Reuse passed test from previous pipeline

yiqingy0 · yiqingy0 · commit 21f90ca6078a · 2025-08-14T07:01:49.000Z
Signed-off-by: Yiqing Yan &lt;yiqingy@nvidia.com&gt;
diff --git a/jenkins/L0_MergeRequest.groovy b/jenkins/L0_MergeRequest.groovy
@@ -1039,7 +1039,7 @@ def launchStages(pipeline, reuseBuild, testFilter, enableFailFast, globalVars)
                             'wheelDockerImagePy312': globalVars["LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE"],
                         ]
 
-                        launchJob("L0_Test-x86_64-Single-GPU", false, enableFailFast, globalVars, "x86_64", additionalParameters)
+                        launchJob("L0_Test-x86_64-Single-GPU", reuseBuild, enableFailFast, globalVars, "x86_64", additionalParameters)
                     } catch (InterruptedException e) {
                         throw e
                     } catch (Exception e) {
@@ -1095,7 +1095,7 @@ def launchStages(pipeline, reuseBuild, testFilter, enableFailFast, globalVars)
                             'wheelDockerImagePy312': globalVars["LLM_ROCKYLINUX8_PY312_DOCKER_IMAGE"],
                         ]
 
-                        launchJob("L0_Test-x86_64-Multi-GPU", false, enableFailFast, globalVars, "x86_64", additionalParameters)
+                        launchJob("L0_Test-x86_64-Multi-GPU", reuseBuild, enableFailFast, globalVars, "x86_64", additionalParameters)
 
                     } catch (InterruptedException e) {
                         throw e
@@ -1143,7 +1143,7 @@ def launchStages(pipeline, reuseBuild, testFilter, enableFailFast, globalVars)
                             "dockerImage": globalVars["LLM_SBSA_DOCKER_IMAGE"],
                         ]
 
-                        launchJob("L0_Test-SBSA-Single-GPU", false, enableFailFast, globalVars, "SBSA", additionalParameters)
+                        launchJob("L0_Test-SBSA-Single-GPU", reuseBuild, enableFailFast, globalVars, "SBSA", additionalParameters)
                     } catch (InterruptedException e) {
                         throw e
                     } catch (Exception e) {
@@ -1197,7 +1197,7 @@ def launchStages(pipeline, reuseBuild, testFilter, enableFailFast, globalVars)
                             "dockerImage": globalVars["LLM_SBSA_DOCKER_IMAGE"],
                         ]
 
-                        launchJob("L0_Test-SBSA-Multi-GPU", false, enableFailFast, globalVars, "SBSA", additionalParameters)
+                        launchJob("L0_Test-SBSA-Multi-GPU", reuseBuild, enableFailFast, globalVars, "SBSA", additionalParameters)
 
                     } catch (InterruptedException e) {
                         throw e
diff --git a/jenkins/L0_Test.groovy b/jenkins/L0_Test.groovy
@@ -25,6 +25,8 @@ LLM_ROOT = "llm"
 ARTIFACT_PATH = env.artifactPath ? env.artifactPath : "sw-tensorrt-generic/llm-artifacts/${JOB_NAME}/${BUILD_NUMBER}"
 UPLOAD_PATH = env.uploadPath ? env.uploadPath : "sw-tensorrt-generic/llm-artifacts/${JOB_NAME}/${BUILD_NUMBER}"
 
+REUSE_ARITIFACT_PATH = env.reuseArtifactPath
+
 X86_64_TRIPLE = "x86_64-linux-gnu"
 AARCH64_TRIPLE = "aarch64-linux-gnu"
 
@@ -349,6 +351,10 @@ def runLLMTestlistOnSlurm_MultiNodes(pipeline, platform, testList, config=VANILL
                 // if the line cannot be split by "=", just ignore that line.
                 def makoOptsJson = transformMakoArgsToJson(["Mako options:"] + makoArgs)
                 def testListPath = renderTestDB(testList, llmSrcLocal, stageName, makoOptsJson)
+                // Reuse passed tests
+                if (REUSE_ARITIFACT_PATH) {
+                    reusePassedTests(REUSE_ARITIFACT_PATH, stageName, testListPath)
+                }
                 Utils.exec(pipeline, script: "sshpass -p '${remote.passwd}' scp -r -p -oStrictHostKeyChecking=no ${testListPath} ${remote.user}@${remote.host}:${testListPathNode}",)
 
                 // Generate Multi Node Job Launch Script
@@ -1063,6 +1069,40 @@ def renderTestDB(testContext, llmSrc, stageName, preDefinedMakoOpts=null) {
     return testList
 }
 
+def reusePassedTests(reusedArtifactPath, stageName, testListFile) {
+    def reusedPath = "${WORKSPACE}/reused"
+    sh "mkdir -p ${reusedPath}"
+    def resultsFileName = "results-${stageName}"
+    def passedTestsFile = "${reusedPath}/${stageName}/passed_tests.txt"
+    try {
+        trtllm_utils.llmExecStepWithRetry(pipeline, script: "cd ${reusedPath} && wget -nv ${reusedArtifactPath}/test-results/${resultsFileName}.tar.gz")
+        sh "cd ${reusedPath} && tar -zxf ${resultsFileName}.tar.gz"
+        // Get passed tests
+        sh """
+            python3 ${llmSrc}/jenkins/scripts/delete_passed_tests.py \
+            get_passed_tests \
+            --input-file=${reusedPath}/${stageName}/results.xml \
+            --output-file=${passedTestsFile}
+        """
+        sh "The passed tests are: $(cat ${passedTestsFile})"
+
+        // Copy the original test file to a new file
+        sh "cp ${testListFile} original_${testListFile}"
+        // Remove passed tests from original test file
+        sh """
+            python3 ${llmSrc}/jenkins/scripts/delete_passed_tests.py \
+            remove_passed_tests \
+            --input-file=${testListFile} \
+            --passed-tests-file=${passedTestsFile}
+        """
+        sh "The test list after removing passed tests is: $(cat ${testListFile})"
+    } catch (InterruptedException e) {
+        throw e
+    } catch (Exception e) {
+        echo "Failed to get passed tests: ${e.message}"
+    }
+}
+
 def getSSHConnectionPorts(portConfigFile, stageName)
 {
     def type = stageName.split('-')[0]
@@ -1409,6 +1449,11 @@ def runLLMTestlistOnPlatformImpl(pipeline, platform, testList, config=VANILLA_CO
         extraInternalEnv += " CPP_TEST_TIMEOUT_OVERRIDDEN=${pytestTestTimeout}"
 
         def testDBList = renderTestDB(testList, llmSrc, stageName)
+        // Reuse passed tests
+        if (REUSE_ARITIFACT_PATH) {
+            reusePassedTests(REUSE_ARITIFACT_PATH, stageName, testDBList)
+        }
+
         testList = "${testList}_${splitId}"
         def testCmdLine = [
             "LLM_ROOT=${llmSrc}",
diff --git a/jenkins/scripts/delete_passed_tests.py b/jenkins/scripts/delete_passed_tests.py
@@ -0,0 +1,92 @@
+import os
+import sys
+import argparse
+import xml.etree.ElementTree as ET
+from test_rerun import parse_name
+
+def get_passed_tests(input_file, output_file):
+    if not os.path.exists(input_file):
+        print(f"Input file {input_file} does not exist")
+        return
+
+    # Parse the JUnit XML file and extract passed test names
+    passed_tests = []
+    try:
+        tree = ET.parse(input_file)
+        root = tree.getroot()
+        suite = root.find('testsuite')
+        for testcase in suite.iter('testcase'):
+            # Check test status
+            has_failure = testcase.find('failure') is not None
+            has_error = testcase.find('error') is not None
+            has_skipped = testcase.find('skipped') is not None
+            if not has_failure and not has_error and not has_skipped:
+                # Parse the test name
+                classname = testcase.attrib.get('classname', '')
+                name = testcase.attrib.get('name', '')
+                filename = testcase.attrib.get('file', '')
+                testName = parse_name(classname, name, filename)
+                passed_tests.append(testName)
+    except Exception as e:
+        print(f"Failed to parse {input_file}: {e}")
+        return
+
+    # Write passed test names to output file, one per line
+    with open(output_file, 'w') as f:
+        for test in passed_tests:
+            f.write(test + '\n')
+
+
+def remove_passed_tests(input_file, passed_tests_file):
+    if not os.path.exists(input_file):
+        print(f"Input file {input_file} does not exist")
+        return
+    if not os.path.exists(passed_tests_file):
+        print(f"Passed tests file {passed_tests_file} does not exist")
+        return
+
+    passed_tests = []
+    # Read passed tests from file
+    with open(passed_tests_file, 'r') as f:
+        for line in f:
+            passed_tests.append(line.strip())
+
+    tests_to_keep = []
+    # Remove passed tests from input file
+    with open(input_file, 'r') as f:
+        for line in f:
+            if line.strip() not in passed_tests:
+                tests_to_keep.append(line.strip())
+
+    # Delete input file
+    try:
+        os.remove(input_file)
+    except Exception as e:
+        print(f"Failed to delete {input_file}: {e}")
+    # Write tests to keep to input file
+    with open(input_file, 'w') as f:
+        for test in tests_to_keep:
+            f.write(test + '\n')
+
+
+if __name__ == '__main__':
+    if (sys.argv[1] == "get_passed_tests"):
+        parser = argparse.ArgumentParser()
+        parser.add_argument('--input-file',
+                            required=True,
+                            help='Input XML file containing test results')
+        parser.add_argument('--output-file',
+                            required=True,
+                            help='Output file to write passed tests')
+        args = parser.parse_args(sys.argv[2:])
+        get_passed_tests(args.input_file, args.output_file)
+    elif (sys.argv[1] == "remove_passed_tests"):
+        parser = argparse.ArgumentParser()
+        parser.add_argument('--input-file',
+                            required=True,
+                            help='Input XML file containing test results')
+        parser.add_argument('--passed-tests-file',
+                            required=True,
+                            help='File containing passed tests')
+        args = parser.parse_args(sys.argv[2:])
+        remove_passed_tests(args.input_file, args.passed_tests_file)
