lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [day] [month] [year] [list]
Message-ID: <294a5a56-e5cc-44c2-841b-25ef73560223@criteo.com>
Date: Tue, 13 May 2025 15:14:15 +0200
From: Erwan Velu <e.velu@...teo.com>
To: patryk.wlazlyn@...ux.intel.com, len.brown@...el.com
Cc: linux-kernel@...r.kernel.org
Subject: Turbostat is duplicating pkgwatt on dual socket with perf mode
 enabled

Hi,

I'm currently testing some dual socket AMD servers and found that 
Turbostat is duplicating the pkgwatt when Perf API is used.

I'm loading only one of the two packages and they both report the same 
pkgwatt which is incorrect according to the raw value reported by the 
SMI interface.

If I'm adding "--no-perf" the pkgwatt gets the proper value.


I wonder if you have some hints on where the issue could be in the 
turbostat code ?

I can make a patch and/or test some if you have hints on a possible reason.


Erwan,


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ