Ask HN: Do you find working on large distributed systems exhausting?

Re:Ask HN: Do you find working on large distributed systems ... by dekhn on Saturday February 19, 2022 @12:10PM (#30398601)

"1 pb is only 56 large enterprise hdds".

umm, what happens when one fails?

With large cloud my startup had excellent support. We negotiated a contract. That's how it works.

[ Parent | on HN ]

Re:Ask HN: Do you find working on large distributed systems ... by fxtentacle on Saturday February 19, 2022 @01:25PM (#30399235)

Typically people use RAID or ZFS to prevent data loss when a few hdds fail.

[ Parent | on HN ]

Re:Ask HN: Do you find working on large distributed systems ... by dekhn on Saturday February 19, 2022 @01:27PM (#30399255)

OK, so basically you're in a completely different class of expectations about how systems perform under disk loss and heavy load then me. A drive array is very different from large-scale cloud storage.

[ Parent | on HN ]

Re:Ask HN: Do you find working on large distributed systems ... by fxtentacle on Saturday February 19, 2022 @01:55PM (#30399491)

Hard to say. My impression is:

- A large ZFS pool of SSDs is much faster than any cloud storage.

- Cloud storage failed much more often than the SSDs in our pool.

- "Noisy neighbor" is an issue on the cloud

[ Parent | on HN ]

Re:Ask HN: Do you find working on large distributed systems ... by qorrect on Saturday February 19, 2022 @05:36PM (#30401190)

This cracked me up. Thanks fxtentacle :D.

[ Parent | on HN ]

Re:Ask HN: Do you find working on large distributed systems ... by dekhn on Monday February 21, 2022 @10:00AM (#30416573)

of course, the reason that's wrong is that if one drive fails you don't have a 56pb storage system, you have something smaller because of redundancy.

That redundancy, and the performance that scales due to it, place cloud services in an entirely different class from on prem servers.

[ Parent | on HN ]