fsdfs

Author: Elena Crenguta Lindqvist

itnot/index.html

@@ -108,7 +108,6 @@
 <!––  SlideX ––>
                                 <section> 									
 <p><b>88%</b> increase in mobile data traffic  Q4-2017 to Q4-2018</p>
-<p><b>88%</b> increase in mobile data traffic  Q4-2017 to Q4-2018</p>
 <p><b>EPC</b> to the rescue</p>										 
                                         <aside class="notes">                                      
 
@@ -171,37 +170,14 @@
 					                                         </tr>
 
                                         <aside class="notes">
-Is it a bird? is it a plane? It's SmartNIC !
-
 How should your architecture look like when using smartNICs.
-
-You could use one smartNIC for data per compute, we're tal
-I was able to reach the new vnic from one of the computes.
-This is what I did.
-
-On leaf-1-a
------------
-vlan-create id 400 scope fabric
-switch-vnic-create ip 192.168.77.2/24 vlan 400 if mgmt
-admin-service-modify if eth1.400 web-ssl
-
-On leaf-1-b
------------
-switch-vnic-create ip 192.168.77.3/24 vlan 400 if mgmt
-admin-service-modify if eth1.400 web-ssl
-
-On compute-1-2
---------------
-vconfig add bond1 400
-ifconfig bond1.400 192.168.77.11/24
-
-I dont know how to propagate this connection into the vCIC. I need some help from CEE with this.
-This at least shows it is possible to set up. CEE king 2x100 Gbps here, that's *a lot* of bandwidth.
+<br><br>
+You could use one smartNIC for data per compute, we're talking 2x100 Gbps here, that's *a lot* of bandwidth.
 In this case, high availability happens at compute level, not at network card level. 
-
+<br><br>
 What if you have a dual socket system. If you plug a smartNIC in a PCIe socket, applications might not like crossing that QPI link (from 2017 called UPI) between the CPUs.
 In this case you can look into using a bifurcated smartNIC, that's basically splitting the card in two physical pieces that you can insert in two PCIe slots, one per NUMA node.
-
+<br><br>
 If you use two smartNICs, do you want two separate ovs controllers in your compute? will OpenStack even support that? 
 
                                         </aside>
@@ -245,6 +221,9 @@
                                         </tr>                                        
                                         <aside class="notes">                                      
 Here you can see the CPUs allocated to ovs under nohz_full ( confirmed with /etc/default PMDs)
+
+Did you have this problem? Poor dimensioned compute (customer cannot aproximate how many VMs it will run on a compute to properly dimension mem for host OS to take be sufficent for device emulation), runs out of mem , oom killer takes down ovs and with it all VMs? with ovs in the NIC this will not happen, of course you need to properly dimension your system anyway. 
+
 nohz_full=cpulist
 The nohz_full parameter is used to treat a list of CPUs differently, with respect to timer ticks. If a CPU is listed as a nohz_full CPU and there is only one runnable task on the CPU, then the kernel will stop sending timer ticks to that CPU, so more time may be spent running the application and less time spent servicing interrupts and context switching.
 https://access.redhat.com/documentation/en-us/red_hat_enterprise_linux_for_real_time/7/html/tuning_guide/isolating_cpus_using_tuned-profiles-realtime
@@ -336,8 +315,11 @@
 
 </font>									 
                                         <aside class="notes">                                      
-In ironic
-Steps: 
+Neutron ml2 OVS changes:
+
+Introduce a new vnic_type for smart-nic.
+
+Update the Neutron ml2 OVS to bind smart-nic vnic_type with binding:profile smart NIC config.Steps: 
 (https://specs.openstack.org/openstack/neutron-specs/specs/stein/neutron-ovs-agent-support-baremetal-with-smart-nic.html)
 1. Create Neutron port with smart-nic vnic_type , this is done in Neutron OVS ML2 driver 
 2. local_link_information wiht info like smartNIC hostname , port ID, ssh public key, ovsdb ssl certificate