Re: [patch] Re: setitimer lowlatency-2.2.13-A1 questions

William Montgomery (william@opinicus.com)
Tue, 7 Dec 1999 09:25:18 -0500 (EST)

I installed the first patch to enable_bh yesterday a few minutes
after I received it, it ran fine for about an hour. Then I got the
email from Andrea with a conceptually safer patch, which I also installed.
It ran fine all afternoon, no problems. I let it run all night
and this morning I found my kernel trace triggered on a similar
problem (maybe the same one). It appears that irq must have
been disabled when enable_bh was called because it seems that the timer_bh
did not run when it should have:

33285.97 0.37 do_IRQ pid(189)
33286.34 2.01 do_8259A_IRQ pid(189)
33288.36 0.33 handle_IRQ_event pid(189)
33288.68 5.79 timer_interrupt pid(189)
33294.48 0.72 do_timer pid(189)
33295.20 0.81 enable_8259A_irq pid(189)
33296.01 0.14 do_IRQ pid(189)
33296.15 0.20 do_bottom_half pid(189)
33296.34 0.69 do_IRQ pid(189)
33297.03 0.14 tcp_write_space pid(189)
33297.17 0.20 __wake_up pid(189)
33297.37 0.30 sock_wake_async pid(189)
33297.68 0.39 kfree_skbmem pid(189)
33298.07 0.99 kfree pid(189)
33299.06 0.73 kmem_cache_free pid(189)
33299.79 0.29 __kfree_skb pid(189)
33300.08 0.13 sock_wfree pid(189)
.
. --- a few more tcp_write_space sequences
.
33311.52 0.14 tcp_write_space pid(189)
33311.66 0.16 __wake_up pid(189)
33311.82 0.27 sock_wake_async pid(189)
33312.09 0.31 kfree_skbmem pid(189)
33312.40 0.81 kfree pid(189)
33313.21 1.35 kmem_cache_free pid(189)
33314.56 0.69 del_timer pid(189)
33315.25 0.22 __kfree_skb pid(189)
33315.47 0.26 sock_rfree pid(189)
33315.73 0.16 kfree_skbmem pid(189)
33315.90 0.54 kfree pid(189)
33316.43 1.18 kmem_cache_free pid(189)
33317.61 2516.13 do_IRQ pid(189)
35833.75 0.66 system_call pid(189)
35834.41 0.62 sys_sigsuspend pid(189)
35835.03 0.80 schedule pid(189)
35835.82 0.44 do_bottom_half pid(189)
35836.26 0.52 timer_bh pid(189)

I'll try to reproduce and put in a printk to verify.
Is it *always* unsafe to do_bottom_half in enable_bh when irq disabled
or does that only apply to the SMP case?

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/