search for: runqueue

Hi, This patch intends to accurate vcpu weighting for CPU intensive job. The reason of this problem is that vcpu round-robin queue blocks large weight vcpus by small weight vcpus. For example, we assume following case on 2pcpu environment. (with 4domains (each domain has 2vcpus)) dom1 vcpu0,1 w128 credit 4 dom2 vcpu0,1 w128 credit 4 dom3 vcpu0,1 w256 credit 8 dom4 vcpu0,1 w512 credit 15

...ing to figure out how to get the scheduler (I''ve only played with bvt) to run the vcpu passed in the hypercall (after some validation) but I''ve run into various bad state situations (do_softirq pending != 0 assert, ''!active_ac_timer(timer)'' failed , and __task_on_runqueue(prev) failed) which tells me I don''t fully understand all of the book-keeping that is needed. Has anyone thought about how to do this with either BVT or the new EDF scheduler? -- Ryan Harper Software Engineer; Linux Technology Center IBM Corp., Austin, Tx (512) 838-9253 T/L: 678-9253...

Address some credit2 issues. This patch series, along with the recent changes to the cpupools interface, should address some of the strange credit2 instability. _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

This patch implements cpu offline feature. Best Regards Haitao Shan _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel

Hi gang! At work I have a DL320 G2 machine I use as my desktop (I know, weird!...). Back when I ran RHEL WS 2.1 on it, it always ran a SMP kernel because it has a HypterThread capable processor. When I installed (fresh from scratch) Centos 4.4 on it a while back, though, Centos installed only the UP kernel. I've looked in the BIOS for settings to enable/disable HT support and I don't

...reached, kjournald shows D state for several seconds. During that same time, block-out "bo" in vmstat consistently shows 0. kjournald is choking. Or something. Also, this appears to get a lot of processes looping on write somewhere in the webserver. Looping on the lockfile, maybe? The runqueue gets huge > 40 often , and apache spirals up to all 75 processes in use. These pauses seem to occur at pretty exact intervals. Something like every 240 seconds. With the disk in question mounted as ext2 I don't get the issue. At all. The disk is IDE, but fairly fast, and we're using...

...better power saving ability with negligible performance impact, following areas may be tweaked and listed here for comments first. Goal is not to silly save power with sacrifice of performance, e.g. we don''t want to prevent migration when there''re free cpus with some pending runqueues. But when free computing power is more than existing requirement, power aware policy can be pushed to choose a less power-intrusive decision. Of course even in latter case, it''s controllable with a scheduler parameter like csched_private.power and exposed to user. ---- a) when there...

...question regarding this - 1. I understand that a guest VM can use the above function with "yield", in order to relinquish CPU time to other guests with running tasks. a) So when the guest VM makes this call does it save/persist any scheduling information about its current processes like runqueue, process state - runnable, ready etc ? If it does can someone point to the code I can look at. c) When yielded guest VM is scheduled back by the hypervisor, does it uses the previous state of the processes which were yielded ? 2. Is there a way in which the Hypervisor_sched_op call can be made fr...

...question regarding this - 1. I understand that a guest VM can use the above function with "yield", in order to relinquish CPU time to other guests with running tasks. a) So when the guest VM makes this call does it save/persist any scheduling information about its current processes like runqueue, process state - runnable, ready etc ? If it does can someone point to the code I can look at. c) When yielded guest VM is scheduled back by the hypervisor, does it uses the previous state of the processes which were yielded ? 2. Is there a way in which the Hypervisor_sched_op call can be made fr...

As discussed in a previous e-mail, this patch series implements yield for the credit scheduler. This allows a VM to actually yield (give up the cpu to another VM) when it wants to. This has been shown to be effective when used in the spinlock code to avoid wasting time spinning when another vcpu is not currently scheduled. _______________________________________________ Xen-devel mailing list

...+++ b/xen/common/sched_credit2.c @@ -1544,31 +1544,24 @@ csched_runtime(const struct scheduler *ops, int cpu, struct csched_vcpu *snext) } } - /* - * snext is about to be scheduled; so: - * - * 1. if snext->credit were less than 0 when it was taken off the - * runqueue, then csched_schedule() should have called - * reset_credit(). So at this point snext->credit must be greater - * than 0. - * - * 2. snext''s credit must be greater than or equal to anyone else - * in the queue, so snext->credit - swait->credit must be greater...

I am seeing a problem with Dom0 crashing on x86_64 whenever I create a DomU. I''ve done some more testing, and it appears that this problem is somehow related to networking. Dom0 crashes as soon as the networking services are started when DomU is coming up. As an experiment, I brought up DomU without networking, and it stayed up. As soon as I started DomU with networking enabled, however,

After updating a very old x86_64 3.x install to 3.8 it still has kernel-2.4.21-27.0.2.EL. Then if I repeat the yum update command, it offers to install kernel 2.4.21-47.EL.ia32e. Neither of these situations seems quite right. -- Les Mikesell lesmikesell at gmail.com

...en as a host and with 3.2 and 3.5 kernels as guests. The pv spinlock assumption I will try to get re-verified by asking to reproduce under a real load with a kernel that just disables that. However, the dumps I am looking at really do look odd there. The first dump I looked at had the spinlock of runqueue[0] being placed into the per-cpu lock_spinners variable for cpu#0 and cpu#7 (doing my tests with 8 VCPUs). So apparently both cpus were waiting on the slow path for it to become free. Though actually it was free! Now, here is one issue I have in understanding the dump: the back traces produced in c...

Hello all, We are working on a new project idea for xen platform. I have summarized as well as given detailed description of what we are trying to achieve. I request your comments on the feasibility of this project. Also I have pointed some relevant works which I feel is primitive considering the goal we are trying to achieve. I request to point me to relevant links if there are any other works

....... host bus clock speed is 200.4673 MHz. cpu: 0, clocks: 2004673, slice: 668224 CPU0<T0:2004672,T1:1336448,D:0,S:668224,C:2004673> cpu: 1, clocks: 2004673, slice: 668224 CPU1<T0:2004672,T1:668224,D:0,S:668224,C:2004673> cpu_sibling_map[0] = 1 cpu_sibling_map[1] = 0 mapping CPU#0's runqueue to CPU#1's runqueue. zapping low mappings. Process timing init...done. Starting migration thread for cpu 0 Starting migration thread for cpu 1 PCI: PCI BIOS revision 2.10 entry at 0xfb010, last bus=1 PCI: Using configuration type 1 PCI: Probing PCI hardware PCI: Ignoring BAR0-3 of IDE controlle...

...ly(current->kmap_ctrl.idx)) + __kmap_local_sched_out(); +#endif +} + +static inline void kmap_local_sched_in(void) +{ +#ifdef CONFIG_KMAP_LOCAL + if (unlikely(current->kmap_ctrl.idx)) + __kmap_local_sched_in(); +#endif +} + /** * prepare_task_switch - prepare to switch tasks * @rq: the runqueue preparing to switch @@ -4075,6 +4091,7 @@ prepare_task_switch(struct rq *rq, struc perf_event_task_sched_out(prev, next); rseq_preempt(prev); fire_sched_out_preempt_notifiers(prev, next); + kmap_local_sched_out(); prepare_task(next); prepare_arch_switch(next); } @@ -4141,6 +4158,7 @@ sta...

...t blocked, dieing,...). The first element + * on this list is running on the processor, if the list is empty the idle + * task will run. As we are implementing EDF, this list is sorted by deadlines. */ DOMAIN_COMPARER(runq, list, d1->deadl_abs, d2->deadl_abs); static inline void __add_to_runqueue_sort(struct vcpu *v) { - PRINT(3,"Adding domain %i.%i (deadl= %"PRIu64") to runq\n", - v->domain->domain_id, v->vcpu_id, EDOM_INFO(v)->deadl_abs); list_insert_sort(RUNQ(v->processor), LIST(v), runq_comp); } @@ -445,22 +401,21 @@ static int sed...

Hi all, I am having confusion regarding the way a newly created domain is allocated vcpu. Initially during dom0 creation alloc_vcpu is called to create vcpu structs for all the available cpu''s and assigned to dom0. But its not the case for domU creation. 1. So how will dom0 relinquish/share vcpu to/with a newly created domU. Does this happen as part of the shared_info page mapping??

..._run_job_work(struct work_struct *w) * drm_sched_init - Init a gpu scheduler instance * * @sched: scheduler instance - * @ops: backend operations for this scheduler - * @submit_wq: workqueue to use for submission. If NULL, an ordered wq is - * allocated and used - * @num_rqs: number of runqueues, one for each priority, up to DRM_SCHED_PRIORITY_COUNT - * @credit_limit: the number of credits this scheduler can hold from all jobs - * @hang_limit: number of times to allow a job to hang before dropping it - * @timeout: timeout value in jiffies for the scheduler - * @timeout_wq: workqueue to us...