• Content Count

  • Joined

  • Last visited

Community Reputation

0 Neutral

About alpha754293

  • Rank

Contact Methods

  • MSN
  • Website URL

Profile Information

  • Location
    Windsor, ON
  • Interests
  1. alpha754293

    Question about RAID5/6 and/or ZFS raidz1/2 theory

    So... What parameters should I be specifying for the par2 command line tool in order to calculate/generate the parity data that mimicks the more traditional RAID5/RAID6 configurations?
  2. alpha754293

    Question about RAID5/6 and/or ZFS raidz1/2 theory

    But that only just postpones/delays the same fundamental failure mode. You're just increasing the number of layers in order to statistically reduce the probability of the failure mode/error state from occurring. I mean, to that end, there is nothing that you can't have septuple parity as your probability of the failure mode occurring will drop to somewhere on the order of 10^-9 to 10^-16 or less. (I haven't done the math, so I'm guessing in regards to the order. If someone else who is smarter than I am can do the math, then I can update that.)
  3. alpha754293

    Question about RAID5/6 and/or ZFS raidz1/2 theory

    But how would you then label the tapes so that the data would be consistent? Wouldn't this mean that in order for the data and the parity to be consistent that you would only be able to write the data in (n-1) "chunks" - i.e. if you had 3 LTO-8 tape drives, the total raw, uncompressed capacity would be 36 TB, with only 24 TB that's "usable" since 12 TB would be used to store the parity data. That also means that those three tapes will always have to work in conjunction with each other, so when you want to read data from this group of tapes, you will have to load all three tapes into the three tape drives simultaneously in order for this to work, correct? And if you have 5 drives, then you would have to load all five tapes in at the same time for this to work, right? (etc. etc. as you increase the number of tape drives) Conversely, why do that when you can just use par2 instead? You write the parity data to each individual tape so that with a single drive, the tape will contain all of the information self-contained within the tape, and if you are worried, you can also create/write parity of the parity data onto the tape as well. Isn't that what double parity does? Single parity is parity on your original data/file. Double parity would be parity on top of your original data/file AND the first set of parity data that was generated/calculated by the RAID HBA or OS/CPU if you're using software RAID? And if you are worried about the tape being a single point of failure (e.g. the tape is burned up in a fire), you can have x number offsite, colocated copies for disaster recovery. This way, you don't have to wait for n number of tape drives to synchronize (and loading n number of tapes simultaneously) to be able to move data around. Instead of waiting to eject and load 5 tapes, while one tape is being ejected, another could already be loaded and it can start reading the next tape already. Whereas with RAIT, you'd have to synchronize the tape drives so that the group of tapes will work as a single unit together. (And the load/unload mechanism isn't exactly the fastest, even with LTO-8. It can still take upto a minute with my current drive (not a tape library) to bring a tape up online so that it can be read/written to.)
  4. alpha754293

    Question about RAID5/6 and/or ZFS raidz1/2 theory

    How would I apply this calculation for "number of drives in the array" when it comes to or refers to LTO-8 tape drive(s) system(s)? Do I need multiple LTO-8 tape drives in order for this parity calculation to work properly then?
  5. alpha754293

    Question about RAID5/6 and/or ZFS raidz1/2 theory

    But this is where I am a tad confused: By the "conventional" understanding of RAID5 (n-1) parity, that means that the redundancy as a percent of the total capacity, given by 1/n drives varies with n. Therefore; expressed at the filesystem level, each file is only 1/n redundant, which, if you have silent corruption in the parity AND the actual file/data, you're kind of screwed. Again, this is what I am getting/coming the to the understanding of by reading the par2cmdline README file and I want to check whether my understanding of the parity theory is correct -- in that if there is silent data corruption with the parity data and also with the actual file data, you're screwed if you don't have parity on top of the parity, or double parity, correct? (And by virtue of that, that means that with each increasing layer of parity, you're only reducing the probability of having an unrecoverable error in the data akin to O^n, correct? Where n is the number of levels of parity)
  6. For "conventional" RAID5/6 implementations and/or ZFS raidz1/2 implementations, what is the "level of redundancy" normally set at (where "level of redudancy" can be described as either a percentage of the total file size or based on the redundancy target size)? I am trying to understand how the parity in those implementations work so that I can mimick it using par2cmdline. Thanks. The par2cmdline README file talks about how you can set the level of redundacy using one of those two methods described above, and/or either the total number of blocks or the block size (in bytes), and the combination of which will produce enough parity data so that it would be able to tolerate x number of errors totalling y bytes. I'm trying to understand how the parity theory works so that I can create it manually using the par2cmdline tool and the reason for this is because I am creating 7-zipped archive files that are then written to LTO-8 tape, and I want to create the parity of the original 7-zip file, and also create a second level of parity data on the parity files itself (e.g. "double parity") so that instead of retaining triplicate copies of the backed up data, I might be able to get away with only using duplicates. Thank you.
  7. For one of my four Intel 540s Series 1 TB SATA 6 Gbps SSD that failed (exhausted the write endurance) = 446.4TB over the course of 8392 power-on hours (~350 days). Attached below is the SMART report that was exported from the Intel SSD Toolbox and imported into Excel. (And I have four of these drives. All of them wore through the write endurance limit. My LOWEST was 314.8 TB. What's shown is my "worst case/worst drive".) I had also previously worn out a 400 GB Intel 750 Series PCIe 3.0 NVMe x4 HHHL AIC SSD, but I don't have the SMART results/data handy. So...yeah.
  8. What is the best way to test/benchmark a four-drive SSD RAID0 array in Linux? I have a four-drive RAID0 SSD array running in CentOS 7.6.1810 and I am wondering - what do people do/use or what's the best way to test/benchmark SSD RAID arrays? I've tried testing it using two entirely different methodologies and I am getting completely different set of results, so I am trying to see what people used and/or what's the industry best practices? Thank you.
  9. (sorry, I was trying to perform a search first before posting, but I couldn't find where the search button was) So I have server which has the following RAID5 configuration 8x HGST 6 TB 7200rpm SATA 6 Gbps drives LSI MegaRAID 9240-8i (and it's already using the latest firmware) I'm trying to replace the array one drive at a time from 6 TB drives to 10 TB drives (HGST He10 10 TB 7200rpm SATA 6 Gbps), and it's saying that the estimate time to rebuild an array that has no data on it is about 105 hours(!). The rebuild rate on the controller is already set to 100. Why it is so slow? Short of deleting the virtual drive configuration, switching all of the drives in the array from the 6 TB drives to the 10 TB drives, and then creating a new virtual drive; is there anything else that I can do to speed up the rebuild process? Thank you.
  10. Has anybody ever seen this before? (Where cygwin doesn't report the available space on a Windows Storage Spaces pool correctly.)
  11. Gotcha. Good tip. Thanks!
  12. Those are the kinds of things that making me nervous about using it as a backup server because I ran into similiar type of problems with ZFS before with similiar outcomes. (I mean, I haven't had any problems yet with Storage Spaces, but if I know what the risks are, then I can better try and at least plan or protect from them). Luckily, this is going to be the backup server (the primary server is just running straight-up HW RAID5 in a single, monolithic array/volume), so I don't feel so bad if this backup server fails. Thanks. (I'm also curious as to whether I can enable compression on a storage pool (and trying to understand the risks associated with that) and also enabling/running deduplication to reduce the amount of space that's actually consumed (a la ZFS).) Thank you for helping me and answering my dumb questions about it. Like I said, I'm only just now beginning to learn about Storage Spaces.
  13. Here are some more "generic" questions about the details of Windows Storage Spaces and I am hoping someone here would be able to help answer: 1) Is the parity calculation for a parity storage pool multithreaded? 2) How does Windows Storage Spaces know what drives are in a pool? Is it by some kind of GUID from the hard drive that are members of that pool or is it something else? (Like if I were to have a drive fail and swap PCBs, will that be enough to bring the pool back online)? 3) If a pool goes offline (or is in another sort of "downgraded" state), what data recovery tools are available to extract the data off the drives? Any help with these questions would be greatly appreciated. Thank you.
  14. This is the chassis that it's going in. It came with the $200 dual Xeon system. For low-profile cards? None that I've seen that doesn't cost significantly more. The cheapest of the cards I think that I've found is going to be like $600 (see the Newegg link above). Conversely, I'm looking right now at an 8-port card ( that's going for $115 max, figuring that it is very hard for me to try and justify the cost of a $600 RAID HBA just to be able to build a single, monolithic array. I mean, I would like to, but it's REALLY difficult for me to justify it when the host system was only $200. (And the drives were about $113 each when I bought them). And the reason why I posted the question here was because I wasn't sure if there was somebody out there that has experience with a cheaper alternative (than the $600 card) that will be able to meet my requirements (low-profile/half height, 12 ports (3x SFF-8087)). And from all of the research that I've BEEN able to do, it doesn't really look like it, but hence why I figured I'd ask in case there was something that I didn't know about. *edit* And to be perfectly honest, I actually bought the dual Xeon system BECAUSE of the chassis, not necessarily because it was a dual Xeon with 16 GB of RAM and an 800 W power supply.
  15. Well, it depends. The problem I am having is finding a low-profile card that can take at least 12 drives. Most are usually 8 (if they're low-profile cards). It's an optimisation. If it would be better to spend the extra money so that I can build a single monolithic RAID5 array, then it might be worth my while. But I can use either ZFS or Storage Spaces and have IT build the parity volume, with minimal performance degradation, then that can be the more cost-efficient way to go. Like I said, I can get an LSI MegaRAID SAS 9261-8i from eBay for $175. It's low profile, supports HW RAID5, but it's only 8-ports. I agree with you. Although I've had Adaptec before and the one that's currently in the primary server is an Areca ARC-1230 I believe (because my primary server actually has a riser to support full-height cards) and that's been working out pretty good. This time, I don't have the riser, and the chassis isn't set up for it either. That's exactly the dilemma that I am trying to solve/get advice on. This is what I've been able to find on Newegg (as an example): It's the Areca ARC-1264IL-12 12-port PCIe x8 2.0 SATA 6 Gbps RAID HBA (with support with RAID5), but it's going for almost $600.