![linux per-thread kernel stack size linux per-thread kernel stack size](https://www.brendangregg.com/perf_events/perf_events_map.png)
![linux per-thread kernel stack size linux per-thread kernel stack size](https://notes.shichao.io/utlk/figure_3-1.png)
Strong reason not to increase kernel stack size on x86_64, for me not I guess this topic was discussed several time so there might be Of course, it could make false positive but at least, it could make a Toward stack consumption on each kernel functions via stacktrace of ftrace.įor example, we can have a bar like that each funcion shouldn't exceed 200KĪnd emit the warning when some function consumes more in runtime. So, my stupid idea is just let's expand stack size and keep an eye Meanwhile, stack usage on 64bit machine was doubled compared to 32bit Lots of developer start to add nice features which will use stackĪgains) and if we consider another more complex feature in I/O layerĪnd/or reclaim path, it might be better to increase stack size( Stack usage but I'm not sure how long it saves the world(surely, Of course, we might sweep every sites we have found for reducing Overflow by another deeper callstack on reclaim/allocator path.
![linux per-thread kernel stack size linux per-thread kernel stack size](https://imgs.developpaper.com/imgs/2836337812-446e9a287bd38d0a_articlex.png)
So did a hundred of byte but overflow was't disappeard so that I encounter I tried to diet stack size of some functions related with alloc/reclaim When I investigated the problem, the callstack was a little bit deeperīy involve with reclaim functions but not direct reclaim path. While I play inhouse patches with much memory pressure on qemu-kvm,ģ.14 kernel was randomly crashed. Peter Anvin", Ingo Molnar, Peter Zijlstra, Mel Gorman, Rik van Riel, Johannes Weiner, Hugh Dickins, , ,ĝave Hansen, Steven Rostedt, Minchan Kim