Open Stack

On Thu, 2016-08-25 at 14:11 +0400, Fawaz Mohammed wrote:
> Have you enabled huge page on the host level?
> Do you have enough vn.nr_hugepages?
> As per your requirements, you need a host with 512 hugepage (1G/2M).
> Check your host's /etc/sysctl.conf file and see vm.nr_hugepages
> value.

As a more immediate test, you can unset the 'hw:mem_page_size'
parameter and see if it boots. If it does, it's the hugepages as
suggested above.

Stephen

> On Aug 25, 2016 1:15 PM, "zhi" <changzhi1990 at gmail.com> wrote:
> > hi, all
> > 
> >     I plan to create VM with huge page. And I created a new flavor
> > like this:
> > 
> > $ nova flavor-show ed8dccd2-adbe-44ee-9e4f-391d045d3653
> > +----------------------------+-------------------------------------
> > -----------------------------------------------------------------
> > -------+
> > | Property                   | Value                              
> >                                                                    
> >     |
> > +----------------------------+-------------------------------------
> > -----------------------------------------------------------------
> > -------+
> > | OS-FLV-DISABLED:disabled   | False                              
> >                                                                    
> >     |
> > | OS-FLV-EXT-DATA:ephemeral  | 0                                  
> >                                                                    
> >     |
> > | disk                       | 30                                  
> >                                                                    
> >    |
> > | extra_specs                |
> > {"aggregate_instance_extra_specs:pinned": "true", "hw:cpu_policy":
> > "dedicated", "hw:mem_page_size": "2048"} |
> > | id                         | ed8dccd2-adbe-44ee-9e4f-391d045d3653 
> >                                                                    
> >    |
> > | name                       | m1.vm_2                            
> >                                                                    
> >     |
> > | os-flavor-access:is_public | True                                
> >                                                                    
> >    |
> > | ram                        | 1024                                
> >                                                                    
> >    |
> > | rxtx_factor                | 1.0                                
> >                                                                    
> >     |
> > | swap                       |                                    
> >                                                                    
> >     |
> > | vcpus                      | 4                                  
> >                                                                    
> >     |
> > +----------------------------+-------------------------------------
> > -----------------------------------------------------------------
> > -------+
> > 
> > Then I create a VM by using this flavor and creating fail. The
> > error message is :
> > "
> > {"message": "Build of instance ada7ac22-1052-44e1-b4a5-c21221dbab87 
> > was re-scheduled: Insufficient compute resources: Requested
> > instance NUMA topology cannot fit the given
> >  host NUMA topology.", "code": 500, "details": "  File
> > \"/usr/lib/python2.7/site-packages/nova/compute/manager.py\", line
> > 1905, in _do_build_and_run_instance
> > "
> > 
> > And, my compute node's numa info is:
> > 
> > $ numactl --hardware
> > available: 2 nodes (0-1)
> > node 0 cpus: 0 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38
> > node 0 size: 32543 MB
> > node 0 free: 28307 MB
> > node 1 cpus: 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39
> > node 1 size: 32768 MB
> > node 1 free: 29970 MB
> > node distances:
> > node   0   1
> >   0:  10  21
> >   1:  21  10
> > 
> > Qemu version is "QEMU emulator version 2.1.2 (qemu-kvm-ev-2.1.2-
> > 23.el7.1)". And libvirtd version is "1.2.17". 
> > 
> > 
> > Did anyone meet the same error like me?
> > 
> > 
> > 
> > B.R.
> > 
> > ___________________________________________________________________
> > _______
> > OpenStack Development Mailing List (not for usage questions)
> > Unsubscribe: OpenStack-dev-request at lists.openstack.org?subject:unsu
> > bscribe
> > http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev
> > 
> _____________________________________________________________________
> _____
> OpenStack Development Mailing List (not for usage questions)
> Unsubscribe: OpenStack-dev-request at lists.openstack.org?subject:unsubs
> cribe
> http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev