David Cross @david@mastodon.crossfamilyweb.com

Are you serious?! I bought one thing ever from them directly. Ever. About 2 months ago. This is ridiculous, unacceptable. Lack of proper separation of sevices, why are they storing any credit card numbers? (What is the point of a partial? Why store it at all? PCI-DSS anyone?). Where’s any kind of credit services or notice to the credit carriers themselves, just some 8xx number to call. This is just an atrocious response. Oh and this isn’t a screenshot of the email, they sent it as a picture.

@lattera What has shaken your ZFS beliefs? (I tend to be sympathetic here, I use ZFS semiregularly and frequently stub my toes on bugs, and non-intuitive interactions that I just never do with any other filesystem)

@bcallah holy shit what already?!

...yes.. yes I did

Did I just see 🌩️ ?

@SwiftOnSecurity Could you share some concrete examples?

@bcallah #cdbug :)

@SwiftOnSecurity 😱

@uep @mgerdts I think the key here is that it is a postgres database store, so the recordsize is 8k to align with postgres pagesize, and with ashift of 4k that means BEST case possible compression is 2x, and anything less than 2x is 1x; that means realized compression has to be in the 2.0 to 1.0 range, whereas on the original I was in the 3.x to 4.x range. Math checks out.

@uep @mgerdts definitely not on dedupe. the culprit was ashift

@elliot@microscopic.network The goal here is to actually have all of the snapshots mirrored,and I zpool destroy and zpool create between each attempt, so any mystery snapshots would have to be coming from the original machine that only has 4T.

That said, latest experiment was a success, and ashift was the culprit

@mgerdts Now all I have to do is kill the pool... and restore.. again.. the ... 5th? time is the charm?

@mgerdts AH-HAH... googling indicates that I need to use zdb vs zpool to get ashift values... and.. there we are. ashift of 12 on the new devices and 9 on the old. I think we have the smoking gun... once I was actually looking in the right place. Thanks!

@mgerdts no raidz at all, simple stripe/concat. 4x1T on machine A, 2x4T on machine B.

@mgerdts I did see that checksums are "on" on the source and "skein" on the destination. but on 4t of 8k pages, that's just 16g or 32g of additional space, total (depending on 256bits or 512bits of hashsize, and that's worsecase since that doesn't account for fletcher7 already being 128bits)