@Jimmy9008 said in CSV... what happens at a lower level?:

That makes sense, would a drop from 1GB/s to 100MB/s be expected? Seems huge...

Depending on the system, yeah, especially with certain kinds of operations.

@scottalanmiller Sounds solid. The speed difference is dramatic. Thanks.

@scottalanmiller Thanks Scott it worked

Could be interesting.

@momurda said in Testing Filesystem Performance under Linux 4.11 of XFS, BtrFS, F2Fs and EXT4:

ext4 still the defaults on Debian distro as well.

Well Debian, sure. Not surprised there. Fuddy duddy distro 😉

Ya with a preallocated qcow2 I can get pretty close to raw speeds. No one is going to notice 10MB/s or even 20 in normal settings.

Veeam just announced this week that they now consider ReFS to be ready for production use for the first time due to last week's WIndows Server patch that addressed some ReFS issues.

@scottalanmiller Ah, yes. That would be a more efficient way of doing it. I was too excited from finally gaining some understanding of mount point concepts, I didn't think though the best way to move the data. 🙂

@scottalanmiller Thanks for this post and answering all my questions. @travisdh1 Thanks for answering all my questions as well. Good Thread!

@Dashrender said:

Right, but when you're working with files that large - why bother storing them in a VM - just st.... OK yeah, that goes against the standard practice now.. so we need a VM, even if the whole host is a VM - welp, I guess your stuck with XFS 🙂

Pretty much. EXT4 is pretty silly for a server of any size, which is why even for desktops RHEL is XFS by default and EXT4 only as an option for advanced users. EXT4's days are pretty much over.

@DustinB3403 said:

Scott have you ever looked at this, http://zfsonlinux.org/

Quite a bit 🙂