search for: __enter_scheduler

Hi all, With the new vm-tools we are trying to get top like capabilities going correctly. Currently we have a program vm-list that has some of this capability but is dependent on the cpu time given by libxc calls (xc_get_dom_info & xc_domain_get_cpu_usage). These two functions give you how much time (in nanoseconds, why is this not documented) the domain has been actively used. Approaches:

I''m working on a new hypercall, do_confer, which allows the directed yielding of a vcpu to another vcpu. It is mainly used when a vcpu fails to acquire a spinlock, yielding to the lock holder instead of spinning. I ported the ppc64 spinlock implementation for the i386 linux portion. In implementing the hypercall, I''ve been trying to figure out how to get the scheduler

...n_wake [ domid = 0x00000062, edomid = 0x00000000 ] CPU0 200130258168511 (+ 1309) switch_infprev [ old_domid = 0x00000000, runtime = 31143 ] CPU0 200130258168716 (+ 205) switch_infnext [ new_domid = 0x00000062, time = 786, r_time = 30000000 ] CPU0 200130258169338 (+ 622) __enter_scheduler [ prev<domid:edomid> = 0x00000000 : 0x00000000, next<domid:edomid> = 0x00000062 : 0x00000000 ] CPU0 200130258175532 (+ 6194) VMENTRY [ dom:vcpu = 0x00000062 ] CPU0 200130258179633 (+ 4101) VMEXIT [ dom:vcpu = 0x00000062, exitcode = 0x0000004e, rIP = 0x0000000080a562b...

...vcpu *v) +{ + send_guest_virq(v, VIRQ_TIMER); +} + /* * Local variables: * mode: C diff -r df0ad1c46f10 -r 686cd624618c xen/common/schedule.c --- a/xen/common/schedule.c Thu Mar 9 16:03:23 2006 +0100 +++ b/xen/common/schedule.c Tue Mar 14 14:56:55 2006 -0600 @@ -465,7 +465,7 @@ static void __enter_scheduler(void) { update_dom_time(next); if ( next->sleep_tick != schedule_data[cpu].tick ) - send_guest_virq(next, VIRQ_TIMER); + arch_send_timer_event(next); } TRACE_4D(TRC_SCHED_SWITCH, @@ -501,7 +501,7 @@ static void t_timer_fn(void *unused)...

...eave_kernel+0x0/0x310 >(XEN) sp=f0000000041c76e0 >bsp=f0000000041c0fa0 >(XEN) [<f0000000040375a0>] csched_schedule+0x970/0xf70 >(XEN) sp=f0000000041c78e0 >bsp=f0000000041c0ee0 >(XEN) [<f00000000403f0b0>] __enter_scheduler+0x150/0x6b0 >(XEN) sp=f0000000041c78f0 >bsp=f0000000041c0e60 >(XEN) [<f00000000403f6a0>] do_yield+0x90/0xb0 >(XEN) sp=f0000000041c7910 >bsp=f0000000041c0e48 >(XEN) [<f00000000403f970>] do_sched_op_compat...

Hi all, sorry to intrude on xen-devel, but I think I need direction from the expertise here. I''ve admin''d Xen servers of various flavors for a couple years, but never seen this before. After a period ranging from several hours to several days, my primary database and development DomU completely locks up. Net disconnects, but CPU(sec) continues to tick in xentop. No errors, and

...258,6 +258,32 @@ /* Check for events /after/ blocking: avoids wakeup waiting race. */ if ( event_pending(v) ) + { + clear_bit(_VCPUF_blocked, &v->vcpu_flags); + } + else + { + TRACE_2D(TRC_SCHED_BLOCK, v->domain->domain_id, v->vcpu_id); + __enter_scheduler(); + } +} + +/* + * Block the currently-executing domain without enabling interrupts, for a + * particular evtchn. Whilst we check for a particular evtchn, /any/ event + * will wake us up again. + */ +static long do_block_on(unsigned long evtchn) +{ + struct vcpu *v = current; + + if ( evt...

...hn_pending)) ) goto out; } if ( sched_poll->timeout != 0 ) set_timer(&v->poll_timer, sched_poll->timeout); - TRACE_2D(TRC_SCHED_BLOCK, v->domain->domain_id, v->vcpu_id); + TRACE_2D(TRC_SCHED_BLOCK, d->domain_id, v->vcpu_id); __enter_scheduler(); stop_timer(&v->poll_timer); Index: 2006-10-04/xen/include/Makefile =================================================================== --- 2006-10-04.orig/xen/include/Makefile 2006-10-04 15:10:46.000000000 +0200 +++ 2006-10-04/xen/include/Makefile 2006-10-04 15:11:03.000000000 +020...

...ct schedule_data *sd; struct task_slice next_slice; s32 r_time; /* time for new dom to run */ + int cpu = smp_processor_id(); ASSERT(!in_irq()); ASSERT(this_cpu(mc_state).flags == 0); + + if (rcu_pending(cpu)) + /* since __enter_scheduler is called from softirq context + * we know we are in a quiescent state */ + rcu_check_callbacks(cpu,1); perfc_incrc(sched_run); @@ -649,6 +656,12 @@ static void t_timer_fn(void *unused) static void t_timer_fn(void *unused) { struct vcpu *v = current; + int cpu =...

...ct schedule_data *sd; struct task_slice next_slice; s32 r_time; /* time for new dom to run */ + int cpu = smp_processor_id(); ASSERT(!in_irq()); ASSERT(this_cpu(mc_state).flags == 0); + + if (rcu_pending(cpu)) + /* since __enter_scheduler is called from softirq context + * we know we are in a quiescent state */ + rcu_check_callbacks(cpu,1); perfc_incrc(sched_run); @@ -649,6 +656,12 @@ static void t_timer_fn(void *unused) static void t_timer_fn(void *unused) { struct vcpu *v = current; + int cpu =...

...c55a3f98 00000000 00070000 c01010c7 00000061 00000246 c55a3f84 00000069 (XEN) 0000007b 0000007b 00000000 00000000 00000001 ff21e080 (XEN) Xen call trace: (XEN) [<ff119c79>] update_queues+0x38e/0x41e (XEN) [<ff11a544>] sedf_do_schedule+0x133/0x410 (XEN) [<ff11d69a>] __enter_scheduler+0xe3/0x479 (XEN) [<ff11e63a>] do_softirq+0xa2/0xb7 (XEN) [<ff12d1a2>] idle_loop+0x5d/0x5f -- Ryan Harper Software Engineer; Linux Technology Center IBM Corp., Austin, Tx (512) 838-9253 T/L: 678-9253 ryanh@us.ibm.com diffstat output: a/tools/xm-test/tests/sedf/01_sedf_multi_...

We (Michael Fetterman, George Dunlap and I) have been working over the last while on a full replacement for Xen''s shadow pagetable support. This mail contains some design notes, below; a patch against xen-unstable, giving a snapshot of the current state of the new shadow code, is at http://www.cl.cam.ac.uk/~tjd21/shadow2.patch Comments on both are welcome, although the code is not