Ceph on Damien Dye's Blog https://blogs.damiendye.uk/en/tags/ceph/ Recent content in Ceph on Damien Dye's Blog Hugo en-GB Thu, 27 Aug 2026 13:00:00 +0100 Who Actually Writes & Uses Ceph https://blogs.damiendye.uk/en/ceph/who-actually-writes-and-uses-ceph/ Thu, 27 Aug 2026 13:00:00 +0100 https://blogs.damiendye.uk/en/ceph/who-actually-writes-and-uses-ceph/ I counted every commit to Ceph's main branch for the last ten years, traced every maintainer to the company that employs them, and gathered the public deployments. 69,613 commits, 1,718 people, 478 organisations, and a project that has outlived most of the companies that built it. Tri-Mode Adapters Buy Flexibility With Your NVMe Queues https://blogs.damiendye.uk/en/hardware/tri-mode-adapters-nvme-as-sas/ Thu, 13 Aug 2026 09:00:00 +0100 https://blogs.damiendye.uk/en/hardware/tri-mode-adapters-nvme-as-sas/ A tri-mode adapter lets any bay take SAS, SATA or NVMe, which is why U.3 backplanes exist. What it hides: your NVMe drives arrive in Linux as SCSI disks on mpt3sas, queue depth 128, sharing one tag pool and one x8 uplink. Two Gen4 drives saturate the card, one Gen5 is already past it. Whether the trade still makes sense in 2026. Making HDD-Backed Proxmox Ceph Clusters Fast — NVMe Metadata, One Optane Per Spindle, and What It Costs You https://blogs.damiendye.uk/en/proxmox/hdd-backed-ceph-bcache-optane/ Fri, 07 Aug 2026 20:00:00 +0100 https://blogs.damiendye.uk/en/proxmox/hdd-backed-ceph-bcache-optane/ Flash pricing has made all-NVMe hard to justify, and enterprise HDDs are worth another look. Acceptable latency out of them on hyper-converged Proxmox Ceph: move RocksDB off the spindle, pair each disk with its own Optane through bcache (Optane, because NAND endurance is wrong for the job), and be honest about the failure modes it buys. A Switchless Proxmox Mesh with SDN OpenFabric — Ceph and Client Networks Without a 100G Switch https://blogs.damiendye.uk/en/proxmox/proxmox-routed-mesh-sdn-openfabric/ Fri, 07 Aug 2026 16:00:00 +0100 https://blogs.damiendye.uk/en/proxmox/proxmox-routed-mesh-sdn-openfabric/ Three Proxmox nodes wired directly to each other in a triangle, with OpenFabric routing over the mesh and Ceph plus VXLAN client networks riding on top. Built entirely in the web interface, and honest about where the design stops scaling. A VM's Clock Cannot Be Trusted — and the ptp_kvm Fix for QEMU/KVM https://blogs.damiendye.uk/en/proxmox/vm-time-ptp-kvm/ Fri, 07 Aug 2026 13:00:00 +0100 https://blogs.damiendye.uk/en/proxmox/vm-time-ptp-kvm/ A virtual machine's clock is built on an assumption virtualisation breaks: that the CPU keeps counting. Why guest time drifts on every hypervisor, what the skew actually breaks — Kerberos, TLS, Ceph, Windows — and how ptp_kvm fixes it properly on QEMU/KVM. 4Kn, 512e and 512n — Why Native 4K Wins, and What the Emulation Costs https://blogs.damiendye.uk/en/proxmox/block-sizes-4kn-512e/ Fri, 07 Aug 2026 12:00:00 +0100 https://blogs.damiendye.uk/en/proxmox/block-sizes-4kn-512e/ 512e drives present 512-byte sectors they do not have, and the firmware makes up the difference on every unaligned write. What that costs on the medium, in the host and in write amplification — why direct synchronous writes are the worst case — and how to convert a fleet to 4Kn.