Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

FreeNAS: Open Source Storage Operating System

freenas.org

Post reply on HN
Print view View original

161–170 of 182 posts

Re: FreeNAS: Open Source Storage Operating System

#161

Post by voltagex_ »

acd wrote: post #155
voltagex_ wrote: post #113

Earlier quoted context omitted.

I noticed a massive write performance hit when I enabled this. Note that it'll only compress data after you enable it, it isn't retroactive

CPU is most likely the bottle neck. So my comment should have read if you have a fast cpu you may benefit from ZFS compression. On modern CPU LZ4 should enable about 400MB/s current PCU write compression https://github.com/Cyan4973/lz4

Thank you for that - it was interesting at least, even if I've probably done it all wrong (TLDR - compression on ZFS definitely varies with the data you try to compress)

https://blog.voltagex.org/2016/08/26/benchmarking-compressio...

Fun fact: while researching this I found yet another article that contradicts the information I had when I built my zpool, and apparently I've done it all wrong (again).

Re: FreeNAS: Open Source Storage Operating System

#162

Post by voltagex_ »

iberinger wrote: post #104
yoasif_ wrote: post #89

Earlier quoted context omitted.

The easiest way to do this is to use mirror vdevs, that way you can add disks two at a time. Of course, you miss out on RAIDZ functionality that way, but that's the simplest setup. I've gone ahead and actually created a new array using btrfs raid10 instead (with an eye towards a RAIDZ2/3 like configuration whenever the btrfs guys get around to fixing it); btrfs allows for online reshaping of the mirroring configurati…

Agreed, mirror vdevs are the way to go. Here's a post that explains the tradeoffs between RAIDZ and mirror vdevs in great detail: http://jrs-s.net/2015/02/06/zfs-you-should-use-mirror-vdevs-...

I'm still not sure what setup I have. I really should have written down every decision I've made while building my NAS (I think I've now found articles that disagree with every single choice I made)

    $ zpool status
  pool: BoxODisks
 state: ONLINE
      scan: scrub repaired 0 in 9h20m with 0 errors on Sun Jul 31 01:31:31 2016
    config:

        NAME                                            STATE     READ WRITE CKSUM
        BoxODisks                                       ONLINE       0     0     0
          mirror-0                                      ONLINE       0     0     0
            gptid/18059e22-b6a4-11e5-9cca-0cc47a6bbf34  ONLINE       0     0     0
            gptid/194649b1-b6a4-11e5-9cca-0cc47a6bbf34  ONLINE       0     0     0
          mirror-1                                      ONLINE       0     0     0
            gptid/1a86b3cc-b6a4-11e5-9cca-0cc47a6bbf34  ONLINE       0     0     0
            gptid/1bcd3ad6-b6a4-11e5-9cca-0cc47a6bbf34  ONLINE       0     0     0
        cache
          diskid/DISK-S24ZNWAG903847Lp1                 ONLINE       0     0     0
I think I have mirrored vdevs.

What does that mean for replacing failed disk/s? What does that mean when I want to upgrade to 8TB drives? The biggest "mistake" I made was buying a very expensive 4 bay enclosure - 4 drives is not enough.

Re: FreeNAS: Open Source Storage Operating System

#164

Post by pmarreck »

Nacraile wrote: post #36
allendoerfer wrote: post #32

Storage is a really weak area of mine, but it is important, and I do not see much technical discussion here anyway, so I am going to expose myself: How does integrity protection work in practice? I know that the bits on the HDD itself do not map one to one to bits you can actually use and that it uses that to protect us from flipped bits. I know that beyond that RAID/RAIDZ is supposed to help. I guess redundancy alon…

RAID generally does not protect against bit-rot (i.e. undetected errors); it only protects against detectable errors / catastrophic disk failure. ZFS does protect against undetected (at the disk level) errors. To a first approximation, it does this by keeping block checksums alongside pointers so that it can verify that a block has not been changed since it was referenced, by keeping multiple checksummed root blocks,…

One thing I didn't consider until just now (sigh) is that if you're using ZFS as a backup medium (I am), unless your source drive is also ZFS (mine isn't), you're still exposed to the same bit-rot your source drive is, since that change would then get backed up to ZFS.

Re: FreeNAS: Open Source Storage Operating System

#165

Post by dragontamer »

pixl97 wrote: post #141
dragontamer wrote: post #54

NAS4Free > FreeNAS. Start your flamewars nerds! -------------- I actually have only used Nas4Free. I know that FreeNAS is technically the fork (despite having the original name), but the technology IMO is quite solid. Its important to know all of the competition however. Here's a basic overview of the technologies: * Nas4Free -- ZFS-based. Free as in beer and Free as in OSS. More barebones and simple than FreeNAS. As…

>I guess one important feature ZFS has is that it supports L2ARC / ARC caching for SSD Acceleration. Which can massively accelerate small file load times. Using this on a VM pool greatly speeds things up. >Also ZFS has compression which can drastically reduce data usage. Which in some virtual environments decreased our data usage by 50 times or more. Windows storage spaces suck balls on speed. Using it in the Microso…

> Which can massively accelerate small file load times. Using this on a VM pool greatly speeds things up.

I did some research, and it appears that Microsoft has added "SSD Tiers" to Storage Spaces. I didn't realize Microsoft had that feature!

> Specific number of disks. You increase the disks size and you can grow you raid.

Yeah. Except my disks don't grow in size. I can have a Storage Space composed of 1TB drives. And then add 2TB drives next year.

Its a nifty trick, and definitely is a smoother transition than ZFS "replace everything" methodology.

Re: FreeNAS: Open Source Storage Operating System

#166

Post by cyphar »

yoasif_ wrote: post #159
cyphar wrote: post #132

Earlier quoted context omitted.

Unless you want to reshape your array. Then md-raid is superior. Btrfs's raid implementation has had some pretty bad issues recently and has been declared "experimental" as a result.

This is inaccurate. Raid56 have always been labeled experimental, but recently, data corruption bugs were found which make it dangerous to use. Other raid levels (raid0, raid1, raid10) work fine and are considered stable -- at least as stable as the filesystem itself. Either way, if you care about the data, you must backup, no matter what fs you use.

Apologies, I only saw the recent mailing list post which basically said "we're removing the ability to even compile support for raid56". I didn't mean to say that btrfs was overly-zealous in their trust of new code (I personally am super excited for the future of btrfs).

Re: FreeNAS: Open Source Storage Operating System

#167

Post by eric_the_read »

qwertyuiop924 wrote: post #107
eric_the_read wrote: post #91

Earlier quoted context omitted.

Yeah, I saw that before, but that isn't quite what I wanted, if I'm reading it right. That tells me how to replace all the drives in my array with new ones; I'd prefer to (for instance) start with 4x 4TB drives, and add new ones as my storage needs build up.

http://docs.oracle.com/cd/E19253-01/819-5461/6n7ht6qvk/index...

Nice! Thanks for that.

Re: FreeNAS: Open Source Storage Operating System

#168

Post by zzzcpan »

barrystaes wrote: post #148
zzzcpan wrote: post #105

Earlier quoted context omitted.

Than a single traditional NAS box, yes. EDIT: Let me explain a bit more: once you start running a distributed system you stop caring about OS, filesystem and disk level issues, because you have redundancy on another level. And it makes all the difference. You don't worry anymore, you can always just reboot, hard-reset or take a node out to investigate. Suddenly you realize that it's not a big deal even if some node s…

If dont want to care for the OS, who do you expect to keep it in check? Someone has to worry about it: you can try and abstract it away and minimize it but its never gone. I see this line of thought that somehow self-hosted "clouds"/clusters look after themselves, but thats usually not the case. You'd come close by buying QNAP or Synology hardware, they provide software updates (including OS). Even buying software so…

> I see this line of thought that somehow self-hosted "clouds"/clusters look after themselves, but thats usually not the case.

They don't really look after themselves, but do handle failures on the highest possible level. Which makes it unnecessary to keep each OS in check. What's critical for a single NAS box is critical for a distributed storage only if all boxes of some replica have the same problem at the exact same time, otherwise you just reboot and move on and it doesn't matter if it happens again, it doesn't cause any downtime.

I actually speak from my own experience. I run and maintain a distributed key-value storage for many years. Although I designed and implemented it myself (and redesigned a bunch of times), I don't see how experience with those other distributed storages, like Swift, would be any different.

Re: FreeNAS: Open Source Storage Operating System

#170

Post by mindslight »

Annatar wrote: post #158
mindslight wrote: post #16

Earlier quoted context omitted.

Once you go unison you will never want to go back. I even run some ZFS without ECC memory, because if hardware goes bad and programmatically corrupts it isn't the end of the world.

What is "unison"?

Bidirectional file synchronization. It makes any single replica not that important.

Don't concentrate your resources into a single "invincible" box.

Post reply on HN