Messages in this thread | | | From | Valentin Schneider <> | Subject | Re: [PATCH v2 2/9] sched/debug: Make sd->flags sysctl read-only | Date | Thu, 19 Mar 2020 12:04:56 +0000 |
| |
On Thu, Mar 19 2020, Dietmar Eggemann wrote: > On 11.03.20 19:15, Valentin Schneider wrote: >> Writing to the sysctl of a sched_domain->flags directly updates the value of >> the field, and goes nowhere near update_top_cache_domain(). This means that >> the cached domain pointers can end up containing stale data (e.g. the >> domain pointed to doesn't have the relevant flag set anymore). >> >> Explicit domain walks that check for flags will be affected by >> the write, but this won't be in sync with the cached pointers which will >> still point to the domains that were cached at the last sched_domain >> build. >> >> In other words, writing to this interface is playing a dangerous game. It >> could be made to trigger an update of the cached sched_domain pointers when >> written to, but this does not seem to be worth the trouble. Make it >> read-only. > > As long as I don't change SD flags for which cached SD pointers exist > (SD_SHARE_PKG_RESOURCES, SD_NUMA, SD_ASYM_PACKING or > SD_ASYM_CPUCAPACITY) the write-able interface still could make some sense. > > E.g. by enabling SD_BALANCE_WAKE on the fly, I can force !want_affine > wakees into slow path. >
True, although since there is no explicit differenciation between the cached and !cached flags, this is still a landmined interface.
> The question is, do people use the writable flags interface to tweak > select_task_rq_fair() behavior in this regard?
I did try asking around on IRC (which admittedly is just a small subset of people) but didn't find anyone.
| |