and delta directory and find the max +long maxWriteId = 0L; +long maxVisibilityId = 0L; +for(FileStatus fileStatus : deltaOrBaseFiles) { + if (!fileStatus.isDirectory()) { +continue; + } + long writeId = 0L; + long visibilityId = 0L; + String folder = fileStatus.getPath().getName(); + if (folder.startsWith(BASE_PREFIX)) { +visibilityId = getVisibilityTxnId(folder); +if (visibilityId > 0) { + folder = removeVisibilityTxnId(folder); +} +writeId = Long.parseLong(folder.substring(BASE_PREFIX.length())); + } else if (folder.startsWith(DELTA_PREFIX) || folder.startsWith(DELETE_DELTA_PREFIX)) { +// See AcidUtils.parseDelta +visibilityId = getVisibilityTxnId(folder); +if (visibilityId > 0) { + folder = removeVisibilityTxnId(folder); +} +boolean isDeleteDelta = folder.startsWith(DELETE_DELTA_PREFIX); +String rest = folder.substring((isDeleteDelta ? DELETE_DELTA_PREFIX : DELTA_PREFIX).length()); +int split = rest.indexOf('_'); +//split2 may be -1 if no statementId +int split2 = rest.indexOf('_', split + 1); +// We always want the second part (it is either the same or greater if it is a compacted delta) +writeId = split2 == -1 ? Long.parseLong(rest.substring(split + 1)) : Long +.parseLong(rest.substring(split + 1, split2)); + } + if (writeId > maxWriteId) { +maxWriteId = writeId; + } + if (visibilityId > maxVisibilityId) { +maxVisibilityId = visibilityId; + } +} +LOG.debug("Max writeId {}, max txnId {} found in partition {}", maxWriteId, maxVisibilityId, +partPath.toUri().toString()); +res.setMaxWriteId(maxWriteId); +res.setMaxTxnId(maxVisibilityId); + } + private long getVisibilityTxnId(String folder) { +int idxOfVis = folder.indexOf(VISIBILITY_PREFIX); Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450338348 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/HiveMetaStoreChecker.java ## @@ -429,6 +451,75 @@ void findUnknownPartitions(Table table, Set partPaths, LOG.debug("Number of partitions not in metastore : " + result.getPartitionsNotInMs().size()); } + /** + * Calculate the maximum seen writeId from the acid directory structure + * @param partPath Path of the partition directory + * @param res Partition result to write the max ids + * @throws IOException ex + */ + private void setMaxTxnAndWriteIdFromPartition(Path partPath, CheckResult.PartitionResult res) throws IOException { +FileSystem fs = partPath.getFileSystem(conf); +FileStatus[] deltaOrBaseFiles = fs.listStatus(partPath, HIDDEN_FILES_PATH_FILTER); + +// Read the writeIds from every base and delta directory and find the max +long maxWriteId = 0L; +long maxVisibilityId = 0L; +for(FileStatus fileStatus : deltaOrBaseFiles) { + if (!fileStatus.isDirectory()) { +continue; + } + long writeId = 0L; + long visibilityId = 0L; + String folder = fileStatus.getPath().getName(); + if (folder.startsWith(BASE_PREFIX)) { +visibilityId = getVisibilityTxnId(folder); +if (visibilityId > 0) { + folder = removeVisibilityTxnId(folder); +} +writeId = Long.parseLong(folder.substring(BASE_PREFIX.length())); + } else if (folder.startsWith(DELTA_PREFIX) || folder.startsWith(DELETE_DELTA_PREFIX)) { +// See AcidUtils.parseDelta +visibilityId = getVisibilityTxnId(folder); +if (visibilityId > 0) { + folder = removeVisibilityTxnId(folder); +} +boolean isDeleteDelta = folder.startsWith(DELETE_DELTA_PREFIX); +String rest = folder.substring((isDeleteDelta ? DELETE_DELTA_PREFIX : DELTA_PREFIX).length()); +int split = rest.indexOf('_'); Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450334396 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/HiveMetaStoreChecker.java ## @@ -111,24 +120,24 @@ public IMetaStoreClient getMsc() { * @param partitions * List of partition name value pairs, if null or empty check all * partitions - * @param table - * @param result - * Fill this with the results of the check + * @param table Table we want to run the check for. + * @return Results of the check * @throws MetastoreException * Failed to get required information from the metastore. * @throws IOException * Most likely filesystem related */ - public void checkMetastore(String catName, String dbName, String tableName, - List> partitions, Table table, CheckResult result) + public CheckResult checkMetastore(String catName, String dbName, String tableName, + List> partitions, Table table) throws MetastoreException, IOException { - +CheckResult result = new CheckResult(); if (dbName == null || "".equalsIgnoreCase(dbName)) { dbName = Warehouse.DEFAULT_DATABASE_NAME; } try { if (tableName == null || "".equals(tableName)) { +// TODO: I do not think this is used by anything other than tests Review comment: I do not know. If I understand correctly there is no way currently to call MSCK repair without a table specified, but it seems like someone made some effort to create that feature and tests for it. But i don't know if we ever want that in production (calling msck repair for every table seems like a quick way to overwhelm the system) I left this comment here, for anybody who tries to makes sense of this code. This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450326885 ## File path: standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/HiveMetaStore.java ## @@ -8322,6 +8322,22 @@ public AllocateTableWriteIdsResponse allocate_table_write_ids( return response; } +@Override +public MaxAllocatedTableWriteIdResponse get_max_allocated_table_write_id(MaxAllocatedTableWriteIdRequest rqst) Review comment: All the functions in HMS looks like this I don't want to break the pattern. On the second glance, I had to change the seedWriteId and seedTxnId to look like this... This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450318970 ## File path: ql/src/test/org/apache/hadoop/hive/ql/TxnCommandsBaseForTests.java ## @@ -162,9 +163,23 @@ protected String getWarehouseDir() { * takes raw data and turns it into a string as if from Driver.getResults() * sorts rows in dictionary order */ - List stringifyValues(int[][] rowsIn) { -return TestTxnCommands2.stringifyValues(rowsIn); + public static List stringifyValues(int[][] rowsIn) { +assert rowsIn.length > 0; +int[][] rows = rowsIn.clone(); +Arrays.sort(rows, new TestTxnCommands2.RowComp()); Review comment: fixed ## File path: ql/src/test/org/apache/hadoop/hive/ql/metadata/TestHiveMetaStoreChecker.java ## @@ -252,37 +241,165 @@ public void testInvalidPartitionKeyName() @Test public void testSkipInvalidPartitionKeyName() throws HiveException, AlreadyExistsException, IOException, MetastoreException { -hive.getConf().set(HiveConf.ConfVars.HIVE_MSCK_PATH_VALIDATION.varname, "skip"); + hive.getConf().set(MetastoreConf.ConfVars.MSCK_PATH_VALIDATION.getVarname(), "skip"); checker = new HiveMetaStoreChecker(msc, hive.getConf()); -Table table = createTestTable(); +Table table = createTestTable(false); List partitions = hive.getPartitions(table); assertEquals(2, partitions.size()); // add a fake partition dir on fs fs = partitions.get(0).getDataLocation().getFileSystem(hive.getConf()); -Path fakePart = -new Path(table.getDataLocation().toString(), "fakedate=2009-01-01/fakecity=sanjose"); -fs.mkdirs(fakePart); -fs.deleteOnExit(fakePart); +addFolderToPath(fs, table.getDataLocation().toString(),"fakedate=2009-01-01/fakecity=sanjose"); createPartitionsDirectoriesOnFS(table, 2); -CheckResult result = new CheckResult(); -checker.checkMetastore(catName, dbName, tableName, null, null, result); +CheckResult result = checker.checkMetastore(catName, dbName, tableName, null, null); assertEquals(Collections. emptySet(), result.getTablesNotInMs()); assertEquals(Collections. emptySet(), result.getTablesNotOnFs()); assertEquals(Collections. emptySet(), result.getPartitionsNotOnFs()); // only 2 valid partitions should be added assertEquals(2, result.getPartitionsNotInMs().size()); } - private Table createTestTable() throws HiveException, AlreadyExistsException { + /* + * Tests the case when we have normal delta_dirs in the partition folder + * does not throw HiveException + */ + @Test + public void testAddPartitionNormalDeltas() throws Exception { +Table table = createTestTable(true); +List partitions = hive.getPartitions(table); +assertEquals(2, partitions.size()); +// add a partition dir on fs +fs = partitions.get(0).getDataLocation().getFileSystem(hive.getConf()); +Path newPart = addFolderToPath(fs, table.getDataLocation().toString(), +partDateName + "=2017-01-01/" + partCityName + "=paloalto"); + +// Add a few deltas +addFolderToPath(fs, newPart.toString(), "delta_001_001_"); +addFolderToPath(fs, newPart.toString(), "delta_010_010_"); +addFolderToPath(fs, newPart.toString(), "delta_101_101_"); +CheckResult result = checker.checkMetastore(catName, dbName, tableName, null, null); +assertEquals(Collections. emptySet(), result.getPartitionsNotOnFs()); +assertEquals(1, result.getPartitionsNotInMs().size()); +// Found the highest writeId +assertEquals(101, result.getPartitionsNotInMs().iterator().next().getMaxWriteId()); +assertEquals(0, result.getPartitionsNotInMs().iterator().next().getMaxTxnId()); + } + /* + * Tests the case when we have normal delta_dirs in the partition folder + * does not throw HiveException + */ + @Test + public void testAddPartitionCompactedDeltas() throws Exception { +Table table = createTestTable(true); +List partitions = hive.getPartitions(table); +assertEquals(2, partitions.size()); +// add a partition dir on fs +fs = partitions.get(0).getDataLocation().getFileSystem(hive.getConf()); +Path newPart = addFolderToPath(fs, table.getDataLocation().toString(), +partDateName + "=2017-01-01/" + partCityName + "=paloalto"); + +// Add a few deltas +addFolderToPath(fs, newPart.toString(), "delta_001_001_"); +addFolderToPath(fs, newPart.toString(), "delta_010_015_v067"); +addFolderToPath(fs, newPart.toString(), "delta_101_120_v087"); +CheckResult result = checker.checkMetastore(catName, dbName, tableName, null, null); +assertEquals(Collections. emptySet(), result.getPartitionsNotOnFs()); +assertEquals(1, result.getPartitionsNotInMs().size()); +// Found the highest writeId +assertEquals(120, result.getPartitionsNotInMs().iterator().next().getMaxWri
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450318861 ## File path: ql/src/java/org/apache/hadoop/hive/ql/io/AcidUtils.java ## @@ -2392,33 +2392,29 @@ public static TableSnapshot getTableSnapshot(Configuration conf, long writeId = -1; ValidWriteIdList validWriteIdList = null; -HiveTxnManager sessionTxnMgr = SessionState.get().getTxnMgr(); -String fullTableName = getFullTableName(dbName, tblName); -if (sessionTxnMgr != null && sessionTxnMgr.getCurrentTxnId() > 0) { - validWriteIdList = getTableValidWriteIdList(conf, fullTableName); - if (isStatsUpdater) { -writeId = SessionState.get().getTxnMgr() != null ? -SessionState.get().getTxnMgr().getAllocatedTableWriteId( - dbName, tblName) : -1; -if (writeId < 1) { - // TODO: this is not ideal... stats updater that doesn't have write ID is currently - // "create table"; writeId would be 0/-1 here. No need to call this w/true. - LOG.debug("Stats updater for {}.{} doesn't have a write ID ({})", - dbName, tblName, writeId); +if (SessionState.get() != null) { + HiveTxnManager sessionTxnMgr = SessionState.get().getTxnMgr(); + String fullTableName = getFullTableName(dbName, tblName); + if (sessionTxnMgr != null && sessionTxnMgr.getCurrentTxnId() > 0) { +validWriteIdList = getTableValidWriteIdList(conf, fullTableName); +if (isStatsUpdater) { + writeId = sessionTxnMgr != null ? sessionTxnMgr.getAllocatedTableWriteId(dbName, tblName) : -1; Review comment: fixed This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450317451 ## File path: ql/src/test/org/apache/hadoop/hive/ql/metadata/TestHiveMetaStoreChecker.java ## @@ -74,21 +76,21 @@ @Before public void setUp() throws Exception { hive = Hive.get(); - hive.getConf().setIntVar(HiveConf.ConfVars.METASTORE_FS_HANDLER_THREADS_COUNT, 15); -hive.getConf().set(HiveConf.ConfVars.HIVE_MSCK_PATH_VALIDATION.varname, "throw"); + hive.getConf().set(MetastoreConf.ConfVars.FS_HANDLER_THREADS_COUNT.getVarname(), "15"); Review comment: It does not work with MetasoreConf.ConfVars This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450315397 ## File path: ql/src/test/org/apache/hadoop/hive/ql/TestTxnCommands2.java ## @@ -2209,20 +2209,7 @@ public void testAcidOrcWritePreservesFieldNames() throws Exception { * sorts rows in dictionary order */ static List stringifyValues(int[][] rowsIn) { -assert rowsIn.length > 0; -int[][] rows = rowsIn.clone(); -Arrays.sort(rows, new RowComp()); -List rs = new ArrayList(); -for(int[] row : rows) { - assert row.length > 0; - StringBuilder sb = new StringBuilder(); - for(int value : row) { -sb.append(value).append("\t"); - } - sb.setLength(sb.length() - 1); - rs.add(sb.toString()); -} -return rs; +return TxnCommandsBaseForTests.stringifyValues(rowsIn); Review comment: I will do this in a separate Jira, started it, but it requires more change. This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450302033 ## File path: ql/src/java/org/apache/hadoop/hive/ql/io/AcidUtils.java ## @@ -2392,33 +2392,29 @@ public static TableSnapshot getTableSnapshot(Configuration conf, long writeId = -1; ValidWriteIdList validWriteIdList = null; -HiveTxnManager sessionTxnMgr = SessionState.get().getTxnMgr(); -String fullTableName = getFullTableName(dbName, tblName); -if (sessionTxnMgr != null && sessionTxnMgr.getCurrentTxnId() > 0) { - validWriteIdList = getTableValidWriteIdList(conf, fullTableName); - if (isStatsUpdater) { -writeId = SessionState.get().getTxnMgr() != null ? -SessionState.get().getTxnMgr().getAllocatedTableWriteId( - dbName, tblName) : -1; -if (writeId < 1) { - // TODO: this is not ideal... stats updater that doesn't have write ID is currently - // "create table"; writeId would be 0/-1 here. No need to call this w/true. - LOG.debug("Stats updater for {}.{} doesn't have a write ID ({})", - dbName, tblName, writeId); +if (SessionState.get() != null) { + HiveTxnManager sessionTxnMgr = SessionState.get().getTxnMgr(); + String fullTableName = getFullTableName(dbName, tblName); + if (sessionTxnMgr != null && sessionTxnMgr.getCurrentTxnId() > 0) { +validWriteIdList = getTableValidWriteIdList(conf, fullTableName); +if (isStatsUpdater) { + writeId = sessionTxnMgr != null ? sessionTxnMgr.getAllocatedTableWriteId(dbName, tblName) : -1; + if (writeId < 1) { Review comment: The comment said so: "stats updater that doesn't have write ID is currently "create table"; writeId would be 0/-1 here." This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org
[GitHub] [hive] pvargacl commented on a change in pull request #1087: HIVE-23671: MSCK repair should handle transactional tables
pvargacl commented on a change in pull request #1087: URL: https://github.com/apache/hive/pull/1087#discussion_r450301348 ## File path: ql/src/java/org/apache/hadoop/hive/ql/io/AcidUtils.java ## @@ -2392,33 +2392,29 @@ public static TableSnapshot getTableSnapshot(Configuration conf, long writeId = -1; ValidWriteIdList validWriteIdList = null; -HiveTxnManager sessionTxnMgr = SessionState.get().getTxnMgr(); -String fullTableName = getFullTableName(dbName, tblName); -if (sessionTxnMgr != null && sessionTxnMgr.getCurrentTxnId() > 0) { - validWriteIdList = getTableValidWriteIdList(conf, fullTableName); - if (isStatsUpdater) { -writeId = SessionState.get().getTxnMgr() != null ? -SessionState.get().getTxnMgr().getAllocatedTableWriteId( - dbName, tblName) : -1; -if (writeId < 1) { - // TODO: this is not ideal... stats updater that doesn't have write ID is currently - // "create table"; writeId would be 0/-1 here. No need to call this w/true. - LOG.debug("Stats updater for {}.{} doesn't have a write ID ({})", - dbName, tblName, writeId); +if (SessionState.get() != null) { Review comment: It can be null, if the sessionstate was not set properly, it was failing one of the tests, i can't remember which. This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org - To unsubscribe, e-mail: gitbox-unsubscr...@hive.apache.org For additional commands, e-mail: gitbox-h...@hive.apache.org