On 3/18/2024 2:04 PM, Luck, Tony wrote: >>> 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. Perhaps ... in this case it may make things easier to understand if those "mon_NODE_*" directories are sub-directories of the appropriate "mon_L3_*" directories. Reinette
