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>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Mon, 18 Mar 2024 21:04:14 +0000
From: "Luck, Tony" <tony.luck@...el.com>
To: "Chatre, Reinette" <reinette.chatre@...el.com>, James Morse
	<james.morse@....com>
CC: "Wieczor-Retman, Maciej" <maciej.wieczor-retman@...el.com>, "Yu, Fenghua"
	<fenghua.yu@...el.com>, Shuah Khan <shuah@...nel.org>,
	"ilpo.jarvinen@...ux.intel.com" <ilpo.jarvinen@...ux.intel.com>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"linux-kselftest@...r.kernel.org" <linux-kselftest@...r.kernel.org>
Subject: RE: [PATCH 4/4] selftests/resctrl: Adjust SNC support messages

> > What is the use case for needing to expose the individual cluster counts? What if
> > resctrl just summed the cluster counts and presented the data as before - per L3
> > cache instance? I doubt that resctrl would be what applications would use to verify
> > whether they are "well behaved" wrt NUMA.
>
> Reinette,
>
> My (perhaps naïve) belief is that in a cloud server environment there are many
> well behaved NUMA applications. Only presenting the sum would lose the detailed
> information from each SNC node.

Is the answer to "A" or "B" ... why not provide both:

$ ls -l /sys/fs/resctrl/mon_data
total 0
dr-xr-xr-x. 2 root root 0 Mar 18 14:01 mon_L3_00
dr-xr-xr-x. 2 root root 0 Mar 18 14:01 mon_L3_01
dr-xr-xr-x. 2 root root 0 Mar 18 14:01 mon_NODE_00
dr-xr-xr-x. 2 root root 0 Mar 18 14:01 mon_NODE_01
dr-xr-xr-x. 2 root root 0 Mar 18 14:01 mon_NODE_02
dr-xr-xr-x. 2 root root 0 Mar 18 14:01 mon_NODE_03

The "L3" entries provide the sum across all SNC nodes sharing the cache. The NODE ones
give the broken out counts.

-Tony

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ