Red Hat purchased these in Q4CY20. I think we had increasingly been asked by customers to test or reproduce on 100% flash systems. We didn't have any until these.
| Name | Use |
|---|---|
| folio01.front.sepia.ceph.com | Laura's machine |
| folio02.front.sepia.ceph.com | Developer Playground |
| folio03.front.sepia.ceph.com | nmordech, Matan Breizman |
| folio04.front.sepia.ceph.com | Arunagirinadan Sudharshan |
| folio05.front.sepia.ceph.com | Sam Just - crimson testing |
| folio06.front.sepia.ceph.com | Mark Kogan - RGW MultiSite |
| folio07.front.sepia.ceph.com | Jiffin Thottan |
| folio08.front.sepia.ceph.com | Yuval Lifshitz |
| folio09.front.sepia.ceph.com | Mark Kogan - RGW MultiSite |
| folio10.front.sepia.ceph.com | Sunny Kumar |
| folio11.front.sepia.ceph.com | Ali Masarwa |
| folio12.front.sepia.ceph.com | Zack Cerza |
| folio13.front.sepia.ceph.com | Developer Playground |
| folio14.front.sepia.ceph.com | Telemetry - Please contact Yaarit before any changes to this box. Do not reboot. |
Formerly tracked: https://docs.google.com/spreadsheets/d/1FINf_UBTv28gPi1FWPWG7VPlFgF_ntAoNuwZHtGGN4s/edit#gid=0
Purchasing ticket: https://redhat.service-now.com/surl.do?n=PNT0912001
Racking ticket: https://redhat.service-now.com/surl.do?n=PNT0912002
| Count | Manufacturer | Model | Capacity | Notes | |
|---|---|---|---|---|---|
| Chassis | 1U | Dell | PowerEdge R640 | N/A | |
| Mainboard | N/A | Dell | 0X45NX | N/A | |
| CPU | 2 | Intel | Intel(R) Xeon(R) Gold 6230 CPU @ 2.10GHz | 80 cores total | ARK |
| RAM | 8 DIMMs | Micron | 36ASF4G72PZ-3G2J3 | 32GB | 256GB Total |
| SSD | 1 | Toshiba | KPM5XVUG960G | 1TB | For OS |
| NVMe | 8 | Dell | P4610 | 1.6TB | |
| NIC | 2 ports | Broadcom | BCM5720 | 1Gb | 1 port as uplink |
| NIC | 2 ports | Mellanox | ConnectX-4 LX | 25Gb | 1 port as uplink |
| BMC | 1 | N/A | N/A | Reachable at $host.ipmi.sepia.ceph.com using usual IPMI credentials. |
These PXE using Legacy/BIOS mode and can be provisioned via Cobbler normally.
These nodes are connected to a QFX5120 uplinked and managed by Red Hat IT. For an example of how to report an outage, see https://redhat.service-now.com/surl.do?n=INC1201508.
Each server has a 25Gb pigtail from a 100Gb breakout cable. The first three QSFP+ ports are configured VLAN101 untagged and VLAN100 tagged. Our DHCP server is configured to hand out leases to the 25Gb interfaces.