search for: upcall_pend

I am currently looking at a bug report[1] which is happening when a Xen PVM guest with multiple VCPUs is running a high IO database load (a test script is available in the bug report). In experimenting it seems that this happens (or is getting more likely) when the number of VCPUs is 8 or higher (though I have not tried 6, only 2 and 4), having autogroup enabled seems to make it more likely, too

...n case any other notifications * are pending. */ - if ( d->shared_info->evtchn_pending[port/BITS_PER_LONG] ) - set_bit(port/BITS_PER_LONG, &v->vcpu_info->evtchn_pending_sel); - if ( v->vcpu_info->evtchn_pending_sel ) - v->vcpu_info->evtchn_upcall_pending = 1; + set_bit(port/BITS_PER_LONG, &v->vcpu_info->evtchn_pending_sel); + v->vcpu_info->evtchn_upcall_pending = 1; } void hvm_safe_block(void) @@ -735,12 +733,15 @@ for ( ; ; ) { /* Clear master flag & selector flag so we will wake from block. */ -...

...f=e8000002 (XEN) XenPage 00000bec: caf=80000001, taf=e8000001 (XEN) XenPage 00000beb: caf=80000001, taf=e8000001 (XEN) XenPage 00000bea: caf=80000001, taf=e8000001 (XEN) XenPage 00000be9: caf=80000002, taf=e8000002 (XEN) VCPU information and callbacks for domain 0: (XEN) VCPU0: CPU0 [has=T] flags=0 upcall_pend = 00, upcall_mask = 00 dirty_cpus={0} cpu_affinity={0} (XEN) 100 Hz periodic timer (period 10 ms) (XEN) Notifying guest (virq 1, port 0, stat 0/-1/0) (XEN) VCPU1: CPU1 [has=F] flags=2 upcall_pend = 00, upcall_mask = 01 dirty_cpus={} cpu_affinity={0-31} (XEN) 100 Hz periodic timer (period 10 ms) (XE...

...K. Without pinning the VCPU performance is an even worse 2.67GB/sec. Is there likely something wrong with my NUMA config? Anyone have any benchmark results to share on Barcelona with HAP enabled? Do I need to pin Dom0 to a particular CPU? HAP looks OK: (XEN) VCPU0: CPU4 [has=F] flags=1 upcall_pend = 00, upcall_mask = 00 dirty_cpus={4} cpu_affinity={4} (XEN) paging assistance: hap, 4 levels NUMA looks OK: nr_cpus : 8 nr_nodes : 2 cores_per_socket : 4 threads_per_core : 1 cpu_mhz : 2000 Thanks in advance, Rob The S...

The patch ''mem_event: use wait queue when ring is full'' I just sent out makes use of the waitqueue feature. There are two issues I get with the change applied: I think I got the logic right, and in my testing vcpu->pause_count drops to zero in p2m_mem_paging_resume(). But for some reason the vcpu does not make progress after the first wakeup. In my debugging there is one

Hello, I''m trying to get PDB working in accordance with the instructions at http://www.cl.cam.ac.uk/~sos22/replay.bk/docs/misc/XenDebugger-HOWTO and a message from this list: http://lists.xensource.com/archives/html/xen-devel/2004-08/msg00017.html When I try to build pdb I first get errors because the Makefile is configured to treat warnings as errors, and there are some warnings.