Is ZFS production ready?

[Matthias Gamsjager]

On 21 jun. 2012, at 17:15, Wojciech Puchar <wojtek at wojtek.tensor.gdynia.pl> wrote:

>> 
>> I do understand your setup but I dont have too agree that it is a good
> 
> so i would repeat my question.
> Assume you have 48 disks, in mirrored configuration (24 mirrors) and 480 users with their data on them.
> 
> Your solution with ZFS - ZFS crashes or you get double disk failure.
> Assuming the latter by average one per 24 file (randomly chosen) is destroyed which - in practice and limited time, means everything destroyed. Actually more than one per 24 - large files can be spread over.
> 
> Your solution with UFS - better as there is fsck which slowly but successfully repairs problem. with double disk failure - the same!
> 
> 
> You restore everything from backup (i assume you have one). This takes like a day or more, one or two complete work days lost+all users in practice lost everything  since last backup.
> 
> My solution with UFS - fsck in case of failure work in parallel on 24 disks so not that long. double disk failure means losing data of 1/24 users.
> 
> every one per 24 user cannot work, others work and i without any stress do recover this 1/24 of users data from backup after putting replacement disks.
> 
> 1/24 of users lost data since last backup, and some hours of time.
> 
> 
> Even assuming ZFS is perfect then we both have problems as often, but my problems are 1/24 as severe as yours.
> 
> 
> Just don't ask me for help when unhappy users will want to cut off your head.
> 
>>> And you've never seen me, yet i still exist.
>>> 
>> 
>> Really? that's you anwser to my question. The most childish answer I could
> 
> stupid answer to stupid question.
> You never seen - but they do happens.

In other topic you hammerd on  fact and if someone ask you to deliver them its a stupid question. 

And about the dram error. I really hope you do use ecc memory in production which renders your scenario invalide. And even then its a claim made by you some random dude on a list. 

Without proper test scenario and documentation such claims are just useless. 

And a proper layout zfs will withstand a double disk failure with zero downtime...where younhave to tell your customer they just lost a day work