Messages in this thread | | | From | Yury Norov <> | Date | Wed, 6 Jan 2021 13:16:50 -0800 | Subject | Re: [PATCH RFC cpumask 4/5] cpumask: Add "last" alias for cpu list specifications |
| |
On Wed, Jan 6, 2021 at 1:50 AM Peter Zijlstra <peterz@infradead.org> wrote: > > On Tue, Jan 05, 2021 at 04:49:55PM -0800, paulmck@kernel.org wrote: > > From: Paul Gortmaker <paul.gortmaker@windriver.com> > > > > It seems that a common configuration is to use the 1st couple cores > > for housekeeping tasks, and or driving a busy peripheral that generates > > a lot of interrupts, or something similar. > > > > This tends to leave the remaining ones to form a pool of similarly > > configured cores to take on the real workload of interest to the user. > > > > So on machine A - with 32 cores, it could be 0-3 for "system" and then > > 4-31 being used in boot args like nohz_full=, or rcu_nocbs= as part of > > setting up the worker pool of CPUs. > > > > But then newer machine B is added, and it has 48 cores, and so while > > the 0-3 part remains unchanged, the pool setup cpu list becomes 4-47. > > > > Deployment would be easier if we could just simply replace 31 and 47 > > with "last" and let the system substitute in the actual number at boot; > > a number that it knows better than we do. > > > > No need to have custom boot args per node, no need to do a trial boot > > in order to snoop /proc/cpuinfo and/or /sys/devices/system/cpu - no > > more fencepost errors of using 32 and 48 instead of 31 and 47. > > > > A generic token replacement is used to substitute "last" with the > > number of CPUs present before handing off to bitmap processing. But > > it could just as easily be used to replace any placeholder token with > > any other token or value only known at/after boot. > > Aside from the comments Yury made, on how all this is better in > bitmap_parselist(), how about doing s/last/N/ here? For me something > like: "4-N" reads much saner than "4-last". > > Also, it might make sense to teach all this about core/node topology, > but that's going to be messy. Imagine something like "Core1-CoreN" or > "Nore1-NodeN" to mean the mask all/{Core,Node}0.
If you just want to teach bitmap_parselist() to "s/Core0/0-4", I think it's doable if we add a hook to a proper subsystem in bitmap_parselist().
> And that is another feature that seems to be missing from parselist, > all/except.
We already support groups in a range. I think it partially covers the proposed all/except.
Can you share examples on what you miss?
| |