#CephFS
LightNews LightNews
selectric.space
cephfs
January 23, 2026 at 4:47 AM
owo.me
feeling cute, made an intrusive thought real
a github commit of a deployment of a bsky relay on cephfs
November 19, 2024 at 1:40 PM
rachel.transitory.social.ap.brid.gy
Uggh whelp

Somehow there are old snapshots clogging ceph

Might have been created via velero? The dashboard is slightly on fire which is a problem for troubleshooting it

It looks like there is a cephfs subvol that is straight up duplicated and not a cephfs snapshot? That has got to be velero […]
Original post on transitory.social
transitory.social
September 22, 2026 at 2:18 PM
anil.recoil.org
I think we just accidentally created one of the biggest storage clusters in Cambridge by pooling together our individual machines into ~1.5PB of usable CephFS storage (for TESSERA embeddings, datasets like GBIF, OpenAlex, OpenStreetmap, AGB maps, downloaded fulltext papers etc)
February 9, 2026 at 4:08 PM
usrbinkat.io
I've deployed ceph on openstack, vanilla kubernetes, and openshift before but I've never actually deployed it from scratch with the dashboard or any rados gateway features enabled.

I'm literally giddy right now.
A screenshot shows the Ceph Dashboard web interface at ceph.0ac949c3.sslip.io displaying a distributed storage cluster overview. The dark purple sidebar navigation lists sections for Dashboard, Multi-Cluster, Cluster management including Pools, Hosts, OSDs, Physical Disks, CRUSH Map, and Monitors, plus Block storage with Images, Mirroring, iSCSI, and NVMe/TCP, Object storage with Buckets, Gateways, and NFS, File storage with CephFS and SMB, Observability with Logs and Alerts, and Administration. The main dashboard shows Details panel listing Cluster ID fd8939c6-d8ac-4a06-b020-cba4c2e8a9c6, Ceph version 20.2.0 tentacle stable, Orchestrator not available, and Telemetry Dashboard inactive. Status panel displays a red error indicator for Cluster health. Capacity shows 0.01% used with 544 MiB of 31.4 TiB total. Inventory lists 3 Hosts, 3 Monitors, 2 Managers with one showing info status, 9 OSDs, 28 Pools, 617 PGs, and 1 Object Gateway, all with green checkmarks except the manager warning. Cluster Utilization graphs for the last hour show minimal activity across Used Capacity, IOPS, OSD Latencies, Client Throughput, and Recovery Throughput. This cluster runs on Talos Linux 1.11.5 with Kubernetes 1.34.2, deployed entirely via Pulumi Python infrastructure as code without Helm or kubectl. The health error stems from a Prometheus module string formatting failure and recent manager crashes, though all 617 placement groups report active and clean. The 31 TiB raw capacity across 9 OSDs provides CephFS, RBD block storage, and S3-compatible object storage via the RADOS Gateway.
November 23, 2025 at 4:25 AM
usrbinkat.io
So tempted to turn replication off to get that raw speeeeed...

But if I wanted speed I'd find a sugar to buy me ConnectX-6 Lx.

Girl's gotta choose between shoes and the rack. Inconceivable.
A screenshot shows Claude Code in a tmux terminal session displaying a YAML diff adding a new NVMe-tier CephFS configuration to Pulumi.optiplex-admin-storage.yaml. Green highlighted lines from 475 to 490 show the new block being added with comment NVMe tier CephFS 1TB WD SN850X TLC. The configuration defines enabled true, name rook-cephfs-nvme, filesystem name cephfs-nvme, pool name data0, device class nvme, is_default false, replicated_size 2, metadata_replicated_size 3, reclaim_policy Delete, allow_volume_expansion true, volume_binding_mode WaitForFirstConsumer, mds_active_count 1, mds_standby_count 1, and pg_autoscale_mode_data and metadata both set to on. Below the new block, the existing SSD tier CephFS configuration beginning with rook-cephfs-ssd remains visible for context. Claude Code prompts with option 1 Yes selected. This adds a dedicated NVMe-backed CephFS filesystem alongside the existing SSD tier, creating a high-performance storage class on the newly installed WD_BLACK SN850X drives. CephFS provides ReadWriteMany access mode essential for KubeVirt live migration, where virtual machine disks must be simultaneously accessible from both source and destination nodes during migration. The replicated_size of 2 balances redundancy with capacity across the three-node cluster, while WaitForFirstConsumer binding ensures volumes are provisioned on nodes with available NVMe-class OSDs.
June 25, 2026 at 5:09 AM
ceph.io
#Storage costs are up, but your hardware budget doesn't have to follow.

Learn how #CephFS file layout transcoding can reclaim raw capacity by moving data to erasure-coded pools with minimal disruption.

Read the blog: t.ly/cephfs-trans...
#Ceph #OpenSource #CephCommunity
June 30, 2026 at 4:45 PM
meldingen.mastodon.bit.nl.ap.brid.gy
BIT Onderhoud - Spoedonderhoud shared filesysteem (CephFS)
https://www.bit.nl/meldingen/spoedonderhoud-shared-filesysteem-cephfs/
Spoedonderhoud shared filesysteem (CephFS) » BIT
www.bit.nl
September 17, 2026 at 7:30 PM
ceph.io
🚨 Attention, #Seattle Ceph Friends! #CephDaysSeattle is tomorrow! 🚨

This #CephDays event will cover:
• #CloudNative and Edge Deployments
• #CephFS Capacity
• Real-world user stories
• And more...

Tickets here: t.ly/CephSeattle2...
#OpenSource #Storage
May 27, 2026 at 9:00 AM
kubernetes.activitypub.awakari.com.ap.brid.gy
CephFS — миграция данных из одного кластера в другой Привет, Хабр! На связи Head of DevOps Владимир Яковлев из Дирекц...

#миграция #данных #CephFS #ceph #cephfs #в #kubernetes

Origin | Interest | Match
December 17, 2025 at 11:27 AM
proyectoa.bsky.social
Crear CephFS para backups en clúster Ceph de proxmox proyectoa.com/crear-cephfs...

Cómo crear un storage CephFS en un clúster de almacenamiento hiperconvergente Ceph sobre nodos Proxmox

#ceph #cephfs #proxmox #storage #backup #copia #seguridad #almacenamiento
Crear CephFS para backups en clúster Ceph de proxmox » Proyecto A
Cómo crear un filesystem CephFS en un clúster de almacenamiento hiperconvergente Ceph sobre nodos Proxmox. Usaremos este tipo de almacenamiento "Directory" como destino del backup de las máquinas virt...
proyectoa.com
December 23, 2025 at 11:02 AM
clyso.bsky.social
Hey folks! #SC24 will soon be upon us! Come visit us at booth 4509 to hear about what we are doing with Ceph. @markhpc.bsky.social will also be giving a lightning talk on how the IO500 is improving CephFS. Join us in Room B20 at 12:15PM on Tue, Nov 19th! lnkd.in/gNC77kpz

#HPC #sc24 #ceph #io500
LinkedIn
This link will take you to a page that’s not on LinkedIn
lnkd.in
November 17, 2024 at 4:13 PM
danvanderster.bsky.social
In 2018 we built a small CephFS for HPC at CERN and it had the 9th highest IO500 score ;) And today at #SC24 my friend and colleague @markhpc.bsky.social showed how we're still keeping that dream alive at @clyso.bsky.social
November 20, 2024 at 7:33 AM
ixmagazin.bsky.social
Cephs Dateisystem CephFS ist mittlerweile produktiv einsetzbar, doch gibt es einiges bei Nutzung und Tuning zu beachten. #Speicher
heise+ | Storage-Software CephFS für Dateisysteme produktiv nutzen und skalieren
Cephs Dateisystem CephFS ist mittlerweile produktiv einsetzbar, doch gibt es einiges bei Nutzung und Tuning zu beachten.
www.heise.de
May 25, 2026 at 5:03 AM
ceph.io
🐙 #Cephalocon Spotlight
Deploying and Operating CephFS for Science Applications – Alison Peisker, @Fermilab
Lessons from running CephFS in production for high-throughput research.
Read more here: t.ly/cephalocon-s...
#Ceph #OpenSource
September 16, 2025 at 11:01 AM
jiridh.bsky.social
Of we even een CephFS cluster van 2PB kunnen opleveren for 16dec.
December 5, 2024 at 3:49 PM
ceph.io
Ceph v18.2.8 (Reef) is out! 🚀

The final expected Reef backport release brings:
🔐 Security fixes (CephFS, mgr alerts)
⚙️ Stability + correctness improvements across RGW, CephFS, BlueStore

Read more: t.ly/Reefv1828
#Ceph #OpenSource #Storage
March 23, 2026 at 4:50 PM
ceph.io
#CephDeveloperSummit 2026, Vampire, wrapped up after two weeks of talks on everything from #RADOS work to #CephFS and #RGW roadmaps.

Sessions are available to watch, offering a glimpse of the project's future direction.

📺️: t.ly/WatchCDS2026
#OpenSource #CephCommunity
August 24, 2026 at 2:37 PM
ceph.io
🐙 #Cephalocon Spotlight
Per-Subvolume IO Metrics in CephFS – Igor Golikov & Alex Markuze, IBM
Granular insights into CephFS performance with new metrics.
Read more here: t.ly/cephalocon-s...
#Ceph #OpenSource
October 7, 2025 at 11:30 AM
ceph.io
🐙 #Cephalocon Spotlight
Deep Dive: CephFS QoS & Fairness – Venky Shankar, IBM
Exploring how to ensure fair resource allocation with QoS in CephFS workloads.
Read more here: t.ly/cephalocon-s...
#Ceph #OpenSource
September 25, 2025 at 10:30 AM
ceph.io
🐙 #Cephalocon Spotlight
CephFS Volume Enhancements for K8s & OpenStack – Rishabh Dave, @IBMcloud
New layouts, better deletion handling, and performance boosts for CephFS PVCs.
Read more here: t.ly/cephalocon-s...
#Ceph #OpenSource
September 16, 2025 at 12:01 PM
blablalinux.be
#Proxmox VE - C'est une question qui revient souvent 😉
Non, je n'ai pas (encore) de stockage distribué #CephFS, et ce, peu importe le cluster❗
En attendant, je m'en passe bien 👍
↪️ pve.proxmox.com/wiki/Deploy_...
December 4, 2024 at 12:48 PM
hierv5.buicha.social.ap.brid.gy
Windowsにcephfsをマウントしてバックアップを移行するなど
November 3, 2024 at 12:59 AM
owo.me
if you do that and get your MDS in a state where all of them are standby-standby, do the unwise + stupid things and do the `ceph fs reset cephfs --yes-i-really-mean-it` thing.

if the journal is bad? yeet it, LOL
cephfs-journal-tool --rank=cephfs:0 journal reset --yes-i-really-really-mean-it
November 17, 2024 at 12:49 PM
phoronix-poster.bsky.social
FSCRYPT Sees Cleanup With Linux 7.3 To Open Door For More Features Like Btrfs Encryption - https://www.phoronix.com/news/Linux-7.3-FSCRYPT
FSCRYPT Sees Cleanup With Linux 7.3 To Open Door For More Features Like Btrfs Encryption
FSCRYPT is the Linux file-system encryption framework for supporting per-directory, transparent encryption. FSCRYPT so far is used by the likes of EXT4, F2FS, and CephFS. For Linux 7.3 there is an important clean-up to the FSCRYPT code to simplify it while also opening the door for new features moving forward into future kernel versions...
www.phoronix.com
August 20, 2026 at 1:23 PM