From: Farley Flud <ff@linux.rocks>
Subject: Kernel 6.13 Changes
Newsgroups: comp.os.linux.advocacy
Mime-Version: 1.0
Message-Id: <pan$373b6$c793bb3$bc06d097$8017066b@linux.rocks>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Lines: 39
Path: ...!eternal-september.org!feeder3.eternal-september.org!usenet.blueworldhosting.com!diablo1.usenet.blueworldhosting.com!feeder.usenetexpress.com!tr1.iad1.usenetexpress.com!news.usenetexpress.com!not-for-mail
Date: Sat, 25 Jan 2025 12:45:55 +0000
Nntp-Posting-Date: Sat, 25 Jan 2025 12:45:55 +0000
X-Received-Bytes: 1701
Organization: UsenetExpress - www.usenetexpress.com
X-Complaints-To: abuse@usenetexpress.com
Bytes: 2035

For the builders, here are some goodies I found in the latest
kernel 6.13:

**Preemption Model
  1. No Forced Preemption (Server) (PREEMPT_NONE)
> 2. Voluntary Kernel Preemption (Desktop) (PREEMPT_VOLUNTARY)
  3. Preemptible Kernel (Low-Latency Desktop) (PREEMPT)
  4. Scheduler controlled preemption model (PREEMPT_LAZY) (NEW)
choice[1-4?]: 4

Yes, definitely select #4, or lazy preemption.

**Enable RCU priority boosting (RCU_BOOST) [N/y/?] (NEW) ?

I'm not sure about this, but the help says to enable if
using RT or heavy loads.  I'll pick "no" which is the default.

**Split Lock Detect and Bus Lock Detect support (X86_BUS_LOCK_DETECT) [Y/n/?] (NEW) ?

Definitely say "yes" to this.  In the event that this occurs it
will improve performance.  Read the docs for more info.

**TLP Processing Hints (PCIE_TPH) [N/y/?] (NEW) ?

I believe that this is AMD specific.  Since I don't use that AMD
junk I say "no."  But it doesn't really matter since this option
is only for PCIe 5th Gen and I don't have that.

**PCIe cooling support (PCIE_THERMAL) [N/y/?] (NEW) ?

My systems are so efficiently cooled that nothing ever rises
far above ambient, so "no."

That's all for this iteration.



-- 
Systemd: solving all the problems that you never knew you had.