| Posted | Nick | Remark | |
|---|---|---|---|
| #openstack-nova - 2021-05-21 | |||
| 10:18:31 | bauzas | correct ? | |
| 10:18:31 | bauzas | correct ? | |
| 10:18:32 | sean-k-mooney | yes mainly because the bandwith is an aspect of a nic which is attached to at most 1 of thoes briges | |
| 10:18:32 | sean-k-mooney | yes mainly because the bandwith is an aspect of a nic which is attached to at most 1 of thoes briges | |
| 10:18:39 | gibi | yepp | |
| 10:19:00 | sean-k-mooney | the standard name for the bridge with the nice is generally br-ex | |
| 10:19:00 | sean-k-mooney | the standard name for the bridge with the nice is generally br-ex | |
| 10:19:01 | bauzas | so, local vm-to-vm communication thru br-int isn't guaranteed, right? | |
| 10:19:02 | bauzas | so, local vm-to-vm communication thru br-int isn't guaranteed, right? | |
| 10:19:16 | openstackgerrit | Brin Zhang proposed openstack/nova master: Replace all_tenants with all_projects in List Server APIs https://review.opendev.org/c/openstack/nova/+/765311 | |
| 10:19:16 | openstackgerrit | Brin Zhang proposed openstack/nova master: Replace all_tenants with all_projects in List Server APIs https://review.opendev.org/c/openstack/nova/+/765311 | |
| 10:19:17 | openstackgerrit | Brin Zhang proposed openstack/nova master: Replaces tenant_id with project_id from Rebuild Server API https://review.opendev.org/c/openstack/nova/+/766380 | |
| 10:19:17 | openstackgerrit | Brin Zhang proposed openstack/nova master: Replaces tenant_id with project_id from Rebuild Server API https://review.opendev.org/c/openstack/nova/+/766380 | |
| 10:19:28 | sean-k-mooney | bauzas: it does not consume any nic bandeith for kernel ovs | |
| 10:19:28 | sean-k-mooney | bauzas: it does not consume any nic bandeith for kernel ovs | |
| 10:19:42 | sean-k-mooney | bauzas: ovs's internal bandwith generally exceeed your nic bandwith | |
| 10:19:42 | bauzas | sean-k-mooney: I know, I just want to make things clear | |
| 10:19:42 | sean-k-mooney | bauzas: ovs's internal bandwith generally exceeed your nic bandwith | |
| 10:19:42 | bauzas | sean-k-mooney: I know, I just want to make things clear | |
| 10:19:47 | sean-k-mooney | but technically no its not | |
| 10:19:47 | sean-k-mooney | but technically no its not | |
| 10:20:06 | sean-k-mooney | we are jsut reserving inter host bandwith | |
| 10:20:06 | sean-k-mooney | we are jsut reserving inter host bandwith | |
| 10:20:09 | bauzas | cool | |
| 10:20:09 | bauzas | cool | |
| 10:20:14 | bauzas | here, back to the pps spec | |
| 10:20:15 | bauzas | here, back to the pps spec | |
| 10:20:30 | bauzas | (and gosh, we should find an acronym for the minimum bandwidth spec) | |
| 10:20:31 | bauzas | (and gosh, we should find an acronym for the minimum bandwidth spec) | |
| 10:20:38 | gibi | bw spec :) | |
| 10:20:38 | gibi | bw spec :) | |
| 10:20:40 | bauzas | min b/w, sorted it | |
| 10:20:40 | bauzas | min b/w, sorted it | |
| 10:20:51 | bauzas | ok, so, back to the pps spec | |
| 10:20:51 | bauzas | ok, so, back to the pps spec | |
| 10:20:51 | sean-k-mooney | :) | |
| 10:21:03 | sean-k-mooney | brb continue and ill catch up | |
| 10:21:03 | sean-k-mooney | brb continue and ill catch up | |
| 10:21:28 | bauzas | here, we want to guarantee the process rate of the internal ovs switch that's on... br-int ? | |
| 10:21:28 | bauzas | here, we want to guarantee the process rate of the internal ovs switch that's on... br-int ? | |
| 10:21:38 | gibi | * gibi free until the top of the hour, then need to jump to two consecutive calls | |
| 10:21:56 | bauzas | * bauzas had to skip his usual Friday gym session :p | |
| 10:25:29 | gibi | in theory I we can rename the OVS Agent RP to br-int. It would help with some mental modelling. But this can be done any time independently of my work. So I would like to push this work to be a burden of the person who proposes the multiple OVS per agent spec. You can hate me for it, but I don't believe we ever get there. So I spare some effort not to do someting that will not be needed. | |
| 10:25:29 | gibi | in theory I we can rename the OVS Agent RP to br-int. It would help with some mental modelling. But this can be done any time independently of my work. So I would like to push this work to be a burden of the person who proposes the multiple OVS per agent spec. You can hate me for it, but I don't believe we ever get there. So I spare some effort not to do someting that will not be needed. | |
| 10:26:10 | gibi | I will documet the renameing idea in the spec | |
| 10:26:10 | gibi | I will documet the renameing idea in the spec | |
| 10:27:49 | bauzas | gibi: honestly, I feel we can just leave as it is, after 1 hour of brainstorming | |
| 10:27:49 | bauzas | gibi: honestly, I feel we can just leave as it is, after 1 hour of brainstorming | |
| 10:28:21 | gibi | I feel the same. but I think we gained some insights during that hour | |
| 10:28:21 | gibi | I feel the same. but I think we gained some insights during that hour | |
| 10:28:29 | bauzas | the main difference between pps and bw features is that one cares about inter-host communication while the other cares about the agent itself | |
| 10:28:29 | bauzas | the main difference between pps and bw features is that one cares about inter-host communication while the other cares about the agent itself | |
| 10:29:08 | gibi | bauzas: this is coming from the fact that the bottlenecks are in different places regarding bw or pps | |
| 10:29:08 | gibi | bauzas: this is coming from the fact that the bottlenecks are in different places regarding bw or pps | |
| 10:29:19 | bauzas | yup, that's what I figured | |
| 10:29:19 | bauzas | yup, that's what I figured | |
| 10:29:29 | sean-k-mooney | bauzas: kind of yes. one is inter host and the other is any traffic that passes though ovs bot inter and intra host traffic | |
| 10:29:29 | sean-k-mooney | bauzas: kind of yes. one is inter host and the other is any traffic that passes though ovs bot inter and intra host traffic | |
| 10:29:32 | bauzas | ok, I'll reply to the spec | |
| 10:29:32 | bauzas | ok, I'll reply to the spec | |
| 10:29:40 | gibi | bauzas: thank you | |
| 10:29:40 | gibi | bauzas: thank you | |
| 10:29:41 | gibi | sean-k-mooney: thank you | |
| 10:29:42 | gibi | sean-k-mooney: thank you | |
| 10:30:00 | gibi | I appreciate your time spent on these topics | |
| 10:30:00 | gibi | I appreciate your time spent on these topics | |
| 10:30:05 | bauzas | by saying that for the good or bad, we've already created a beast called "the agent" | |
| 10:30:06 | bauzas | by saying that for the good or bad, we've already created a beast called "the agent" | |
| 10:30:23 | bauzas | which is actually something between br-int and other things | |
| 10:30:23 | bauzas | which is actually something between br-int and other things | |
| 10:30:48 | bauzas | by adding resources to this "beast", we're making it clear this is the *switch* | |
| 10:30:48 | bauzas | by adding resources to this "beast", we're making it clear this is the *switch* | |
| 10:30:54 | sean-k-mooney | yes like the compute node it currenlty modesl multiple things | |
| 10:30:54 | sean-k-mooney | yes like the compute node it currenlty modesl multiple things | |
| 10:31:28 | bauzas | if someone pops up with wanting to monitor the number of ports per agent, we could then say "mmmm, maybe create a parent RP" | |
| 10:31:28 | bauzas | if someone pops up with wanting to monitor the number of ports per agent, we could then say "mmmm, maybe create a parent RP" | |
| 10:31:39 | bauzas | but this is unfair to ask gibi to pay the price now | |
| 10:31:39 | bauzas | but this is unfair to ask gibi to pay the price now | |
| 10:31:54 | sean-k-mooney | or just add it to the beast | |
| 10:31:54 | sean-k-mooney | or just add it to the beast | |
| 10:32:01 | bauzas | we just internally defined this as an agent, but this is untrue | |
| 10:32:01 | bauzas | we just internally defined this as an agent, but this is untrue | |
| 10:32:39 | bauzas | sean-k-mooney: yup, another spec, another day of discussions | |
| 10:32:39 | bauzas | sean-k-mooney: yup, another spec, another day of discussions | |
| 10:32:43 | sean-k-mooney | we shoudl add in scare quotes "the beast" beside all mentions of the agent rp and just not say why | |
| 10:32:43 | sean-k-mooney | we shoudl add in scare quotes "the beast" beside all mentions of the agent rp and just not say why | |
| 10:32:47 | gibi | until the agent and the switch has 1:1 relationship you can attach resources to the RP for both reasons | |
| 10:32:47 | gibi | until the agent and the switch has 1:1 relationship you can attach resources to the RP for both reasons | |
| 10:33:11 | gibi | it is a beast | |
| 10:33:11 | gibi | it is a beast | |
| 10:33:22 | gibi | but we are taming it with our 1:1 assumption | |
| 10:33:22 | gibi | but we are taming it with our 1:1 assumption | |
| 10:33:50 | sean-k-mooney | yes im tryiing to avoid discussign the added complxity hardware offload adds | |
| 10:33:50 | sean-k-mooney | yes im tryiing to avoid discussign the added complxity hardware offload adds | |
| 10:34:06 | sean-k-mooney | we have adress that via the different resouce classes however | |
| 10:34:06 | sean-k-mooney | we have adress that via the different resouce classes however | |
| 10:34:32 | gibi | which might be a compromise but as far as I see it is an acceptable one | |
| 10:34:32 | gibi | which might be a compromise but as far as I see it is an acceptable one | |
| 10:34:38 | bauzas | technically we created a beast in nova too | |
| 10:34:38 | bauzas | technically we created a beast in nova too | |