diff --git a/config/jobs/kubernetes/wg-k8s-infra/canaries/sig-scalability.yaml b/config/jobs/kubernetes/wg-k8s-infra/canaries/sig-scalability.yaml
index 87928e6d9d773..59f987eee8c3e 100644
--- a/config/jobs/kubernetes/wg-k8s-infra/canaries/sig-scalability.yaml
+++ b/config/jobs/kubernetes/wg-k8s-infra/canaries/sig-scalability.yaml
@@ -502,3 +502,76 @@ periodics:
         limits:
           cpu: 6
           memory: "16Gi"
+
+presubmits:
+- name: pull-kubernetes-e2e-gce-large-performance-canary
+  cluster: k8s-infra-prow-build
+  always_run: false
+  max_concurrency: 1
+  branches:
+  - master
+  decorate: true
+  path_alias: k8s.io/kubernetes
+  decoration_config:
+    timeout: 570m
+  extra_refs:
+  - org: kubernetes
+    repo: perf-tests
+    base_ref: master
+    path_alias: k8s.io/perf-tests
+  - org: kubernetes
+    repo: release
+    base_ref: master
+    path_alias: k8s.io/release
+  labels:
+    preset-service-account: "true"
+    preset-k8s-ssh: "true"
+    preset-dind-enabled: "true"
+    preset-e2e-scalability-common: "true"
+    preset-e2e-scalability-presubmits: "true"
+  annotations:
+    testgrid-dashboards: wg-k8s-infra-canaries
+    testgrid-tab-name: pull-kubernetes-e2e-gce-large-performance-canary
+  spec:
+    containers:
+    - image: gcr.io/k8s-testimages/kubekins-e2e:v20210715-521d667-master
+      command:
+      - runner.sh
+      - /workspace/scenarios/kubernetes_e2e.py
+      args:
+      - --build=quick
+      - --cluster=
+      - --env=HEAPSTER_MACHINE_TYPE=e2-standard-8
+      - --extract=local
+      - --flush-mem-after-build=true
+      - --gcp-nodes=5000
+      - --gcp-project=k8s-infra-e2e-scale-5k-project
+      - --gcp-zone=us-east1-b
+      - --provider=gce
+      - --stage=gs://kubernetes-release-pull/ci/pull-kubernetes-e2e-gce-large-performance
+      - --env=CL2_ENABLE_HUGE_SERVICES=true
+      - --env=CL2_ENABLE_HUGE_SERVICES_MULTIPLE_REPLICAS=true
+      - --test=false
+      - --test-cmd=$GOPATH/src/k8s.io/perf-tests/run-e2e.sh
+      - --test-cmd-args=cluster-loader2
+      - --test-cmd-args=--experimental-gcp-snapshot-prometheus-disk=true
+      - --test-cmd-args=--nodes=5000
+      - --test-cmd-args=--provider=gce
+      - --test-cmd-args=--report-dir=$(ARTIFACTS)
+      - --test-cmd-args=--testconfig=testing/load/config.yaml
+      - --test-cmd-args=--testconfig=testing/access-tokens/config.yaml
+      - --test-cmd-args=--testoverrides=./testing/overrides/5000_nodes.yaml
+      - --test-cmd-name=ClusterLoaderV2
+      - --timeout=540m
+      - --use-logexporter
+      - --logexporter-gcs-path=gs://sig-scalability-logs/$(JOB_NAME)/$(BUILD_ID)
+      resources:
+        limits:
+          # Using 6 CPU to speed up bazel build phase (4 is enough for the test itself)
+          cpu: 6
+          memory: "16Gi"
+        requests:
+          cpu: 6
+          memory: "16Gi"
+      securityContext:
+        privileged: true