[EMAIL PROTECTED] wrote: > > > > > > The are some long delays (approx. 40 secs) around __alloc_pages. > > > Finally it crashes in memset. With the attached xenomai > > patch, which > > > touches the reserved page once, memset works fine. Let's wait what > > > Philippe says. I remember that the "touch" was needed for > > RTAI shared memory as well. > > > > What is the difference between touching the page in kernel > > space and in user space? Is there no risk that the kernel > > will oops then at some point? Do we get the same result when > > touching the heap pages in user space immediately after > > rt_help_alloc'ing them? Roderik's demo allocates first and > > then touches/memsets. [I have no problem with the patch, I'm > > just trying to understand the mechanism.] > > > > Presumed that touch means "use it" (=memset) I tried to allocate a block > > and immediatelly use it (use memset before new heap is created). > But this causes a segmentation fault too. > Inspired by Gilles I set /proc/sys/vm/overcommit_memory to 2, which > worsens > the task behaviour (it crashes every time, not just some times). > Do you have any further suggestions ?
Maybe the task is in fact killed by the OOM killer ? It would prove that this function is working correctly, since the killed task is the one that allocates all the memory. Is there no trace in the logs ? -- Gilles Chanteperdrix. _______________________________________________ Xenomai-help mailing list Xenomai-help@gna.org https://mail.gna.org/listinfo/xenomai-help