Proxmox placement audit
J.M. Field cluster, 6 nodes plus planned node 7 and the E5-2470 v2 box. Data read live 2026-10-05 from pvesh: allocations, current use, and 7-day CPU (average and peak, % of the VM's own vCPUs). Read only, nothing moved.
Bottom line
Node 1 is the new OOM risk. Running VMs are promised 123 GB on a 125 GB host. That is the same shape that killed MariaDB on node 5. It survives today only because guests are not using all of it and it has 24 GB swap.
Node 4 is next: 85 GB promised on 110 GB with no swap, and aivscript-3.240 is using 30 of its 32 GB.
Node 6 is mostly empty (96 of 252 GB promised, CPU near idle). It and node 7 are where load should go, not new hardware RAM.
No RAM purchase is needed to fix placement. Moving 3 or 4 VMs fixes the risk. The old E5-2470 v2 box is a good home for idle dev and legacy VMs, with one hard rule below.
Nodes ranked by CPU
| Node | CPU | Gen | Threads | RAM | Promised to running VMs | Swap | Status |
|---|---|---|---|---|---|---|---|
| JMFPMX05 | 2x Gold 6334 3.6 GHz | Ice Lake | 32 | 251 GB | 179 GB (71%) | 0 | OK after fixes |
| JMFPMX06 | 2x Gold 6134 3.2 GHz | Skylake | 32 | 252 GB | 96 GB (38%) | 0 | Lots of room |
| JMFPMX01 | 2x Gold 6154 3.0 GHz | Skylake | 72 | 125 GB | 123 GB (98%) | 24 GB | Over-promised |
| Node 7 (planned) | 2x Gold 6142 2.6 GHz | Skylake | 64 | 128 GB | 0 | - | Not built |
| JMFPMX02 | 2x E5-2690 v4 2.6 GHz | Broadwell | 56 | 189 GB | 106 GB (56%) | 24 GB | OK |
| JMFPMX04 | 2x E5-2690 v4 2.6 GHz | Broadwell | 56 | 110 GB | 85 GB (77%) | 0 | Tight, no swap |
| JMFPMX03 | 2x Silver 4110 2.1 GHz | Skylake | 32 | 126 GB | 54 GB (42%) | 24 GB | OK, slowest |
| E5-2470 v2 box | E5-2470 v2 2.4 GHz | Ivy Bridge | ? | 188 GB | 0 | - | Not in cluster |
The whole cluster is idle on CPU: no node averages over 8%. RAM is the only constraint, so "Gold vs Silver" matters less than "where is there free RAM". CPU only matters for the few VMs that peak hard (below).
Live-migration groups
VMs set to cpu: host can only live-migrate between the same CPU generation. Otherwise they need a shutdown and cold start.
- Skylake: nodes 1, 6, node 7, and probably 3 (Silver is Skylake too, untested). The largest group, and node 7 joins it.
- Broadwell: nodes 2 and 4.
- Ice Lake: node 5 alone.
- Ivy Bridge: E5-2470 v2 box alone. It has no AVX2.
Who actually needs a fast CPU
Peak = busiest moment in 7 days, as % of the VM's vCPUs. Over ~60% means it really uses its cores at times.
| VM | Node | vCPU | Avg | Peak | Verdict |
|---|---|---|---|---|---|
| 130 MariaDB-3.230 | 5 | 16 | 17.8% | 106% | Right place. Fastest cores. |
| 112 jmfxups | 2 | 4 | 31.5% | 106% | Busiest small VM. Keep on a modern node. Uses x86-64-v3, so never the 2470 box. |
| 129 pmg | 5 | 2 | 1.5% | 101% | Short spikes only (spam scans). Fine anywhere. |
| 123 API-Server-3.244 | 1 | 8 | 2.9% | 99% | Spiky (OP2 runs here). Keep on Skylake. |
| 145 FreePBX-v17 | 3 | 2 | 9.1% | 74% | Phones. Keep off the 2470 box (latency). |
| 148 Exchange2019 | 3 | 2 | 18.8% | 72% | Hybrid management server only; mail lives in 365. 2 vCPU / 8 GB is fine for that. Could live on the 2470 box. |
| 113 jmfxfedex | 2 | 4 | 11.3% | 66% | x86-64-v3, never the 2470 box. |
| 121 aivscripttesting3.202 | 2 | 2 | 11.4% | 63% | Dev, but busy. OK on the 2470 box. |
| 126 aivscript-3.240 | 4 | 8 | 14.6% | 59% | Real workload. Stay modern. |
Everything else averages under 15% and peaks under 55%. Any of those would run fine on Silver or on the 2470 box.
Proposed moves
| # | VM | From | To | Frees | Why | How |
|---|---|---|---|---|---|---|
| 1 | 122 aivqueue-3.216 (30 GB, 1% CPU) | 1 | 6 | 30 GB on node 1 | Takes node 1 from 98% to 74% promised. | Live (Skylake to Skylake). Test once, check status after. |
| 2 | 133 AIV-3.234 (32 GB, 1% avg, dev, Server 2012) | 4 | 2470 box | 32 GB on node 4 | Idle dev box on the tightest node. | Cold. Set CPU to x86-64-v2-AES first. |
| 3 | 120 MySQL-Dev-Server-3.210, 142 MySQL-Dev-2 (24 GB each, dev) | 2 | 2470 box | 48 GB on node 2 | Dev databases. Room on node 2 for Broadwell workloads. | Cold, CPU change first. Not 120 if Dave parks his DBs there. |
| 4 | 121 aivscripttesting3.202, 111 GrandeBay-Terminal | 2, 1 | 2470 box | 34 GB | Testing box and a terminal server at 1% CPU. | Cold, CPU change first. |
| 5 | Dave's 3.241 DBs (new VM) | bare metal | 6, later 7 | - | Already planned. Skylake both, so it can live-move to 7. | As per the R740 plan. |
Shrink, don't move
- 152 JMFAGENT is a test RDS host for Sage, so its 31 GB is sized for the users it will carry. Do not shrink it. While it is in testing, consider lowering its balloon minimum from 24 GB so node 5 can take memory back. When it goes live, it would sit well on node 6 or node 7, in the same Skylake group as the Sage server (110 on node 1), and off node 5 where MariaDB lives. That move needs a reboot (Ice Lake to Skylake).
- 133 AIV-3.234: 32 GB, using 1.4 GB. If it moves to the 2470 box, also cut to 8 GB.
- 126 aivscript-3.240 is the opposite: 29.9 of 32 GB used. Watch it, don't shrink.
The E5-2470 v2 box: rules
No AVX2 (Ivy Bridge, 2013). Any VM using x86-64-v3 (112 jmfxups, 113 jmfxfedex) will not boot there. Any VM on cpu: host moved there must switch to x86-64-v2-AES first, and software inside it that needs AVX2 will then fail. Most notable: MongoDB 5+, some newer Docker images, RHEL 10 / Alma 10. Ubuntu, Windows Server, MySQL/MariaDB are fine.
DDR3 and high idle power. Expect 200 to 300 W at idle. Cost it against the RAM you are not buying.
Single generation group. Nothing live-migrates to or from it. Every move is a reboot.
Good for: dev and test VMs, idle legacy Windows, a second PBS target or replica. Not for: phones, DCs you depend on, MariaDB-3.230, anything client-facing.
Clean-up candidates (decide, then archive)
Stopped VMs cost no RAM, but they hold disk and some would cause an IP conflict if someone starts them.
| VM | Node | Note |
|---|---|---|
| 127 MariaDB-3.230-DONOTPOWER | 3 | Old copy of the live DB server. Same IP as 130. Back up to PBS, then delete. |
| 124 mailsvr-DONOTPOWER | 2 | Back up, then delete. |
| 105 FTP-Retired, 106 Sage-Test-Box, 100 Sage2025 | 2 | Confirm with the Sage owner. |
| 117 FreePBX-v16-Production | 2 | v17 (145) is live. Archive v16. |
| 107 mariadbmonitor, 135 node3worker, 140 akaunting, 146 erpnext | 3 | Unused experiments? |
| 103 RLDEV-Browsershot, 125 WebServer-3.246 | 4 | Stopped since at least last week. |
| 101 pdf-renderer | 6 | Stopped. |
| 136 aivqueue (running, 0% CPU all week) | 6 | Running but did nothing in 7 days. Duplicate of 122 aivqueue-3.216? Check before stopping. |
End-of-life operating systems
- 148 Exchange2019: Exchange 2019 support ended October 2025. It is hybrid management only, so the option is Microsoft's management-tools-only setup (Exchange 2019 CU12+) and retiring the VM. Check what still relies on it (SMTP relay, recipient management) first.
- 119 jmffs0.216: Windows Server 2008. File server, out of support since 2020. The highest risk VM in the cluster.
- 115 BackupAdminsvr, 133 AIV-3.234: Server 2012. Out of support since 2023.
- 121 aivscripttesting, 126 aivscript-3.240: CentOS. CentOS 7 is out of support since mid-2024 (version not checked).
What this audit did not check
- Disk: storage use per node and which ZFS pools each VM lives on. Moves to the 2470 box need its storage and network set up first.
- Network: whether the 2470 box has 10G. If not, cold moves of 24 to 32 GB disks go at 1G.
- The 2470 box itself: model, core count, and whether its RAM and disks are healthy.
- CPU flags of the Silver 4110 vs the Gold Skylakes. Node 3 in the Skylake group is likely, not tested.
- Guest OS versions beyond Proxmox tags.
Generated 2026-10-05. Internal. Not indexed.