Add clickhouse to regression

.github/workflows/regression.yml

@@ -17,7 +17,7 @@ jobs:
   strategy:
     fail-fast: false
     matrix:
-      solution: [data.table, collapse, dplyr, pandas, pydatatable, spark, juliadf, juliads, polars, arrow, duckdb, duckdb-latest, datafusion]
+      solution: [data.table, collapse, dplyr, pandas, pydatatable, spark, juliadf, juliads, polars, arrow, duckdb, duckdb-latest, datafusion, clickhouse]
   name: Regression Tests solo solutions
   runs-on: ubuntu-20.04
   env:
@@ -54,6 +54,9 @@ jobs:
       shell: bash
       run: sudo swapoff -a
 
+    - name: Setup tmate session
+      uses: mxschmitt/action-tmate@v3
+
     - name: Run mini GroupBy benchmark
       shell: bash
       run: |

_benchplot/benchplot-dict.R

@@ -490,8 +490,6 @@ join.data.exceptions = {list(
   "juliads" = {list(
   )},
   "clickhouse" = {list(
-    "out of memory" = c("J1_1e9_NA_0_0",                                                  # q1 r2 #169
-                        "J1_1e9_NA_5_0","J1_1e9_NA_0_1")                                  # q1 r1
   )},
   "polars" = {list(
     "out of memory" = c("J1_1e9_NA_0_0","J1_1e9_NA_5_0","J1_1e9_NA_0_1")

_launcher/launcher.R

@@ -16,8 +16,7 @@ file.ext = function(x) {
     x,
     "collapse"=, "data.table"=, "dplyr"=, "h2o"=, "arrow"=, "duckdb"="R", "duckdb-latest"="R",
     "pandas"=, "spark"=, "pydatatable"=, "modin"=, "dask"=, "datafusion"=, "polars"="py",
-    "clickhouse"="sql",
-    "juliadf"="jl", "juliads"="jl",
+    "clickhouse"="sh", "juliadf"="jl", "juliads"="jl",
   )
   if (is.null(ans)) stop(sprintf("solution %s does not have file extension defined in file.ext helper function", x))
   ans

_launcher/solution.R

@@ -112,8 +112,7 @@ file.ext = function(x) {
     x,
     "collapse"=, "data.table"=, "dplyr"=, "h2o"=, "arrow"=, "duckdb"="R", "duckdb-latest"="R",
     "pandas"="py", "spark"=, "pydatatable"=, "modin"=, "dask"=, "datafusion"=, "polars"="py",
-    "clickhouse"="sql",
-    "juliadf"="jl", "juliads"="jl"
+    "clickhouse"="sh", "juliadf"="jl", "juliads"="jl"
   )
   if (is.null(ans)) stop(sprintf("solution %s does not have file extension defined in file.ext helper function", x))
   ans

_utils/install_all_solutions.py

@@ -26,9 +26,7 @@ def install_all_solutions():
     with open(SOLUTIONS_FILENAME, newline="") as solutions_file:
         solutions = csv.DictReader(solutions_file, delimiter=',')
         for row in solutions:
-            if row['solution'] == "clickhouse":
-                continue
-            elif row['solution'] == "data.table":
+            if row['solution'] == "data.table":
                 install_solutions.add("datatable")
             else:
                 install_solutions.add(row['solution'])
@@ -44,9 +42,7 @@ def install_all_solutions():
     if solution.strip() == "all":
         install_all_solutions()
     else:
-        if solution == "clickhouse":
-            continue
-        elif solution == "data.table":
+        if solution == "data.table":
             install_solution("datatable")
         else:
             install_solution(solution)

_utils/prep_solutions.py

@@ -5,7 +5,7 @@
 SOLUTIONS_FILENAME = "_control/solutions.csv"
 RUN_CONF_FILENAME = "run.conf"
 
-SKIPPED_SOLUTIONS = ["clickhouse"]
+SKIPPED_SOLUTIONS = []
 
 
 def print_usage():

clickhouse/VERSION

@@ -1 +1 @@
-23.9.1.1854
+23.10.2.13

clickhouse/ch.sh

@@ -1,16 +1,59 @@
 ch_installed() {
   dpkg-query -Wf'${db:Status-abbrev}' clickhouse-server 2>/dev/null | grep -q '^i'
 }
+
+ch_active() {
+  clickhouse-client --query="SELECT 0;" > /dev/null 2>&1
+  local ret=$?;
+  if [[ $ret -eq 0 ]]; then return 0; elif [[ $ret -eq 210 ]]; then return 1; else echo "Unexpected return code from clickhouse-client: $ret" >&2 && return 1; fi;
+}
+
+ch_wait() {
+  for _ in $(seq 1 60); do if [[ $(wget -q 'localhost:8123' -O-) == 'Ok.' ]]; then break ; else sleep 1; fi ; done
+  ch_active
+}
+
 ch_start() {
   echo '# ch_start: starting clickhouse-server'
-  sudo service clickhouse-server start && sleep 15
+  sudo service clickhouse-server start
+  ch_wait
 }
+
 ch_stop() {
   echo '# ch_stop: stopping clickhouse-server'
   sudo service clickhouse-server stop && sleep 15
 }
-ch_active() {
-  clickhouse-client --query="SELECT 0;" > /dev/null 2>&1
+
+ch_query() {
+  ENGINE=Memory
+  if [ $ON_DISK -eq 1 ]; then
+  ENGINE="MergeTree ORDER BY tuple()"
+  fi
+  sudo touch '/var/lib/clickhouse/flags/force_drop_table' && sudo chmod 666 '/var/lib/clickhouse/flags/force_drop_table'
+  clickhouse-client --query "DROP TABLE IF EXISTS ans;"
+  clickhouse-client --log_comment ${RUNNAME} --query "CREATE TABLE ans ENGINE = ${ENGINE} AS ${QUERY} SETTINGS max_insert_threads=${THREADS}, max_threads=${THREADS};"
+  local ret=$?;
+  if [[ $ret -eq 0 ]]; then return 0; elif [[ $ret -eq 210 ]]; then return 1; else echo "Unexpected return code from clickhouse-client: $ret" >&2 && return 1; fi;
+  clickhouse-client --query "SELECT * FROM ans LIMIT 3;"
+  sudo touch '/var/lib/clickhouse/flags/force_drop_table' && sudo chmod 666 '/var/lib/clickhouse/flags/force_drop_table'
+  clickhouse-client --query "DROP TABLE ans;"
+}
+
+ch_logrun() {
+  clickhouse-client --query "SYSTEM FLUSH LOGS;"
+  clickhouse-client --query "SELECT ${RUN} AS run, toUnixTimestamp(now()) AS timestamp, '${TASK}' AS task, '${SRC_DATANAME}' AS data_name, NULL AS in_rows, '${QUESTION}' AS question, result_rows AS out_rows, NULL AS out_cols, 'clickhouse' AS solution, version() AS version, NULL AS git, '${FUNCTION}' AS fun, query_duration_ms/1000 AS time_sec, memory_usage/1073741824 AS mem_gb, 1 AS cache, NULL AS chk, NULL AS chk_time_sec, 1 AS on_disk FROM system.query_log WHERE type='QueryFinish' AND log_comment='${RUNNAME}' ORDER BY query_start_time DESC LIMIT 1 FORMAT CSVWithNames;" > clickhouse/log/${RUNNAME}.csv
   local ret=$?;
   if [[ $ret -eq 0 ]]; then return 0; elif [[ $ret -eq 210 ]]; then return 1; else echo "Unexpected return code from clickhouse-client: $ret" >&2 && return 1; fi;
 }
+
+ch_make_2_runs() {
+  RUN=1
+  RUNNAME="${TASK}_${SRC_DATANAME}_q${Q}_r${RUN}"
+  ch_query
+  ch_logrun
+
+  RUN=2
+  RUNNAME="${TASK}_${SRC_DATANAME}_q${Q}_r${RUN}"
+  ch_query
+  ch_logrun
+}