Ryan Harper
2005-Jan-14 17:01 UTC
[Xen-devel] xen-unstable dom0/1 smp schedule while atomic
While running xen-unstable (2005-01-13 nightly) with dom0 and dom1 with CONFIG_SMP=y I got 271k of output... sshd was running in dom0 and I remotely initiated an scp from dom0 to another remote host (not dom1) Ill only post the first and last few "scheduling while atomic" entries, let me know if someone wants the whole trace. scheduling while atomic [schedule+1682/1696] schedule+0x692/0x6a0 [sys_read+126/128] sys_read+0x7e/0x80 [work_resched+5/47] work_resched+0x5/0x2f scheduling while atomic [schedule+1682/1696] schedule+0x692/0x6a0 [sys_read+126/128] sys_read+0x7e/0x80 [work_resched+5/47] work_resched+0x5/0x2f scheduling while atomic [schedule+1682/1696] schedule+0x692/0x6a0 [do_softirq+155/160] do_softirq+0x9b/0xa0 [irq_exit+57/64] irq_exit+0x39/0x40 [do_IRQ+34/48] do_IRQ+0x22/0x30 [evtchn_do_upcall+190/320] evtchn_do_upcall+0xbe/0x140 [work_resched+5/47] work_resched+0x5/0x2f scheduling while atomic [schedule+1682/1696] schedule+0x692/0x6a0 [do_softirq+155/160] do_softirq+0x9b/0xa0 [irq_exit+57/64] irq_exit+0x39/0x40 [do_IRQ+34/48] do_IRQ+0x22/0x30 [evtchn_do_upcall+190/320] evtchn_do_upcall+0xbe/0x140 [work_resched+5/47] work_resched+0x5/0x2f <snip> scheduling while atomic [schedule+1682/1696] schedule+0x692/0x6a0 [__change_page_attr+203/624] __change_page_attr+0xcb/0x270 [sys_sched_yield+89/112] sys_sched_yield+0x59/0x70 [coredump_wait+63/176] coredump_wait+0x3f/0xb0 [do_coredump+222/471] do_coredump+0xde/0x1d7 [__dequeue_signal+296/432] __dequeue_signal+0x128/0x1b0 [__dequeue_signal+245/432] __dequeue_signal+0xf5/0x1b0 [dequeue_signal+53/160] dequeue_signal+0x35/0xa0 [get_signal_to_deliver+599/848] get_signal_to_deliver+0x257/0x350 [do_signal+103/288] do_signal+0x67/0x120 [dnotify_parent+58/176] dnotify_parent+0x3a/0xb0 [vfs_read+210/304] vfs_read+0xd2/0x130 [fget_light+130/144] fget_light+0x82/0x90 [sys_read+126/128] sys_read+0x7e/0x80 [do_notify_resume+55/60] do_notify_resume+0x37/0x3c [work_notifysig+19/24] work_notifysig+0x13/0x18 scheduling while atomic [schedule+1682/1696] schedule+0x692/0x6a0 [wake_up_state+24/32] wake_up_state+0x18/0x20 [wait_for_completion+148/224] wait_for_completion+0x94/0xe0 [default_wake_function+0/32] default_wake_function+0x0/0x20 [force_sig_specific+99/144] force_sig_specific+0x63/0x90 [default_wake_function+0/32] default_wake_function+0x0/0x20 [zap_threads+92/160] zap_threads+0x5c/0xa0 [coredump_wait+169/176] coredump_wait+0xa9/0xb0 [do_coredump+222/471] do_coredump+0xde/0x1d7 [__dequeue_signal+296/432] __dequeue_signal+0x128/0x1b0 [__dequeue_signal+245/432] __dequeue_signal+0xf5/0x1b0 [dequeue_signal+53/160] dequeue_signal+0x35/0xa0 [get_signal_to_deliver+599/848] get_signal_to_deliver+0x257/0x350 [do_signal+103/288] do_signal+0x67/0x120 [dnotify_parent+58/176] dnotify_parent+0x3a/0xb0 [vfs_read+210/304] vfs_read+0xd2/0x130 [fget_light+130/144] fget_light+0x82/0x90 [sys_read+126/128] sys_read+0x7e/0x80 [do_notify_resume+55/60] do_notify_resume+0x37/0x3c [work_notifysig+19/24] work_notifysig+0x13/0x18 note: sshd[20450] exited with preempt_count 1 Ryan Harper ------------------------------------------------------- The SF.Net email is sponsored by: Beat the post-holiday blues Get a FREE limited edition SourceForge.net t-shirt from ThinkGeek. It''s fun and FREE -- well, almost....http://www.thinkgeek.com/sfshirt _______________________________________________ Xen-devel mailing list Xen-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/xen-devel
Christian Limpach
2005-Jan-17 21:44 UTC
Re: [Xen-devel] xen-unstable dom0/1 smp schedule while atomic
On Fri, Jan 14, 2005 at 11:01:37AM -0600, Ryan Harper wrote:> While running xen-unstable (2005-01-13 nightly) with dom0 and dom1 with > CONFIG_SMP=y I got 271k of output... sshd was running in dom0 and I remotely > initiated an scp from dom0 to another remote host (not dom1) Ill only post the > first and last few "scheduling while atomic" entries, let me know if someone > wants the whole trace.It looks like I forgot to push my final change to the fixup code out to the unstable tree. It''s pushed now. christian ------------------------------------------------------- The SF.Net email is sponsored by: Beat the post-holiday blues Get a FREE limited edition SourceForge.net t-shirt from ThinkGeek. It''s fun and FREE -- well, almost....http://www.thinkgeek.com/sfshirt _______________________________________________ Xen-devel mailing list Xen-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/xen-devel