-
We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.
What NAS HDD speed...
- Thread starter Zebo
- Start date
Phynaz
Lifer
Why aren't you running ILO? Or hot spares for that matter?
Zebo
Elite Member
I use GB ethernet/wireless. Router is Cisco e2000. Snynology 411j Seems extremely slow compared to regular HDD in a system but overall very happy - just want more speed and one more drive won't hurt either.
Check out performance difference when building a 1511+
http://www.synology.com/enu/products/4-5bay_perf.php
That said just wondering if 7200prm would help.
Last edited:
Zebo
Elite Member
Raid 5 is better than no RAID and two disks failing at once is like winning lotto. Did you have email for NAS application notification sent to you when one drive was failing? Probably not. Most people don't know what's going on until it's too late because they don't program NAS correctly.
not to mention if two fail on RAID 10 you're SOL of it's the wrong two.
Last edited:
What is the sample size out of curiosity?
Cerb
Elite Member
I'm sure too low is the answer. Really, anything not in the hundreds is too low, and even then, he would only just be reaching a significant sample size, except for drives that have a high failure rate (Segate 7200.12 now, IBM 75GXP of ages past). I've had three Samsungs fail, one in a RAID, one still within the RMA period. They must be terrible drives.
I have had really bad luck with newer (.11 and .12) Seagates, by way of infant mortality, and a nice firmware bug, so am avoiding them (by Newegg reviews, I'm far from alone). Otherwise, it's hard to tell, until enough people have enough experience, at which point the drive series will have been replaced. IMO, the best policy is a backup drive, of a different drive series than the drive it is copying from.
If using the NAS as a file server, with no meaningful amount of random R/W, faster drives could help, but there isn't a good way to know how much, unless someone benchmarks the difference. Given the RAID 5 performance in that link, it looks like the NAS is able to do a good job of prefetching and buffering, for sequential transfers. In that case, there would probably not be a difference. But, when you start dealing with smaller files (with RAID 5, even single-digit MB might be small enough), the difference might start becoming apparent.
IMO, if you can afford a $700+ NAS, you might as well spend a little extra and be sure you won't have drives that slow you down. That said, if you want to try slower-spinning drives, Samsung's seem to perform the best in random loads, of those slower drives.
The DS1511+ is supposed to be even faster using link aggregation. 190MB/s read, 160MB/s write.
The Hitachi drives are supposed to be fast, and hot and loud.
Zebo, how are the F4 drives doing? I'm waiting for my DS411+ to arrive. I bought 2x 2TB F4s. I'm hoping there aren't any issues and they don't need to be patched. Unfortunately the compatibility list for 2TB drives is short and most seem to have issues or are loud/hot or expensive.
The Hitachi drives are supposed to be fast, and hot and loud.
Zebo, how are the F4 drives doing? I'm waiting for my DS411+ to arrive. I bought 2x 2TB F4s. I'm hoping there aren't any issues and they don't need to be patched. Unfortunately the compatibility list for 2TB drives is short and most seem to have issues or are loud/hot or expensive.
CurseTheSky
Diamond Member
Keep in mind that gigabit ethernet is only 1000 bits per second. Since there are 8 bits in a byte, you're looking at 125 MB/s theoretical maximum, and your actual throughput will be significantly lower (probably in the 50-60 MB/s range). Wireless is, of course, much slower. I believe a good wireless N connection can reach something like 200-300 Mb/s (~20-37.5 MB/s) - less than 1/3rd of the throughput of gigabit ethernet.
7200 RPM drives may help, but do not expect a night and day difference. I'd personally stick with 5400 RPM drives unless the price difference is negligible or every last ounce of performance really counts. I wouldn't expect modern 5400 RPM drives with high platter density to be your bottleneck.
Zebo
Elite Member
i have been using 4 of them 8 months now no problem and no noise. 2TB drives seem to be problem childs based on newegg reviews most with a abysmal 2.5-3 stars which is low rating for HDD so I just went with the best star rating, F4 and seems to have worked out.
Unfortunately I paid $110, now they can be had as low as $69 with hot deals.
Zebo
Elite Member
Based on what you and Cerb are saying it might be best just to stick with what I got for now because throughput won't improve much if at all. Someday soon I will have to build a DIY NAS with 10-15 disks if this one keeps filling up. OTOH I like the 1511+ because you can add modules to it up to 15 disks...plus in general the synology software is outstanding.
Unfortunately there aren't many reviews of the 1511+. However, of all the reviews of the 411+ I've read, it's definitely possible to hit 100MB/s (read/write) on a single gigabit connection.
http://www.smallnetbuilder.com/nas/nas-reviews/31324-new-to-the-charts-synology-ds411-diskstation
http://www.slashgear.com/synology-diskstation-ds411-nas-review-2695389/
The 1511+ should be able to do faster, though not too much faster unless you use both gigabit connections.
Zebo
Elite Member
Hey ace I forgot to mention when you get F4s apply the patch
http://www.samsung.com/global/busine...bbs_msg_id=386
Yeah - if all clients were connected via cable I see where you're coming from. I should have got the 1511+ and will or build equivalent next time. 411+ was a good move. You bought right, I'll buy twice. See sig.
http://www.samsung.com/global/busine...bbs_msg_id=386
Yeah - if all clients were connected via cable I see where you're coming from. I should have got the 1511+ and will or build equivalent next time. 411+ was a good move. You bought right, I'll buy twice. See sig.
Last edited:
I am using a relatively inexpensive DLink DNS-320 NAS. Although it works well for how we use it, in real world RAID 1 use, it is very slow. It is my understanding, relative to the DNS-320, the NAS electronics are the bottleneck and using faster drives would not help. I do not know if this same issue applies to more expensive and higher performing NAS's but it might be a consideration before incurring the cost of faster drives. Even if more expensive NAS's are better performing, will faster drives provide a consequential or only marginal increase in performnace?
yes vcenter notified me of alarm condition. dunno about you but at 3am on sunday night i don't go drive in for 1 drive out on a raid-10. that's the point of not going raid-5 . and hot spares - not feasible anymore. that would be raid-6(ADG). regardless the point was i was reading the drive #'s to support and low and behold another drive fails right in front of my eyes. that is freaking lotto time. i've had a two drive failure before (non catastrophic) due to a cage losing power and every drive on the other side failing talk about pissing yourself.
raid-5 = do not want. timebomb. even with a hot spare. you might as well do raid-10 since the odds are so low compared to ADG.
realistically if i had raid-5 i'd probably do hot spare and raid-6 and come in at 3am if a drive failed. but you must remember the level of service i got is next business day. hp mission critical is necessary for 6 hour call to repair 😉 (that is a correct answer on the test)
raid-5 = do not want. timebomb. even with a hot spare. you might as well do raid-10 since the odds are so low compared to ADG.
realistically if i had raid-5 i'd probably do hot spare and raid-6 and come in at 3am if a drive failed. but you must remember the level of service i got is next business day. hp mission critical is necessary for 6 hour call to repair 😉 (that is a correct answer on the test)
The F4s are from 12 2010 and onward, supposedly it doesn't need to be patched. Though, I should just try the patch anyways since NAS won't get here for a few days.
The 411j could always be used as a backup NAS. I'm planning on just using an external drive as backup for irreplaceable essentials.
Damn. I should be buying lotto tickets then. I have had this issue more than once. Typically with larger capacity disks. Old 15k 146GB drives chug for 10 years, 600GB 15k SAS disks are accumulating errors.
It is statistics at work. As the disk sizes grow (and sector count increases), the odds of a read error increases. When a disk is failed out and offline, all it takes is one bad sector during the rebuild to bomb an array.
Last edited:
Spikesoldier
Diamond Member
i recently built a freenas box with four 7200rpm hard disks, running two RAID1 mirrors 1TB and 750GB. the rig powering it is a E6420 @ 2.13 and 2GB of ddr2 @ 533 4-4-4-12.
transfer write speed from a 7200rpm hard disk hooked up to my machine was 85.1MB/s over a gigabit link, and using freenas software raid, CPU load never broke 60% writing at that speed.
i cant directly compare 7200rpm to 5400/5900rpm drives, but since i built a full tower, i figured i can get away with running the 7200's. I think that thermal would be your biggest concern in a smaller chassis though. my case has space for eight hard disks, and capability to hold twelve with an appropriate 5.25" backplane.
right now, zacate is looking very sexy for a nas box. just slap 1gb ddr3 in there and its good to go. uses minimal power, four-five sata3 ports, and pci-e 4x slot for cheap pcie 1x sata controller, or optionally, a nicer 4x controller.
transfer write speed from a 7200rpm hard disk hooked up to my machine was 85.1MB/s over a gigabit link, and using freenas software raid, CPU load never broke 60% writing at that speed.
i cant directly compare 7200rpm to 5400/5900rpm drives, but since i built a full tower, i figured i can get away with running the 7200's. I think that thermal would be your biggest concern in a smaller chassis though. my case has space for eight hard disks, and capability to hold twelve with an appropriate 5.25" backplane.
right now, zacate is looking very sexy for a nas box. just slap 1gb ddr3 in there and its good to go. uses minimal power, four-five sata3 ports, and pci-e 4x slot for cheap pcie 1x sata controller, or optionally, a nicer 4x controller.
Last edited:
VirtualLarry
No Lifer
Do the SATA ports on Zacate mini-ITX mobos support RAID out of the box? Or would one have to get a RAID controller card?
Spikesoldier
Diamond Member
in my case of running freenas, i accomplish raid1 by using software raid.
looks like on the zacate the new controller on there provides sata3 but no mentioning of raid capability.
its advised that hardware raid on a board can be nightmarish if the board fails. a good feature of brazos/zacate is the pci-e 4x slot which can be used for both a good raid controller or a simple, entry level one.
when i expand this nas further, ill have to add a simple pci sata2 4 port card. after that, a second one of those, and a $100 4 port 5.25 backplane allows me to get twelve disks in there.
here is the case i am using: http://www.newegg.com/Product/Produc...-062-_-Product
if i go zacate, i would get the micro-atx one by asus because its fanless, and also the pci slots help when adding more controller cards.
Last edited:
Evadman
Administrator Emeritus<br>Elite Member
Here is a quick summary of complete array failure probabilities, speed, cost, and available storage size based upon four $100 each 2TB drives with 1M hrs MTBF and 50 MB/sec read/write.
In terms of space, here is a summary:
RAID0 - 8 TB
RAID5 - 6 TB
RAID6 - 4 TB
RAID10 - 4 TB
In terms of probability of array failure over the life of the array (3 years):
RAID0 - 10.5%
RAID5 - 0.000105%
RAID10 - 0.0000525%
RAID6 - 0.00000000000105%
In terms of speed (perfect controller):
RAID0 - 200 MB/Sec
RAID5 - 150 MB/sec
RAID10 - 100MB/sec
RAID6 - 100MB/sec
In terms of dollars per usable TB:
RAID0 - 8 TB / $400 = $50 per TB
RAID5 - 6 TB / $400 = $67 per TB ($17 more than RAID0 to drop the rate from 10.5% to 0.000105%)
RAID6 - 4 TB / $400 = $100 per TB ($33 more than RAID5 to drop the rate from 0.000105% to 0.00000000000105%)
RAID10 - 4 TB / $400= $100 per TB
In terms of space, here is a summary:
RAID0 - 8 TB
RAID5 - 6 TB
RAID6 - 4 TB
RAID10 - 4 TB
In terms of probability of array failure over the life of the array (3 years):
RAID0 - 10.5%
RAID5 - 0.000105%
RAID10 - 0.0000525%
RAID6 - 0.00000000000105%
In terms of speed (perfect controller):
RAID0 - 200 MB/Sec
RAID5 - 150 MB/sec
RAID10 - 100MB/sec
RAID6 - 100MB/sec
In terms of dollars per usable TB:
RAID0 - 8 TB / $400 = $50 per TB
RAID5 - 6 TB / $400 = $67 per TB ($17 more than RAID0 to drop the rate from 10.5% to 0.000105%)
RAID6 - 4 TB / $400 = $100 per TB ($33 more than RAID5 to drop the rate from 0.000105% to 0.00000000000105%)
RAID10 - 4 TB / $400= $100 per TB
raid-10 reads from all drives (we are talking about raid-1 pairs striped raid-0 yes?) it has the best read&write speed for a protected environment.
keep in mind the cache size, and backup can cripple raid-5/6. If you have a battery back write cache and it fails(it will if its a battery) your speed will drop to 10-20mb/s . this is definitely enough to cause failures left and right in a degraded operations mode. raid-10 not as badly.
factor in $100 drives have a bitrate error of about 1 bit always - the probably of rebuild and time of rebuild must be considered - also the priority of rebuild to usability is very much important.
I was hoping someone would come along and make an SLC drive manage the ECC (Raid-3 like) for mechanical drives. since 600gb SAS 2.5" are now mainstream this would rock imo. wish i had the time to hypothetically try that. or use a pair of ssd's for tiered storage cache of a disk set (not far off from flash back write cache).
keep in mind the cache size, and backup can cripple raid-5/6. If you have a battery back write cache and it fails(it will if its a battery) your speed will drop to 10-20mb/s . this is definitely enough to cause failures left and right in a degraded operations mode. raid-10 not as badly.
factor in $100 drives have a bitrate error of about 1 bit always - the probably of rebuild and time of rebuild must be considered - also the priority of rebuild to usability is very much important.
I was hoping someone would come along and make an SLC drive manage the ECC (Raid-3 like) for mechanical drives. since 600gb SAS 2.5" are now mainstream this would rock imo. wish i had the time to hypothetically try that. or use a pair of ssd's for tiered storage cache of a disk set (not far off from flash back write cache).
TRENDING THREADS
-
Discussion Zen 5 Speculation (EPYC Turin and Strix Point/Granite Ridge - Ryzen 9000)- Started by DisEnchantment
- Replies: 25K
-
Discussion Intel Meteor, Arrow, Lunar & Panther Lakes + WCL Discussion Threads
- Started by Tigerick
- Replies: 25K
-
Discussion Intel current and future Lakes & Rapids thread- Started by TheF34RChannel
- Replies: 24K
-
-
