Arch Linux

ugjka

Member

From: Latvia

Registered: 2014-04-01

Posts: 1,862

Website

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

I don't know if the issue I posted at https://github.com/dhabyx/plasma-simple … /issues/61 is where to put this or somewhere else?

https://bugs.kde.org/

---

https://ugjka.net
paru > yay | vesktop > discord
pacman -S spotify-launcher
mount /dev/disk/by-...

post-factum

Member

From: /cz

Registered: 2008-09-12

Posts: 152

Website

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

Would you be able to test the patch from here: [1]?

[1] https://lore.kernel.org/lkml/11ded843-a … nel.dk/raw

---

uname == latest pf-kernel

mcloaked

Member

From: Yorkshire, UK

Registered: 2012-02-02

Posts: 1,276

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

Tested kernel 6.4.6 built with the referenced patch, and the anomalous 100% cpu activity on a single core is no longer displayed in the System Monitor widget, and mpstat no longer shows >94% io-wait. So this resolves the issue for my systems.

If fijxu also finds the patch resolves the issue then perhaps as original poster he can mark this as solved?

Last edited by mcloaked (2023-07-24 18:39:57)

---

Mike C

loqs

Member

Registered: 2014-03-06

Posts: 18,042

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

6.4.5 with https://lore.kernel.org/lkml/11ded843-a … @kernel.dk applied:
https://drive.google.com/file/d/19vLa9Q … sp=sharing linux-6.4.5.arch1-1.1-x86_64.pkg.tar.zst
https://drive.google.com/file/d/1BNibKn … sp=sharing linux-headers-6.4.5.arch1-1.1-x86_64.pkg.tar.zst

Fijxu

Member

Registered: 2021-08-11

Posts: 44

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

If fijxu also finds the patch resolves the issue then perhaps as original poster he can mark this as solved?

I will test it later, if it works I will mark this issue as SOLVED.

Fijxu

Member

Registered: 2021-08-11

Posts: 44

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

Tested, works as intended, there is no io-wait load under the CPU now. Thanks everyone who helped, specially loqs (Thanks for compiling Linux again, and again, and again... AND AGAIN)

So now we have to wait for Linux 6.4.5 right? What do I do now with my BugZilla report? I just mark it as solved and that's it?

Edit: I didn't even noticed that Linux 6.4.5 is already out, so, we need to wait for 6.4.6?

Last edited by Fijxu (2023-07-25 00:05:25)

loqs

Member

Registered: 2014-03-06

Posts: 18,042

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

Edit: I didn't even noticed that Linux 6.4.5 is already out, so, we need to wait for 6.4.6?

It is not in 6.4.6.  It will not make 6.4.7 as it is only in the block tree https://git.kernel.org/pub/scm/linux/ke … 8bdac8ed69 and it needs to be pulled to mainline then it can be queued for stable.  Arch could add the fix before that possibly by requesting https://bugs.archlinux.org/task/79177 is reopened.

mcloaked

Member

From: Yorkshire, UK

Registered: 2012-02-02

Posts: 1,276

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

It looks like the patches for this are now in Linus' tree so hopefully they will be in 6.4.8 when it gets released in the next few days.

https://github.com/torvalds/linux/commi … daa4347813

Last edited by mcloaked (2023-07-29 09:13:57)

---

Mike C

loqs

Member

Registered: 2014-03-06

Posts: 18,042

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

Queued for 6.4.8 https://git.kernel.org/pub/scm/linux/ke … e9cd1e0d69

Fijxu

Member

Registered: 2021-08-11

Posts: 44

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

Just tested it. Now there is no false IO-Wait load into the CPU. Thanks everyone for the help.

mcloaked

Member

From: Yorkshire, UK

Registered: 2012-02-02

Posts: 1,276

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

Yes 6.4.8 has the fix and works fine now.

---

Mike C

dreieck

Member

Registered: 2012-10-08

Posts: 64

Re: [SOLVED] Linux 6.4.4 introduces high IO-Wait CPU operations on one ...

Wow, what a great thread, in the hunt for an issue :-)

This should have been reported directly to maintainers using email instead of BZ (almost no one reads the BZ)

I also once was annoyed that there is a kernel bugtracker but it is not read. I had issues with i915 to report.

why is it there then? Why not closing it?

Offering a way of communicatiion but not reading the communication inbox offered is not a good stance to people wanting to give awareness to issues ...

As you seem to be a kernel developer, too, can you comment on this? When to use which way of communicating stuff to the kernel developers?

Regards!

Last edited by dreieck (2023-08-06 15:04:00)