Of course neither the new memory nor the BIOS update fixed the random crashes, but fortunately I’ve got another hint: Maybe it’s a linux-specific problem, and not one with memory timing. This post<\/a> suggests that it’s a problem with C-States and RCU. Adding the following kernel command line parameters should help:<\/p>\n As always, nothing is as simple as it seems \ud83d\ude41<\/p>\n For max_cstate to take effect, I had to actually enable Global C-State-Control in the UEFI-thingy of my mobo! The default was Auto, which in turn defaulted to Disabled. After enabling it, dmesg reported this:<\/p>\n Before that, there was no mentioning of C-states in the kernel log, so I doubt that it has any impact, but one should never give up hope!<\/p>\n What it is (quoting Paul E. McKenney from LKML<\/a>):<\/p>\n It’s much more likely to be the cause of the problem since I once saw something like this after a reboot on the console:<\/p>\n The process was “systemd” instead of “DOM Worker”, but that shouldn’t matter. Anyway, the parameter\u00a0rcu_nocbs=0-11 has no effect if the kernel config option\u00a0CONFIG_RCU_NOCB_CPU is not set. Guess what, in the stock archlinux kernel it’s unset, lucky me!<\/p>\n So I ventured out to compile a custom kernel for arch. That turned out to be disappointingly easy! The available documentation<\/a> just works ™! Four hints, though:<\/p>\n should be in dmesg after a reboot, otherwise it didn’t work. I’m waiting with baited breath how it turns out!<\/p>\n Previous parts of my adventure: Part 1<\/a>, Part 2<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":" Take 3 Of course neither the new memory nor the BIOS update fixed the random crashes, but fortunately I’ve got another hint: Maybe it’s a linux-specific problem, and not one with memory timing. This post suggests that it’s a problem with C-States and RCU. Adding the following kernel command line parameters should help: processor.max_cstate=1 rcu_nocbs=0-11 … Continue reading Ryzen, Part 3<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[19,79,77],"tags":[],"class_list":["post-379","post","type-post","status-publish","format-standard","hentry","category-arch-linux","category-hardware","category-linux"],"_links":{"self":[{"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=\/wp\/v2\/posts\/379","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=379"}],"version-history":[{"count":4,"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=\/wp\/v2\/posts\/379\/revisions"}],"predecessor-version":[{"id":384,"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=\/wp\/v2\/posts\/379\/revisions\/384"}],"wp:attachment":[{"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=379"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=379"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/tollana.d-tor.org\/notes-to-self\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=379"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}processor.
The C-States<\/h3>\n
ACPI: ACPI: processor limited to max C-state 1<\/pre>\n
The RCU-Thingy<\/h3>\n
Read-copy update (RCU) is a synchronization mechanism that was added to the Linux kernel in October of 2002. RCU achieves scalability improvements by allowing reads to occur concurrently with updates.<\/pre>\n
NMI watchdog: BUG: soft lockup - CPU#12 stuck for 23s! [DOM Worker:1364]<\/pre>\n
\n
Offload RCU callbacks from CPUs: 0-11.<\/pre>\n