
Ceph Hardware Recommendations for Small Clusters
Ceph hardware recommendations for small clusters: CPU threads and RAM per OSD, PLP SSDs, 10 Gb/s networking, …

Ceph has no show pools command. Use ceph osd pool ls detail, ceph df and autoscale-status to list pools, read their settings and check usage.
Read the article →
Ceph hardware recommendations for small clusters: CPU threads and RAM per OSD, PLP SSDs, 10 Gb/s networking, …

Add a Ceph OSD without wiping the wrong disk: verify health, inventory the device, dry-run an OSD spec, deplo…

Compare Ceph and GlusterFS by storage model, workload fit, hardware requirements, cluster size, and support o…

How erasure coding and replication differ in space amplification, failure tolerance and write cost, with a k+…

Ceph needs at least 3 nodes, 4 GiB of RAM per OSD by default, 1 to 6 CPU threads per OSD, 1 TiB drives and a …

A triage order for Ceph HEALTH_WARN covering degraded placement groups, nearfull OSDs, missed deep scrubs, au…
A three-replica pool turns a third of raw storage into usable space. A 4+2 erasure-coded pool turns two thirds of it into usable space, and charges for that in write latency and CPU. The calculator takes an OSD count, a drive size and a redundancy profile, and estimates raw capacity, theoretical usable capacity and the sum of default OSD memory targets.
Open the Ceph erasure coding calculatorExpanding an existing cluster? Follow the guide to add an OSD to Ceph for device checks, a deployment preview and rebalance verification.