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

Backblaze has ordered 100 petabytes of hard drives

backblaze.com

Post reply on HN
Print view View original

111–120 of 146 posts

Re: Backblaze has ordered 100 petabytes of hard drives

#111

Post by infogulch »

amelius wrote: post #85
brianwski wrote: post #71

Earlier quoted context omitted.

Brian from Backblaze here. > Have you ever computed how much power you would save if you turned them off when not needed? Electrical power is a gigantic part of our datacenter bill (like 60%). However, we cannot really ever turn off the hard drives. If they were powered down, it would take too long to retrieve data. It would be like Amazon Glacier where it can take 15 minutes to get a single image back. > is every po…

> If they were powered down, it would take too long to retrieve data. It would be like Amazon Glacier where it can take 15 minutes to get a single image back. Well, speaking for myself, I don't mind if I have to restore a backup, and have to wait 1 minute extra for a system to come online (that's about the typical boot time of a Linux system, so I suppose for a storage pod it would be about the same). By the way, it…

This is what I thought amelius' comment was originally about. You could save power on drives plus it would only take a few seconds to come back online. I imagine it could save a lot of electricity if the additional complication is worth it.

Complications like a write cache drive in case of power failure, or grouping expected-cold data together. Also I wonder if powering the drive up and down occasionally will have a positive or negative impact on drive reliability compared to having it on 100% of the time.

Re: Backblaze has ordered 100 petabytes of hard drives

#112

Post by spondyl »

e40 wrote: post #94
godzillabrennus wrote: post #91

Earlier quoted context omitted.

I had a Mac Pro Mid-2010 workstation with a RAID 5 Array configured to have a hot spare for redundancy. Then I had a locally attached hard drive for time machine backups + BackBlaze + a hosted repo for the work I do + I use a third party encrypted cloud file sharing service for the most important documents. The problem started when I decided to upgrade to High Sierra. The upgrade was catastrophic for this configurati…

For the life of me, I can't figure out why people upgrade to new operating systems so quickly. I never upgrade my macOS until x.x.4, but I prefer x.x.5. I'm on 10.11.6 because 1) it works perfectly, and 2) Karabiner doesn't work on 10.12.

Karabiner was updated a couple of months back in the form of Karabiner Elements, a rewrite "due to kernel architecture changes in macOS Sierra".

https://github.com/tekezo/Karabiner-Elements

Re: Backblaze has ordered 100 petabytes of hard drives

#113

Post by SimonPStevens »

elfchief wrote: post #89
brianwski wrote: post #80

Earlier quoted context omitted.

I'll answer these in reverse order: > 2. Why are zip files being created? We actually offer two forms of restore: A) Zip File Download, and B) External USB Hard Drive FedEx'ed to your home. In the case of the Zip file download, we chose the format of zip because both Mac and PC (the most common desktops) natively understand it with no additional software needed. In other words, if you just lost your computer, go to A…

I would really like #2 to have the option of sending encrypted files on disk or zip, and y'all providing a client that will decrypt them using my passphrase, locally. Nothing personal, but I really don't want y'all seeing my data, even if I need to restore. (context: I've been a Backblaze user for years and love the hell out of you. I've never really thought of how the restore would work with my encrypted data, thoug…

Yes, +1 for this. This is what I want, #2, but with a restore that transfers the encrypted data and decrypts locally.

This is how CrashPlan worked. (And incidentally, as I'm sure the guys at backblaze are fully aware, CrashPlan home is shutting down and I'm currently struggling to find a replacement that meets my desires. So if backblaze started to offer that #2 + encrypted restore soon they would gain my custom at the least.)

Re: Backblaze has ordered 100 petabytes of hard drives

#114

Post by pnutjam »

jstrassburg wrote: post #67
ericfrederich wrote: post #20

I love the articles from Backblaze. I enjoy them publishing the failure rates of drives and anything else on the blog. Two things missing from them in my opinion 1) a Linux client and 2) a second location I guess I could get away without a Linux client if there was an unRAID plugin for B2.

Second on the linux client. I have a linux machine with a zfs volume that I've been backing up to crashplan. Since they've announced they're dumping their consumer market I have no cost-effective place to go. Most likely, I'll be more picky about my backups and use S3 life-cycled to Glacier.

time4vps.eu has some nicely price storage servers. They have no backup, since they're designed to be part of a larger backup strategy, but it works for me.

affiliate link: https://billing.time4vps.eu/?affid=1881

Cheaper then backblaze in most situations and you get a full linux host.

Re: Backblaze has ordered 100 petabytes of hard drives

#115

Post by BadassFractal »

godzillabrennus wrote: post #34

I’ve been a customer for years and recently had a catastrophic failure of a computer and it’s direct attached backup drive. I have spent the last four days waiting for backblaze to create a restore a backup for a computer on and last I checked it was at 9%. I chatted with support and they said this is normal. That progress may jump to completed any time because the restore only tracks file count. I wish I could say I…

That's the thing that always terrifies me about Backblaze. I really want to like it, the pricing is good and they are so open about how their business and technology operates, yet you constantly hear of people on HN getting bitten by corner cases where they lose their data :(

Re: Backblaze has ordered 100 petabytes of hard drives

#116

Post by rsync »

x4d66a5ce wrote: post #65
ac29 wrote: post #46

Earlier quoted context omitted.

Theyve repeatedly said no -- it breaks their business model to allow Linux machines (often servers) to backup "unlimited" data for $5/month. People with multi-hundred TB NAS machines would end that business model, quickly (see Amazon Cloud Drive, Crashplan, and others). But if youre using S3, just switch to B2, its per GB pricing, much cheaper than S3 and supports lots of Linux tools. I use rclone.

I took the GP's remark about how he "went with s3 as s3cmd had a path of least resistance to storing backups" to mean that he considered B2 but opted for S3 since the latter offers a backup utility, but the former supports neither a "native" (e.g., git or rsync over SSH) backup interface, nor does it have a Linux client—the approach for backup on B2 from desktop Linux is to roll your own backup solution or use somebo…

"For big backups, storage is (slightly less than) twice as expensive as S3, but unlike S3, there are no bandwidth costs."

Just to clarify ... we (rsync.net) support "borg backup" now (with borg deployed on the server side ...) which is the "holy grail" of efficient, zero knowledge, remote backups:

https://www.stavros.io/posts/holy-grail-backups/

... and if you are willing to give up our ZFS snapshots on the account (you manage retention yourself with borg) and you are willing to handle your own technical support of borg, we offer a 3 cents rate. This is about the same price as S3:

http://rsync.net/products/attic.html

Re: Backblaze has ordered 100 petabytes of hard drives

#117

Post by godzillabrennus »

godzillabrennus wrote: post #34

I’ve been a customer for years and recently had a catastrophic failure of a computer and it’s direct attached backup drive. I have spent the last four days waiting for backblaze to create a restore a backup for a computer on and last I checked it was at 9%. I chatted with support and they said this is normal. That progress may jump to completed any time because the restore only tracks file count. I wish I could say I…

Brian from BackBlaze reached out and provided some feedback:

I checked into it, and we think your restore is slow for several reasons:

1) Lots of tiny files (we are fixing this in a rewrite literally this week)

2) It landed on a slow restore server. (We are planning on decommissioning that server soon because it is 8 years old and slow.)

We have the technology to move your restore to a faster restore server. However, the restore experts here tell me your restore is actually 90% through the part that would speed up, so they recommend just "let it run". I really really hope it will be finished and ready for you in the next few days.

If you need some of your files any faster, I think you should prepare several smaller restores. It turns out that if you prepare four restores, each one 25% as large as the original, the four restores will complete 4x faster because they are prepared by four separate servers.

You can create up to 10 simultaneous ZIP restores, and they are totally free, so feel free to spin up a few more restores even if they overlap with the original large 1.1 TByte restore.

Please reach out to me again if your restore isn't ready by Tuesday (October 10th).

Re: Backblaze has ordered 100 petabytes of hard drives

#118

Post by notatoad »

ensignavenger wrote: post #107
linsomniac wrote: post #32

I've watched Backblaze closely, and I love their detailed reports of drive stats. I've always been curious about their choices of manufacturers though. In my past I found that Hitachi/HGST drives were far more reliable than others. We had a couple people doing hardware and software support on ~120 machines, and hard drive replacements were expensive (in man-hours) for us, so whenever possible we got Hitachi drives. T…

The last I heard, I understood that Backblaze doesn't go around replacing single drives that fail in a pod, rather, their software marks that drive bad and only once a certain percentage of the capacity of the entire pod is gone, do they yank it our and rebuild the pod. That probably helps a lot versus an environment where had to have technicians replacing single drive failures randomly throughout your data center.

they operate at datacenter scale: https://xkcd.com/1737/

Re: Backblaze has ordered 100 petabytes of hard drives

#119

Post by Spooky23 »

unixhero wrote: post #106
godzillabrennus wrote: post #55

Earlier quoted context omitted.

It’s nearly 500GB of data. Email me Hn strapr.com if you want more details

Which is nothing

It's alot of data when the application is typically write-only, and throws little chunks of data all over the place!

Re: Backblaze has ordered 100 petabytes of hard drives

#120

Post by 15155 »

volkl48 wrote: post #88
linsomniac wrote: post #32

I've watched Backblaze closely, and I love their detailed reports of drive stats. I've always been curious about their choices of manufacturers though. In my past I found that Hitachi/HGST drives were far more reliable than others. We had a couple people doing hardware and software support on ~120 machines, and hard drive replacements were expensive (in man-hours) for us, so whenever possible we got Hitachi drives. T…

It is worth considering that the use-case of Backblaze is different from the average end-user. No power on/off cycles, no physical impacts to worry about (even most desktops occasionally get bumped into), but non-stop operation and presumably near continuous read/write operations. You'll likely get different failure patterns as a result.

> but non-stop operation and presumably near continuous read/write operations.

I thought it would be more like: continuous writes until full, and then likely a handful of reads for the rest of that drive's life.

Post reply on HN