I keep having this “too good to be true feeling” specially from Evil Corp #2.
Basically they give you 4x2Ghz Ampere Arm cores with 24GB memory that can be split to up to 4x 1vcpu 6GB ram, 2 AMD EPIC vms with 1GB memory and 200GB block storage. Each vm uses a 50GB boot drive tho so you max out at 4VMs. A vnet and a load balancer are also on the menu.
And its “always free”. It is indeed free but I don’t buy the always part. They will probably get tired of my freeloading ass one way or another. Full list is here: Cloud Free Tier | Oracle
They are probably doing this to attract developers and train their team since they are not a first class citizen in the cloud provider world.
But well… who am I to complain.
In any case I’m running k3s with the following setup:
1 EPIC VM: static database server
1 EPIC VM: control-plane,master
2 ARM VMs: worker nodes
I’ve setup Traefik ingress controllers on NodePort and directed the Oracle load balancer to its ports. Things work pretty well except for the master controller becoming a bit unstable after I’ve installed too many addons to the cluster specially longhorn which was a bit too much. Willl probably run some funny projects.
Anyway in case anyone is curious here are the lscpu results for the EPYC and Ampere machines:
They use this weird concept called OCPU. It seems one OCPU is basically 2 vcpus. Not sure if threaded.
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 2
On-line CPU(s) list: 0,1
Thread(s) per core: 2
Core(s) per socket: 1
Socket(s): 1
NUMA node(s): 1
Vendor ID: AuthenticAMD
BIOS Vendor ID: QEMU
CPU family: 23
Model: 1
Model name: AMD EPYC 7551 32-Core Processor
BIOS Model name: pc-i440fx-4.2
Stepping: 2
CPU MHz: 1996.250
BogoMIPS: 3992.50
Virtualization: AMD-V
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 64K
L1i cache: 64K
L2 cache: 512K
L3 cache: 16384K
NUMA node0 CPU(s): 0,1
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm rep_good nopl cpuid extd_apicid tsc_known_freq pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd ibpb vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 rdseed adx smap clflushopt sha_ni xsaveopt xsavec xgetbv1 xsaves nt_good clzero xsaveerptr virt_ssbd arat npt nrip_save arch_capabilities
I’ve split my ARM quota into 2 VMS so it only shows 2 cores here.
Architecture: aarch64
Byte Order: Little Endian
CPU(s): 2
On-line CPU(s) list: 0,1
Thread(s) per core: 1
Core(s) per cluster: 2
Socket(s): -
Cluster(s): 1
NUMA node(s): 1
Vendor ID: ARM
Model: 1
Model name: Neoverse-N1
Stepping: r3p1
BogoMIPS: 50.00
NUMA node0 CPU(s): 0,1
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm lrcpc dcpop asimddp ssbs
Maybe I can connect this to Hetzner’s ridiculously cheap SFTP storage and run stuff like Emby. I can run websites and projects. Might also use this to build ARM binaries and container images. My creativity to laziness ratio (and their patience) are the limit here. Don’t trust this thing to run anything long term or a run a business tho. They are probably trigger happy to cancel accounts that do things corporations are not keen of.