Back to bug 1827283
| Who | When | What | Removed | Added |
|---|---|---|---|---|
| Franck Baudin | 2020-04-23 14:21:34 UTC | Keywords | FutureFeature, TestOnly | |
| Assignee | amuller | vchundur | ||
| Target Milestone | --- | beta | ||
| QA Contact | ekuris | supadhya | ||
| Franck Baudin | 2020-04-23 14:22:27 UTC | Blocks | 1820742 | |
| Christophe Fontaine | 2020-04-24 09:17:37 UTC | Keywords | Triaged | |
| Priority | unspecified | high | ||
| CC | cfontain | |||
| Federico Iezzi | 2020-04-28 11:03:38 UTC | CC | fiezzi | |
| Karrar Fida | 2020-08-07 15:03:23 UTC | CC | kfida | |
| RHEL Program Management | 2020-08-07 15:03:31 UTC | Target Release | --- | 16.2 (Train on RHEL 8.4) |
| Haresh Khandelwal | 2020-09-03 10:22:12 UTC | Keywords | TechPreview | |
| Target Release | 16.2 (Train on RHEL 8.4) | 16.1 (Train on RHEL 8.2) | ||
| CC | hakhande | |||
| Target Milestone | beta | z2 | ||
| Doc Type | If docs needed, set a value | Technology Preview | ||
| RHEL Program Management | 2020-09-03 10:22:22 UTC | Target Release | 16.1 (Train on RHEL 8.2) | 16.2 (Train on RHEL 8.4) |
| Haresh Khandelwal | 2020-09-03 18:16:25 UTC | Status | NEW | ON_QA |
| RHEL Program Management | 2020-09-03 18:16:32 UTC | Target Release | 16.2 (Train on RHEL 8.4) | --- |
| Yariv | 2020-09-07 11:07:57 UTC | CC | yrachman | |
| Flags | needinfo?(kfida) | |||
| Haresh Khandelwal | 2020-09-07 14:17:00 UTC | Target Release | --- | 16.1 (Train on RHEL 8.2) |
| RHEL Program Management | 2020-09-07 14:17:07 UTC | Target Release | 16.1 (Train on RHEL 8.2) | --- |
| RHEL Program Management | 2020-09-07 14:51:59 UTC | Target Release | --- | 16.1 (Train on RHEL 8.2) |
| RHEL Program Management | 2020-09-08 16:40:15 UTC | Target Release | 16.1 (Train on RHEL 8.2) | 16.2 (Train on RHEL 8.4) |
| Karrar Fida | 2020-09-08 16:40:59 UTC | Target Milestone | z2 | beta |
| Karrar Fida | 2020-09-08 17:01:46 UTC | Flags | needinfo?(kfida) | |
| RHEL Program Management | 2020-09-09 16:25:08 UTC | Target Release | 16.2 (Train on RHEL 8.4) | 16.1 (Train on RHEL 8.2) |
| Karrar Fida | 2020-09-09 16:25:39 UTC | Target Milestone | beta | z2 |
| Karrar Fida | 2020-09-14 17:53:45 UTC | Assignee | vchundur | kfida |
| Sanjay Upadhyay | 2020-09-17 13:47:58 UTC | Flags | needinfo?(kfida) | |
| Karrar Fida | 2020-09-17 17:26:35 UTC | Summary | [TestOnly] AMD EPYC 7702 host with SR-IOV (without OVS-DPDK) | [TestOnly][TechPreview] AMD EPYC 7702 host with SR-IOV (without OVS-DPDK) |
| Karrar Fida | 2020-09-17 17:54:10 UTC | Blocks | 1880120 | |
| Karrar Fida | 2020-09-17 18:07:59 UTC | Flags | needinfo?(kfida) | |
| Ofer Blaut | 2020-09-23 11:51:28 UTC | Status | ON_QA | ON_DEV |
| CC | oblaut | |||
| Erwan Gallen | 2020-09-29 14:48:23 UTC | Blocks | 1883554 | |
| James Smith | 2020-10-13 19:42:48 UTC | CC | jamsmith | |
| James Smith | 2020-10-19 13:50:47 UTC | Flags | needinfo?(cfontain) | |
| Christophe Fontaine | 2020-10-20 09:19:16 UTC | Doc Text | Package(s) providing the Technology Preview: Description of the Technology Preview: With 16.1.2, AMD EPYC 2 (Rome) platform is now “Tech Preview”, with the UEFI setting “NPS (Numa Per Socket)” set to “1”. Other values of NPS (2 or 4) are used in DPDK benchmark to reach the platform peak performances, without OpenStack, on bare-metal. We are currently evaluating the operational trade-off of NPS=2 or NPS=4 with OpenStack, as this means exposing multiple numa nodes per socket. | |
| Flags | needinfo?(cfontain) | |||
| James Smith | 2020-10-20 17:06:21 UTC | CC | mgeary | |
| Doc Text | Package(s) providing the Technology Preview: Description of the Technology Preview: With 16.1.2, AMD EPYC 2 (Rome) platform is now “Tech Preview”, with the UEFI setting “NPS (Numa Per Socket)” set to “1”. Other values of NPS (2 or 4) are used in DPDK benchmark to reach the platform peak performances, without OpenStack, on bare-metal. We are currently evaluating the operational trade-off of NPS=2 or NPS=4 with OpenStack, as this means exposing multiple numa nodes per socket. | RHOSP 16.1.2 introduces a technology preview of the AMD EPYC 2 (Rome) platform with the UEFI setting “NPS (Numa Per Socket)” set to “1”. + Other values of NPS (2 or 4) are used in DPDK benchmarks to reach the platform peak performances, without OpenStack, on bare-metal. + Red Hat continues to evaluate the operational trade-off of NPS=2 or NPS=4 with OpenStack. This configuration exposes multiple Numa nodes per socket. | ||
| Flags | needinfo?(mgeary) | |||
| Christophe Fontaine | 2020-10-22 12:30:01 UTC | Status | ON_DEV | VERIFIED |
| mgeary | 2020-10-23 10:45:13 UTC | Flags | needinfo?(mgeary) | |
| Greg Rakauskas | 2020-10-27 19:45:58 UTC | CC | gregraka | |
| Doc Text | RHOSP 16.1.2 introduces a technology preview of the AMD EPYC 2 (Rome) platform with the UEFI setting “NPS (Numa Per Socket)” set to “1”. + Other values of NPS (2 or 4) are used in DPDK benchmarks to reach the platform peak performances, without OpenStack, on bare-metal. + Red Hat continues to evaluate the operational trade-off of NPS=2 or NPS=4 with OpenStack. This configuration exposes multiple Numa nodes per socket. | RHOSP 16.1.2 introduces a technology preview of the AMD EPYC 2 (Rome) platform with the UEFI setting `NPS` (Numa Per Socket)` set to `1`. + Other values of `NPS` (2 or 4) are used in DPDK benchmarks to reach the platform peak performances, without OpenStack, on bare metal. + Red Hat continues to evaluate the operational trade-off of `NPS=2` or `NPS=4` with OpenStack. This configuration exposes multiple Numa nodes per socket. |
||
| Greg Rakauskas | 2020-10-27 19:49:23 UTC | Doc Text | RHOSP 16.1.2 introduces a technology preview of the AMD EPYC 2 (Rome) platform with the UEFI setting `NPS` (Numa Per Socket)` set to `1`. + Other values of `NPS` (2 or 4) are used in DPDK benchmarks to reach the platform peak performances, without OpenStack, on bare metal. + Red Hat continues to evaluate the operational trade-off of `NPS=2` or `NPS=4` with OpenStack. This configuration exposes multiple Numa nodes per socket. | Red Hat OpenStack Platform 16.1.2 introduces a technology preview of the AMD EPYC 2 (Rome) platform with the UEFI setting `NPS` (Numa Per Socket)` set to `1`. + Other values of `NPS` (2 or 4) are used in DPDK benchmarks to reach the platform peak performances, without OpenStack, on bare metal. + Red Hat continues to evaluate the operational trade-off of `NPS=2` or `NPS=4` with OpenStack. This configuration exposes multiple Numa nodes per socket. |
| Greg Rakauskas | 2020-10-27 21:18:42 UTC | Doc Text | Red Hat OpenStack Platform 16.1.2 introduces a technology preview of the AMD EPYC 2 (Rome) platform with the UEFI setting `NPS` (Numa Per Socket)` set to `1`. + Other values of `NPS` (2 or 4) are used in DPDK benchmarks to reach the platform peak performances, without OpenStack, on bare metal. + Red Hat continues to evaluate the operational trade-off of `NPS=2` or `NPS=4` with OpenStack. This configuration exposes multiple Numa nodes per socket. | Red Hat OpenStack Platform 16.1.2 introduces a technology preview of the AMD EPYC 2 (Rome) platform with the UEFI setting `NPS` (Numa Per Socket) set to `1`. + Other values of `NPS` (2 or 4) are used in DPDK benchmarks to reach the platform peak performances, without OpenStack, on bare metal. + Red Hat continues to evaluate the operational trade-off of `NPS=2` or `NPS=4` with OpenStack. This configuration exposes multiple Numa nodes per socket. |
| errata-xmlrpc | 2020-10-27 21:26:42 UTC | Status | VERIFIED | RELEASE_PENDING |
| errata-xmlrpc | 2020-10-28 15:36:49 UTC | Status | RELEASE_PENDING | CLOSED |
| Resolution | --- | ERRATA | ||
| Last Closed | 2020-10-28 15:36:49 UTC | |||
| errata-xmlrpc | 2020-10-28 15:37:18 UTC | Link ID | Red Hat Product Errata RHEA-2020:4284 | |
| Karrar Fida | 2020-12-07 18:14:33 UTC | Blocks | 1905209 | |
| Sanjay Upadhyay | 2021-02-23 14:44:08 UTC | CC | supadhya |
Back to bug 1827283