[Hyprland] Minflair 2.1.0 — native OSDs, dynamic SDDM and new shell modules
Link: https://redd.it/1xhx85w
#unixporn #linux #screenshot
Link: https://redd.it/1xhx85w
#unixporn #linux #screenshot
October 28, 2026 at 7:12 PM
[Hyprland] Minflair 2.1.0 — native OSDs, dynamic SDDM and new shell modules
Link: https://redd.it/1xhx85w
#unixporn #linux #screenshot
Link: https://redd.it/1xhx85w
#unixporn #linux #screenshot
Ceph NVMe/HDD tiering: set a CRUSH device class on NVMe OSDs, create a replicated rule scoped to that class, bind a pool to it. Hot data on flash, bulk on spinning disk. https://www.valtersit.com/vault/configure-crush-device-classes-and-rule-for-nvme-vs-hdd-tier-d6fa6c/
Configure CRUSH Device Classes and Rule for NVMe vs HDD Tiering
www.valtersit.com
October 28, 2026 at 2:50 AM
Ceph NVMe/HDD tiering: set a CRUSH device class on NVMe OSDs, create a replicated rule scoped to that class, bind a pool to it. Hot data on flash, bulk on spinning disk. https://www.valtersit.com/vault/configure-crush-device-classes-and-rule-for-nvme-vs-hdd-tier-d6fa6c/
Today I discovered Monitor Control: github.com/MonitorContr...
My monitor's menu button is broken. This solves that problem nicely.
My monitor's menu button is broken. This solves that problem nicely.
GitHub - MonitorControl/MonitorControl: 🖥 Control your display's brightness & volume on your Mac as if it was a native Apple Display. Use Apple Keyboard keys or custom shortcuts. Shows the native macO...
🖥 Control your display's brightness & volume on your Mac as if it was a native Apple Display. Use Apple Keyboard keys or custom shortcuts. Shows the native macOS OSDs. - MonitorControl/Moni...
github.com
October 18, 2026 at 5:36 PM
Today I discovered Monitor Control: github.com/MonitorContr...
My monitor's menu button is broken. This solves that problem nicely.
My monitor's menu button is broken. This solves that problem nicely.
Currently on attempt 3, a few hours in, manually upgrading OSDs (will need to upgrade 12 of 16)
BTW any time you specify "INCORRECT" for an ID, you know you're doing it wrong.
At least now I know why Ceph says to upgrade cephadm after upgrading the cluster 🫠
BTW any time you specify "INCORRECT" for an ID, you know you're doing it wrong.
At least now I know why Ceph says to upgrade cephadm after upgrading the cluster 🫠
September 5, 2026 at 12:02 PM
Currently on attempt 3, a few hours in, manually upgrading OSDs (will need to upgrade 12 of 16)
BTW any time you specify "INCORRECT" for an ID, you know you're doing it wrong.
At least now I know why Ceph says to upgrade cephadm after upgrading the cluster 🫠
BTW any time you specify "INCORRECT" for an ID, you know you're doing it wrong.
At least now I know why Ceph says to upgrade cephadm after upgrading the cluster 🫠
I sized every Ceph database at 4% and reserved 2,887 GiB of NVMe. Nineteen of them use 87.
The docs weren't wrong. I'd treated the conservative number like a measurement of my workload.
Then the 500x benchmark failed the same test. I'd measured a sick cluster, then a healthy one.
The docs weren't wrong. I'd treated the conservative number like a measurement of my workload.
Then the 500x benchmark failed the same test. I'd measured a sick cluster, then a healthy one.
I reserved 2,887 GiB for metadata. Ceph uses 87. · ProbablyFine
I sized BlueStore metadata for nineteen spinning-disk OSDs at 4% and reserved 2,887 GiB. They use 87.2 GiB, and the benchmark I was about to publish turned out to be a benchmark of my own VM.
probablyfine.dev
September 2, 2026 at 12:01 AM
I sized every Ceph database at 4% and reserved 2,887 GiB of NVMe. Nineteen of them use 87.
The docs weren't wrong. I'd treated the conservative number like a measurement of my workload.
Then the 500x benchmark failed the same test. I'd measured a sick cluster, then a healthy one.
The docs weren't wrong. I'd treated the conservative number like a measurement of my workload.
Then the 500x benchmark failed the same test. I'd measured a sick cluster, then a healthy one.
that is definitely a part of it, but this has also happened outside of osds, though to a lesser extent thankfully
July 21, 2026 at 6:22 PM
that is definitely a part of it, but this has also happened outside of osds, though to a lesser extent thankfully
I mean, it performs better/faster for reads now than it did before (technically, reads can be spread across the 3 hosts, and reads can leverage parallel reads from 4 OSDs at once... per host... in theory)... But oooof... that's a lot of overhead to get there.
June 5, 2026 at 6:31 AM
I mean, it performs better/faster for reads now than it did before (technically, reads can be spread across the 3 hosts, and reads can leverage parallel reads from 4 OSDs at once... per host... in theory)... But oooof... that's a lot of overhead to get there.
8 of the 10 OSDs have updated their metadata… waiting on the last two which are taking a while.
In the meantime, the RBD volume that runs PostgreSQL is blocked… so I'll hang around on here for a hour or two.
In the meantime, the RBD volume that runs PostgreSQL is blocked… so I'll hang around on here for a hour or two.
June 30, 2025 at 10:48 PM
8 of the 10 OSDs have updated their metadata… waiting on the last two which are taking a while.
In the meantime, the RBD volume that runs PostgreSQL is blocked… so I'll hang around on here for a hour or two.
In the meantime, the RBD volume that runs PostgreSQL is blocked… so I'll hang around on here for a hour or two.
"Lessons from Skittles for poets and activists" now up on The Seminal -- thanks all for the help! <a href="http://is.gd/osDS" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">http://is.gd/osDS #p2 #rebelleft #topprog
November 6, 2024 at 7:23 PM
"Lessons from Skittles for poets and activists" now up on The Seminal -- thanks all for the help! <a href="http://is.gd/osDS" class="hover:underline text-blue-600 dark:text-sky-400 no-card-link" target="_blank" rel="noopener" data-link="bsky">http://is.gd/osDS #p2 #rebelleft #topprog
yeah, send it! two of my ceph boxes are also doing some compute tasks (mostly VMs) and it's been running fine. proxmox is nice, i'm not using their built-in ceph tools but i do have ceph daemons and OSDs running /on/ proxmox hosts (cephadm is good and you should probably use it instead of prox's)
November 21, 2025 at 7:03 PM
yeah, send it! two of my ceph boxes are also doing some compute tasks (mostly VMs) and it's been running fine. proxmox is nice, i'm not using their built-in ceph tools but i do have ceph daemons and OSDs running /on/ proxmox hosts (cephadm is good and you should probably use it instead of prox's)
MX17S 2/3: The monitor is from 1993! and is still sharp and bright. It is from an era when analogue geometry controls were being replaced by digital ones, but before OSDs became common. So it has its own backlit LCD screen showing its status. Some analogue controls are found behind knobs or pots.
July 14, 2025 at 12:43 AM
MX17S 2/3: The monitor is from 1993! and is still sharp and bright. It is from an era when analogue geometry controls were being replaced by digital ones, but before OSDs became common. So it has its own backlit LCD screen showing its status. Some analogue controls are found behind knobs or pots.
Auf einmal würdest du Entdeckt, ÖSDS
January 6, 2025 at 10:32 AM
Auf einmal würdest du Entdeckt, ÖSDS
🔴 Des pertes colossales ▶️ https://l.bfmtv.com/oSds
May 7, 2026 at 3:20 PM
🔴 Des pertes colossales ▶️ https://l.bfmtv.com/oSds
dude cmon the osds literally also calls me a kitty
November 20, 2024 at 12:51 PM
dude cmon the osds literally also calls me a kitty
A little gem of a tool for macOS is github.com/MonitorContr.... It enables you to use your brightness control keys on any third party monitor.
GitHub - MonitorControl/MonitorControl: 🖥 Control your display's brightness & volume on your Mac as if it was a native Apple Display. Use Apple Keyboard keys or custom shortcuts. Shows the native macO...
🖥 Control your display's brightness & volume on your Mac as if it was a native Apple Display. Use Apple Keyboard keys or custom shortcuts. Shows the native macOS OSDs. - MonitorControl/Moni...
github.com
November 14, 2024 at 1:35 PM
A little gem of a tool for macOS is github.com/MonitorContr.... It enables you to use your brightness control keys on any third party monitor.
Learning some useful ceph commands this weekend, namely "ceph osd tree" for listing where the osds are, and "ceph device ls" for listing what device osds are using
September 7, 2025 at 10:49 AM
Learning some useful ceph commands this weekend, namely "ceph osd tree" for listing where the osds are, and "ceph device ls" for listing what device osds are using
cluster looks happy
cluster:
id:
health: HEALTH_OK
services:
mon: 3 daemons, quorum e,f,g (age 14m)
mgr: b(active, since 11m), standbys: a
mds: 1/1 daemons up, 1 standby
osd: 8 osds: 8 up (since 16m), 8 in (since 16m)
rgw: 2 […]
cluster:
id:
health: HEALTH_OK
services:
mon: 3 daemons, quorum e,f,g (age 14m)
mgr: b(active, since 11m), standbys: a
mds: 1/1 daemons up, 1 standby
osd: 8 osds: 8 up (since 16m), 8 in (since 16m)
rgw: 2 […]
Original post on transitory.social
transitory.social
May 21, 2025 at 8:25 PM
cluster looks happy
cluster:
id:
health: HEALTH_OK
services:
mon: 3 daemons, quorum e,f,g (age 14m)
mgr: b(active, since 11m), standbys: a
mds: 1/1 daemons up, 1 standby
osd: 8 osds: 8 up (since 16m), 8 in (since 16m)
rgw: 2 […]
cluster:
id:
health: HEALTH_OK
services:
mon: 3 daemons, quorum e,f,g (age 14m)
mgr: b(active, since 11m), standbys: a
mds: 1/1 daemons up, 1 standby
osd: 8 osds: 8 up (since 16m), 8 in (since 16m)
rgw: 2 […]
Almost moved the ceph OSDs to the new hardware :neocat_floof:
I should probably figure out how to monitor to see if the network is bottlenecking anything
I should probably figure out how to monitor to see if the network is bottlenecking anything
May 21, 2025 at 7:24 PM
Almost moved the ceph OSDs to the new hardware :neocat_floof:
I should probably figure out how to monitor to see if the network is bottlenecking anything
I should probably figure out how to monitor to see if the network is bottlenecking anything
Ok looks like it I is rebalancing nodes
Now to see if I can figure out the command to monitor the rebalance before the rebalance itself finishes
From now on I need to add to kick out an old VM-based node so I can reclaim disks each time I add a node
.... Actually wait, could I just move OSDs […]
Now to see if I can figure out the command to monitor the rebalance before the rebalance itself finishes
From now on I need to add to kick out an old VM-based node so I can reclaim disks each time I add a node
.... Actually wait, could I just move OSDs […]
Original post on transitory.social
transitory.social
May 12, 2025 at 5:34 PM
Ok looks like it I is rebalancing nodes
Now to see if I can figure out the command to monitor the rebalance before the rebalance itself finishes
From now on I need to add to kick out an old VM-based node so I can reclaim disks each time I add a node
.... Actually wait, could I just move OSDs […]
Now to see if I can figure out the command to monitor the rebalance before the rebalance itself finishes
From now on I need to add to kick out an old VM-based node so I can reclaim disks each time I add a node
.... Actually wait, could I just move OSDs […]
Cluster rebuild planning:
I can punt the node idea by just running two ceph VMS on the fileserver/proxmox (plenty of space to shove drives)
When I finally build out a decent third node I can move the disks/osds over there
Only one problem.
The server rack is downstairs and I am really cozy […]
I can punt the node idea by just running two ceph VMS on the fileserver/proxmox (plenty of space to shove drives)
When I finally build out a decent third node I can move the disks/osds over there
Only one problem.
The server rack is downstairs and I am really cozy […]
Original post on transitory.social
transitory.social
January 16, 2025 at 1:15 AM
Cluster rebuild planning:
I can punt the node idea by just running two ceph VMS on the fileserver/proxmox (plenty of space to shove drives)
When I finally build out a decent third node I can move the disks/osds over there
Only one problem.
The server rack is downstairs and I am really cozy […]
I can punt the node idea by just running two ceph VMS on the fileserver/proxmox (plenty of space to shove drives)
When I finally build out a decent third node I can move the disks/osds over there
Only one problem.
The server rack is downstairs and I am really cozy […]
[LIVE ON] Segue o link:
「 www.youtube.com/watch?v=OSdS... 」
「 www.youtube.com/watch?v=OSdS... 」
Após o fim vamos para a DLC! [AI LIMIT] - Parte 12
YouTube video by EruShido274
www.youtube.com
April 8, 2026 at 12:00 AM
[LIVE ON] Segue o link:
「 www.youtube.com/watch?v=OSdS... 」
「 www.youtube.com/watch?v=OSdS... 」