Re: timer_bh behaviour incorrect for 2.2.13?

William Montgomery (william@opinicus.com)
Thu, 9 Dec 1999 14:59:25 -0500 (EST)


The patch no longer causes an Oops and it *does* appear to solve
the problem of timer_bh not running, but my task doesnt get switched
in and when pid == 0 I'm not sure what is running.

c010e1ce timer_interrupt +<12/12c> ( 5.74 ) ( 28274.37 ) pid(0)
c011418d do_timer +<d/5c> ( 0.75 ) ( 28280.11 ) pid(0)
c010a109 enable_8259A_irq +<d/3c> ( 0.85 ) ( 28280.86 ) pid(0)
c010a672 do_IRQ +<32/54> ( 0.14 ) ( 28281.71 ) pid(0)
c011b630 do_bottom_half +<10/84> ( 0.16 ) ( 28281.85 ) pid(0)
c010a68d do_IRQ +<4d/54> ( 0.44 ) ( 28282.00 ) pid(0)
c01c4867 tulip_interrupt +<13/450> ( 1.73 ) ( 28282.44 ) pid(0)
c01636ff __kfree_skb +<f/b0> ( 0.24 ) ( 28284.17 ) pid(0)
c0162b2d sock_wfree +<d/2c> ( 0.17 ) ( 28284.41 ) pid(0)
c017085a tcp_write_space +<e/60> ( 0.14 ) ( 28284.58 ) pid(0)
c0113508 __wake_up +<10/58> ( 0.41 ) ( 28284.72 ) pid(0)
c0112e09 wake_up_process +<d/54> ( 0.32 ) ( 28285.14 ) pid(0)
c0112d82 reschedule_idle +<e/88> ( 0.29 ) ( 28285.45 ) pid(0)
c0161301 sock_wake_async +<d/6c> ( 0.34 ) ( 28285.75 ) pid(0)
c01636ae kfree_skbmem +<e/50> ( 0.23 ) ( 28286.09 ) pid(0)
c0123ccb kmem_cache_free +<13/170> ( 1.79 ) ( 28286.32 ) pid(0)
c010a109 enable_8259A_irq +<d/3c> ( 0.86 ) ( 28288.11 ) pid(0)
c010a672 do_IRQ +<32/54> ( 0.14 ) ( 28288.97 ) pid(0)
c011b630 do_bottom_half +<10/84> ( 0.33 ) ( 28289.11 ) pid(0)
c0113e54 timer_bh +<10/33c> ( 0.44 ) ( 28289.44 ) pid(0)
c0113cae update_wall_time +<e/58> ( 0.25 ) ( 28289.88 ) pid(0)
c0113bea update_wall_time_one_tick +<e/c4> ( 0.47 ) ( 28290.13 ) pid(0)
c0113de7 update_process_times +<f/6c> ( 0.19 ) ( 28290.60 ) pid(0)
c0113d08 update_one_process +<10/e0> ( 1.49 ) ( 28290.79 ) pid(0)
c011ab22 it_real_fn +<e/58> ( 0.22 ) ( 28292.28 ) pid(0)
c0111d69 send_sig +<d/2c> ( 0.26 ) ( 28292.50 ) pid(0)
c011180f send_sig_info +<13/28c> ( 0.57 ) ( 28292.76 ) pid(0)
c0111796 ignored_signal +<e/74> ( 0.46 ) ( 28293.33 ) pid(0)
c0112e09 wake_up_process +<d/54> ( 0.25 ) ( 28293.79 ) pid(0)
c0112d82 reschedule_idle +<e/88> ( 0.27 ) ( 28294.04 ) pid(0)
c0112e7a add_timer +<e/190> ( 0.51 ) ( 28294.31 ) pid(0)
c0112e5d process_timeout +<d/1c> ( 0.14 ) ( 28294.82 ) pid(0)
c0112e09 wake_up_process +<d/54> ( 0.25 ) ( 28294.96 ) pid(0)
c0112d82 reschedule_idle +<e/88> ( 0.60 ) ( 28295.21 ) pid(0)
c010a68d do_IRQ +<4d/54> ( 8281.10 ) ( 28295.81 ) pid(0)
^^^^^^^ not sure whats happening here?

c010a64d do_IRQ +<d/54> ( 0.22 ) ( 36576.91 ) pid(0)
c010a1cf do_8259A_IRQ +<13/b4> ( 2.04 ) ( 36577.12 ) pid(0)
c010a4f4 handle_IRQ_event +<10/78> ( 0.20 ) ( 36579.16 ) pid(0)
c010e1ce timer_interrupt +<12/12c> ( 5.66 ) ( 36579.36 ) pid(0)

I am forcing a lot of tcp traffic to trigger this problem.
Does this make sense to anybody?

Wm

-
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/