Add datacenter node setup scripts (#5517)

automerge

net/datacenter-node-install/README.md

@@ -0,0 +1,11 @@
+# Introduction
+
+These scripts are intended to facilitate the preparation of dedicated Solana
+nodes.  They have been tested as working from a clean installation of Ubuntu
+18.04 Server.  Use elsewhere is unsupported.
+
+# Installation
+
+1) `sudo ./setup-dc-node-1.sh`
+2) `sudo reboot`
+3) `sudo ./setup-dc-node-2.sh`

net/datacenter-node-install/disable-networkd-wait.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+set -xe
+
+systemctl disable systemd-networkd-wait-online.service
+systemctl mask systemd-networkd-wait-online.service

net/datacenter-node-install/disable-nouveau.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+cat <<EOF > /etc/modprobe.d/blacklist-nouveau.conf
+blacklist nouveau
+options nouveau modeset=0
+EOF
+
+update-initramfs -u

net/datacenter-node-install/set-hostname.sh

@@ -0,0 +1,14 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+set -xe
+
+echo "preserve_hostname: false" > /etc/cloud/cloud.cfg.d/99-disable-preserve-hostname.cfg
+systemctl restart cloud-init
+hostnamectl set-hostname "$1"

net/datacenter-node-install/setup-cuda.sh

@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+set -xe
+
+apt update
+apt install -y gcc make dkms
+
+sh cuda_10.0.130_410.48_linux.run --silent --driver --toolkit
+sh cuda_10.1.168_418.67_linux.run --silent --driver --toolkit

net/datacenter-node-install/setup-dc-node-1.sh

@@ -0,0 +1,69 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+exit
+
+if [[ -n "$1" ]]; then
+  PUBKEY_FILE="$1"
+else
+  cat <<EOF
+Usage: $0 [pubkey_file]
+
+The pubkey_file should be the pubkey that will be set up to allow the current user
+(assumed to be the machine admin) to log in via ssh
+EOF
+  exit 1
+fi
+
+set -xe
+
+apt update
+apt upgrade -y
+apt install -y build-essential pkg-config clang
+
+"$HERE"/../scripts/install-docker.sh
+usermod -aG docker "$SETUP_USER"
+"$HERE"/../scripts/install-certbot.sh
+"$HERE"/setup-sudoers.sh
+"$HERE"/setup-ssh.sh
+
+# Allow admin user to log in
+BASE_SSH_DIR="${SETUP_HOME}/.ssh"
+mkdir "$BASE_SSH_DIR"
+chown "$SETUP_USER:$SETUP_USER" "$BASE_SSH_DIR"
+cat "$PUBKEY_FILE" > "${BASE_SSH_DIR}/authorized_keys"
+chown "$SETUP_USER:$SETUP_USER" "${BASE_SSH_DIR}/.ssh/authorized_keys"
+
+"$HERE"/disable-nouveau.sh
+"$HERE"/disable-networkd-wait.sh
+"$HERE"/setup-grub.sh
+"$HERE"/../scripts/install-earlyoom.sh
+"$HERE"/../scripts/install-nodeljs.sh
+"$HERE"/../scripts/localtime.sh
+"$HERE"/../scripts/install-redis.sh
+"$HERE"/../scripts/install-rsync.sh
+"$HERE"/../scripts/install-libssl-compatability.sh
+
+# Setup kernel constants
+cat > /etc/sysctl.d/20-solana-node.conf <<EOF
+
+# Solana networking requirements
+net.core.rmem_default=1610612736
+net.core.rmem_max=1610612736
+net.core.wmem_default=1610612736
+net.core.wmem_max=1610612736
+
+# Solana earlyoom setup
+kernel.sysrq=$(( $(cat /proc/sys/kernel/sysrq) | 64 ))
+EOF
+
+# Allow more files to be opened by a user
+sed -i 's/^\(# End of file\)/* soft nofile 65535\n\n\1/' /etc/security/limits.conf
+
+echo "Please reboot then run setup-dc-node-2.sh"

net/datacenter-node-install/setup-dc-node-2.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+set -xe
+
+"$HERE"/setup-cuda.sh
+
+# setup persistence mode across reboots
+TMPDIR="$(mktemp)"
+mkdir -p "$TMPDIR"
+if pushd "$TMPDIR"; then
+  tar -xvf /usr/share/doc/NVIDIA_GLX-1.0/sample/nvidia-persistenced-init.tar.bz2
+  ./nvidia-persistenced-init/install.sh systemd
+  popd
+  rm -rf "$TMPDIR"
+fi

net/datacenter-node-install/setup-grub.sh

@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+set -xe
+
+printf "GRUB_GFXPAYLOAD_LINUX=1280x1024x32\n\n" >> /etc/default/grub
+update-grub

net/datacenter-node-install/setup-ssh.sh

@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+set -xe
+# Setup sshd
+sed -i 's/^PasswordAuthentication yes//' /etc/ssh/sshd_config
+sed -i 's/^#\(PasswordAuthentication\) yes/\1 no/' /etc/ssh/sshd_config
+sed -i 's/^#\(PermitRootLogin\) .*/\1 no/' /etc/ssh/sshd_config
+systemctl restart sshd

net/datacenter-node-install/setup-sudoers.sh

@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+set -xe
+
+# Enable passwordless sudo
+EDITOR='tee' visudo <<EOF 
+#
+# This file MUST be edited with the 'visudo' command as root.
+#
+# Please consider adding local content in /etc/sudoers.d/ instead of
+# directly modifying this file.
+#
+# See the man page for details on how to write a sudoers file.
+#
+Defaults	env_reset
+Defaults	mail_badpass
+Defaults	secure_path="/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin"
+
+# Host alias specification
+
+# User alias specification
+
+# Cmnd alias specification
+
+# User privilege specification
+root	ALL=(ALL:ALL) ALL
+
+# Members of the admin group may gain root privileges
+%admin ALL=(ALL) ALL
+
+# Allow members of group sudo to execute any command
+%sudo	ALL=(ALL:ALL) ALL
+
+# Allow all members of sudo group to use passwordless sudo
+%sudo	ALL=(ALL) NOPASSWD:ALL
+
+# See sudoers(5) for more information on "#include" directives:
+
+#includedir /etc/sudoers.d
+EOF
+

net/datacenter-node-install/setup-validator.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+
+HERE="$(dirname "$0")"
+
+# shellcheck source=net/datacenter-node-install/utils.sh
+source "$HERE"/utils.sh
+
+ensure_env || exit 1
+
+set -xe
+
+"$HERE"/disable-networkd-wait.sh
+
+"$HERE"/setup-grub.sh
+
+"$HERE"/setup-cuda.sh
+
+PASSWORD="$(dd if=/dev/urandom bs=1 count=9 status=none | base64)"
+echo "$PASSWORD"
+chpasswd <<< "solana:$PASSWORD"
+

net/datacenter-node-install/utils.sh

@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+
+# We need root access, but also appropriate envvar values. Require scripts to
+# run with sudo as a normal user
+ensure_env() {
+  RC=false
+  [ $EUID -eq 0 ] && [ -n "$SUDO_USER" ] && [ "$SUDO_USER" != "root" ] && RC=true
+  if $RC; then
+    export SETUP_USER="$SUDO_USER"
+    export SETUP_HOME="$HOME"
+  else
+    echo "Please run \"$0\" via sudo as a normal user"
+  fi
+  $RC
+}
+