A beginner-friendly guide to understanding and fixing AMD GPU crashes, freezes, and instability on Linux.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| From: Helmut Januschka <helmut@januschka.com> | |
| Subject: [PATCH] platform/x86/amd/pmc: firmware-handled LPS0 quirk for MINISFORUM MS-S1 MAX | |
| The MINISFORUM MS-S1 MAX (SHWSA, Strix Halo) ships firmware whose LPS0 | |
| PEP device only implements the Microsoft _DSM UUID; its entry/exit | |
| functions trap into SMM (port 0xB2, 0xEA/0xEB) and perform the platform | |
| sleep handshake there. The AMD _DSM UUID advertises no entry/exit | |
| functions at all (function mask 0x3). | |
| When amd_pmc additionally sends OS_HINT, s2idle never resumes: with both |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| System Sensors Summary | |
| CPU (AMD Ryzen) | |
| ────────────────────────────────────────────────── | |
| Tctl: 47.6°C | |
| CCD1: 39.6°C | |
| CCD2: 37.6°C | |
| Motherboard (ASUS) | |
| ────────────────────────────────────────────────── |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| * PCI legacy (from https://lore.kernel.org/all/20171026223701.GA25649@bhelgaas-glaptop.roam.corp.google.com): | |
| Fixes: | |
| Closes: (link or Message-ID] | |
| Suggested-by: | |
| Link: | |
| Reported-by: | |
| Tested-by: | |
| Co-developed-by: (co-author) | |
| Signed-off-by: (co-author) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| cd ./ccache/build | |
| make clean | |
| export PATH='/usr/local/bin:/usr/local/sbin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin' | |
| ccmake -DDEPS=DOWNLOAD -DCMAKE_BUILD_TYPE=Release -DENABLE_TESTING=OFF -DREDIS_STORAGE_BACKEND=OFF -DCMAKE_INSTALL_PREFIX=/usr -DCMAKE_INSTALL_SYSCONFDIR=/etc .. | |
| make -j$(nproc) | |
| make DESTDIR='/tmp/ccache' PREFIX='/usr' install |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ccflags-y := -DDEBUG -Wfatal-errors | |
| ifneq ($(KERNELRELEASE),) | |
| obj-m += state-toggle.o | |
| else | |
| BUILD_KERNEL ?= /lib/modules/$(shell uname -r)/build | |
| default: | |
| $(MAKE) -C $(BUILD_KERNEL) M=$(CURDIR) modules | |
| endif |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // Usage: node apparmor-docker-default.js | |
| const path = require("node:path"); | |
| const fs = require("node:fs"); | |
| const profileDirectory = "/etc/apparmor.d" | |
| /** | |
| * @typedef ProfileData | |
| * @property {string} name |
It seems that is a common practice in HPC and AI/ML environments that use MPI applications to populate a hosts files with all the nodes on the cluster and copy it over all the nodes, ref https://help.ubuntu.com/community/MpichCluster
It is my observation that in Kubernetes, Headless Services are used to implement this Service Discovery This is very handy because it allows to reference a pod by hostname without having to copy over a generace /etc/hosts.
There must also be an A record of the following form for each ready endpoint with hostname of and IPv4 address . If there are multiple IPv4 addresses for a given hostname, then there must be one such A record returned for each IP.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # See for more options https://kubernetes.io/docs/concepts/workloads/controllers/daemonset/ | |
| apiVersion: apps/v1 | |
| kind: DaemonSet | |
| metadata: | |
| name: node-ethtool | |
| namespace: kube-system | |
| labels: | |
| k8s-app: node-ethtool-config | |
| spec: | |
| selector: |
NewerOlder