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

Testing two 18 TB white label SATA hard drives from datablocks.dev

ounapuu.ee

Post reply on HN
Print view View original

131–140 of 163 posts

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#131

Post by dontlaugh »

tombert wrote: post #63
leobg wrote: post #19

I was about to buy a NAS. I find the idea of using an old laptop instead interesting. Especially since it comes with UPS built in. The author is using a ThinkPad T430. Any experiences?

I don't use a laptop, but I use something fairly adjacent: the Beelink SER6 ( https://www.amazon.com/Beelink-4-75GHz-PCIe4-0-Supports-HDMI... ), which is basically a gaming laptop converted into a small desktop. For the most part, it has actually been pretty great. It's quiet, has a CPU that is much better than I expected, and a decent enough GPU to do hardware transcoding for Jellyfin without much issue. I use USB c…

There’s also variants of three mini PCs with hard drive bays. I recently bought an Aostar WTR Pro and I’d considered the Ugreen competitor.

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#132

Post by bombela »

yyhhsj0521 wrote: post #83
IgorPartola wrote: post #64

Earlier quoted context omitted.

For me it was important to have ECC RAM and laptops pretty much never have that. My personal recommendation is an old IBM/Lenovo workstation tower as the base. I bought one for $35 on eBay and added $40 of RAM (32GB). A $10 UPS from Goodwill with a $25 battery from Amazon, and whatever hard drives you want. I run Ubuntu and ZFS on it but next time would probably opt for FreeBSD for a nicer OS.

Why is it important for an NAS to have ECC RAM?

So that you don't lose your data to random bit flips from cosmic rays.

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#133

Post by tombert »

dontlaugh wrote: post #131
tombert wrote: post #63

Earlier quoted context omitted.

I don't use a laptop, but I use something fairly adjacent: the Beelink SER6 ( https://www.amazon.com/Beelink-4-75GHz-PCIe4-0-Supports-HDMI... ), which is basically a gaming laptop converted into a small desktop. For the most part, it has actually been pretty great. It's quiet, has a CPU that is much better than I expected, and a decent enough GPU to do hardware transcoding for Jellyfin without much issue. I use USB c…

There’s also variants of three mini PCs with hard drive bays. I recently bought an Aostar WTR Pro and I’d considered the Ugreen competitor.

Yeah, though I have 24 drives so I think by definition I couldn't really have a "mini" with enough bays to handle that.

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#134

Post by dapperdrake »

reliablereason wrote: post #121
leobg wrote: post #19

I was about to buy a NAS. I find the idea of using an old laptop instead interesting. Especially since it comes with UPS built in. The author is using a ThinkPad T430. Any experiences?

The laptop batteries tend to go bad(either just stop working or expand and become a major fire hazard) after a year or two as they are not built to be fully charged for years on end. I tried doing it twice and that is what happened both times. Would not recommend; if you want a UPS just buy one, the small ones are not that expensive, like 70 USD.

On Thinkpads tlp(8) can set a maximum battery charge threshold of 80%. The embedded controller takes care of it. Never had problems.

Makes batteries live way longer.

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#135

Post by dapperdrake »

whazor wrote: post #28
leobg wrote: post #19

I was about to buy a NAS. I find the idea of using an old laptop instead interesting. Especially since it comes with UPS built in. The author is using a ThinkPad T430. Any experiences?

When I used a laptop as server, the battery became a spicy pillow. I think laptops are not designed to be running continuously and on warmer temperatures than normal.

Thinkpads can use tlp to cap battery charge at 80%. It works.

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#136

Post by scottlamb »

master_crab wrote: post #82
scottlamb wrote: post #61

Earlier quoted context omitted.

> How do you store ~100 TB of content with room to grow without a wide NAS? In the cloud (S3) or on offline (unpowered HDDs or tapes or optical media) I suppose. Most people just don't store that much content. > So far none of this seems to solve the problem that is solved quite elegantly by the 1U enterprise box... if only you don't look at the power bill. What kind of power bill are you talking about? I'd expect th…

2U is definitely better, but I didn’t notice significant drops in dB till I could stuff a 120mm fan in the case. That requires a 3U or more. And if you need a good fan that’s quiet enough for the CPU, you’re looking at 4U. Otherwise, you’ll need AIOs hooked up to the aforementioned 120s.

> And if you need a good fan that’s quiet enough for the CPU, you’re looking at 4U.

Depends on the CPU, I imagine. I'm using one with a 65W TDP. I'm hopeful that I can cool that quietly with air in 2U, without having to nerf it with lower BIOS settings. Many NASs have even lower power CPUs like the Intel N97 and friends.

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#137

Post by f_devd »

lproven wrote: post #117
zozbot234 wrote: post #46

Earlier quoted context omitted.

btrfs RAID is quite infamous for eating your data. Has it been fixed recently?

To be fair, your statement could be edited as follows to increase its accuracy: > btrfs is quite infamous for eating your data. This is the reason for the slogan on the bcachefs website: "The COW filesystem for Linux that won't eat your data". https://bcachefs.org/ After over a decade of in-kernel development, Btrfs still can't either give an accurate answer to `df -h`, or repair a damaged volume. Because it can't te…

> Btrfs still can't either give an accurate answer to `df -h`, or repair a damaged volume.

> In my personal experience, writing to a full volume corrupts it irretrievably 100% of the time, and then it cannot be repaired.

While I get the frustration, I think you could have probably resolved both of them by reading the manual. Btrfs separates metadata & regular data, meaning if you create a lot of small files your filesystem may be 'full' while still having data available; `btrfs f df -h ` would give you the break down. Since everything is journaled & CoW it will disallow most actions to prevent actual damage. If you run into this you can recover by adding an additional disk for metadata (can just be a loopback image), rebalancing, and then taking steps to resolve the root cause, finally removing the additional disk.

May seem daunting but it's actually only about 6 commands.

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#138

Post by master_crab »

scottlamb wrote: post #136
master_crab wrote: post #82

Earlier quoted context omitted.

2U is definitely better, but I didn’t notice significant drops in dB till I could stuff a 120mm fan in the case. That requires a 3U or more. And if you need a good fan that’s quiet enough for the CPU, you’re looking at 4U. Otherwise, you’ll need AIOs hooked up to the aforementioned 120s.

> And if you need a good fan that’s quiet enough for the CPU, you’re looking at 4U. Depends on the CPU, I imagine. I'm using one with a 65W TDP. I'm hopeful that I can cool that quietly with air in 2U, without having to nerf it with lower BIOS settings. Many NASs have even lower power CPUs like the Intel N97 and friends.

Oh yes, you can definitely get away with much less for something like that or an ARM, Ryzen embedded chips, etc. The 4U is more for full scale desktop CPUs like the i9-12900k I am running (like an NH-D15 sink/fan). You may even be able to get away with passive cooling at the 65W range.

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#139

Post by aftbit »

_kb wrote: post #114
aftbit wrote: post #34

I've been considering "de-enterprising" my home storage stack to save power and noise and gain something a bit more modular. Currently I'm running on an old NAS 1U machine that I bought on eBay for about $300, with a raidz2 of 12x 18TB drives. I have yet to find a good way to get nearly that much storage without going enterprise or spending an absolute fortune. I'm always interested in these DIY NAS builds, but they…

There's a bit of a trend of vendors packaging mobile CPUs in desktop form factor which are a good candidate for this. Rather than the prebuilt mini PCs this also includes mini-ITX boards. Personally I use the Minisforum BD795i SE, but there are others too. Check for PCIe bifurcation support. If that's there you can pop in a PCIe to quad M.2 adapter. That will split a PCIe x16 slot into 4 x M.2s. Each of those (and th…

This sounds like a really nice setup. Which M.2 to SATA adapters are you using? I've heard some of those are dodgy and others are alright.

Re: Testing two 18 TB white label SATA hard drives from datablocks.dev

#140

Post by toast0 »

aftbit wrote: post #139
_kb wrote: post #114

Earlier quoted context omitted.

There's a bit of a trend of vendors packaging mobile CPUs in desktop form factor which are a good candidate for this. Rather than the prebuilt mini PCs this also includes mini-ITX boards. Personally I use the Minisforum BD795i SE, but there are others too. Check for PCIe bifurcation support. If that's there you can pop in a PCIe to quad M.2 adapter. That will split a PCIe x16 slot into 4 x M.2s. Each of those (and th…

This sounds like a really nice setup. Which M.2 to SATA adapters are you using? I've heard some of those are dodgy and others are alright.

I've not used any of them, but from my shopping some of them are multiport SATA adapters, and some of them are a single port SATA adapter plus a SATA port multiplier. I would expect the port multiplier variants to be dodgier.
Post reply on HN