Our data is GONE... Again

[Nystemy]

1 minute ago, Bigun said:

@Nystemy

 

The tape libraries to run them.  I'm basing this off of using Scalar i3 libraries.  They hold about 50 tapes per library and 3 tape decks a piece.

Massive overkill for a medium sized media production company.

 

For a website doing online archiving, then yes a robotic tape library can be "cost effective", but some of these companies one can at times need to wait in the queue for hours before a tape drive is available. Ie, there is a rather large throughput of data to facilitate the cost. But that wouldn't be the case for LMG.

 

Secondly, LTO tape wears out, an LTO 8 tape is only rated for being unspooled some 20 thousand times, but just writing it full consumes 168 passes. And for a backup one shouldn't really play with the MTBF of the storage medium itself, even if one is at the low side of the scale.

 

And lastly, 50 tapes at 12 TB each is not a lot of data. An external tape drive and an IKEA bookshelf is far more cost effective as a backup. The tiny bit of manual labor to stack them on the shelf doesn't cost much, and in the rare case of data loss, one can always rent a few more tape drives to read it out in a much more parallel fashion.

[Bigun]

15 minutes ago, Nystemy said:

Massive overkill for a medium sized media production company.

 

For a website doing online archiving, then yes a robotic tape library can be "cost effective", but some of these companies one can at times need to wait in the queue for hours before a tape drive is available. Ie, there is a rather large throughput of data to facilitate the cost. But that wouldn't be the case for LMG.

 

Secondly, LTO tape wears out, an LTO 8 tape is only rated for being unspooled some 20 thousand times, but just writing it full consumes 168 passes. And for a backup one shouldn't really play with the MTBF of the storage medium itself, even if one is at the low side of the scale.

 

And lastly, 50 tapes at 12 TB each is not a lot of data. An external tape drive and an IKEA bookshelf is far more cost effective as a backup. The tiny bit of manual labor to stack them on the shelf doesn't cost much, and in the rare case of data loss, one can always rent a few more tape drives to read it out in a much more parallel fashion.

1)  That's what the proposal is for, and after all the information is gathered (which you and I really don't have), that's when the decision is made

2)  That's why you cycle tapes

3)  You didn't work the math:  50 tapes @ 12TB each per library.  Each library would have 50 tapes and 3 decks each, writing simultaneously @ 300 MB/s per deck.

Again, I need more info, and I'm itching to see if this could work for them.

[Dmytro Bondarenko]

Why not use LTO as a cold backup option? Like the latest revision of LTO, LTO-9.
It can store 18TB of raw data without compression per tape and cost approx. $200 each. With your reputation and order size even cheaper. 
780TB will fit on ~44 drives and will cost you about 44 * 200 = 8800USD, plus you need to invest some money into LTO drive (a few thousand USD).
But this storage is like forever. It could be even cheaper if it can compress your type of data. 
 

[Bigun]

5 minutes ago, Dmytro Bondarenko said:

Why not use LTO as a cold backup option? Like the latest revision of LTO, LTO-9.
It can store 18TB of raw data without compression per tape and cost approx. $200 each. With your reputation and order size even cheaper. 
780TB will fit on ~44 drives and will cost you about 44 * 200 = 8800USD, plus you need to invest some money into LTO drive (a few thousand USD).
But this storage is like forever. It could be even cheaper if it can compress your type of data. 
 

Thank you!  "Back me up" on this.

 

[/dad joke]

One minor correction, compressed video is hard to compress.  So no advantage there, but everything else stands.

[Nystemy]

2 minutes ago, Bigun said:

1)  That's what the proposal is for, and after all the information is gathered (which you and I really don't have), that's when the decision is made

2)  That's why you cycle tapes

3)  You didn't work the math:  50 tapes @ 12TB each per library.  Each library would have 50 tapes and 3 decks each, writing simultaneously @ 300 MB/s.

Again, I need more info, and I'm itching to see if this could work for them.

1. LMG isn't really an archival company.
2. Yes, one can cycle tapes, but for a backup solution there is little reason to use them as primary storage of the data that one intends to backup. _{(because then they aren't a backup!)}
3. A 50 tape library is rather small as far as tape libraries go. I have seen ones that hold thousands, but yet again, primarily in online archiving applications where "quick" data retrieval among hundreds of PB of data is desired.

3 minutes ago, Bigun said:

Thank you!  "Back me up" on this.

Nice to see you seeking support from someone saying "Why not use LTO as a cold backup option?" which is exactly what I have been stating this whole time...

[Bigun]

3 minutes ago, Nystemy said:

1. LMG isn't really an archival company.
2. Yes, one can cycle tapes, but for a backup solution there is little reason to use them as primary storage of the data that one intends to backup. _{(because then they aren't a backup!)}
3. A 50 tape library is rather small as far as tape libraries go. I have seen ones that hold thousands, but yet again, primarily in online archiving applications where "quick" data retrieval among hundreds of PB of data is desired.

Nice to see you seeking support from someone saying "Why not use LTO as a cold backup option?" which is exactly what I have been stating this whole time...

1)  They fooled me

2)  Not stating they need to use it as primary storage for anything except really, really old video

3)  I know, the libraries can be expanded as well, but the tape decks are really what I'm aiming for..  Also the libraries can be scaled to be much, much larger.

4)  Then you fooled me as well.  

 

Imma go eat

[Nystemy]

13 minutes ago, Bigun said:

1)  They fooled me

2)  Not stating they need to use it as primary storage for anything except really, really old video

3)  I know, the libraries can be expanded as well, but the tape decks are really what I'm aiming for..  Also the libraries can be scaled to be much, much larger.

4)  Then you fooled me as well.  

 

Imma go eat

1. I guess you are very new here...
2. One don't have a backup unless it is stored in at least 2 places. So having it in the active HDD storage isn't a bad place, and for those times it is needed, one can easily retrieve it in seconds, not minutes or hours since the tapes should preferably be off site. _{(and if that fails, retrieve it from the tape in the closet at home, but a decent storage server is sufficiently redundant that if it "fails", one will have to retrieve more than one tape regardless. (And this is why one should serialize tapes and record what is on what somewhere safe.))}
3. Yet again, for offline backups, a bookshelf is far cheaper. But having multiple small libraries isn't usually cheaper than having 1 library of the same total capacity. _{(unless one wants backups in different locations. Then one don't really have a choice then to go with more than 1 library. Another reason is servicing/downtime, but that is another can of worms.)}
4. How weren't it obvious that I stated offline tape backup stored off site were a logical thing to have... It is literally the only thing I have said in this thread... _{(except the first message where I do state a robotic tape library in some far off office where one won't have any staff, thereby it needing to be robotic in that case. But that is honestly overkill, a bookshelf at home is sufficiently "far away" for a company of this type.)}

[Salv8 (sam)]

i dearly hope you guys learned from this and are now getting an IT admin to take care of the servers in the event something goes wrong.

[Bigun]

13 minutes ago, Nystemy said:

1. I guess you are very new here...
2. One don't have a backup unless it is stored in at least 2 places. So having it in the active HDD storage isn't a bad place, and for those times it is needed, one can easily retrieve it in seconds, not minutes or hours since the tapes should preferably be off site. _{(and if that fails, retrieve it from the tape in the closet at home, but a decent storage server is sufficiently redundant that if it "fails", one will have to retrieve more than one tape regardless. (And this is why one should serialize tapes and record what is on what somewhere safe.))}
3. Yet again, for offline backups, a bookshelf is far cheaper. But having multiple small libraries isn't usually cheaper than having 1 library of the same total capacity. _{(unless one wants backups in different locations. Then one don't really have a choice then to go with more than 1 library. Another reason is servicing/downtime, but that is another can of worms.)}
4. How weren't it obvious that I stated offline tape backup stored off site were a logical thing to have... It is literally the only thing I have said in this thread... _{(except the first message where I do state a robotic tape library in some far off office where one won't have any staff, thereby it needing to be robotic in that case. But that is honestly overkill, a bookshelf at home is sufficiently "far away" for a company of this type.)}

1)  The moment you decide to keep everything - you're archiving

 

2)  Yes, which is why I suggested 5 days to complete full monthly backups.  I figured the "offsite" part didn't need to be stated.

3)  The multiple libraries is more for the decks and speed than holding the tapes.  With LTO-8 @ 300 MB/s, you need multiple drives and multiple jobs to speed things along with any regularity.

4)  Then I missed the point, my apologies.

[Ultraforce]

17 minutes ago, Bigun said:

1)  The moment you decide to keep everything - you're archiving

 

I think what is meant is that LMG is not an archival company. While they do archive videos and projects the goal of the company is to make money via videos and merchandise not from archiving.

Archiving is a means to the end of having a copy in case the video needs to be referred back to in the future.

[Nystemy]

Just now, Bigun said:

1)  The moment you decide to keep everything - your archiving

 

2)  Yes, which is why I suggested 5 days to complete full monthly backups.  I figured the "offsite" part didn't need to be stated.

3)  The multiple libraries is more for the decks and speed than holding the tapes.  With LTO-8 @ 300 MB/s, you need multiple drives and multiple jobs to speed things along with any regularity.

4)  Then I missed the point, my apologies.

LMG built their last extension to the petabyte project (adding a whole petabyte) like 1.5-2 years ago, if not longer, so that is only a tiny 1-2 TB a day. That isn't even a single LTO 8 tape that only takes a bit over 9 hours to fill. So as far as automatic tape libraries go. It just doesn't make sense for this type of operation. They could literally spit out 5x more content and still only really need 1 tape a day, hardly a chore to take home at the end of the day/week and put onto a shelf. _{(And sneakerneting it has the advantage of not clogging up extra internet bandwidth. Latency isn't important for an "in case of emergency" backup like this.)}

 

If a business on the other hand writes a couple of TB an hour, and needs cheap high density storage for their workload that can tolerate access times in the hours, then yes an automatic tape library makes sense. For almost everything else, these automated machines don't make much sense. _{(unless one's employees are really bad at manually organizing tapes onto a regular shelf (or just misplaces them on a regular basis), or if the data needs to be securely stored without reliance on humans (ie, protection against theft))}

 

And yes, if one hoards data and saves "all of it", then yes one is more or less archiving. I don't say anything against that.

But one typically don't need an excessively expensive automated tape library to store the tapes in, a bookshelf does fine... _{(Even some archiving companies does it this way. If the human breaks, one can just use another one. Also, humans unlike tape robots don't tend to get stuck among the aisles. And archival bookshelves are considerably cheaper than automated tape libraries for the amount of shelf space one gets. Downside with humans is that they want breaks, go home at the end of the day, and want extra pay for night shifts. And might have higher access latency if preoccupied with jokes around the water cooler.)}

[AnonymousGuy]

*checks my own server*

 

Oh yeah I'm using MegaRaid so it does patrol and consistency checks on its own.  Commercial software FTW.

[Bigun]

9 minutes ago, Nystemy said:

LMG built their last extension to the petabyte project (adding a whole petabyte) like 1.5-2 years ago, if not longer, so that is only a tiny 1-2 TB a day. That isn't even a single LTO 8 tape that only takes a bit over 9 hours to fill. So as far as automatic tape libraries go. It just doesn't make sense for this type of operation. They could literally spit out 5x more content and still only really need 1 tape a day, hardly a chore to take home at the end of the day/week and put onto a shelf. _{(And sneakerneting it has the advantage of not clogging up extra internet bandwidth. Latency isn't important for an "in case of emergency" backup like this.)}

 

If a business on the other hand writes a couple of TB an hour, and needs cheap high density storage for their workload that can tolerate access times in the hours, then yes an automatic tape library makes sense. For almost everything else, these automated machines don't make much sense. _{(unless one's employees are really bad at manually organizing tapes onto a regular shelf (or just misplaces them on a regular basis), or if the data needs to be securely stored without reliance on humans (ie, protection against theft))}

 

And yes, if one hoards data and saves "all of it", then yes one is more or less archiving. I don't say anything against that.

But one typically don't need an excessively expensive automated tape library to store the tapes in, a bookshelf does fine... _{(Even some archiving companies does it this way. If the human breaks, one can just use another one. Also, humans unlike tape robots don't tend to get stuck among the aisles. And archival bookshelves are considerably cheaper than automated tape libraries for the amount of shelf space one gets. Downside with humans is that they want breaks, go home at the end of the day, and want extra pay for night shifts. And might have higher access latency if preoccupied with jokes around the water cooler.)}

I see where your coming from now, and I still disagree.

 

The libraries are more for auto tape swapping and automation.  Not for tape archival, not for tape storage - speed and automation.  The standard for tape cycle is to produce a full backup every month, otherwise you are piling incrementals on top of incrementals with no refresh.  That's what the full monthly's are for, a refresh of the incremental.  This also speeds up the RPO in the case of an incident.  This means you will need to write (potentially) 2 PB of data to tape every month.  This is why I suggested so many libraries. 

 

Just cycling off incrementals every day with no refresh of a full backup is begging for an insane RPO in a matter of months.

[Spindel]

Linus you forgot one point in your ending words of this video:

 

…also don’t use Seagate drives. 

[Nystemy]

1 minute ago, Bigun said:

I see where your coming from now, and I still disagree.

 

The libraries are more for auto tape swapping and automation.  Not for tape archival, not for tape storage - speed and automation.  The standard for tape cycle is to produce a full backup every month, otherwise you are piling incrementals on top of incrementals with no refresh.  That's what the full monthly's are for, a refresh of the incremental.  This also speeds up the RPO in the case of an incident.  This means you will need to write (potentially) 2 PB of data to tape every month.  This is why I suggested so many libraries. 

 

Just cycling off incrementals every day with no refresh of a full backup is begging for an insane RPO in a matter of months.

A fun thing with archiving the raw videos coming from the camera and finished project files is that they never change. It isn't an active database where any file anywhere within it can change over time. The data is more or less just dormant, laying in wait to one day see the light of day again and be used in another project, but even then it isn't changed. So there is no "incremental" data to store for any of these files.

 

Backing up active databases where any data anywhere in the database can have changed when the next backup comes along, then yes an automated tape library makes sense again. But that isn't really the case for backing up old project files that one won't really change nor edit. And if one wants to edit an old project, then one makes a new version of it, ie a new copy. Since the original is still worth while keeping around in its original form, and this means one just has a new set of files for the new version of the project. Yet again no incremental data.

 

However, storing the active section of the database is another topic. But here one can just write a "snapshot" of just the active portion, ie any files that has recently been edited _{(a fairly small subset of the whole)}. And store them on its own set of tapes. The archival tapes storing dormant data can lag behind a week or two to ensure that the data on them won't see any further edits. _{(or one can be more mindful and selectively store the data that one knows will not change (like ingested footage), but this is more hassle to set up.)}

 

Having followed the petabyte project and Linus talks about his data hoarding practices in videos and on the WAN show throughout the years, the database at hand is more or less 99% dormant data, only a few TB is active projects at any given moment. _{(The dormant data is however read from on a semi regular basis, anyone watching LTT and other LMG channels knows their proficient use of callbacks. So having the videos stored in a more online server as they currently have is still useful. But it somewhat lacks a proper offsite backup, not that they even state that they need/want one, so they won't really put 10's of grand on it..)}

 

In the end.

One don't use an automated tape library for an offsite backup storing dormant data in case of an emergency. _{(unless one has an insane bandwidth requirement like AWS, Facebook, Google, etc.)}

[Bigun]

22 minutes ago, Nystemy said:

A fun thing with archiving the raw videos coming from the camera and finished project files is that they never change. It isn't an active database where any file anywhere within it can change over time. The data is more or less just dormant, laying in wait to one day see the light of day again and be used in another project, but even then it isn't changed. So there is no "incremental" data to store for any of these files.

 

Backing up active databases where any data anywhere in the database can have changed when the next backup comes along, then yes an automated tape library makes sense again. But that isn't really the case for backing up old project files that one won't really change nor edit. And if one wants to edit an old project, then one makes a new version of it, ie a new copy. Since the original is still worth while keeping around in its original form, and this means one just has a new set of files for the new version of the project. Yet again no incremental data.

 

However, storing the active section of the database is another topic. But here one can just write a "snapshot" of just the active portion, ie any files that has recently been edited _{(a fairly small subset of the whole)}. And store them on its own set of tapes. The archival tapes storing dormant data can lag behind a week or two to ensure that the data on them won't see any further edits. _{(or one can be more mindful and selectively store the data that one knows will not change (like ingested footage), but this is more hassle to set up.)}

 

Having followed the petabyte project and Linus talks about his data hoarding practices in videos and on the WAN show throughout the years, the database at hand is more or less 99% dormant data, only a few TB is active projects at any given moment. _{(The dormant data is however read from on a semi regular basis, anyone watching LTT and other LMG channels knows their proficient use of callbacks. So having the videos stored in a more online server as they currently have is still useful. But it somewhat lacks a proper offsite backup, not that they even state that they need/want one, so they won't really put 10's of grand on it..)}

 

In the end.

One don't use an automated tape library for an offsite backup storing dormant data in case of an emergency. _{(unless one has an insane bandwidth requirement like AWS, Facebook, Google, etc.)}

That still doesn't address RPO.  Even if you keep just two months of full incrementals and allow one set to expire, your RPO significantly drops.  With Just one full backup and 2 years of incrementals, you will have to load up **ALL** of the tapes (The one full and two years of incrementals) to do a full recovery - that's not even including the prayers that every single tape in the chain is good or testing recovery.  You would have to test the same set of tapes at least twice a year.

Call it preference if you want, but two two months of cycling tapes, your chance of recovery doubles.

*edit*

 and dramatically increase your chance of finding bad tape in case 2nd law dips his head in.

[myxiplx]

Petabytes of data, Seagate drives, ZFS, no hot spares and no scrubs.  For anybody who's been in the storage industry for any length of time, this was a disaster waiting to happen.

 

Hard drives are consumables.  They're mechanical, which means they wear out, and at petabyte scale using cheap drives you can expect to be seeing drive errors on a regular basis.  If those drives aren't being managed by a software stack that expects that, corrects the faults, and manages the health of the drives constantly then it's a question of when, not if you'll be losing data.  ZFS has some good points, but unfortunately hardware management and fault recovery are two major weaknesses and there are very, very few enterprise storage companies who have made it robust enough to be a viable solution.  It doesn't re-map bad blocks well, doesn't handle large amounts of errors on drives well, and only scrubs your data, not the entire mechanical platter on the disks.  It's very good at telling you that you've lost data, but unfortunately not so good at preventing it.

 

I would strongly recommend Linus and the team reach out to Nexsan and take a look at their petabyte scale Unity range.  Those are ZFS fronted appliances that use Nexsan's high-density E-Series systems for the disk management, and that makes them probably the most bulletproof ZFS storage solution in the industry.

 

I've no connection to Nexsan these days, but I know their hardware well:  Many years ago I worked there, both in their customer service team and as a solutions engineer, and their E-Series and Beast range are to this day some of the most resilient pieces of IT infrastructure I've ever worked with.  I've seen them survive datacentre fires, floods and numerous power cuts.  Heck, back in the day some of their devices were installed in tanks.  They've been managing large scale environments with hundreds of disks for decades, and the arrays scrub every single block of every drive in the background, and automatically re-map bad blocks.  They also report cable or SAS link errors as well as drive bit errors or drive failures.  They're very, very thorough and I had customers back in the day with arrays that were 9 years old but which refused to die.

 

You can also quite literally destroy nearly the entire array and still not lose data.  You can lose the chassis, the power supplies, both controllers, and a chunk of your disks and still not lose data.  Provided you had enough disks surviving to be a valid (partial) raid set they were always able to recover.  You can literally move drives into another Nexsan array (in any order, shuffle the drives as you wish), and that array will boot up, ask if you'd like it to load your previous settings, and bring all your data back online, with all your data, volumes, IP addresses, the works restored.

Heck, even after doing all that if you were still having problems the support team would still have enough logging and disgnostic data to tell you which of your drives were healthiest, which order they failed in, what your best options are for getting data back, and they can literally force faulting drives back online while you copy data off.

Now the E-Series and Beast are block storage devices so aren't ideal for Linus Tech Tips, but the Nexsan Unity range takes those bomb proof pieces of hardware as the foundation of the storage system, and then adds all the filesharing, caching, snapshots and other goodies of ZFS on top.

It's by far and away the most reliable ZFS solution I've seen in more than a decade in the storage industry. 

[Luscious]

I don't have anywhere near the data LMG has (just four 8TB drives configured using StableBit DrivePool) yet even for me I invested in a LTO tape drive to keep a backup in case I get a hard drive fail, the rig they're plugged into dies OR the partitioning software "shits the bed" so to speak.

 

In my particular case I have a single external LTO-7 drive with a USB interface - yes, you read that right, USB. Why go down that road? So that I can plug it into ANY SYSTEM to retrieve data. I can use my main desktop for it or even my laptop. Not needing a dedicated machine is extra piece of mind, likewise for the home user who doesn't have a rack with SAS/FC capability.

 

Getting to the point here, a modern LTO-8 or 9 investment is sorely missing, more so when you are able to work that into the daily routine of the staff. Maybe it really did come down to a delegation issue, but the fact that ALL THREE of the IT monkeys there failed to pick up on the drive errors means they NEED either a dedicated person to handle backups or rotate the task among the three with a check process to make sure it actually happens.

 

A dual drive LTO-8 setup will back up 24TB of uncompressed data, with the two drives costing maybe $10K and the tapes around $73/pop. If the IT monkey on call can load the tapes in the drives and click on a backup script then the job can be left to run unattended - repeat this every morning, or until you have the entire system backed up. Then as an added step you could make a #2 copy of the tape and take that offsite. It really doesn't require much work, just some smart planning, to have a bulletproof backup strategy in place.

 

This review here pretty much sums up my experience:

 

 

[Nystemy]

4 minutes ago, Bigun said:

That still doesn't address RPO.  Even if you keep just two months of full incrementals and allow one set to expire, your RPO significantly drops.  With Just one full backup and 2 years of incrementals, you will have to load up **ALL** of the tapes (The one full and two years of incrementals) to do a full recovery - that's not even including the prayers that every single tape in the chain is good or testing recovery.  You would have to test the same set of tapes at least twice a year.

Call it preference if you want, but two two months of cycling tapes, your chance of recovery doubles.

I think you are missing my point.

 

The majority of the data is dormant and in its own storage pool, it never changes except when new files are added. Ie, there should never be any incrementals to deal with here. Just storing the files as Files in chronological order onto tapes and storing their related file path that they belong to is sufficient as a backup. Since this data itself never changes. To be fair. They could just copy over the project folders from the vault one by one onto tapes. No need to even be fancy with keeping intact file paths. _{(other than keeping file linking in projects intact, but this is rather easily solved by proper folder naming conventions. (my own archive of furry yiff isn't much different than this...))}

 

The active portion of the database, ie the current projects in the pipe will however see files that do get edits, these are however stored on another server. And do get incrementally backed up onto the Vault on a daily basis and fully backed up every week. It is put into its own storage pool and isn't mixed with the otherwise dormant data. (IIRC)
 

The active data will however need a more fancy backup system, but this is however only a few TB and LMG has access to 6Gb/s up to the larger internet _{(and 10 Gb/s to the Vancouver internet Exchange)} and could likely store their backup on some webservice where they would then only really need a handful of TBs. _{(Likely only storing a simple mirror of whatever is in the pool on the Vault. it should be sufficiently up to date)}

 

So how don't I address the RPO if I may ask?

There is two datasets here, one huge one with data that never changes, and one small that handles ongoing projects and these two databases are largely isolated from each other.

[Ultraforce]

Are Seagate drives really considered bad ? I got 2 of them for a beginner QNAP NAS since I wanted to try and dual boot and was having trouble trying to have stuff go between Windows and Linux. Also just since I don't know how much longer I will use my current desktop and wanted something to get my feet wet with network attached storage.

[dogwitch]

1 minute ago, Ultraforce said:

Are Seagate drives really considered bad ? I got 2 of them for a beginner QNAP NAS since I wanted to try and dual boot and was having trouble trying to have stuff go between Windows and Linux. Also just since I don't know how much longer I will use my current desktop and wanted something to get my feet wet with network attached storage.

there not. like in anything . you can get bad batches. but  people think the back blaze is the storage bible...

when you base you research off of only 1 source. its never a  good idea . does not matter even if its a some what decent source.

[BrokenText]

As an IT tech, I can related when this happens, hope you recover all the important data.

 

Worked with one of the best monitoring solution like Grafana and Prometheus.(both open source)

Would highly recommend them to alert and audit similar issues.

 

hope it helps.

[Nystemy]

3 minutes ago, Ultraforce said:

Are Seagate drives really considered bad ? I got 2 of them for a beginner QNAP NAS since I wanted to try and dual boot and was having trouble trying to have stuff go between Windows and Linux. Also just since I don't know how much longer I will use my current desktop and wanted something to get my feet wet with network attached storage.

In regards to seagate and Western Digital reliability.
Some people have had bad luck with one drive or the other and base their whole reality on what effectively is pot luck.

 

I personally have 3 WD drives that have died, and 1 that has some weird behavior where it constantly interrupts the CPU and leads to an immense reduction in system performance from just having the drive plugged in...

 

Meanwhile I have only had one seagate fail.

 

So in my case, I would go with seagate, but logically speaking, it isn't a major difference. Hard drives die eventually, and some gives up the ghost far faster than logical at times. Doesn't really matter the brand.

 

One can't judge quality and consistency from a handful of samples in most cases, not to mention that people have a large dose of confirmation bias towards their own opinions.

[dogwitch]

19 minutes ago, Nystemy said:

In regards to seagate and Western Digital reliability.
Some people have had bad luck with one drive or the other and base their whole reality on what effectively is pot luck.

 

I personally have 3 WD drives that have died, and 1 that has some weird behavior where it constantly interrupts the CPU and leads to an immense reduction in system performance from just having the drive plugged in...

 

Meanwhile I have only had one seagate fail.

 

So in my case, I would go with seagate, but logically speaking, it isn't a major difference. Hard drives die eventually, and some gives up the ghost far faster than logical at times. Doesn't really matter the brand.

 

One can't judge quality and consistency from a handful of samples in most cases, not to mention that people have a large dose of confirmation bias towards their own opinions.

oh yeah had 2  drives from wd do that. some poor board software on the drive itself..

 

btw i have wd,seagate,tosbiba,samsung,

ssd are samsung,intel,scan disk,pny, micron oem badge

[cmndr]

HOT SPARES.

I know just enough to be dangerous... and even I know that there should've been at least 2-3 hot spares in the arrays.

I say this while trying to get my ZFS based NAS to work properly again (config issues that are on me - 0 data loss though).