Date: Mon, 23 Sep 2024 12:42:47 +0000 From: Alexey Sukhoguzov <mail@eseipi.net> To: freebsd-hackers@freebsd.org Subject: Re: nvme(4): some non-operational power states are broken Message-ID: <ZvFh8XfOK07kUrxj@eseipi.net> In-Reply-To: <CANCZdfp0g118BecYsUjXOj1stMURsDfb-OMK7XT=3i=tCQMBtw@mail.gmail.com> References: <ZvE3f_gTC4D6TqBe@eseipi.net> <CANCZdfpv6EbB_HSnZG4Sy4crOJBbX16PGo3iwjCdkBzvTE7SVA@mail.gmail.com> <CANCZdfp0g118BecYsUjXOj1stMURsDfb-OMK7XT=3i=tCQMBtw@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Mon, Sep 23, 2024 at 11:10:15AM +0100, Warner Losh wrote: > Does Linux have active power state management? I didn't know there was such a thing, thanks! I tried to boot with 'pcie_aspm=off' kernel parameter and dmesg said that ASPM was disabled, but I didn't see any difference in terms of temperature or /sys/class/power_supply/BAT0/power_now value, they all are within normal boundaries. > And what's the workload? This machine is my workstation, so I would say there is almost no workload in terms of IO. > What performance are you seeing? I have no other issues with the device, except for power consumption in states 4 and 5. After enabling APST (I patched the kernel for this) and limiting idle transitions to state 3 this problem was mostly resolved as well, but I think it would still be worth finding out what is actually going on. > And what's the reported model number? What form factor? Model number is KXG5AZNV256G, form factor is M.2 2280. If necessary, I can send Identify command output. > We used these at work years ago, but in only one hw spin. For production machines idle power consumption may not be relevant at all, but for a laptop it's a huge difference. And that's a good news if it's just my faulty device and no one else is having the same problem. No additional work is needed then, which is always great :)
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?ZvFh8XfOK07kUrxj>