parent 6ab796e

author shirly121 <yihe.zxl@alibaba-inc.com> 1694167237 +0800
committer xiaolei.zl <xiaolei.zl@alibaba-inc.com> 1695348300 +0800

parent 6ab796e
author shirly121 <yihe.zxl@alibaba-inc.com> 1694167237 +0800
committer xiaolei.zl <xiaolei.zl@alibaba-inc.com> 1695348286 +0800

[GIE Compiler] fix bugs of columnId in schema

refactor(flex): Replace the Adhoc csv reader with Arrow CSV reader (alibaba#3154)

1. Use Arrow CSV Reader to replace current adhoc csv reader, to support
more configurable options in `bulk_load.yaml`.
2. Introduce `CSVFragmentLoader`, `BasicFragmentLoader` for
`MutablePropertyFragment`.

With this PR merged, `MutablePropertyFragment` will support loading
fragment from csv with options:
- delimeter: default '|'
- header_row: default true
- quoting: default false
- quoting_char: default '"'
- escaping: default false
- escaping_char: default'\\'
- batch_size: the batch size of when reading file into memory, default
1MB.
- batch_reader: default false. If set to true,
`arrow::csv::StreamingReader` will be used to parse the input file.
Otherwise, `arrow::TableReader` will be used.

With this PR merged, the performance of graph loading will be improved.
The Adhoc Reader denote the current implemented csv parser, 1,2,4,8
denotes the parallelism of graph loading, i.e. how many labels of
vertex/edge are concurrently processed.

Note that TableReader is around 10x faster than StreamingReader. The
possible reason could be the multi-threading is used.
See [arrow-csv-doc](https://arrow.apache.org/docs/cpp/csv.html) for
details.

| Reader | Phase | 1 | 2 | 4 | 8 |
| --------- | -------------- | ---------- |---------- |----------
|---------- |
| Adhoc Reader | ReadFile\+LoadGraph |805s|	468s|	349s|	313s|
| Adhoc Reader | Serialization | 126s|	126s|	126s|	126s|
| Adhoc Reader  | **Total** |931s|	594s|	475s|	439s|
| Table Reader |  ReadFile | 9s	|9s	|9s|	9s|
| Table Reader | LoadGraph |455s|	280s|	211s|	182s|
| Table Reader |Serialization |126s|	126s|	126s|	126s|
| Table Reader | **Total** | 600s|	415s|	346s|	317s|
| Streaming Reader | ReadFile |91s|	91s|	91s|	91s|
| Streaming Reader | LoadGraph | 555s|	289s|	196s|	149s|
| Streaming Reader | Serialization |126s|	126s|	126s|	126s|
| Streaming Reader | **Total** | 772s|	506s|	413s|	366s|

| Reader | Phase | 1 | 2 | 4 | 8 |
| --------- | -------------- | ---------- |---------- |----------
|---------- |
| Adhoc Reader | ReadFile\+LoadGraph |2720s|	1548s|	1176s|	948s|
| Adhoc Reader | Serialization | 409s|	409s|	409s|	409s|
| Adhoc Reader  | **Total** | 3129s|	1957s|	1585s|	1357s|
| Table Reader |  ReadFile |24s|	24s|	24s|	24s|
| Table Reader | LoadGraph |1576s|	949s|	728s|	602s|
| Table Reader |Serialization |409s|	409s|	409s|	409s|
| Table Reader | **Total** | 2009s|	1382s|	1161s|	1035s|
| Streaming Reader | ReadFile |300s|	300s|	300s|	300s|
| Streaming Reader | LoadGraph | 1740s|	965s|	669s|	497s|
| Streaming Reader | Serialization | 409s|	409s|	409s|	409s|
| Streaming Reader | **Total** | 2539s|	1674s|	1378s|	1206s|
| Reader | Phase | 1 | 2 | 4 | 8 |
| --------- | -------------- | ---------- |---------- |----------
|---------- |
| Adhoc Reader | ReadFile\+LoadGraph | 8260s|	4900s	|3603s	|2999s|
| Adhoc Reader | Serialization | 1201s |	1201s|	1201s	|1201s|
| Adhoc Reader  | **Total** | 9461s|	6101s | 4804s	|4200s|
| Table Reader |  ReadFile | 73s	|73s|	96s|	96s|
| Table Reader | LoadGraph |4650s|	2768s|	2155s	|1778s|
| Table Reader |Serialization | 1201s |	1201s|	1201s	|1201s|
| Table Reader | **Total** | 5924s|	4042s|	3452s|	3075s|
| Streaming Reader | ReadFile | 889s |889s | 889s| 889s|
| Streaming Reader | LoadGraph | 5589s|	3005s|	2200s|	1712s|
| Streaming Reader | Serialization | 1201s| 1201s| 1201s |1201s |
| Streaming Reader | **Total** | 7679s	| 5095s |4290s| 	3802s|

FIx alibaba#3116

minor fix and move modern graph

fix grin test

todo: do_start

fix

fix

stash

fix

fix

make rules unique

dockerfile stash

minor change

remove plugin-dir

fix

minor fix

debug

debug

fix

fix

fix bulk_load.yaml

bash format

some fix

fix format

fix grin test

some fi

check ci

fix ci

set

fix ci

fix

dd

f

disable tmate

fix some bug

fix

fix

refactor

fix

fix

fix

minor

some fix

fix

support default src_dst primarykey mapping in bulk load

fix

fix

fix

fix

Ci

rename

fix java and add get_person_name.cypher

[GIE Compiler] minor fix

use graphscope gstest

format

add movie queries

dd

debug

add movie test

format

format

fix script

debug

fix test script

minor

sort query results

minor

minor

format

fix ci

format

gstest

Add License

.github/workflows/hqps-db-ci.yml

@@ -78,8 +78,8 @@ jobs:
         which cargo
 
         # build compiler
-        cd ${GIE_HOME}/compiler
-        make build
+        cd ${GIE_HOME}/
+        mvn clean install -Pexperimental -DskipTests
 
     - name: Prepare dataset and workspace
       env:
@@ -91,6 +91,8 @@ jobs:
         mkdir -p ${INTERACTIVE_WORKSPACE}/data/ldbc
         GRAPH_SCHEMA_YAML=${GS_TEST_DIR}/flex/ldbc-sf01-long-date/audit_graph_schema.yaml
         cp ${GRAPH_SCHEMA_YAML} ${INTERACTIVE_WORKSPACE}/data/ldbc/graph.yaml
+        mkdir -p ${INTERACTIVE_WORKSPACE}/data/movies
+        cp ${GS_TEST_DIR}/flex/movies/movies_schema.yaml ${INTERACTIVE_WORKSPACE}/data/movies/graph.yaml
 
     - name: Sample Query test
       env:
@@ -129,7 +131,19 @@ jobs:
           eval ${cmd}
         done
 
-    - name: Run End-to-End cypher adhoc query test
+        # test movie graph, 8,9,10 are not supported now
+        # change the default_graph config in ${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml to movies
+        sed -i 's/default_graph: ldbc/default_graph: movies/g' ${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml
+        for i in 1 2 3 4 5 6 7 11 12 13 14 15;
+        do
+          cmd="./load_plan_and_gen.sh -e=hqps -i=../tests/hqps/queries/movie/query${i}.cypher -w=/tmp/codgen/"
+          cmd=${cmd}" -o=/tmp/plugin --ir_conf=${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml "
+          cmd=${cmd}" --graph_schema_path=${INTERACTIVE_WORKSPACE}/data/movies/graph.yaml"
+          echo $cmd
+          eval ${cmd}
+        done
+
+    - name: Run End-to-End cypher adhoc ldbc query test
       env:
         GS_TEST_DIR: ${{ github.workspace }}/gstest
         HOME : /home/graphscope/
@@ -138,5 +152,23 @@ jobs:
         cd ${GITHUB_WORKSPACE}/flex/tests/hqps/
         export FLEX_DATA_DIR=${GS_TEST_DIR}/flex/ldbc-sf01-long-date
         export ENGINE_TYPE=hiactor
-        bash hqps_cypher_test.sh ${GS_TEST_DIR} ${INTERACTIVE_WORKSPACE}
+        # change the default_graph config in ${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml to ldbc
+        sed -i 's/default_graph: movies/default_graph: ldbc/g' ${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml
+        bash hqps_cypher_test.sh ${INTERACTIVE_WORKSPACE} ldbc ${GS_TEST_DIR}/flex/ldbc-sf01-long-date/audit_bulk_load.yaml \
+              ${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml
+
+    - name: Run End-to-End cypher adhoc movie query test
+      env:
+        GS_TEST_DIR: ${{ github.workspace }}/gstest
+        HOME : /home/graphscope/
+        INTERACTIVE_WORKSPACE: /tmp/interactive_workspace
+      run: |
+        cd ${GITHUB_WORKSPACE}/flex/tests/hqps/
+        export FLEX_DATA_DIR=../../interactive/examples/movies/
+        export ENGINE_TYPE=hiactor
+        # change the default_graph config in ${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml to movies
+        sed -i 's/default_graph: ldbc/default_graph: movies/g' ${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml
+        bash hqps_cypher_test.sh ${INTERACTIVE_WORKSPACE} movies ${GS_TEST_DIR}/flex/movies/movies_import.yaml \
+          ${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml
+
 

flex/interactive/examples/modern_graph/get_person_name.cypher

@@ -1 +1 @@
-MATCH(p : person {id: $personId}) RETURN p.name;
+MATCH(p : person {id: $personId}) RETURN p.name;

flex/tests/hqps/hqps_cypher_test.sh

@@ -19,47 +19,50 @@ SERVER_BIN=${FLEX_HOME}/build/bin/sync_server
 GIE_HOME=${FLEX_HOME}/../interactive_engine/
 
 # 
-if [ $# -lt 2 ]; then
-  echo "only receives: $# args, need 2"
-  echo "Usage: $0 <GS_TEST_DIR> <INTERACTIVE_WORKSPACE>"
+if [ ! $# -eq 4 ]; then
+  echo "only receives: $# args, need 4"
+  echo "Usage: $0 <INTERACTIVE_WORKSPACE> <GRAPH_NAME> <BULK_LOAD_FILE> <ENGINE_CONFIG>"
   exit 1
 fi
 
-GS_TEST_DIR=$1
-INTERACTIVE_WORKSPACE=$2
-if [ ! -d ${GS_TEST_DIR} ]; then
-  echo "GS_TEST_DIR: ${GS_TEST_DIR} not exists"
-  exit 1
-fi
+INTERACTIVE_WORKSPACE=$1
+GRAPH_NAME=$2
+GRAPH_BULK_LOAD_YAML=$3
+ENGINE_CONFIG_PATH=$4
 if [ ! -d ${INTERACTIVE_WORKSPACE} ]; then
   echo "INTERACTIVE_WORKSPACE: ${INTERACTIVE_WORKSPACE} not exists"
   exit 1
 fi
-
-ENGINE_CONFIG_PATH=${GS_TEST_DIR}/flex/ldbc-sf01-long-date/engine_config.yaml
-ORI_GRAPH_SCHEMA_YAML=${GS_TEST_DIR}/flex/ldbc-sf01-long-date/audit_graph_schema.yaml
-GRAPH_SCHEMA_YAML=${INTERACTIVE_WORKSPACE}/data/ldbc/graph.yaml
-GRAPH_BULK_LOAD_YAML=${GS_TEST_DIR}/flex/ldbc-sf01-long-date/audit_bulk_load.yaml
-COMPILER_GRAPH_SCHEMA=${GS_TEST_DIR}/flex/ldbc-sf01-long-date/audit_graph_schema.yaml
-GRAPH_CSR_DATA_DIR=${HOME}/csr-data-dir/
-# check if GRAPH_SCHEMA_YAML exists
-if [ ! -f ${GRAPH_SCHEMA_YAML} ]; then
-  echo "GRAPH_SCHEMA_YAML: ${GRAPH_SCHEMA_YAML} not found"
+# check graph is ldbc or movies
+if [ ${GRAPH_NAME} != "ldbc" ] && [ ${GRAPH_NAME} != "movies" ]; then
+  echo "GRAPH_NAME: ${GRAPH_NAME} not supported, use movies or ldbc"
+  exit 1
+fi
+if [ ! -d ${INTERACTIVE_WORKSPACE}/data/${GRAPH_NAME} ]; then
+  echo "GRAPH: ${GRAPH_NAME} not exists"
+  exit 1
+fi
+if [ ! -f ${INTERACTIVE_WORKSPACE}/data/${GRAPH_NAME}/graph.yaml ]; then
+  echo "GRAPH_SCHEMA_FILE: ${BULK_LOAD_FILE} not exists"
   exit 1
 fi
-
-# check if GRAPH_BULK_LOAD_YAML exists
 if [ ! -f ${GRAPH_BULK_LOAD_YAML} ]; then
-  echo "GRAPH_BULK_LOAD_YAML: ${GRAPH_BULK_LOAD_YAML} not found"
+  echo "GRAPH_BULK_LOAD_YAML: ${GRAPH_BULK_LOAD_YAML} not exists"
   exit 1
 fi
-
-# check if COMPILER_GRAPH_SCHEMA exists
-if [ ! -f ${COMPILER_GRAPH_SCHEMA} ]; then
-  echo "COMPILER_GRAPH_SCHEMA: ${COMPILER_GRAPH_SCHEMA} not found"
+if [ ! -f ${ENGINE_CONFIG_PATH} ]; then
+  echo "ENGINE_CONFIG: ${ENGINE_CONFIG_PATH} not exists"
   exit 1
 fi
 
+GRAPH_SCHEMA_YAML=${INTERACTIVE_WORKSPACE}/data/${GRAPH_NAME}/graph.yaml
+GRAPH_CSR_DATA_DIR=${HOME}/csr-data-dir/
+# rm data dir if exists
+if [ -d ${GRAPH_CSR_DATA_DIR} ]; then
+  rm -rf ${GRAPH_CSR_DATA_DIR}
+fi
+
+
 RED='\033[0;31m'
 GREEN='\033[0;32m'
 NC='\033[0m' # No Color
@@ -92,8 +95,6 @@ start_engine_service(){
         err "SERVER_BIN not found"
         exit 1
     fi
-    # export FLEX_DATA_DIR
-    export FLEX_DATA_DIR=${GS_TEST_DIR}/flex/ldbc-sf01-long-date/
 
     cmd="${SERVER_BIN} -c ${ENGINE_CONFIG_PATH} -g ${GRAPH_SCHEMA_YAML} "
     cmd="${cmd} --data-path ${GRAPH_CSR_DATA_DIR} -l ${GRAPH_BULK_LOAD_YAML} "
@@ -111,7 +112,7 @@ start_engine_service(){
 start_compiler_service(){
   echo "try to start compiler service"
   pushd ${GIE_HOME}/compiler
-  cmd="make run graph.schema=${COMPILER_GRAPH_SCHEMA} config.path=${ENGINE_CONFIG_PATH}"
+  cmd="make run graph.schema=${GRAPH_SCHEMA_YAML} config.path=${ENGINE_CONFIG_PATH}"
   echo "Start compiler service with command: ${cmd}"
   ${cmd} &
   sleep 5
@@ -141,11 +142,27 @@ run_simple_test(){
   popd
 }
 
+run_movie_test(){
+  echo "run movie test"
+  pushd ${GIE_HOME}/compiler
+  cmd="mvn test -Dtest=com.alibaba.graphscope.cypher.integration.movie.MovieTest"
+  echo "Start movie test: ${cmd}"
+  ${cmd}
+  info "Finish movie test"
+  popd
+}
+
 kill_service
 start_engine_service
 start_compiler_service
-run_ldbc_test
-run_simple_test
+# if GRAPH_NAME equals ldbc
+if [ "${GRAPH_NAME}" == "ldbc" ]; then
+  run_ldbc_test
+  run_simple_test
+else
+  run_movie_test
+fi
+
 kill_service
 
 

flex/tests/hqps/queries/movie/query1.cypher

@@ -0,0 +1 @@
+MATCH (tom:Person) WHERE tom.name = "Tom Hanks" RETURN tom.born AS bornYear,tom.name AS personName;

flex/tests/hqps/queries/movie/query10.cypher

@@ -0,0 +1,4 @@
+MATCH p=shortestPath(
+  (bacon:Person {name:"Kevin Bacon"})-[*]-(meg:Person {name:"Meg Ryan"})
+)
+RETURN p;

flex/tests/hqps/queries/movie/query11.cypher

@@ -0,0 +1,4 @@
+MATCH (tom:Person {name: 'Tom Hanks'})-[r:ACTED_IN]->(movie:Movie)
+WITH movie.title as movieTitle, movie.released as movieReleased
+ORDER BY movieReleased DESC, movieTitle ASC LIMIT 10
+return movieTitle, movieReleased;

flex/tests/hqps/queries/movie/query12.cypher

@@ -0,0 +1,2 @@
+MATCH (tom:Person {name: 'Tom Hanks'})-[:ACTED_IN]->(:Movie)<-[:ACTED_IN]-(coActor:Person)
+WITH DISTINCT coActor.name AS coActorName ORDER BY coActorName ASC LIMIT 10 return coActorName;

flex/tests/hqps/queries/movie/query13.cypher

@@ -0,0 +1,4 @@
+MATCH (tom:Person {name: 'Tom Hanks'})-[:ACTED_IN]->(movie1:Movie)<-[:ACTED_IN]-(coActor:Person)-[:ACTED_IN]->(movie2:Movie)<-[:ACTED_IN]-(coCoActor:Person)
+WHERE tom <> coCoActor
+AND NOT (tom)-[:ACTED_IN]->(:Movie)<-[:ACTED_IN]-(coCoActor)
+RETURN coCoActor.name AS coCoActorName ORDER BY coCoActorName ASC LIMIT 10;

flex/tests/hqps/queries/movie/query14.cypher

@@ -0,0 +1,6 @@
+MATCH (tom:Person {name: 'Tom Hanks'})-[:ACTED_IN]->(movie1:Movie)<-[:ACTED_IN]-(coActor:Person)-[:ACTED_IN]->(movie2:Movie)<-[:ACTED_IN]-(coCoActor:Person)
+WHERE tom <> coCoActor
+AND NOT (tom)-[:ACTED_IN]->(:Movie)<-[:ACTED_IN]-(coCoActor)
+RETURN coCoActor.name AS coCoActorName, count(coCoActor) AS frequency
+ORDER BY frequency DESC, coCoActorName ASC
+LIMIT 5;

flex/tests/hqps/queries/movie/query15.cypher

@@ -0,0 +1,4 @@
+MATCH (tom:Person {name: 'Tom Hanks'})-[:ACTED_IN]->(movie1:Movie)<-[:ACTED_IN]-(coActor:Person)-[:ACTED_IN]->(movie2:Movie)<-[:ACTED_IN]-(cruise:Person {name: 'Tom Cruise'})
+WHERE NOT (tom)-[:ACTED_IN]->(:Movie)<-[:ACTED_IN]-(cruise)
+RETURN tom.name AS actorName, movie1.title AS movie1Title, coActor.name AS coActorName, movie2.title AS movie2Title, cruise.name AS coCoActorName
+ORDER BY movie1Title ASC, movie2Title ASC LIMIT 10;

flex/tests/hqps/queries/movie/query2.cypher

@@ -0,0 +1 @@
+MATCH (cloudAtlas:Movie {title: "Cloud Atlas"}) RETURN cloudAtlas.tagline AS tagline, cloudAtlas.released AS releasedYear,cloudAtlas.title AS title;

flex/tests/hqps/queries/movie/query3.cypher

@@ -0,0 +1 @@
+MATCH (people:Person) RETURN people.name AS personName ORDER BY personName ASC LIMIT 10;

flex/tests/hqps/queries/movie/query4.cypher

@@ -0,0 +1,2 @@
+MATCH (nineties:Movie) WHERE nineties.released >= 1990 AND nineties.released < 2000
+RETURN nineties.title AS ninetiesTitle ORDER BY ninetiesTitle DESC LIMIT 10;

flex/tests/hqps/queries/movie/query5.cypher

@@ -0,0 +1,6 @@
+MATCH (tom:Person {name: "Tom Hanks"})-[:ACTED_IN]->(tomHanksMovies)
+RETURN tom.born AS bornYear,
+    tomHanksMovies.tagline AS movieTagline, 
+    tomHanksMovies.title AS movieTitle,
+    tomHanksMovies.released AS releaseYear
+ORDER BY releaseYear DESC, movieTitle ASC LIMIT 10;

flex/tests/hqps/queries/movie/query6.cypher

@@ -0,0 +1,2 @@
+MATCH (cloudAtlas:Movie {title: "Cloud Atlas"})<-[:DIRECTED]-(directors)
+RETURN directors.name AS directorsName ORDER BY directorsName ASC LIMIT 10;

flex/tests/hqps/queries/movie/query7.cypher

@@ -0,0 +1,3 @@
+MATCH (tom:Person {name:"Tom Hanks"})-[:ACTED_IN]->(m)<-[:ACTED_IN]-(coActors)
+RETURN m.title AS movieTitle, m.released AS releasedYear, coActors.name AS coActorName
+ORDER BY releasedYear DESC, movieTitle ASC LIMIT 10;

flex/tests/hqps/queries/movie/query8.cypher

@@ -0,0 +1,2 @@
+MATCH (people:Person)-[relatedTo]-(:Movie {title: "Cloud Atlas"})
+RETURN people.name, type(relatedTo), relatedTo

flex/tests/hqps/queries/movie/query9.cypher

@@ -0,0 +1,2 @@
+MATCH (bacon:Person {name:"Kevin Bacon"})-[*1..3]-(hollywood)
+RETURN DISTINCT bacon, hollywood

interactive_engine/compiler/pom.xml

@@ -253,6 +253,7 @@
                         <exclude>**/IrLdbcTest.java</exclude>
                         <exclude>**/SimpleMatchTest.java</exclude>
                         <exclude>**/IrPatternTest.java</exclude>
+                        <exclude>**/MovieTest.java</exclude>
                     </excludes>
                 </configuration>
             </plugin>