Second test was on the PBS.
Not sure if I can follow.
I would even argue that the culprit is both CPUs.
The first clear bottleneck seems to be TLS.
I gave you 4 parts of TLS.
We can rule out 1.
According to you, we can also rule out 2.
For 3...
What speeds do you expect?
I think that 3GB/s per second is already pretty fast.
What is your target speed you aim at?
Is the current speed a problem? Or are you just surprised that you can't reach line speed and suspect an issue with your setup...
Nur weil etwas möglich ist, ist es noch lange nicht sinvoll.
Aber ja, Server2 könnte mit HDD passtrough als VM laufen, sowie auch PBS3 eine VM sein könnte und auch Server4.
Nur warum? Und warum all die negativen Konsequenzen in Kauf nehmen? Und...
That's mainly for legal reasons so not comparable. Also zfs isn't just a one-man-show and has multiple comanies funding development and is mature enough not to loose data. In contrast bcachefs developer Kent Overstreet wanted to violate kernel...
And this is unlikely to change since the main developer of bcachefs has shown that he isn't able to conform to the kernel developers workflow: https://www.phoronix.com/news/Bcachefs-Removed-Linux-6.18
This is imho a large red flag why I...
Server1: PVE für VMs.
Server2: TrueNAS oder OMV ZFS für Daten
Server3: PBS für Backups der PVE VMs
Server4: ZFS destination für ZFS von Server2
Dann noch Server2 und Server3 mit S3 Backup ergänzen.
Ja, aber das ist noch immer Mist.
Nehmen wir mal an, du hättest nur 100 Fotos à 10MB also 1GB an Daten.
PBS, erste Sicherung:
Liest die komplette 1GB. Macht ca. 4MB chucks, sichert die weg.
PBS, zweite Sicherung:
Liest nochmals die kompletten...
Dazu nochmal meine Gedanken:
Backups, die du auf mehrere Bänder verteilt musst, sind Riesenmist
Bänder sind sowieso ein totes Pferd und nur in ganz engen Nischen alternativlos
Änderungen des Workflows helfen häufig immens ohne hohe Kosten zu...
Warum überhaupt OMV? Wenn es dir um eine GUI für Dateifreigaben gibt, dafür tut es dann auch eine Debian-VM mit Webmin oder Cockpit. Oder ein lxc-Container mit den turnkey-fileserver o.ä, etwa https://github.com/bashclub/zamba-lxc-toolbox...
Luckily enough both are not five years old, the first version of ZFS was released in 2006 and development started in 2001 if I recall correctly.
In contrast the BSD filesystems as well as xfs or ext2/ext3/ext4 are basically decades old but they...
I did not ignore them. I did not mention them, because NTFS was only an example. You are spot on, I also don't trust ext4, xfs....
I do, yes.
That is why I wrote "maybe" for BTRFS. For me personally, it is not battle tested enough. (as we saw...
Mein Tipp: Tue es nicht!
Schau, deine VM zu sichern mit PBS, heisst Blockstorage zu sichern.
Blockstorage zu sichern ist extrem nervig. Es dauert ewigs. Die kompletten 20TB müssen gelesen werden, eine checksum berechnet werden, die veränderten...
Sure. But first tier providers also sometimes do not so smart stuff. That argumentum ad verecundiam is not that strong IMHO. Some would probably even argue that Synology is first tier and look what they do with BTRFS ;)
Simply because it has no...
Even though I believe @somedude, I also agree with @guruevi that there are shady vendors. Mabye shady is a little bit extreme, let me rephrase that to "vendors I would not trust my data".
Just like NTFS is IMHO a shady FS.
For example, I only...
> Battery backup of a single cache still makes it a SPOF
No, it doesn't.
In your scenario, another, prior and unaddressed, failure is required to make NVRAM (and/or other component(s)) a potential single point of failure.
It doesn't make it a...
@alex:
- Dell 'managed' IT - they'll sell Kubernetes (RHEL OpenShift) with an Emulex FibreChannel SPOF proprietary RAID - Ceph is available upon request, but the per-TB licensing cost is (much) higher. I've gotten similar constructions from just...
Just because a vendor does it, doesn’t mean it’s a good idea. Vendors sell some shady stuff and it works, most of the time. Most VMware clusters, even relatively large ones indeed have a storage design that basically resembles DRBD, mdraid or...
like I wrote earlier - the server will calculate and set the CRC for all incoming chunks, and will verify the digest if the chunk is unencrypted (verifying the digest of an encrypted chunk would require the encryption key, which only the client...
I am not 100% certain either. But since we use LLMs to make wild guesses, here are my wild human made guesses: ;)
Course not, incoming data is already optionally encrypted and or compressed. Checksums (verify) are probably not important at this...
You realize how wonky that sounds?
That is like me saying "hey I have this super stable Windows Server here, but unless I run that bat script to release the DHCP every night at 02:00, the NIC won't have an IP the next day".