DAMO v2.2.2 is released. The important change in this release is the introduction of 'replay' command[1]. It receives 'damo record' output and replay the recorded access pattern. Hopefully it will help reproducing the real-world's memory access pattern for analysis and benchmarks. The command is in an experimental level and not formally documented at the moment, though.

[1] https://github.com/awslabs/damo/blob/v2.2.2/release_note#L5

#linux #kernel #damon #damo

I just marked my linux kernel mails management tool as v1 (https://sjp38.github.io/post/hackermail_v1/). I hope it answers the questions on my mails management workflow, better than I did in the past.

#linux #kernel #hackermail

DAMON talk for OSSummit NA 2024 has been accepted and scheduled[1]. The talk will present DAMOS auto-tuning and hopefully, more new DAMO features. The features are still under development, but hopefully, the power of presentation-driven development will make it. ;) Looking forward to meeting you there!

[1] https://sched.co/1aBOg

#ossummit #ossummitna #linux #kernel #damon #damo

[$] A turning point for CVE numbers https://lwn.net/Articles/961978/ #LWN

Linux is now a CNA: http://www.kroah.com/log/blog/2024/02/13/linux-is-a-cna/

This has taken a long time, I'd like to thank all the groups that helped, and especially the CVE group themselves. Our application was a bit different than other groups, but they understood that this is important for security overall.

The kernel becomes its own CNA https://lwn.net/Articles/961961/ #LWN

After about 8 years of progress on my little hobby project[1], the Korean translation of @paulmckrcu 's book, I'm marking it as completed a humble milestone[2]. It was a very fun and informative journey.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/paulmck/perfbook.git/commit/?id=edbfcdee0460
[2] https://lore.kernel.org/perfbook/20240211175355.4986-1-sj38.park@gmail.com/

CFP for LPC 2024 is out!

Please mark your calendar:

Deadline to propose a microconference: April 4, 2024
Deadline to submit talks to LPC Refereed and Kernel Summit track: June 16, 2024

https://lpc.events/event/18/abstracts/

#linuxplumbers

DAMON in Amazon Linux 5.10.y kernel[0] has updated to that of v6.7 Linux kernel. Major updates on this change include

- DAMOS apply target regions tracing[1] and
- Sampling interval granularity monitoring results generation[2] and DAMOS[3].

[0] https://github.com/amazonlinux/linux/tree/amazon-5.10.y/master/mm/damon
[1] https://git.kernel.org/torvalds/c/c603c630b509
[2] https://git.kernel.org/torvalds/c/78fbfb155d20
[3] https://git.kernel.org/torvalds/c/affa87c70818

#linux #kernel #damon

LPC 2024 website is up!
Linux Plumbers Conference 2024 will take place on Wednesday 18th, Thursday 19th and Friday 20th of September. The in-person venue is the Austria Center, Vienna, Austria. Please checkout the website for more details!

https://lpc.events/

#linuxplumbers

Yesterday, I received a newsletter saying Google Bard now supports image creation. So I asked Bard to create some DAMON logo candidates. Bard is not perfect, but draws definitely better than I :)

#linux #kernel #damon

[$] The hard life of a virtual-filesystem developer https://lwn.net/Articles/960088/ #LWN

I also once considered implementing DAMON-dedicated virtual file system, and even made the name: damonfs. I eventually settled on sysfs and now I believe it was a wise decision :)

https://social.kernel.org/notice/AeRckekHQlmmCAohFY

#linux #kernel #damon

LSF/MM/BPF 2024 topic proposal for DAMON has posted: https://lore.kernel.org/linux-mm/20240129204749.68549-1-sj@kernel.org/

Hopefully that will help conference-presentation-driven development of DAMON :)

#linux #kernel #damon #lsfmm

[$] The things nobody wants to pay for https://lwn.net/Articles/959069/ #LWN

After 4 years the strlcpy() API has been fully removed from the Linux kernel. Long live strscpy().
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=d26270061ae66b915138af7cd73ca6f8b85e6b44

Next up, strncpy()!
https://github.com/KSPP/linux/issues/90

Staycation: day five.

Power still off, but outside is warming up. So now it’s a big ice rink outside with people playing bumper cars with the real things.

Not interested in partaking in that particular contact sport, and as a result I’m still not leaving the house even if the worry about frozen pipes is fading.

Instead trying to see how far I can get on the remaining merge window pulls on just battery power. Not very far I bet, but at least something.

PGE claims power back tonight. Of course, they did that yesterday too…

SK Hynix shared[1] their DAMOS-based tiered memory management test results, with patches for that. To quote,

“DAMON 2-tier” memory management reduces the performance slowdown compared to the “default” memory policy from 15~17% to 4~5% when the system runs with high memory pressure on its fast tier DRAM nodes.

[1] https://lore.kernel.org/damon/20240115045253.1775-1-honggyu.kim@sk.com/

#linux #kernel #damon

"In hopes of having a single compressed pages allocator at some point,
and following in the footsteps of SLAB, deprecate z3fold."

Well well, look who's a trendsetter now!
https://lore.kernel.org/all/20240112193103.3798287-1-yosryahmed@google.com/

Day four of no power and no Internet. This big tree is the reason. One among hundreds in the area, but this is the one that took out *our* power and Internet.

PGE (Portland General Electric) claims we should get power back by 10pm today, but the ice storm arrives today, so we'll see.

Edit: well, it looks like PGE fixed the outage by just removing me from the outage database, not by actually reconnecting power. That was the second time that happened, so I re-re-reported the outage. Not that I was hugely optimistic about the 10pm timeframe, but it looks even less likely now.