This is an automated email from the ASF dual-hosted git repository.
JackieTien97 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/iotdb.git
The following commit(s) were added to refs/heads/master by this push:
new 9330c7fc0b4 Shard 5 dual-cluster jobs to speed up Multi-Cluster IT
(#17695)
9330c7fc0b4 is described below
commit 9330c7fc0b4382c25edfcd31ff8977e9d72bf68b
Author: Jackie Tien <[email protected]>
AuthorDate: Sun May 17 15:07:44 2026 +0800
Shard 5 dual-cluster jobs to speed up Multi-Cluster IT (#17695)
---
.github/workflows/pipe-it.yml | 115 ++++++++++++++++++++++++++++++++++++++++--
1 file changed, 110 insertions(+), 5 deletions(-)
diff --git a/.github/workflows/pipe-it.yml b/.github/workflows/pipe-it.yml
index 0968e7739a0..fb2f732560d 100644
--- a/.github/workflows/pipe-it.yml
+++ b/.github/workflows/pipe-it.yml
@@ -119,6 +119,8 @@ jobs:
name: cluster-log-single-java${{ matrix.java }}-${{ runner.os }}-${{
matrix.cluster1 }}-${{ matrix.cluster2 }}
path: integration-test/target/cluster-logs
retention-days: 30
+ # 12 IT classes split across 3 parallel shards to cut the historical ~42 min
+ # wall clock to ~14 min. See cluster-it-1c1d.yml for the shard pattern.
dual-tree-auto-basic:
strategy:
fail-fast: false
@@ -128,6 +130,7 @@ jobs:
# StrongConsistencyClusterMode is ignored now because RatisConsensus
has not been supported yet.
cluster: [HighPerformanceMode]
os: [ubuntu-latest]
+ shard: [0, 1, 2]
runs-on: ${{ matrix.os }}
steps:
- uses: actions/checkout@v5
@@ -147,6 +150,21 @@ jobs:
- name: Sleep for a random duration between 0 and 10000 milliseconds
run: |
sleep $(( $(( RANDOM % 10000 + 1 )) / 1000))
+ - name: Build IT shard list
+ shell: bash
+ # See cluster-it-1c1d.yml for the shard-list pattern. Write under
+ # $RUNNER_TEMP (outside the repo) so Apache RAT doesn't flag the file.
+ run: |
+ set -euo pipefail
+ SHARD=${{ matrix.shard }}
+ TOTAL=3
+ grep -rlE --include='*IT.java'
'\bMultiClusterIT2DualTreeAutoBasic\b' integration-test/src/test/java \
+ | awk -F'/' '{print $NF}' | sed 's/\.java$//' \
+ | sort \
+ | awk -v s=$SHARD -v t=$TOTAL 'NR%t==s' \
+ > "$RUNNER_TEMP/it-shard.txt"
+ echo "Shard $SHARD/$TOTAL contains $(wc -l <
"$RUNNER_TEMP/it-shard.txt") test classes"
+ head -5 "$RUNNER_TEMP/it-shard.txt"
- name: IT Test
shell: bash
# we do not compile client-cpp for saving time, it is tested in
client.yml
@@ -164,6 +182,9 @@ jobs:
-DskipUTs \
-DintegrationTest.forkCount=1 -DConfigNodeMaxHeapSize=256
-DDataNodeMaxHeapSize=1024 -DDataNodeMaxDirectMemorySize=768 \
-DClusterConfigurations=${{ matrix.cluster }},${{ matrix.cluster
}} \
+ -Dfailsafe.includesFile="$RUNNER_TEMP/it-shard.txt" \
+ -DfailIfNoTests=false \
+ -Dfailsafe.failIfNoSpecifiedTests=false \
-pl integration-test \
-am -PMultiClusterIT2DualTreeAutoBasic \
-ntp >> ~/run-tests-$attempt.log && return 0
@@ -201,9 +222,11 @@ jobs:
if: failure()
uses: actions/upload-artifact@v6
with:
- name: cluster-log-dual-tree-auto-basic-java${{ matrix.java }}-${{
runner.os }}-${{ matrix.cluster }}-${{ matrix.cluster }}
+ name: cluster-log-dual-tree-auto-basic-shard${{ matrix.shard
}}-java${{ matrix.java }}-${{ runner.os }}-${{ matrix.cluster }}-${{
matrix.cluster }}
path: integration-test/target/cluster-logs
retention-days: 30
+ # 9 IT classes split across 3 parallel shards to cut the historical ~51 min
+ # wall clock to ~17 min. See cluster-it-1c1d.yml for the shard pattern.
dual-tree-auto-enhanced:
strategy:
fail-fast: false
@@ -214,6 +237,7 @@ jobs:
cluster1: [HighPerformanceMode]
cluster2: [HighPerformanceMode]
os: [ubuntu-latest]
+ shard: [0, 1, 2]
runs-on: ${{ matrix.os }}
steps:
- uses: actions/checkout@v5
@@ -233,6 +257,21 @@ jobs:
- name: Sleep for a random duration between 0 and 10000 milliseconds
run: |
sleep $(( $(( RANDOM % 10000 + 1 )) / 1000))
+ - name: Build IT shard list
+ shell: bash
+ # See cluster-it-1c1d.yml for the shard-list pattern. Write under
+ # $RUNNER_TEMP (outside the repo) so Apache RAT doesn't flag the file.
+ run: |
+ set -euo pipefail
+ SHARD=${{ matrix.shard }}
+ TOTAL=3
+ grep -rlE --include='*IT.java'
'\bMultiClusterIT2DualTreeAutoEnhanced\b' integration-test/src/test/java \
+ | awk -F'/' '{print $NF}' | sed 's/\.java$//' \
+ | sort \
+ | awk -v s=$SHARD -v t=$TOTAL 'NR%t==s' \
+ > "$RUNNER_TEMP/it-shard.txt"
+ echo "Shard $SHARD/$TOTAL contains $(wc -l <
"$RUNNER_TEMP/it-shard.txt") test classes"
+ head -5 "$RUNNER_TEMP/it-shard.txt"
- name: IT Test
shell: bash
# we do not compile client-cpp for saving time, it is tested in
client.yml
@@ -250,6 +289,9 @@ jobs:
-DskipUTs \
-DintegrationTest.forkCount=1 -DConfigNodeMaxHeapSize=256
-DDataNodeMaxHeapSize=1024 -DDataNodeMaxDirectMemorySize=768 \
-DClusterConfigurations=${{ matrix.cluster1 }},${{
matrix.cluster2 }} \
+ -Dfailsafe.includesFile="$RUNNER_TEMP/it-shard.txt" \
+ -DfailIfNoTests=false \
+ -Dfailsafe.failIfNoSpecifiedTests=false \
-pl integration-test \
-am -PMultiClusterIT2DualTreeAutoEnhanced \
-ntp >> ~/run-tests-$attempt.log && return 0
@@ -287,9 +329,11 @@ jobs:
if: failure()
uses: actions/upload-artifact@v6
with:
- name: cluster-log-dual-tree-auto-enhanced-java${{ matrix.java }}-${{
runner.os }}-${{ matrix.cluster1 }}-${{ matrix.cluster2 }}
+ name: cluster-log-dual-tree-auto-enhanced-shard${{ matrix.shard
}}-java${{ matrix.java }}-${{ runner.os }}-${{ matrix.cluster1 }}-${{
matrix.cluster2 }}
path: integration-test/target/cluster-logs
retention-days: 30
+ # 11 IT classes split across 3 parallel shards to cut the historical ~27 min
+ # wall clock to ~9 min. See cluster-it-1c1d.yml for the shard pattern.
dual-tree-manual:
strategy:
fail-fast: false
@@ -300,6 +344,7 @@ jobs:
cluster1: [HighPerformanceMode]
cluster2: [HighPerformanceMode]
os: [ubuntu-latest]
+ shard: [0, 1, 2]
runs-on: ${{ matrix.os }}
steps:
- uses: actions/checkout@v5
@@ -319,6 +364,21 @@ jobs:
- name: Sleep for a random duration between 0 and 10000 milliseconds
run: |
sleep $(( $(( RANDOM % 10000 + 1 )) / 1000))
+ - name: Build IT shard list
+ shell: bash
+ # See cluster-it-1c1d.yml for the shard-list pattern. Write under
+ # $RUNNER_TEMP (outside the repo) so Apache RAT doesn't flag the file.
+ run: |
+ set -euo pipefail
+ SHARD=${{ matrix.shard }}
+ TOTAL=3
+ grep -rlE --include='*IT.java' '\bMultiClusterIT2DualTreeManual\b'
integration-test/src/test/java \
+ | awk -F'/' '{print $NF}' | sed 's/\.java$//' \
+ | sort \
+ | awk -v s=$SHARD -v t=$TOTAL 'NR%t==s' \
+ > "$RUNNER_TEMP/it-shard.txt"
+ echo "Shard $SHARD/$TOTAL contains $(wc -l <
"$RUNNER_TEMP/it-shard.txt") test classes"
+ head -5 "$RUNNER_TEMP/it-shard.txt"
- name: IT Test
shell: bash
# we do not compile client-cpp for saving time, it is tested in
client.yml
@@ -336,6 +396,9 @@ jobs:
-DskipUTs \
-DintegrationTest.forkCount=1 -DConfigNodeMaxHeapSize=256
-DDataNodeMaxHeapSize=1024 -DDataNodeMaxDirectMemorySize=768 \
-DClusterConfigurations=${{ matrix.cluster1 }},${{
matrix.cluster2 }} \
+ -Dfailsafe.includesFile="$RUNNER_TEMP/it-shard.txt" \
+ -DfailIfNoTests=false \
+ -Dfailsafe.failIfNoSpecifiedTests=false \
-pl integration-test \
-am -PMultiClusterIT2DualTreeManual \
-ntp >> ~/run-tests-$attempt.log && return 0
@@ -373,7 +436,7 @@ jobs:
if: failure()
uses: actions/upload-artifact@v6
with:
- name: cluster-log-dual-tree-manual-java${{ matrix.java }}-${{
runner.os }}-${{ matrix.cluster1 }}-${{ matrix.cluster2 }}
+ name: cluster-log-dual-tree-manual-shard${{ matrix.shard }}-java${{
matrix.java }}-${{ runner.os }}-${{ matrix.cluster1 }}-${{ matrix.cluster2 }}
path: integration-test/target/cluster-logs
retention-days: 30
subscription-tree-arch-verification:
@@ -720,6 +783,8 @@ jobs:
name: cluster-log-subscription-tree-regression-misc-java${{
matrix.java }}-${{ runner.os }}-${{ matrix.cluster1 }}-${{ matrix.cluster2 }}
path: integration-test/target/cluster-logs
retention-days: 30
+ # 13 IT classes split across 3 parallel shards to cut the historical ~63 min
+ # wall clock to ~22 min. See cluster-it-1c1d.yml for the shard pattern.
dual-table-manual-basic:
strategy:
fail-fast: false
@@ -729,6 +794,7 @@ jobs:
# StrongConsistencyClusterMode is ignored now because RatisConsensus
has not been supported yet.
cluster: [HighPerformanceMode]
os: [ubuntu-latest]
+ shard: [0, 1, 2]
runs-on: ${{ matrix.os }}
steps:
- uses: actions/checkout@v5
@@ -748,6 +814,21 @@ jobs:
- name: Sleep for a random duration between 0 and 10000 milliseconds
run: |
sleep $(( $(( RANDOM % 10000 + 1 )) / 1000))
+ - name: Build IT shard list
+ shell: bash
+ # See cluster-it-1c1d.yml for the shard-list pattern. Write under
+ # $RUNNER_TEMP (outside the repo) so Apache RAT doesn't flag the file.
+ run: |
+ set -euo pipefail
+ SHARD=${{ matrix.shard }}
+ TOTAL=3
+ grep -rlE --include='*IT.java'
'\bMultiClusterIT2DualTableManualBasic\b' integration-test/src/test/java \
+ | awk -F'/' '{print $NF}' | sed 's/\.java$//' \
+ | sort \
+ | awk -v s=$SHARD -v t=$TOTAL 'NR%t==s' \
+ > "$RUNNER_TEMP/it-shard.txt"
+ echo "Shard $SHARD/$TOTAL contains $(wc -l <
"$RUNNER_TEMP/it-shard.txt") test classes"
+ head -5 "$RUNNER_TEMP/it-shard.txt"
- name: IT Test
shell: bash
# we do not compile client-cpp for saving time, it is tested in
client.yml
@@ -765,6 +846,9 @@ jobs:
-DskipUTs \
-DintegrationTest.forkCount=1 -DConfigNodeMaxHeapSize=256
-DDataNodeMaxHeapSize=1024 -DDataNodeMaxDirectMemorySize=768 \
-DClusterConfigurations=${{ matrix.cluster }},${{ matrix.cluster
}} \
+ -Dfailsafe.includesFile="$RUNNER_TEMP/it-shard.txt" \
+ -DfailIfNoTests=false \
+ -Dfailsafe.failIfNoSpecifiedTests=false \
-pl integration-test \
-am -PMultiClusterIT2DualTableManualBasic \
-ntp >> ~/run-tests-$attempt.log && return 0
@@ -802,9 +886,11 @@ jobs:
if: failure()
uses: actions/upload-artifact@v6
with:
- name: cluster-log-dual-table-manual-basic-java${{ matrix.java }}-${{
runner.os }}-${{ matrix.cluster }}-${{ matrix.cluster }}
+ name: cluster-log-dual-table-manual-basic-shard${{ matrix.shard
}}-java${{ matrix.java }}-${{ runner.os }}-${{ matrix.cluster }}-${{
matrix.cluster }}
path: integration-test/target/cluster-logs
retention-days: 30
+ # 11 IT classes split across 3 parallel shards to cut the historical ~62 min
+ # wall clock to ~22 min. See cluster-it-1c1d.yml for the shard pattern.
dual-table-manual-enhanced:
strategy:
fail-fast: false
@@ -814,6 +900,7 @@ jobs:
# StrongConsistencyClusterMode is ignored now because RatisConsensus
has not been supported yet.
cluster: [HighPerformanceMode]
os: [ubuntu-latest]
+ shard: [0, 1, 2]
runs-on: ${{ matrix.os }}
steps:
- uses: actions/checkout@v5
@@ -833,6 +920,21 @@ jobs:
- name: Sleep for a random duration between 0 and 10000 milliseconds
run: |
sleep $(( $(( RANDOM % 10000 + 1 )) / 1000))
+ - name: Build IT shard list
+ shell: bash
+ # See cluster-it-1c1d.yml for the shard-list pattern. Write under
+ # $RUNNER_TEMP (outside the repo) so Apache RAT doesn't flag the file.
+ run: |
+ set -euo pipefail
+ SHARD=${{ matrix.shard }}
+ TOTAL=3
+ grep -rlE --include='*IT.java'
'\bMultiClusterIT2DualTableManualEnhanced\b' integration-test/src/test/java \
+ | awk -F'/' '{print $NF}' | sed 's/\.java$//' \
+ | sort \
+ | awk -v s=$SHARD -v t=$TOTAL 'NR%t==s' \
+ > "$RUNNER_TEMP/it-shard.txt"
+ echo "Shard $SHARD/$TOTAL contains $(wc -l <
"$RUNNER_TEMP/it-shard.txt") test classes"
+ head -5 "$RUNNER_TEMP/it-shard.txt"
- name: IT Test
shell: bash
# we do not compile client-cpp for saving time, it is tested in
client.yml
@@ -850,6 +952,9 @@ jobs:
-DskipUTs \
-DintegrationTest.forkCount=1 -DConfigNodeMaxHeapSize=256
-DDataNodeMaxHeapSize=1024 -DDataNodeMaxDirectMemorySize=768 \
-DClusterConfigurations=${{ matrix.cluster }},${{ matrix.cluster
}} \
+ -Dfailsafe.includesFile="$RUNNER_TEMP/it-shard.txt" \
+ -DfailIfNoTests=false \
+ -Dfailsafe.failIfNoSpecifiedTests=false \
-pl integration-test \
-am -PMultiClusterIT2DualTableManualEnhanced \
-ntp >> ~/run-tests-$attempt.log && return 0
@@ -887,7 +992,7 @@ jobs:
if: failure()
uses: actions/upload-artifact@v6
with:
- name: cluster-log-dual-table-manual-enhanced-java${{ matrix.java
}}-${{ runner.os }}-${{ matrix.cluster }}-${{ matrix.cluster }}
+ name: cluster-log-dual-table-manual-enhanced-shard${{ matrix.shard
}}-java${{ matrix.java }}-${{ runner.os }}-${{ matrix.cluster }}-${{
matrix.cluster }}
path: integration-test/target/cluster-logs
retention-days: 30
triple:
