klueska

# Reproduction image for the sandbox-gpu-cdi-support branch's real-hardware GPU tests.
#
# Stage 1 builds runsc (gVisor) from source instead of using the prebuilt release
# binary from storage.googleapis.com/gvisor. Why: gVisor checks the *runtime* host's
# page size against a Go constant baked in at *compile* time (unix.Getpagesize() vs.
# hostarch.PageSize in runsc/cmd/sentry/sentrycmd/boot.go) and fatals on a mismatch in
# either direction. The prebuilt aarch64 release binary is compiled for 4K pages only
# (pkg/hostarch/hostarch_arm64.go's default), which hard-fails on ARM64 hosts whose
# kernel boots with 64K pages (e.g. NVIDIA Grace/GB200 -- NVIDIA recommends 64K there
# for HBM throughput, even though most distros default to 4K and the silicon supports

klueska

package api

import (
	"k8s.io/apimachinery/pkg/api/resource"
	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
)

const (
	DevMgmtAPIVersion = "devmgmtproto.k8s.io/v1alpha1"
)

klueska

package main

import (
	semverv4 "github.com/blang/semver/v4"
	"k8s.io/apimachinery/pkg/api/resource"
)

type NodeResourceSliceSpec struct {
	// NodeName identifies the node where the capacity is available.
	// A field selector can be used to list only NodeResources

klueska

diff --git a/pkg/kubelet/cm/devicemanager/plugin/v1beta1/handler.go b/pkg/kubelet/cm/devicemanager/plugin/v1beta1/handler.go
index cea6317257e..bdec8984139 100644
--- a/pkg/kubelet/cm/devicemanager/plugin/v1beta1/handler.go
+++ b/pkg/kubelet/cm/devicemanager/plugin/v1beta1/handler.go
@@ -44,10 +44,9 @@ func (s *server) RegisterPlugin(pluginName string, endpoint string, versions []s

 func (s *server) DeRegisterPlugin(pluginName string) {
 	klog.V(2).InfoS("Deregistering plugin", "plugin", pluginName)
-	s.mutex.Lock()
-	defer s.mutex.Unlock()

klueska

# Run the export command of nvidia-mig-parted
nvidia-mig-parted export

# Show nvidia-smi on the host with 8 full GPUs
nvidia-smi -L

# List out the NVIDIA container toolkit packages installed
dpkg -l | grep nvidia-container; dpkg -l | grep nvidia-docker

# Show that docker is configured to run with the nvidia container toolkit

klueska

layout	blog
title	Kubernetes Topology Manager Moves to Beta - Align Up!
date	2020-03-30
slug	kubernetes-1-18-feature-topoloy-manager-beta

Authors: Kevin Klues (NVIDIA), Victor Pickard (RedHat), Conor Nolan (Intel)

This blog post describes the TopologyManager, a beta feature of Kubernetes in release 1.18. The TopologyManager feature enables NUMA alignment of CPUs and peripheral devices (such as SR-IOV VFs and GPUs), allowing your workload to run in an environment optimized for low-latency.

klueska

--- blog-orig.md	2020-03-31 13:06:09.899071690 +0200
+++ blog.md	2020-03-31 13:04:49.594078489 +0200
@@ -7,46 +7,52 @@

 **Authors:** Kevin Klues (NVIDIA), Victor Pickard (RedHat), Conor Nolan (Intel)

-This blog post describes the **<code>TopologyManager</code>**, a beta feature of Kubernetes in release 1.18. The <strong><code>TopologyManager</code></strong> feature enables NUMA alignment of CPUs and peripheral devices (such as SR-IOV VFs and GPUs), allowing your workload to run in an environment optimized for low-latency.
+This blog post describes the **<code>TopologyManager</code>**, a beta feature of Kubernetes in release 1.18. The **<code>TopologyManager</code>** feature enables NUMA alignment of CPUs and peripheral devices (such as SR-IOV VFs and GPUs), allowing your workload to run in an environment optimized for low-latency.

-Prior to the introduction of the **<code>TopologyManager</code>**, the CPU and Device Manager would make resource allocation decisions independent of each other. This could resu

klueska

#!/usr/bin/env bash

# Declare some helper functions
function get_kubernetes_hostname() {
local json="$(kubectl get nodes -o json)"
echo ${json} | python -c "$(cat << EOF
import sys
import json

nodes = json.load(sys.stdin)

klueska

import itertools
import prettytable

from prettytable import PrettyTable

affinities = [
  (0,1),
  (1,0),
  (1,1),
]

klueska

$ mesos --help
Mesos CLI

Usage:
  mesos (-h | --help)
  mesos --version
  mesos <command> [<args>...]

Options:
  -h --help  Show this screen.