xtremeownage

Both CloudNordic and Azero said that they were working to rebuild customers’ web and email systems from scratch, albeit without their data.

Yea.... Don't bother. But, do expect to hear from my lawyers.....

CloudNordic said that it “had no knowledge that there was an infection.” CloudNordic and Azero are owned by Denmark-registered Certiqa Holding, which also owns Netquest, a provider of threat intelligence for telcos and governments.

Edit-

https://www.cloudnordic.com/

Knock on wood, I have not used them in quite a while.

My adventures in building out a ceph cluster for proxmox storage.

As a random note, my particular instance (lemmyonline.com) is hosted on that particular ceph cluster.

I can't say for sure- but, there is a good chance I might have a problem.

The main picture attached to this post, is a pair of dual bifurcation cards, each with a pair of Samsung PM963 1T enterprise NVMes.

It is going into my r730XD. Which... is getting pretty full. This will fill up the last empty PCIe slots.

But, knock on wood, My r730XD supports bifurcation! LOTS of Bifurcation.

As a result, it now has more HDDs, and NVMes then I can count.

What's the problem you ask? Well. That is just one of the many servers I have laying around here, all completely filled with NVMe and SATA SSDs....

Figured I would share. Seeing a bunch of SSDs is always a pretty sight.

And- as of two hours ago, my particular lemmy instance was migrated to these new NVMes completely transparently too.

So, last month, my kubernetes cluster decided to literally eat shit while I was out on a work conference.

When I returned, I decided to try something a tad different, by rolling out proxmox to all of my servers.

Well, I am a huge fan of hyper-converged, and clustered architectures for my home network / lab, so, I decided to give ceph another try.

I have previously used it in the past with relative success with Kubernetes (via rook/ceph), and currently leverage longhorn.

Cluster Details

1. Kube01 - Optiplex SFF

• i7-8700 / 32G DDR4
• 1T Samsung 980 NVMe
• 128G KIOXIA NVMe (Boot disk)
• 512G Sata SSD
• 10G via ConnectX-3

2. Kube02 - R730XD

• 2x E5-2697a v4 (32c / 64t)
• 256G DDR4
• 128T of spinning disk.
• 2x 1T 970 evo
• 2x 1T 970 evo plus
• A few more NVMes, and Sata
• Nvidia Tesla P4 GPU.
• 2x Google Coral TPU
• 10G intel networking

3. Kube05 - HP z240

• i5-6500 / 28G ram
• 2T Samsung 970 Evo plus NVMe
• 512G Samsung boot NVMe
• 10G via ConnectX-3

4. Kube06 - Optiplex Micro

• i7-6700 / 16G DDR4
• Liteon 256G Sata SSD (boot)
• 1T Samsung 980

Attempt number one.

I installed and configured ceph, using Kube01, and Kube05.

I used a mixture of 5x 970 evo / 970 evo plus / 980 NVMe drives, and expected it to work pretty decently.

It didn't. The IO was so bad, it was causing my servers to crash.

I ended up removing ceph, and using LVM / ZFS for the time being.

Here are some benchmarks I found online:

https://docs.google.com/spreadsheets/d/1E9-eXjzsKboiCCX-0u0r5fAjjufLKayaut_FOPxYZjc/edit#gid=0

https://www.proxmox.com/images/download/pve/docs/Proxmox-VE_Ceph-Benchmark-202009-rev2.pdf

The TLDR; after lots of research- Don't use consumer SSDs. Only use enterprise SSDs.

Attempt / Experiment Number 2.

I ended up ordering 5x 1T Samsung PM863a enterprise sata drives.

After, reinstalling ceph, I put three of the drives into kube05, and one more into kube01 (no ports / power for adding more then a single sata disk...).

And- put the cluster together. At first, performance wasn't great.... (but, was still 10x the performance of the first attempt!). But, after updating the crush map to set the failure domain to OSD rather then host, performance picked up quite dramatically.

This- is due to the current imbalance of storage/host. Kube05 has 3T of drives, Kube01 has 1T. No storage elsewhere.

BUT.... since this was a very successful test, and it was able to deliver enough IOPs to run my I/O heavy kubernetes workloads.... I decided to take it up another step.

A few notes-

Can you guess which drive is the samsung 980 EVO, and which drives are enterprise SATA SSDs? (look at the latency column)

Future - Attempt #3

The next goal, is to properly distribute OSDs.

Since, I am maxed out on the number of 2.5" SATA drives I can deploy... I picked up some NVMe.

5x 1T Samsung PM963 M.2 NVMe.

I picked up a pair of dual-spot half-height bifurcation cards for Kube02. This will allow me to place 4 of these into it, with dedicated bandwidth to the CPU.

The remaining one, will be placed inside of Kube01, to replace the 1T samsung 980 NVMe.

This should give me a pretty decent distribution of data, and with all enterprise drives, it should deliver pretty acceptable performance.

More to come....

Since, my doctor recommend that I put more fiber in my diet- I decided to comply.

So.... in a few hours, I will be running a few OS2 runs across my house, with 10G LR SFP+ modules.

Both runs will be from my rack to the office. One run will be dedicated for the incoming WAN connection (Coupled with the existing fiber that.... I don't want to re terminate). The other, will be replacing the 10G copper run already in place, to save 10 or 20w of energy.

This, was sparked due to a 10GBase-T module overheating, and becoming very intermittent earlier this week causing a bunch of issues. After replacing the module, links came back up and started working normally.... but... yea, I need to replace the 10G copper links.

With only twinax and fiber 10G links plugged into my 8-port aggregation switch, it is only pulling around 5 watts, which is outstanding, given a single 10GBase-T module uses more then that.

Edit,

Also, I ordered the wrong modules. BUT... the hard part of running the fiber is done!

Surprisingly, I guess this didn't exist. Well, if you like talking automotive technology, it does now.

Turbocharged

Yup. always gotta be that one single threaded program. In this case, appears to be frigate.