HPE Proliant DL360 G10 8-Bay 2.5"
Configure Your System:
1 Processor Required
Step 1: Choose a generation and tier
The DL360 Gen10 takes both waves of Intel's Xeon Scalable family. 1st Gen (Skylake) is the value entry: mature, plentiful, and the lowest cost into this platform. 2nd Gen (Cascade Lake) is the same socket refined: better clocks per watt and faster memory support, and our default recommendation when the price gap is modest.
Within each generation, the tiers are the same story: Silver for value compute, Gold for the mainstream where nearly every serious build lands, and Platinum for dense consolidation at the top of the range.
One connection worth knowing: your processor sets your memory speed. Higher tiers and the newer generation run the DIMMs faster, so a Silver chip quietly caps the memory bus you paid for. It is one of the honest arguments for Gold.
Whichever you pick, populate both sockets; half the memory channels and PCIe lanes route through the second CPU, and on a dense 1U those lanes are exactly what you are paying for.
Step 2: Choose your CPU
The DL360 Gen10 is the dense virtualization node of its generation, so core count usually wins here.
Running Windows Server? Two 8-core CPUs land exactly on the 16-core base license. Our picks are the Gold 6134 (8 cores, high clocks) in 1st Gen and the Gold 6234 in 2nd Gen: top per-core performance with nothing wasted on the license.
Virtualizing on vSphere? VMware licenses a 16-core minimum per socket, so the 8-core strategy buys you nothing there; take 16-core parts and use every core you are paying to license.
General consolidation lands in the middle Golds, and the high-core Golds and Platinums are how one DL360 replaces a shelf of older servers.
Not sure where your workload lands? We configure these daily; call 1-800-778-1545.
2 Heat Sink Optional
What still matters in a 1U chassis is airflow discipline, because there is no spare vertical space to forgive mistakes. Keep every drive bay blank and internal baffle installed; the DL360 cools front to back through small high-speed fans, and an open path lets air skip the components that need it. Scalable silicon at the top of the range runs warm under load, and the platform manages it well exactly as long as the airflow path stays intact.
Also set expectations on noise: a 1U server under load sounds like a 1U server under load. It will run fine in an office closet, but if the rack shares a wall with a desk, a 2U chassis is the kinder choice.
3 Memory (RAM) 24 DIMM slots, modules added in sets of 2 Required
Twelve matched DIMMs, six per socket, engages every channel once at full speed, and that is our default for this chassis. Memory bandwidth is exactly what a virtualization host feels, and twelve channels of it is the Gen10's quiet advantage over its predecessor.
Twenty-four DIMMs doubles capacity at two per channel with no speed penalty on this platform, and it is the natural full build when RAM is the constraint.
Your processor sets the speed: the newer generation and higher tiers run the DIMMs faster, which is part of what you buy when you step up in the processor step. The configurator pairs the right DIMMs with your chip.
In between, populate in multiples of six and keep both sockets even; a lopsided population starves channels you paid for.
Whichever count you choose, buy it as one matched set, now. Hunting for matching DIMMs a year into production means a maintenance window and rank-matching roulette, and a mismatch clocks the whole bank down.
Common landing spots: 96 GB (12x 8 GB) for general duty, 192 GB (12x 16 GB) is our default virtualization host, and 384 GB (12x 32 GB or 24x 16 GB) for dense consolidation.
4 RAID Controllers Optional
What it gives you: full hardware RAID across the backplane with a battery-protected write cache, which is what keeps parity arrays performing under real write load, plus the modern Smart Array feature set.
The part worth knowing: the P408i also runs in HBA mode, passing drives straight through to the operating system. That matters because it makes this one controller correct for both storage philosophies, traditional hardware RAID for Windows and general virtualization duty, and direct drive access for vSAN, Storage Spaces Direct, Ceph, and ZFS builds; a dense Gen10 1U is a textbook software-defined storage node. If your build is software-defined, tell us at quote time and we will ship it configured the right way.
Array guidance for the hardware RAID path: RAID 10 where write latency matters, RAID 6 over RAID 5 on anything large and spinning, and a hot spare on any array whose rebuild you would rather not race.
5 Storage Drives Select up to 8 drives (0/8 Slots Used) Optional
The 2.5" DL360 Gen10 takes SAS and SATA in both flavors, with NVMe where the backplane supports it, and by this generation the honest guidance leans flash: SSDs for virtualization datastores, databases, and application volumes, with 10K SAS spinning drives only where capacity per dollar outranks IOPS. A dense 1U compute node wants its hot data local and fast, so most DL360 builds are SSD builds.
Buy new, and on flash we will add the technical reason to the usual one: endurance is consumed by writes, and every drive here ships with its full write budget ahead of it. We steer you away from refurbished on drives specifically, and we say that as a company that sells refurbished servers all day.
Plan the boot volume out of your data bays: a small RAID 1 pair of SSDs in two bays is the standard pattern on this platform. It costs you two bays and it is worth it; a boot failure and a data failure should never be the same event.
Fair warning on capacity math: RAID overhead, hot spares, and filesystem headroom mean usable space lands well under the sum of the labels. Size for the usable number, and when in doubt, one drive size up is cheap insurance.
6 Remote Access Required
Every unit includes the integrated iLO controller with the standard feature set: health monitoring, remote power control, and basic management through a clean modern interface. The dividing line is the Advanced license, which unlocks the full remote console and virtual media, meaning you can reach the server's screen, mount an ISO, and rebuild an OS from anywhere, even when the operating system is down. Without it, any problem below the OS level means walking to the rack.
Our pick is the Advanced license, and on a production host the math is short: the license costs a fraction of one emergency site visit, and the first bad firmware day pays for it. iLO 5 also brings HPE's silicon root of trust and firmware protection machinery, and the Advanced tier is where its best capabilities live.
Standard iLO is the right call only when the server sits down the hall and someone can physically reach it without ceremony, and even then, think about whether that stays true for the machine's whole life.
If you are deploying 5 or more units, take the Advanced license on all of them. Fleet management without remote console access does not work in practice.
7 Power Supply 2x included in build Required
2x 800W is the configurator default on this chassis, and it is an honest default: Scalable silicon runs hungrier at the top of the range than its predecessors, and the 800W pair holds the 50 percent load target, where a PSU runs at peak efficiency, runs cooler, and lasts longer than one working near its limit, across nearly any build this 1U can hold.
2x 500W is the value option for restrained builds: Silver or mid-Gold processors, a sensible memory load, and a bay of SSDs land inside it, and HPE's Gen10 supplies are excellent at partial load. If the budget is tight and the build is modest, it is a legitimate saving.
Watch the estimated TDP counter at the bottom of the page as you add components to see where your build lands, and when it sits between the two, take the 800W pair; the price difference is a rounding error against the efficiency and headroom you get back.
8 Network Cards Required
Quad 1 GbE covers file, print, and light application duty, and it is the honest budget answer when the clients are desktops on gigabit switching.
10 Gb is the practical floor for the virtualization work a Gen10 1U gets bought for; a modern hypervisor on gigabit networking is bottlenecked at the card, not the CPUs. The dual 10 Gb options are the sweet spot: production on the fast pair, management on the embedded ports.
Then port type, and this is the one that catches people. SFP+ ports take fiber or DAC cables and talk to datacenter-grade switches. BASE-T ports are 10 Gb copper on ordinary RJ45. Neither is better; they must simply match your switch. Order SFP+ against a copper-only switch and the server racks up with nothing to plug into.
Need more ports, or separate links for storage and VM traffic? PCIe network cards stack on top of whatever you choose here. Call 1-800-778-1545 and we will spec the whole path, switch ports included.
9 Operating System Required
The good news on this platform: the Gen10's Xeon Scalable processors are fully supported by every modern OS, so the choice is about your environment, not compatibility.
Windows Server 2022 is the mainstream pick, and Windows Server 2025 is fully supported if you want the newest platform. Licensing is per core with a 16-core base, which is why our processor guidance steers Windows buyers to two 8-core CPUs: the 16-Core license covers that build exactly. Past 16 total cores, you need the larger tiers, and heavy VM density is where Datacenter edition with unlimited virtualization rights earns its keep. On CALs, count your users and round up.
Fair warning on Evaluation Editions: free and fully functional for 180 days, then they expire. Right for labs and proof-of-concept, wrong for production.
VMware ESXi is fully supported on this platform for shops standing on vSphere; we will install the version your cluster runs.
Proxmox VE is our quiet favorite for new virtualization deployments: open-source KVM with clustering and live migration, no per-core license math, and a pair of Gen10 DL360s running it is a seriously capable cluster for the money.
Ubuntu Server LTS covers Linux application duty with five years of free updates, and No OS is there for teams imaging from their own deployment infrastructure.
Not sure which fits? Tell us the workload at quote time, or call 1-800-778-1545.
WServer Warranty
HPE ProLiant DL360 Gen10 8-Bay 2.5" Drives [Gen10] Detailed Review
The HPE ProLiant DL360 Gen10 8-Bay 2.5" is the mainstream 1U SFF configuration in the Gen10 lineup and the most-deployed DL360 variant across HPE customer sites. Eight 2.5" SAS/SATA hot-swap bays, dual-socket Intel Xeon Scalable (Skylake-SP or Cascade Lake-SP), 24 DDR4 DIMM slots, iLO 5 with Silicon Root of Trust, and the same Smart Array storage controller family as the rest of the Gen10 line. For virtualization hosts, application servers, scale-out compute nodes, and most workloads where 8 SFF bays cover the storage design, this is the standard 1U HPE pick - and almost always the right one over the 10-Bay variant.
This is the sibling page to the DL360 Gen10 10-Bay 2.5" canonical. The full platform vocabulary - Purley socket support, memory architecture, controller comparisons, iLO 5 details, FlexibleLOM networking, GPU constraints, generational positioning - lives on that page and applies identically here. This page focuses on what's specific to the 8-Bay configuration: when it's the right pick, how the bay count maps to common workloads, and the cost-versus-flexibility tradeoff against the 10-Bay.
To configure a build, call 1-800-778-1545 or use the quote form below. Every refurbished unit ships under our 180-day warranty with 12+ hour burn-in testing, and volume pricing starts at 5 units.
Why the 8-Bay Is the Right Default
Eight 2.5" SFF bays in 1U is the configuration HPE built the DL360 around. The 10-Bay is a density variant for specific workloads where two extra bays measurably change the cluster math; the 8-Bay is the version that fits the bulk of real-world 1U deployments. If you're not running Ceph at scale, vSAN with two disk groups per host, or a distributed database that genuinely wants 10 drives per node, the 8-Bay covers your storage design with no compromise.
The cost difference is modest but real - the 10-Bay backplane and additional drive cage carry a premium, plus two more drives in your bill of materials if you're filling the bays. For a virtualization host running 4-6 SSDs for local datastore plus an M.2 boot device, the 8-Bay is the right answer. For an application server with 2-4 SSDs and primary data on SAN, the 8-Bay has surplus capacity. The 10-Bay earns its premium when the extra bays land in a specific cluster math problem; the 8-Bay wins everywhere else.
Bay-count map for common 8-Bay deployments:
- vSphere host with local SSD datastore: 2 drives RAID 1 for OS + 4-6 SSDs RAID 10 for datastore, 0-2 bays held back for spares. Comfortable fit.
- Hyper-V cluster node with CSV on iSCSI/FC: 2 drives RAID 1 for OS + 4 SSDs for Hyper-V Replica or Cluster Shared Storage cache, remaining bays unused or M.2 boot frees all 8 bays for data. Plenty of room.
- Kubernetes worker with local PV provisioning: M.2 boot + 4-8 SSDs for CSI-attached persistent volumes. Bays scale with the per-node PV workload.
- vSAN single-disk-group host: 1 cache SSD + 4-7 capacity drives is a single vSAN disk group, perfectly served by 8 bays. Two disk groups per host pushes you toward the 10-Bay, which is exactly why the 10-Bay exists.
- Application server with local SSD storage: 2 drives RAID 1 OS + 2-4 SSDs for application/log volumes. 8 bays is more than enough.
- Veeam proxy or distributed component: 2 drives RAID 1 + 2-4 SSDs for staging or cache. Typical proxy build fits cleanly in 8 bays.
Storage and Controllers
Eight 2.5" SAS/SATA hot-swap bays on the standard backplane. SAS SSDs, SATA SSDs, SAS HDDs at 10K and 15K, and NL-SAS SFF drives are all supported. Controller options are the full Smart Array Gen10 family covered on the 10-Bay canonical page: P408i-a SR (2 GB FBWC, mainstream production controller), P816i-a SR (4 GB FBWC, write-heavy or tri-mode requirements), E208i-a SR (HBA mode for vSAN, Ceph, S2D, ZFS), and S100i SR (software RAID, boot-only).
For 8-Bay deployments specifically, the P408i-a is the right controller in 90%+ of cases. Its 2 GB FBWC is sized appropriately for the I/O patterns 8 SFF drives produce in a 1U chassis. The P816i-a's larger cache earns its place at higher drive counts (16+ bays in the DL380 platform) where cache pressure becomes a real bottleneck; in the 1U 8-Bay envelope, the P408i-a almost always covers the working set. The E208i-a HBA is the right pick for any software-defined storage workload, and S100i should only be used for OS boot mirroring when no Smart Array P-series is in the build.
FBWC battery is a wear item with roughly 5-year service life - same caveat that applies to every P-series Smart Array, documented on the canonical page and disclosed on every build quote.
Boot Drive Options
HPE M.2 enablement kit is the cleanest boot solution on the DL360 Gen10 8-Bay. It mounts in a PCIe slot, takes a SATA M.2 drive (typically 480 GB), and frees all 8 SFF bays for data. Strongly recommended when you're using all 8 bays for the workload's data tier.
Alternative: 2x SFF SAS or SATA SSDs in two of the 8 bays under hardware RAID 1, consuming 2 bays for OS. This is the right approach when the M.2 kit isn't available or when you're not using all 8 bays for data and don't mind giving up two of them for OS mirroring. For a build with 4-6 data drives, the 2-bay OS mirror is perfectly reasonable.
HPE NS204i-p (the dedicated dual-NVMe M.2 boot device) is a Gen10 Plus and Gen11 feature, not a Gen10 option. If you need NVMe boot specifically on Gen10, it's via the M.2 enablement kit (SATA M.2) or via a PCIe-attached NVMe drive routed to a specific bay - not via NS204i-p.
Processors, Memory, and Networking
Same as the canonical: dual-socket LGA 3647 Purley platform, 1st Gen and 2nd Gen Xeon Scalable drop-in compatible, 24 DDR4 DIMM slots, DDR4-2933 on Gold 6200/5222 (DDR4-2666 on the rest), up to 1.5 TB RDIMM or 3 TB LRDIMM dual-socket, HPE Smart Memory required for rated speed operation. The full processor and memory documentation lives on the 10-Bay canonical page.
Networking: HPE FlexibleLOM mezzanine slot (does not consume PCIe) for the primary network interface, 3 PCIe Gen3 slots in the standard riser configuration for HBAs, additional NICs, or up to two single-width T4-class GPUs. The 1U PCIe constraint is the same as the 10-Bay; the bay-count difference doesn't change the PCIe layout.
The 8-Bay vs. 10-Bay Decision
Three questions decide it:
- Does your storage design fit in 8 bays? If yes - and for most virtualization, application, and compute-primary deployments, yes - the 8-Bay is the right choice. The 10-Bay's premium isn't justified.
- Are you running vSAN with two disk groups per host, or Ceph at 10 OSDs per 1U? If yes, the 10-Bay's two extra bays land in a specific cluster math problem. Take the 10-Bay.
- Is the per-node data-drive count in your design 9 or 10? This usually means a distributed database or storage workload with explicit 1U density requirements. Take the 10-Bay.
If the answer to all three is no, the 8-Bay is the cleaner pick. Same processors, same memory, same management, same controllers - just two fewer bays and a slightly lower price.
Workload Fit
| This server excels at | Consider alternatives for |
|---|---|
| ✅ Standard 1U virtualization hosts (vSphere, Hyper-V, KVM) | ❌ vSAN 2-disk-group hosts (use 10-Bay) |
| ✅ Application servers with local SSD datastores | ❌ Ceph at 10 OSDs per 1U (use 10-Bay) |
| ✅ Kubernetes worker pools with M.2 boot + 4-8 PVs | ❌ LFF drive requirements in 1U (use 4-Bay 3.5") |
| ✅ Scale-out compute clusters in HPE shops | ❌ More than 8 SFF bays needed (use DL380) |
| ✅ Veeam proxies and distributed backup infrastructure | ❌ GPU compute beyond 2x T4 (use DL380) |
| ✅ SAN-connected compute with minimal local storage | ❌ PCIe Gen4 NVMe bandwidth required (use Gen10 Plus) |
Honest Limitations
Same generational caveats as the rest of the DL360 Gen10 family: PCIe Gen3 (modern Gen4 NVMe runs at half rated bandwidth), DDR4-2933 maximum memory speed (Ice Lake-SP and Sapphire Rapids beat it), 1U thermal envelope constrains top-bin Platinum CPUs, FBWC battery is a wear item, iLO Advanced licensing is typically separate on refurbished units, HPE Smart Memory required for rated DIMM speed. The 10-Bay canonical covers each of these in detail. Same platform, same generation, same constraints - the only thing that changes between 8-Bay and 10-Bay is the bay count itself.
Where to Look Instead
- Need 10 SFF bays at 1U density? → DL360 Gen10 10-Bay 2.5" (canonical)
- Need LFF drives in 1U? → DL360 Gen10 4-Bay 3.5"
- Need more PCIe slots, more bays, or GPU compute? → DL380 Gen10 16-Bay 2.5"
- Dell shop alternative? → Dell PowerEdge R640 8-Bay 2.5" - architectural counterpart on the Dell side
Ready to Configure?
Tell us the workload, CPU SKU preference (or per-socket core count and clock target), memory capacity, storage configuration including controller preference, network topology and FlexibleLOM choice, and quantity. We respond within 24 hours, every refurbished unit ships with the 180-day warranty and 12+ hour burn-in, and volume pricing starts at 5 units. Call 1-800-778-1545 or use the quote form below.
Save Your Design
Click the Add to Quote button at the bottom of your screen to save your design as a draft order for future reference and to check for discounts, lead time, and availability. Most servers ship within 1-3 days.
