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

Samsung ships the world's highest capacity SSD, with 15TB of storage

computerworld.com

Post reply on HN
Print view View original

81–90 of 147 posts

Re: Samsung ships the world's highest capacity SSD, with 15TB of storage

#81

Post by ryao »

scurvy wrote: post #25

Why SAS and not NVMe? You can buy all NVMe enclosures/servers now. Is this solely aimed at replacing drives in existing enclosures? Not much good there as most of them will be SAS6. They'll still work, but not nearly as fast as SAS12 nor NVMe.

NVMe likely cannot scale to thousands of attached drives simultaneously due to limitations of PCI-E while SAS can. Scaling to thousands of attached disks was the motivation for QEMU's virtio-scsi because virtio-blk's 1 block device per PCI-E device meant that virtual machines using virtio-bulk could not scale past 32 drives. nVMe's 1 drive per PCI l-E device model should suffer from the same limitation.

Similarly, SAS supports multipath for HA while PCI-E does not appear to offer that ability. If it does, then I have yet to hear of an example of hardware implementing it.

Lastly, the idea is likely to appeal to those that care about density. For that purpose, it is better to lower costs and requiring a multitude of PCI express slots is not a great way of doing that. Motherboards with more PCI-E slots are expensive due to the layers needed to accommodate the circuits required by them. Assuming JBODs for such things exist (using a chip to share lanes among multiple devices), they would be expensive and also add to cost.

There is also a decent write up on this here:

http://www.datacenterjournal.com/nvme-connected-ssds/

Re: Samsung ships the world's highest capacity SSD, with 15TB of storage

#83

Post by SixSigma »

guy_c wrote: post #19
stray wrote: post #16

Earlier quoted context omitted.

That sounds perfectly reasonable, and 20 years ago I'd have said the same thing. It's even fairly likely that I did say it. You know where this is going, right? I was a SysAdmin at the time and one of the things I was responsible for was Oracle Financials. It was at the core of everything that mattered at that company -- and I was absolutely convinced that short of a water balloon fight in the machine room, my raid c…

I wonder, for such mission critical data a good strategy would be to start rotating out old drives at set periods. Maybe replace one drive of your RAID5 every 6 months, not matter what the health. Once you've replaced all the drives, they will all be staggered in age by 6 months. Hopefully then the chances of multiple failures is greatly reduced.

That would make your failure rate higher (from increased infant mortaility) and your maintenance more expensive (more spares, more transaction costs, more work, replacing perfectly fine working parts too soon).

Drives have on-condition monitoring via SMART so you can predict age related failure.

Scheduled replacement is almost the worst maintenance policy.

Re: Samsung ships the world's highest capacity SSD, with 15TB of storage

#84

Post by semi-extrinsic »

vidarh wrote: post #38
guy_c wrote: post #19

Earlier quoted context omitted.

I wonder, for such mission critical data a good strategy would be to start rotating out old drives at set periods. Maybe replace one drive of your RAID5 every 6 months, not matter what the health. Once you've replaced all the drives, they will all be staggered in age by 6 months. Hopefully then the chances of multiple failures is greatly reduced.

Replacing a drive in a RAID5 would mean voluntarily placing yourself in a high risk position every 6 months. If you're going to do that, you better make sure you use a raid level that gives you at least two drive redundancy.

In the GGP post he mentions being "down to just RAID5", so presumably he was at RAID6.

(Bookmarking this entire thread for much RAID wisdom.)

Re: Samsung ships the world's highest capacity SSD, with 15TB of storage

#85

Post by ryao »

ars wrote: post #17
stray wrote: post #16

Earlier quoted context omitted.

That sounds perfectly reasonable, and 20 years ago I'd have said the same thing. It's even fairly likely that I did say it. You know where this is going, right? I was a SysAdmin at the time and one of the things I was responsible for was Oracle Financials. It was at the core of everything that mattered at that company -- and I was absolutely convinced that short of a water balloon fight in the machine room, my raid c…

> The first disk died late on Friday. I had two on-hand so I casually replaced it -- and before I got back to my desk another had died. That happens very very very often. It has nothing to do with a bad batch. The second disk actually failed a while ago, but no one noticed because no one read from that part of it. When you did the rebuild you read from the failed area and woke up the failure. When you setup raid you…

I think you have different definitions of failure. The previous person seems to claim it meant the disk was dead (i.e. no read works) while you seem to claim that it means an error caught by low level formatting.

Those scrubs do nothing to catch errors that the drives do not report such as misdirected writes. Consequently, there is no correct way to setup RAID in a way that makes dats safe. A check summing filesystem such as ZFS would handle this without a problem though.

Re: Samsung ships the world's highest capacity SSD, with 15TB of storage

#87

Post by ryao »

robbiemitchell wrote: post #56
userbinator wrote: post #49

Earlier quoted context omitted.

On the other hand, I still remember when hard drives (the spinning platter ones) reached the $1/GB mark ~10 years ago. Now high-end SSDs are there. A billion bits of storage costing $1 is pretty amazing, I think.

Hell, I remember reading PC Mag and being SHOCKED about a 4GB HD that cost a few hundred bucks. (Also shocked that I subscribed to PC Mag.)

I was shocked when 200GB drives were called drivezilla and cost $400.

Re: Samsung ships the world's highest capacity SSD, with 15TB of storage

#88

Post by ryao »

zanny wrote: post #7
cm2187 wrote: post #6

Earlier quoted context omitted.

I thought RAID and SSD were a terrible combination. As if both drives do exactly the same writes at the same time, chances are they will fail at the same time. Plus most RAID controllers don't support TRIM. Has the thinking changed?

A Raid 5 could work, since you are not writing the same data. You would need a hardware coprocessor to handle generating the checksums at 4GB/s though.

RAID 5 is terrible with 4K random IO. I know guys who measured >1 million IOPS with MD RAID 0 and then switched to MD RAID 5 only to have performance drop from read-modify-write overhead. They could not believe that RAID 5 was the cause.

Re: Samsung ships the world's highest capacity SSD, with 15TB of storage

#89

Post by baq »

kabdib wrote: post #46
ChoGGi wrote: post #35

Earlier quoted context omitted.

I wonder how that 1200MBps will hold up with the thermal throttling with their other V-NAND products (SM951/950 Pro), especially when doing a raid rebuild? I happen to have a 950 Pro, and normal usage keeps the temperature at reasonable levels (though I stuck heatsinks on mine), but this is much more dense (512 vs 2 on the 950 Pro).

FusionIO drives (PCIe attached flash storage) have serious heat sinks. The heat sinks are not for show. I get about 2GByte/second sustained. It's fun :)

i remember the times when RAM of this speed was something to brag about... guess i'm getting old.

Re: Samsung ships the world's highest capacity SSD, with 15TB of storage

#90

Post by cm2187 »

tim333 wrote: post #57
bluedino wrote: post #32

Earlier quoted context omitted.

10,000 USD?

Samsung's 2TB SSD is $860 so maybe something like that. http://www.amazon.com/Samsung-2-5-Inch-SATA-Internal-MZ-7KE2...

That's a consumer SSD. The 16TB looks like an enterprise SSD (much higher endurance).
Post reply on HN