Hi,
I'm running linux-2.2.15pre4 with Rik's VM fix and get messages
gfp called by non-running (1) task from c011e896!
Output of grep c011e /System.map gives
nc14$ grep -i c011e /System.map
c011e254 t put_page
c011e27c T put_dirty_page
c011e400 t do_wp_page
c011e600 t partial_clear
c011e6b8 T vmtruncate
c011e79c t do_swap_page
c011e868 t do_anonymous_page
c011e8ec t do_no_page
c011e9e0 T handle_mm_fault
c011ebac T make_pages_present
c011ec0c T vm_enough_memory
c011ec8c T sys_brk
c011edac T do_mmap
This gfp stuff occures pretty much as soon as the machine boots and starts to
handle any network traffic.
I had wondered if this particular VM problem might explain why under high
network traffic, CPU load, (and swapping) machines would go into infinite loops
of network hangs, where sysrq's show repeated buffer allocation failures. I'm
running some destruction tests now to see if I still get this hangup under the
new code.
Mark
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Mon Jan 31 2000 - 21:00:18 EST