----------------------- Execution Plan ----------------------- { "nodes": [ { "id": 6, "type": "source", "pact": "Data Source", "contents": "TextInputFormat (file:/home/hoenicke/flink-0.6-incubating/input/inputNummeriert.txt) - UTF-8", "parallelism": "1", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "428.46 M" }, { "name": "Est. Cardinality", "value": "410.75 K" } ], "costs": [ { "name": "Network", "value": "0.0" }, { "name": "Disk I/O", "value": "428.46 M" }, { "name": "CPU", "value": "0.0" }, { "name": "Cumulative Network", "value": "0.0" }, { "name": "Cumulative Disk I/O", "value": "428.46 M" }, { "name": "Cumulative CPU", "value": "0.0" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 11, "type": "source", "pact": "Data Source", "contents": "TextInputFormat (file:/home/hoenicke/flink-0.6-incubating/input/inputNummeriert.txt) - UTF-8", "parallelism": "1", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "428.46 M" }, { "name": "Est. Cardinality", "value": "410.75 K" } ], "costs": [ { "name": "Network", "value": "0.0" }, { "name": "Disk I/O", "value": "428.46 M" }, { "name": "CPU", "value": "0.0" }, { "name": "Cumulative Network", "value": "0.0" }, { "name": "Cumulative Disk I/O", "value": "428.46 M" }, { "name": "Cumulative CPU", "value": "0.0" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 10, "type": "pact", "pact": "FlatMap", "contents": "eu.stratosphere.version6.MassJoinOriginJob$FlatMapFrequencies", "parallelism": "1", "predecessors": [ {"id": 11, "ship_strategy": "Forward"} ], "driver_strategy": "Map", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "2.05 M" } ], "costs": [ { "name": "Network", "value": "0.0" }, { "name": "Disk I/O", "value": "0.0" }, { "name": "CPU", "value": "0.0" }, { "name": "Cumulative Network", "value": "0.0" }, { "name": "Cumulative Disk I/O", "value": "428.46 M" }, { "name": "Cumulative CPU", "value": "0.0" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 9, "type": "pact", "pact": "GroupReduce", "contents": "SUM(1)", "parallelism": "1", "predecessors": [ {"id": 10, "ship_strategy": "Forward"} ], "driver_strategy": "Sorted Combine", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "2.05 M" } ], "costs": [ { "name": "Network", "value": "0.0" }, { "name": "Disk I/O", "value": "0.0" }, { "name": "CPU", "value": "0.0" }, { "name": "Cumulative Network", "value": "0.0" }, { "name": "Cumulative Disk I/O", "value": "428.46 M" }, { "name": "Cumulative CPU", "value": "0.0" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 8, "type": "pact", "pact": "GroupReduce", "contents": "SUM(1)", "parallelism": "1", "predecessors": [ {"id": 9, "ship_strategy": "Hash Partition on [0]", "local_strategy": "Sort (combining) on [0:ASC]"} ], "driver_strategy": "Sorted Group Reduce", "global_properties": [ { "name": "Partitioning", "value": "HASH_PARTITIONED" }, { "name": "Partitioned on", "value": "[0]" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "[0:ASC]" }, { "name": "Grouped on", "value": "[0]" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "(unknown)" } ], "costs": [ { "name": "Network", "value": "(unknown)" }, { "name": "Disk I/O", "value": "(unknown)" }, { "name": "CPU", "value": "(unknown)" }, { "name": "Cumulative Network", "value": "(unknown)" }, { "name": "Cumulative Disk I/O", "value": "(unknown)" }, { "name": "Cumulative CPU", "value": "(unknown)" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 7, "type": "pact", "pact": "GroupReduce", "contents": "eu.stratosphere.version6.MassJoinOriginJob$ReduceGroupTokenOrdering", "parallelism": "1", "predecessors": [ {"id": 8, "ship_strategy": "Forward"} ], "driver_strategy": "Group Reduce All", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "(unknown)" } ], "costs": [ { "name": "Network", "value": "0.0" }, { "name": "Disk I/O", "value": "0.0" }, { "name": "CPU", "value": "0.0" }, { "name": "Cumulative Network", "value": "(unknown)" }, { "name": "Cumulative Disk I/O", "value": "(unknown)" }, { "name": "Cumulative CPU", "value": "(unknown)" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 5, "type": "pact", "pact": "Map", "contents": "eu.stratosphere.version6.MassJoinOriginJob$SplitNMapper", "parallelism": "1", "predecessors": [ {"id": 6, "side": "first", "ship_strategy": "Forward"}, {"id": 7, "side": "second", "ship_strategy": "Broadcast"} ], "driver_strategy": "Map", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "410.75 K" } ], "costs": [ { "name": "Network", "value": "0.0" }, { "name": "Disk I/O", "value": "0.0" }, { "name": "CPU", "value": "0.0" }, { "name": "Cumulative Network", "value": "(unknown)" }, { "name": "Cumulative Disk I/O", "value": "(unknown)" }, { "name": "Cumulative CPU", "value": "(unknown)" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 4, "type": "pact", "pact": "FlatMap", "contents": "eu.stratosphere.version6.MassJoinOriginJob$MapSignaturesR", "parallelism": "1", "predecessors": [ {"id": 5, "side": "first", "ship_strategy": "Forward"}, {"id": 7, "side": "second", "ship_strategy": "Broadcast"} ], "driver_strategy": "Map", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "2.05 M" } ], "costs": [ { "name": "Network", "value": "0.0" }, { "name": "Disk I/O", "value": "0.0" }, { "name": "CPU", "value": "0.0" }, { "name": "Cumulative Network", "value": "(unknown)" }, { "name": "Cumulative Disk I/O", "value": "(unknown)" }, { "name": "Cumulative CPU", "value": "(unknown)" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 12, "type": "pact", "pact": "FlatMap", "contents": "eu.stratosphere.version6.MassJoinOriginJob$MapSignaturesS", "parallelism": "1", "predecessors": [ {"id": 5, "side": "first", "ship_strategy": "Forward"}, {"id": 7, "side": "second", "ship_strategy": "Broadcast"} ], "driver_strategy": "Map", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "2.05 M" } ], "costs": [ { "name": "Network", "value": "0.0" }, { "name": "Disk I/O", "value": "0.0" }, { "name": "CPU", "value": "0.0" }, { "name": "Cumulative Network", "value": "(unknown)" }, { "name": "Cumulative Disk I/O", "value": "(unknown)" }, { "name": "Cumulative CPU", "value": "(unknown)" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 3, "type": "pact", "pact": "CoGroup", "contents": "eu.stratosphere.version6.MassJoinOriginJob$CoGroupSignatures", "parallelism": "1", "predecessors": [ {"id": 4, "side": "first", "ship_strategy": "Hash Partition on [0]", "local_strategy": "Sort on [0:ASC]"}, {"id": 12, "side": "second", "ship_strategy": "Hash Partition on [0]", "local_strategy": "Sort on [0:ASC]"} ], "driver_strategy": "Co-Group", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "(unknown)" } ], "costs": [ { "name": "Network", "value": "(unknown)" }, { "name": "Disk I/O", "value": "(unknown)" }, { "name": "CPU", "value": "(unknown)" }, { "name": "Cumulative Network", "value": "(unknown)" }, { "name": "Cumulative Disk I/O", "value": "(unknown)" }, { "name": "Cumulative CPU", "value": "(unknown)" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 2, "type": "pact", "pact": "CoGroup", "contents": "eu.stratosphere.version6.MassJoinOriginJob$CoGroupVerifikation", "parallelism": "1", "predecessors": [ {"id": 3, "side": "first", "ship_strategy": "Hash Partition on [0]", "local_strategy": "Sort on [0:ASC]"}, {"id": 5, "side": "second", "ship_strategy": "Hash Partition on [0]", "local_strategy": "Sort on [0:ASC]"} ], "driver_strategy": "Co-Group", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "(unknown)" } ], "costs": [ { "name": "Network", "value": "(unknown)" }, { "name": "Disk I/O", "value": "(unknown)" }, { "name": "CPU", "value": "(unknown)" }, { "name": "Cumulative Network", "value": "(unknown)" }, { "name": "Cumulative Disk I/O", "value": "(unknown)" }, { "name": "Cumulative CPU", "value": "(unknown)" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 1, "type": "pact", "pact": "CoGroup", "contents": "eu.stratosphere.version6.MassJoinOriginJob$CoGroupResult", "parallelism": "1", "predecessors": [ {"id": 2, "side": "first", "ship_strategy": "Hash Partition on [0]", "local_strategy": "Sort on [0:ASC]"}, {"id": 5, "side": "second", "ship_strategy": "Hash Partition on [0]", "local_strategy": "Sort on [0:ASC]"} ], "driver_strategy": "Co-Group", "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "(unknown)" } ], "costs": [ { "name": "Network", "value": "(unknown)" }, { "name": "Disk I/O", "value": "(unknown)" }, { "name": "CPU", "value": "(unknown)" }, { "name": "Cumulative Network", "value": "(unknown)" }, { "name": "Cumulative Disk I/O", "value": "(unknown)" }, { "name": "Cumulative CPU", "value": "(unknown)" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] }, { "id": 0, "type": "sink", "pact": "Data Sink", "contents": "TextOutputFormat (file:/home/hoenicke/flink-0.6-incubating/output) - UTF-8", "parallelism": "1", "predecessors": [ {"id": 1, "ship_strategy": "Forward"} ], "global_properties": [ { "name": "Partitioning", "value": "RANDOM" }, { "name": "Partitioning Order", "value": "(none)" }, { "name": "Uniqueness", "value": "not unique" } ], "local_properties": [ { "name": "Order", "value": "(none)" }, { "name": "Grouping", "value": "not grouped" }, { "name": "Uniqueness", "value": "not unique" } ], "estimates": [ { "name": "Est. Output Size", "value": "(unknown)" }, { "name": "Est. Cardinality", "value": "(unknown)" } ], "costs": [ { "name": "Network", "value": "0.0" }, { "name": "Disk I/O", "value": "0.0" }, { "name": "CPU", "value": "0.0" }, { "name": "Cumulative Network", "value": "(unknown)" }, { "name": "Cumulative Disk I/O", "value": "(unknown)" }, { "name": "Cumulative CPU", "value": "(unknown)" } ], "compiler_hints": [ { "name": "Output Size (bytes)", "value": "(none)" }, { "name": "Output Cardinality", "value": "(none)" }, { "name": "Avg. Output Record Size (bytes)", "value": "(none)" }, { "name": "Filter Factor", "value": "(none)" } ] } ] } --------------------------------------------------------------