feat(mockibsysfs): ibping support via synthetic umad emulation

.github/workflows/nvml-mock-e2e.yaml

@@ -41,7 +41,22 @@ on:
         type: string
 
 jobs:
+  mockib-integration:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install infiniband-diags
+        run: sudo apt-get update && sudo apt-get install -y infiniband-diags
+
+      - name: Build libibmocksys and run integration tests
+        run: |
+          make -C pkg/network/mockibsysfs
+          go test ./pkg/network/mockibsysfs/...
+          go test -tags=integration ./pkg/network/mockibsysfs/render/...
+
   e2e-device-plugin:
+    needs: mockib-integration
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
@@ -141,6 +156,13 @@ jobs:
           # IB-enabled profiles are expected to expose 2 HCAs.
           ./tests/e2e/validate-ibstat.sh "$POD" "${{ matrix.gpu-profile }}" 2
 
+      - name: Validate ibping (vendor MAD / libibumad)
+        run: |
+          chmod +x tests/e2e/validate-ibping.sh
+          POD=$(kubectl get pods -l app.kubernetes.io/name=nvml-mock \
+            -o jsonpath='{.items[0].metadata.name}')
+          ./tests/e2e/validate-ibping.sh "$POD" "${{ matrix.gpu-profile }}" 2
+
       - name: Deploy NVIDIA device plugin
         run: |
           kubectl apply -f tests/e2e/device-plugin-mock.yaml
@@ -780,6 +802,13 @@ jobs:
             -o jsonpath='{.items[0].metadata.name}')
           ./tests/e2e/validate-ibstat.sh "$T4_POD" t4 2
 
+      - name: Validate ibping on A100 worker
+        run: |
+          chmod +x tests/e2e/validate-ibping.sh
+          A100_POD=$(kubectl get pods -l app.kubernetes.io/instance=nvml-mock-a100 \
+            -o jsonpath='{.items[0].metadata.name}')
+          ./tests/e2e/validate-ibping.sh "$A100_POD" a100 2
+
       - name: Deploy NVIDIA device plugin
         run: |
           kubectl apply -f tests/e2e/device-plugin-mock.yaml

.gitignore

@@ -10,6 +10,9 @@
 
 # Agentic working artifacts
 .agents/
+.cursor/
+.worktrees/
 AGENTS.md
+CLAUDE.md
 docs/plans/
 docs/superpowers/

CHANGELOG.md

@@ -8,6 +8,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [Unreleased]
 
 ### Added
+- InfiniBand mock: `ibping` (OpenIB vendor ping MAD class only) via synthetic
+  umad fds, global `umad-bus/` for cross-HCA server/client, TID-matched replies,
+  `REGISTER_AGENT2`, and mixed-fd `poll()` with libc.
+- InfiniBand mock: real `ibstat`, `ibstatus`, `iblinkinfo`, and other
+  `infiniband-diags` / `rdma-core` tools now work inside the nvml-mock
+  DaemonSet without IB hardware. Implementation: `LD_PRELOAD` shim
+  (`libibmocksys.so`) redirects libc filesystem accesses against
+  `/sys/class/infiniband*` and `/dev/infiniband` to a fake tree rendered
+  at startup by `render-ib-sysfs` from each profile's new `infiniband:`
+  block. Defaults: `a100` -> ConnectX-6 HDR; `h100` / `b200` / `gb200`
+  -> ConnectX-7 NDR; `l40s` / `t4` -> disabled.
 - New GPU profile `gb300` modeling the NVIDIA GB300 NVL (Grace-Blackwell
   Ultra Superchip): 8 GPUs/node arranged as 4 Grace+2×B300 trays, 288 GiB
   HBM3e per GPU, 1.4 kW default TDP / 1.6 kW boost, PCIe Gen6, NVLink v5
@@ -47,14 +58,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   the same string verbatim in `nvmlPciInfo.busId`; the new format aligns
   the mock with what real Linux PCI sysfs exposes and is a hard
   prerequisite for the PCIe sysfs renderer above. (#263)
-- InfiniBand mock: real `ibstat`, `ibstatus`, `iblinkinfo`, and other
-  `infiniband-diags` / `rdma-core` tools now work inside the nvml-mock
-  DaemonSet without IB hardware. Implementation: `LD_PRELOAD` shim
-  (`libibmocksys.so`) redirects libc filesystem accesses against
-  `/sys/class/infiniband*` and `/dev/infiniband` to a fake tree rendered
-  at startup by `render-ib-sysfs` from each profile's new `infiniband:`
-  block. Defaults: `a100` -> ConnectX-6 HDR; `h100` / `b200` / `gb200`
-  -> ConnectX-7 NDR; `l40s` / `t4` -> disabled.
 
 ## [0.1.0] - 2026-04-07
 

deployments/nvml-mock/helm/nvml-mock/README.md

@@ -13,7 +13,7 @@ Deploys a DaemonSet that creates on every node:
 - Node label `nvidia.com/gpu.present=true`
 - A fake InfiniBand sysfs tree at `/var/lib/nvml-mock/ib/sys/class/infiniband/...`
   paired with `libibmocksys.so` (`LD_PRELOAD`) so real `ibstat`, `ibstatus`,
-  `iblinkinfo`, ... read mock HCAs
+  `iblinkinfo`, `ibping`, ... use mock HCAs (sysfs + synthetic umad)
 - A fake PCI sysfs tree at `/var/lib/nvml-mock/sys/bus/pci/devices/...` (symlinks
   into `/var/lib/nvml-mock/sys/devices/pciDDDD:BB/...`) so topology-aware
   consumers (NVIDIA DRA driver `dra.k8s.io/pcieRoot`, NUMA-aware schedulers)
@@ -503,8 +503,21 @@ read from the rendered tree:
 POD=$(kubectl get pods -l app.kubernetes.io/name=nvml-mock -o jsonpath='{.items[0].metadata.name}')
 kubectl exec "$POD" -- ibstat
 kubectl exec "$POD" -- ibstatus
+kubectl exec "$POD" -- ibping -c 1 -C mlx5_0 -P 1 1
 ```
 
+**Environment (DaemonSet):**
+
+| Variable | Value | Purpose |
+|----------|--------|---------|
+| `LD_PRELOAD` | `/usr/local/lib/libibmocksys.so.1` | Sysfs redirect + synthetic umad |
+| `MOCK_IB_ROOT` | `/var/lib/nvml-mock/ib` | Fake sysfs + `umad-bus/` runtime dir |
+| `MOCK_IB_DISABLE` | unset (set `1` to bypass) | Debug escape hatch |
+
+**Limitations:** sysfs tools (`ibstat`, …) read the rendered tree. **`ibping`**
+uses emulated umad (vendor ping MADs only), not real HCAs or RDMA. Runtime
+MAD relay files live under `/var/lib/nvml-mock/ib/umad-bus/`.
+
 ### Defaults per profile
 
 | Profile | Enabled | HCA | Speed | HCAs per GPU |

deployments/nvml-mock/helm/nvml-mock/templates/daemonset.yaml

@@ -79,9 +79,8 @@ spec:
             {{- end }}
             # LD_PRELOAD installs the InfiniBand sysfs redirector in every
             # process spawned in this container (e.g. `kubectl exec ibstat`).
-            # The shim only rewrites paths under /sys/class/infiniband*,
-            # /sys/class/infiniband_mad/, /sys/class/infiniband_verbs/ and
-            # /dev/infiniband — every other path passes through unchanged.
+            # The shim rewrites IB sysfs/dev paths and emulates umad for ibping.
+            # Every other path passes through unchanged.
             - name: LD_PRELOAD
               value: "/usr/local/lib/libibmocksys.so.1"
             - name: MOCK_IB_ROOT

pkg/network/mockibsysfs/Makefile

@@ -2,20 +2,20 @@
 # SPDX-License-Identifier: Apache-2.0
 
 CC      ?= gcc
-CFLAGS  ?= -O2 -Wall -Wextra -fPIC -fvisibility=default
-LDFLAGS ?= -shared -Wl,-soname,libibmocksys.so.1 -ldl
+CFLAGS  ?= -O2 -Wall -Wextra -Wno-format-truncation -fPIC -fvisibility=default
+LDFLAGS ?= -shared -Wl,-soname,libibmocksys.so.1 -ldl -lpthread
 
 LIB_NAME    := libibmocksys.so
 LIB_SONAME  := $(LIB_NAME).1
-LIB_VERSION ?= 1.0.0
+LIB_VERSION ?= 1.2.0
 LIB_REAL    := $(LIB_NAME).$(LIB_VERSION)
 
 .PHONY: all clean
 
 all: $(LIB_NAME)
 
-$(LIB_REAL): shim.c
-	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $<
+$(LIB_REAL): shim.c umad_mock.c mock_ib_root.c umad_mock.h mock_ib_root.h
+	$(CC) $(CFLAGS) $(LDFLAGS) -o $@ shim.c umad_mock.c mock_ib_root.c
 
 $(LIB_NAME): $(LIB_REAL)
 	ln -sf $(LIB_REAL) $(LIB_SONAME)