Benchmarks Of ZFS-FUSE On Linux Against EXT4, Btrfs

[RealNC]

EXT4 is seriously kicking ass in those benches :P

[kraftman]

Like the fact that ext4 will loose your data ( it has done, no one will trust it for another 5 years ). And btrfs is still a bit raw, but has potential. Still needs a few years worth of enterprise usage to be considered trustworthy.

If this was Ext4 fault and if this happened in enterprise system (which didn't).

It's amazing that linux has so many filesystems to choose from, but not one really good choise

Damn troll. Ext3, Ext4, XFS are great file systems. And no, it's not amazing, but it's something natural, because it's an Operating System which is present probably in every environment. What's the good choice in your opinion?

[andrnils]

who the heck use zfs or btrfs for server work with one disk and no redundancy?

Hopefully no one. But what has that to do with how easy it is to make a backup?

Even with ext4 on a 20 drive raid6 you would potentionally want to do a backup. With or with downtime, that is the question...

[edogawaconan]

Hopefully no one. But what has that to do with how easy it is to make a backup?

Well, actually I'm waiting for benchmark on mirrored/raid(5|z) disks (also the benchmark with failed disk(s)), not on a simple disk.

Even with ext4 on a 20 drive raid6 you would potentionally want to do a backup. With or with downtime, that is the question...

20 drives raid6 sounds like a nightmare.

[kraftman]

BTRFS sucks, and now that it's biggest pusher (Oracle) stopped caring about Linux, I seriously doubt it will ever get better. In fact, Oracle has an incentive to hurt BTRFS and Linux because they're a free alternative (and in direct competition) to their proprietary and revenue-generating Solaris.

While there are demands for ZFS on Linux I don't consider there's any serious competition. If Oracle will slow down btrfs development then people will use ZFS with Linux.

One example it can hurt BTRFS is by not allowing it to be licensed GPL3+ and thus usable in the Grub2 bootloader.

If btrfs will be licensed under GPL3+ then will it be compatible with the rest of the kernel?

[locovaca]

Given /some/dir to be backed up at regular intervals, how much work is involved to do that for the different FSes? To spicy things up, the backup has to be of the state of that dir at exactly 1pm.

Works just fine for me with rsnapshot. Pretty minimal configuration, too. Why write an entire new FS for something that cron and rsync can do today?

[andrnils]

If this was Ext4 fault and if this happened in enterprise system (which didn't).

... then what? It's a design problem with ext4. Had they gone for COW things would have been better.

Damn troll. Ext3, Ext4, XFS are great file systems. And no, it's not amazing, but it's something natural, because it's an Operating System which is present probably in every environment. What's the good choice in your opinion?

I guess sarcasm isn't your thing. When I have to use linux i tend to go with ext3.

I guess i'm just naive and believe that if the devs of 2 FSes sat down togheter they could acheive something that was better than their individual tries.

[andrnils]

Works just fine for me with rsnapshot. Pretty minimal configuration, too. Why write an entire new FS for something that cron and rsync can do today?

So say that the rsnapshot takes 30 minutes to run, does it guarantee that the last file to be transfered hasn't been altered?

[curaga]

On page 2:

While OpenSolaris is designed around OpenSolaris

True, but I guess not what you meant to say


@topic: So fuse about halfs the performance compared to native, and uses a ton of cpu. Did that surprise anyone?

[kraftman]

... then what? It's a design problem with ext4. Had they gone for COW things would have been better.

And that if Ubuntu allowed to use Ext4 then it's not the same if some enterprise distribution would allow to. If I would be making some serious server or workstation I'd use enterprise distribution and I wouldn't judge file system just, because Ubuntu allowed me to use it (even if Ted said it's stable). If it was really Ext4 fault then it's bad, but it could be something else. Ext4 is just some kind of pudding before btrfs, so maybe COW wasn't worth to do.

I guess sarcasm isn't your thing. When I have to use linux i tend to go with ext3.

I guess i'm just naive and believe that if the devs of 2 FSes sat down togheter they could acheive something that was better than their individual tries.

If only these file systems would have same goals.