• Content Count

  • Joined

  • Last visited

Everything posted by alpha754293

  1. 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.
  2. 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.
  3. (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.
  4. Has anybody ever seen this before? (Where cygwin doesn't report the available space on a Windows Storage Spaces pool correctly.)
  5. 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.
  6. Gotcha. Good tip. Thanks!
  7. 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.
  8. 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.
  9. Hello. Sorry for jumping into this discussion late, but I'm just looking into Windows Server 2012 R2 for deployment at home (possibly). So what I'm trying to do is to build my second 10 * 3 TB SATA array, but unfortunately, the 2U system that I got only takes half-height cards (2x PCIe 2.0 x8, 1x PCIe 2.0 x4) and there are 6 SATA headers on board, so it looks like that I'm going to have to use the onboard controller and also another RAID HBA. And I only recently learned about Windows Server 2012 R2 storage pools and how it can create a parity pool. Does anybody have any benchmark data on how that performs vs. various HW RAID solution? From the reliability/fault-tolerance perspective, would it be better for me to create a parity storage pool from the Windows Server 2012 R2 (so that I can write the parity data across both controllers) or would it be better for me to create two RAID5 arrays using the controllers and then creating a stripped pool to bridge the two arrays? (I'm trying to optimise between capacity, fault tolerance, and write speed). Any insights or thoughts on this dilemma would be greatly appreciated. Thank you.
  10. 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.
  11. I know that it will start out as being sequential for the initial/first sync, but I don't know how sequential it will be afterwards. I read on one of the MS TechNet blogs that the performance can drop from 140 MB/s down to 25 MB/s if storage spaces is what's building the parity data (which, when you're doing the initial sync up of 20 TB, that's going to take an awfully long time).
  12. Thank you for the person who helped me split this topic. I added it to the other thread only because it was the only thing that I really found that was relevant to the parity storage pool aspect of the discussion. The primary purpose of this server will be to act as a live backup/mirror to my first (30 TB) server. I already have the drives and the 12-bay system already (it's another server, not a DAS or NAS), so really the last piece of the puzzle is what to do with the 12-port SATA RAID HBA that's either half-height or low-profile. I'm trying to keep the cost of the RAID HBA plus any expander cables to around $200 if at all possible. Speed won't be too much of a concern, since I'll likely run rsync or similiar once a week to keep the two servers sync'd up with each other. But it would depend on whether I can actually get said half-height/low-profile 12-port SATA RAID HBA because if I can't, then I would either need to built two RAID5 arrays (one on the onboard controller and one on another controller card) and then stripe them together using Windows Server 2012 R2 storage pool (as a stripped volume) or I would have to just leave it as JBOD (for all of the drives) and then create a ZFS zpool.
  13. What's the most cost effective, cost efficient way of backing up ~ 10 TB of data? The probability that the data is going to change is very small. Would it be better for me to just build another live hard disk array and then power it up only when I want to run rsync or would it be better for me to use some kind of optical medial like BD-DL or BD-XL or would it be better for me to go with something like a LTO-3/LTO-4 solution? Backup speed isn't too critical/too important (as I can likely run the backup job overnight). I'm looking for something that has a relatively low cost of entry (initial capital expenditure) and also a reasonably low cost of maintaining the backup solution (as the volume of data increases over time). Advice/suggestions/comments is GREATLY appreciated. Thanks.
  14. Thanks. I thought about using ZFS because then I can enable compression on it and also turn on deduplication as well, so it would save a bit of physical storage space. That was the logic/reasoning behind it. But I do agree with the NTFS though. Such a shame that it doesn't have de-dup natively (although I was reading that I think it was in Windows Server 2012 that it has it or something very similiar to it, but I've not read ALL of the details in terms of how it works/how it does the dedup), so... Thanks for your feedback.
  15. Thank you all for your input. I actually purposely left out a few of the details because I didn't want to contaminate or influence the opinions of the people who have been providing them. So, I'm going to fill in the back story now. My current RAID array is 10 * 3 TB drives on RAID5. They're Hitachi 3 TB drives that I bought a couple of months before the floods in Thailand, not knowing that there was going to be a flood, but because they worked out to be like $114 each per drive, so it was a really good deal. Yayyy eBay. My original intent was to have the first 10 drives (out of a box of 20) to be deployed in my current server and then the second group of 10 to be deployed as the backup; BUT now you might be asking "so why did you ask?" well...I want to make sure that that was still the better way to go and that LTO and BD-DL or BD-XL hasn't replaced it in terms of cost and viability and reliability. I haven't built the second backup server yet because I'm still debating as to whether I want to keep it as NTFS or whether I want to migrate back over to ZFS as the backup server. (Aside from one or two other experimental file systems, those are the only ones that will support a single volume that size.) I actually already have the drives, I'm just waiting to get the enclosure and the rest of the server hardware (motherboard, CPU, PSU) etc. before I can launch and deploy the backup server, but I just wanted to make sure that the initial plan still held its own when tested by other people. And given the feedback, it seems like that hard drives is the way to go, although trying to expand the capacity of either systems would be a little harder, unless I just get bigger drives, but the same number of them. Thank you all for your feedback/input.
  16. So...mechanical hard drives is still the way for me to go then?
  17. alpha754293

    secure data transfer

    Well, I am hoping that the data will be somewhat live so that as my master copy is updated, so will the colo copy(ies). Would it be better to encrypt the drive or just the archive will be sufficient? Or both? I thought that I read somewhere that the SHA-256 hash isn't as secure as it was once thought to be? Does it matter if it's AES-CBC or AES-ECB? Yea....I'm not really THAT skilled in system administration to be able to set that up let alone teach it to my friend who's NOT a sysadmin. Can you SEND ZFS to another system that's NOT located on the local network? Or rsync over the net? How do you define a remote target for the send/receive commands? Or would it be a ssh/rsh port forward (at the router side of things)? (Forgive me for asking dumb questions) - but just trying to figure out what would be the best way to transmit data securely.
  18. alpha754293

    secure data transfer

    One of my friends have agreed to colo financial data for me and I was wondering - what's the best, most secure way of transferring the data? I've heard that there are now external drives that support full disk encryption? Would that be at the device level or OS level? Or would it be better for me to encrypt the data and then just copy it to a disk? Or would it be better for me to put that into a password protected archive and then encrypt the disk? Thoughts? Suggestions? He runs Ubuntu and I run Windows (primarily) but I can also run Ubuntu as well. (Or Solaris or Mac OS X). Thanks.
  19. alpha754293

    Dead drive in Solaris ZFS pool

    Yeah, I built the array a LONG time ago (16x 500 GB drives) and so I was expecting that I would need the capacity moreso than the protection. And it didn't help that the person who shipped the drives to me didn't export the pool first before pulling them from the server, and then the drives also weren't packed properly for transit so I think that two of them died that way. But if they clone EVERYTHING on the drive, ZFS should be able to think that it is still the same drive and bring the pool back up online, right?
  20. I have a Solaris ZFS pool (striped) across 16-disks and I think that two of the drives died in transit. If I were to take the drives to a data recovery company and have them do a bit-by-bit copy, will that be sufficient to restore the drive/array? I remember reading something about ZFS writing an EFID to the disk. If I tell them that they have to clone the entire drive PERFECTLY, would they know what I mean by that or do I have to explicitly spell it out for them? Thanks.
  21. alpha754293

    correcting size on disk with defrag on RAID5 array?

    Well, that's just the applications directory (directory where the applications are being served out of). In another directory, I have a LOT of really big files. The space-on-disk vs. space utilization is much better (sitting somewhere around the 0.9-0.95 factor). And that's the thing too - I couldn't predict what the installation files would unpack to. And whether the application will run over the network (some do. Some won't. Some won't even let me installed to a mapped network drive.) (As for backup, I'm starting to think about looking into getting a LTO-3 drive and do a grandfather-father-son type dealio. But that's another discussion. (ORIGINALLY, the plan was for me to build a second live server running ZFS and then run rsync weekly), but I dunno. I know that usually, the discussion around stripe vs. cluster size is due to performance considerations. Whereas in my case, I'm not really too overly concerned about that. (I've got a 12-port SATA 3 Gbps controller, and my network is only 1 Gbps, which means that I am much likely to bottleneck and oversaturate the network long before I will run out of performance room from the array.) So this ends up being an optimization of a different kind - one that I don't think that very many people has done.
  22. I'm a little confused about this. I know that the difference between size and size on disk is because small files can take up a whole cluster even if they don't fill the cluster. And I am under the impression that defragging might be able to help improve what I've termed "cluster utilization" (more small files that use different parts of the same cluster). Example being say that my clusters are 4 kiB, and I have a file that's 17 kiB, that means that it's going to use 5 clusters (20 kiB) leaving 3 kiB wasted. If I have four of these files, will defragging be able to help make better use of that last cluster that would normally only be partially used? System/OS details: 10x 3 TB drives on ARC-1230 RAID5 formatted as NTFS with 64kiB clusters running on Server 2008 HPC. I'm also asking cuz I was checking on of my mounts and it's showing like some 31.7 GB actual size, but the size on disk is closer to 66.1 GB; so I am wondering if defragging might fix that. Or would it matter? The way that Windows reports disk utilization - is it based on the actual size or is it based on the size-on-disk? Any help/advice would be greatly appreciated. Thanks.
  23. alpha754293

    correcting size on disk with defrag on RAID5 array?

    Well...they're actually the applications that are installed. I created a directory on the array, and then mapped it as a network drive so that instead of installing the apps over and over on the client machines, wherever possible, it's a single instance, stored on the network server, but across multiple clients. So it's whatever the file breakdown ends up being whatever it happens to be. I don't suppose that there's a way for me to format different part of the drive without having to repartition the drive into multiple partitions, and then assigning a separate drive letter to each, is there? Also, should the stripe size for a RAID5 array match the format settings? Or does not matter? I also tried copying the folder onto another drive (the OS drive) and then copying it back to see if "re-organizing" the layout might help. It didn't.
  24. Are there any (free) tools available that can help dedup a NTFS volume? Host system is a single Socket604 Xeon 2.8 GHz, with HTT enabled. 2 GB of RAM. Areca ARC-1230 12-port SATA-II RAID HBA with 10 Hitachi 3 TB 7.2krpm SATA-3 drives in RAID5. OS is actually the base of Windows HPC Server 2008 without the HPC pack installed (yet). So it boots up as Windows HPC Server, but is otherwise and effectively Windows Server 2008.
  25. alpha754293

    Which file system should I go with?

    But that's the thing though, I shouldn't have to do that ex post facto. The idea is to be able to do the rapid deployment without having to further configure the system. Especially after the system is up, there's already about 6 TB that needs to be transferred over. (Actually, it's closer to 12 TB, but of course, you can't fit 12 TB of data onto a 10 TB array. lol...) The idea is that I should be able to configure the mount at install, not after. If I can do that, then it doesn't matter which fs I use, because there's a bunch of them. I don't think that FUSE is a valid option because if the failure's with the filesystem extensions, then you're toast. And then you have to go in there with a data recovery tool. I don't know about you, but do you know of any XFS data recovery tools where you would be able to mount the array on another system that isn't running Linux with the XFS extensions?