Notices by nepi (nepi@fedi.snepi.space)

Embed this notice
nepi (nepi@fedi.snepi.space)'s status on Sunday, 27-Nov-2022 12:06:58 JST nepi
in reply to
- arcanicanis
@arcanicanis Interesting! I remembered hearing about the exFAT patent thing a few years back. Never really had a use for it, personally.

For what it's worth, we investigated ZFS when rebuilding that doc server, but we just couldn't get the performance to a usable state. These were Ubuntu VMs within vCenter running on (i believe) a Cisco UCS chassis with some external SAN appliance. It just didn't work out, there was probably some bottleneck somewhere. On that same chassis we had absolute *garbage* performance with an infinidat appliance so I hesitate to place the blame on ZFS.

In conversation Sunday, 27-Nov-2022 12:06:58 JST from fedi.snepi.space permalink
Embed this notice
nepi (nepi@fedi.snepi.space)'s status on Sunday, 27-Nov-2022 11:54:51 JST nepi

Docker desktop don't use 4GB of ram to run one Alpine container challenge (IMPOSSIBLE)

In conversation Sunday, 27-Nov-2022 11:54:51 JST from fedi.snepi.space permalink
Embed this notice
nepi (nepi@fedi.snepi.space)'s status on Sunday, 27-Nov-2022 11:52:23 JST nepi
in reply to
- arcanicanis
@arcanicanis Yup, it’s an rPi running OpenWRT. This isn’t the first EXT4 file system I’ve had spontaneously explode. At a previous job we had one which held several hundred gigs of document scans bite the dust completely out of the blue. We switched to XFS afterwards.

I’ll have to look into F2FS! I don’t really dabble in the embedded linux world so I wasn’t even really aware of it haha

In conversation Sunday, 27-Nov-2022 11:52:23 JST from fedi.snepi.space permalink
Embed this notice
nepi (nepi@fedi.snepi.space)'s status on Sunday, 27-Nov-2022 11:39:21 JST nepi
in reply to
- arcanicanis
@arcanicanis Holy shit, was this on a 1st gen Ryzen processor, by chance? I bought one off eBay and had similar issues in a B350 chipset board until I disabled C-States! I think there was a bad run of early first gen 1700s.

In another hilarious coincidence, I also had ZFS arrays hooked up to that thing when it started failing. It survived as well, but I was really sweating when I started getting drives dropping out of arrays due to write errors because of segfaults.

In conversation Sunday, 27-Nov-2022 11:39:21 JST from fedi.snepi.space permalink
Embed this notice
nepi (nepi@fedi.snepi.space)'s status on Sunday, 27-Nov-2022 11:26:02 JST nepi

Aaaand it's looking like I bought a replacement CPU for no reason. Oh well, guess it goes into the ZFS box!

In conversation Sunday, 27-Nov-2022 11:26:02 JST from fedi.snepi.space permalink
Embed this notice
nepi (nepi@fedi.snepi.space)'s status on Sunday, 27-Nov-2022 11:26:01 JST nepi
in reply to
- nepi
The series of unfortunate events went something like this:

- pull out CPU from socket in the wrong way (red herring)
- in the process of removing/reinstalling the CPU, the PCIE riser cable goes from a marginal connection to one that no longer works
- machine no longer boots
- attempt to re-seat cable, but attempt wasn't good enough as it's really difficult to manipulate when the machine is fully installed in the case
- become increasingly convinced that the problem is the CPU even though the lights on the motherboard get stuck at the VGA step (initializing the VGA is handled directly by the CPU over PCIE so a problem with the CPU could manifest itself as being unable to initialize graphics)
- reset the BIOS, which changes the default PCIE protocol to PCIE 4.0, which the riser cable does not support (apparently there's no way to fall back to lesser protocols if both devices negotiate PCIE4 at initialization?)
- swap GPUs for a GPU that I thought was good, but appears to be bad or at least incompatible with ryzen 5000 systems
- install CPU in old motherboard with different RAM, with said bad GPU, machine gets stuck at DIMM training for an improbably long time
- become convinced problem is the cpu
- order new CPU and install it into current motherboard, problem still persists
- plug full-fat GPU into old motherboard with old CPU, machine boots just fine
- reconsider every choice in my life until this point
- plug full-fat GPU into current motherboard with new CPU and reconfigure the PCIE link to 3.0
- rebuild entire system, boots fine

In conversation Sunday, 27-Nov-2022 11:26:01 JST from fedi.snepi.space permalink
Embed this notice
nepi (nepi@fedi.snepi.space)'s status on Sunday, 27-Nov-2022 10:20:34 JST nepi
in reply to
- nepi
[26518752.530874] EXT4-fs (mmcblk0p2): re-mounted. Opts: (null)
:)))))))))))))))))

In conversation Sunday, 27-Nov-2022 10:20:34 JST from fedi.snepi.space permalink
Embed this notice
nepi (nepi@fedi.snepi.space)'s status on Sunday, 27-Nov-2022 10:20:34 JST nepi

“I never thought that EXT4 would blow up on ME, said person who voted for the EXT4-as-default-root-filesystem party”

In conversation Sunday, 27-Nov-2022 10:20:34 JST from fedi.snepi.space permalink
Embed this notice
nepi (nepi@fedi.snepi.space)'s status on Sunday, 27-Nov-2022 10:11:00 JST nepi
in reply to
- arcanicanis
@arcanicanis Wow, I managed to grab a couple 10tb drives at ~200/drive a few years ago, and that was shucking portable drives that weren't even NAS grade. Crazy that CMRs are still coming down in price per TB!

In conversation Sunday, 27-Nov-2022 10:11:00 JST from fedi.snepi.space permalink

Public

Notices by nepi (nepi@fedi.snepi.space)

User actions

Following 0

Followers 0

Groups 0

Statistics

Feeds