"iSCSI killer" Native in Linux 235
jar writes "First came Fibre Channel, then iSCSI. Now, for the increasingly popular idea of using a network to connect storage to servers, there's a third option called ATA over Ethernet (AoE). Upstart Linux developer and kernel contributor Coraid could use AoE shake up networked storage with a significantly less expensive way to do storage -- under $1 per Gigabyte. Linux Journal also has a full description of how AoE works." Note that the LJ article is from last year; the news story is more recent.
AOE? (Score:5, Funny)
Re:AOE? (Score:2, Funny)
Re:AOE? (Score:2, Funny)
I'm sure that'll go over great with your party fighting enemies in a narrow hallway.
I'm sure the DM and your party members will be VERY forgiving when they have to create new characters.
I forget, the AoE of Fireball is either 5 feet or 5 meters. Either way, using it in a small room is not a good idea when you're in the room, unless you don't like your "friends."
Re:AOE? (Score:2)
n00b? Am I the only person for whom "AOE" means "Aces Over Europe"
Age of Umpires (Score:2)
Will it catch on? (Score:5, Insightful)
Some significant caveats mean that not everyone is so keen on the technology. For a start, it's a specification from Coraid, not an industry standard. Its networking abilities are limited. And its detractors include storage heavyweights such as Hewlett-Packard and Network Appliance.
So will this ever develop into a real standard or will it remain the sole domain of one company? I do not know if I want to invest time and money into it if the latter is true. From a comp sci point of view this is a great approach to networked storage. It uses what people already have to make storage reletively cheap. I am going to wait to see where this technology goes. Maybe it will blossom and become a serious contender.
Re:Will it catch on? (Score:4, Informative)
I don't know that this is true, because the LinuxJournal article directly contradicts it. (Unless I'm misreading it.) Here's what the LJ says:
ATA over Ethernet is a network protocol registered with the IEEE as Ethernet protocol 0x88a2.
So, it looks like the protocol has been officially registered and was granted approval by the IEEE--so that makes it an industry standard. It may not be adopted yet, but it's certainly not something like 802.11 pre-n or anything; there's an official and approved protocol.
Re:Will it catch on? (Score:5, Informative)
Anyone can register a protocol number with IEEE by paying a $1000 fee. It doesn't mean it's a protocol endorsed by IEEE in any shape, way or form.
Re:Will it catch on? (Score:2)
So then what qualifies as an "industry standard?" Is that just a euphemism for: "the big players have decided to implement this technology?"
Re:Will it catch on? (Score:2)
Re:Will it catch on? (Score:2)
The problem with ethernet is that it's hard to make go fast. We have 1G now but 10G is difficult because of all the processing involve
Re:Will it catch on? (Score:3, Informative)
The only way to really do it is to purchase a dedicated Block Controller (spare ethernet card) and a dedicated Block Data Cable (Cat 5) and hook it up to a dedicated Block Device Multiple
Re:Will it catch on? (Score:2)
I could see benefit in using this over iSCSI for 10G NIC's without TOE's but I wonder if there will be any of those. There real advantage of running anything over ethernet is to get the benefit of huge volumes, so I would suspect all 10G Nics wil
Re:Will it catch on? (Score:2)
Re:Will it catch on? (Score:2)
Re:Will it catch on? (Score:2)
Cheaper? (Score:4, Interesting)
Re:Cheaper? (Score:3, Informative)
The main disadvantage with AoE is that it's hideously sensitive to network latency, due to the limited payload size.
Re:Cheaper? (Score:2, Informative)
Re:Cheaper? (Score:2)
Correct, I built a Windows 2003 Cluster (just for testing, not a production system!) using a Linux iSCSI target on an IDE drive and the stock iSCSI initiators on the 2003 boxes. Performance wasn't great but it worked fine.
With Copper Gigabit Ethernet and Jumbo frames (standard Ethernet is 1500 bytes, but disk blocks are usually 4K so you uneed Jumbo frames to eliminate fragmentation), I'd think you would save a lot of money over Fib
Re:Cheaper? (Score:2)
Re:Cheaper? (Score:3, Informative)
2 P II 400MHz systems running FC4
One system had software raid 0 on 2 IDE drives.
The target has a spare 10GB IDE drive.
Added 2 10/100T cards with a crossover cable.
Did a quick dd if=/dev/zero count=some large number of=the raid mirror or iSCSI target.
The iSCSI target was 30% slower.
Way cool.
Re:Cheaper? (Score:3, Insightful)
More for business? (Score:2)
Not sure if I follow this. Harddrives are well under $1/GB. If you buy several 400 GB drives and just connect them in an old PC thats on the network, aren't you accomplishing the same thing? I have a terraserver at home and it cost http://religiousfreaks.com/ [religiousfreaks.com]
Re:More for business? (Score:2)
Re:More for business? (Score:2)
Re:More for business? (Score:3, Informative)
Re:More for business? (Score:2, Interesting)
iSCSI and AoE don't necessary directly benefit the small/home server market, but for the things that SANs are traditionally used for (data replication across geographically separated sites without any changes to the application software) there could end up being a big win in cost.
Re:More for business? (Score:3, Interesting)
Reliability (Score:2, Interesting)
Re:Reliability (Score:3, Insightful)
reliability of SCSI versus ATA is largely imagined and the rest is intentional. drive manufacturers want you to believe their enterprise drives are more reliable and right now those drives are largely SCSI.
Re:Reliability (Score:4, Informative)
This is not necessarily true. [storagereview.com] It all depends on how your network storage is being used. SCSI drives are built and firmware'd for the sole purpose of running a server, and they consistently beat any ATA drive (be it IDE or Serial) when it comes to server performance and reliability. ATA drives just aren't built to handle the sort of usage a server requires--note that this isn't a reflection of quality, but of purpose. But a file server (which is the only thing the SAN would be used for) requires much less robust firmware than a server housing MySQL, PHP, maybe a CRM suite, e-mail server, etc.--and so ATA drives shouldn't immediately be ruled as less reliable. The maturity of the technology plays a more important role than the interface.
Re:Reliability (Score:2, Informative)
Re:Reliability (Score:2)
Even the enterprise and datacenter are starting to use SATA for the vastly superior price per GB over high speed SCSI or FC drives in tiered storage systems. Store the bulk of your data on cheap SATA drives in a RAID5, then when you use it, move it to a 15k RP
Re:Reliability (Score:3, Informative)
No, they aren't. Just have an array running for a year or two and bring it down for maintenance, your chances of multiple drive failures are VERY good. Of course that happens even with SCSI drives, but it even more underscores the need for a premium part. Btw I just live through a scare this weekend. We lost one drive after powering up one of our main DB servers, then lost a second about 10 minutes later, luckily the 16 drive array was setup as RAID6 i
Re:Reliability (Score:2)
ftp://ftp.research.microsoft.com/pub/tr/TR-2004-10 7.pdf [microsoft.com]
Section 3 ("Operations Experience") starting on p 16 is interesting, along with Section 4 ("Conclusion") starting on p 19:
Re:Reliability (Score:2)
The answer to your question is that, assuming there are more ATA drives of assumed lower reliability, the ATA system will be less reliable. You, sir, total fail it.
Re:Reliability (Score:2)
PoE, AoE, ... , EoE! (Score:2, Funny)
Re:PoE, AoE, ... , EoE! (Score:2)
Pretty impressive... considering Ethernet has no knowledge nor concept of TCP/IP.
How does it lower costs? (Score:2)
Re:How does it lower costs? (Score:3, Informative)
Re:How does it lower costs? (Score:4, Informative)
Re:How does it lower costs? (Score:2)
Re:How does it lower costs? (Score:2)
TFA isn't responding, so maybe I'm missing something but how does this new protocol actually result in cheaper costs per GB?
The idea is that iSCSI uses TCP, which requires a lot of additional processing, which bogs down both the machine using the storage and the machine that contains the storage. The solution usually recommended is to buy expensive network cards that offload the TCP overhead from the main CPU. With AoE, you don't have the TCP overhead and therefore don't need the more expensive TCP-off
Re:How does it lower costs? (Score:2)
not at 10G they won't.
the question isn't whether iSCSI or AoE is better but rather why you would use either of them.
Will there be any 10G NIC's that don't offer offload engines? If not, what is the advantage architecturally of AoE?
What about direct DMA and zero-buffer?
Re:How does it lower costs? (Score:2)
the question isn't whether iSCSI or AoE is better but rather why you would use either of them.
I think the costs and benefits are pretty clear. I'd actually love to see some drives with AoE/iSCSI built into them for home use. Need more storage for your video collection? Just buy an AoE/iSCSI drive and plug it into your switch. Although it would be done differently, unlimited expandability is the main advantage for enterprise environments as well. I don't know how this notion compares with SAN solutio
Re:How does it lower costs? (Score:2)
None of this is being done for the home user, so if you see this from that perspective you aren't really understanding it.
iSCSI, and no
Re:How does it lower costs? (Score:2)
iSCSI, and now AoE, were done as competitors to FC and InfiniBand.
Ah, I see where you're coming from now. I agree that they aren't going to compete with FC or IB in terms of performance. I see them as being useful in environments where performance is less important than low cost and easy expansion.
Yes! (Score:4, Interesting)
I like the look of this technology. The great thing it has going for it is that most of the non-hard-disk infrastructure (switches and cabling) leverages the tremendous investment in ethernet. That is great.
The thing that needs work, in my view, is that the bit that links the disks and the rest isn't cheap enough. In fact what would be awesome here is if, say, Seagate provided disks with native ATAoE connectors built-in. They might have to buy Coraid for that to happen.
In case anyone thinks I'm out of my mind here, don't forget that disks can already be had with ATA interface, SCSI interface, FCAL interface, SATA, SAS - that's five and there are probably more. Yes they might be a bit more expensive, but if they come in under the combined price of "regular ATA disk" + Coraid ATAoE disk adapter then you'd come out ahead. Someone like Seagate would, I think, have the industry-wide clout and respect to succeed in making this an open standard. Something that will be a challenge for Coraid for a long time (I have nothing against them, btw, they are friendly and their mailing list didn't spam me when I signed up).
When I was on the OpenSolaris pilot project I tried to get people interested in using this with Solaris. I think it might be great for ZFS, for example. At that point the real storage wizards were more interested in iSCSI, but I respectfully disagree, OpenSolaris + ZFS + cheap storage = awesome file server. Emphasis on the cheap. As Sun people will admit, their previous attempts at RAID were more like RAVED (Redundant Array of Very Expensive Disk). Coraid does have a Solaris driver, so this is definitely feasible.
Re:Yes! (Score:2)
These days, an embedded Ethernet controller adds, say, $10 to the total cost of a device. And hard disks already have onboard intelligent controllers, so getting them to speak the ATAoE protocol shouldn't be much more than a
Re:Yes! (Score:2)
Re:Yes! (Score:2)
Your post is misleading. ZFS is only available on Solaris 10. The only driver available from Coraid for Solaris 10 is in beta and it does not support x86.
Sorry if you found it misleading, but I don't agree. I was talking to Solaris -developers- about this protocol. It was a forward-looking prospect. At the time ZFS was not even released, but I liked the sound of it for some future time, and I also like the sound of AoE so I figured the two might combine nicely. If I had the time I'd get the dev hardware,
Re:Yes! (Score:3, Funny)
It's the eyeliner. It doesn't look half as good in the morning.
Re:Yes! (Score:2)
I don't think that this is going to save any money. You can purchase devices from several people that get loaded up with ATA or SATA disks, and which present a SCSI
iSCSI killer? (Score:4, Interesting)
Works great and is a lot (>10x) faster than the about similarly priced NAS device that was used for the same task before.
Re:iSCSI killer? (Score:2)
sloth jr
Re:iSCSI killer? (Score:2)
It's called soap.
Jeez... didn't your parents teach you proper hygiene?
iSCSI can talk to ATA drives (Score:2, Insightful)
So, why would you need AoE? It's already cheap, and been for sale for some time.
Re:iSCSI can talk to ATA drives (Score:2)
what are the benefits of SCSI commands for storage? Oh yeah, command queuing. ATA has that.
Bootable? (Score:2, Interesting)
Re:Bootable? (Score:2)
Since most x86 BIOSes only support PXE as their network boot protocol, I doubt it will work out of the box. Something would have to provide block-level access to the HD in order for the OS to bootstrap, and PXE doesn't do that.
Coraid (or someone else) would have to make a bootable floppy, CD, or flash drive image that could add
Re:Bootable? (Score:2, Informative)
Re:Bootable? (Score:2, Insightful)
Re:Bootable? (Score:2)
Not an iSCSI killer, here are the reasons why not (Score:4, Insightful)
2) It is not a standard and is only really supported by one vendor. This may change in the future but it is significant right now. It is registered with the IEEE but that hardly makes it a peer-reviewed standard with input/improvements from many experts.
3) No boot from SAN. Until someone makes some sort of mini bootstrap system on a CD or a hardware card implementation of AoE that can be addressed as a block device admins will be unable to host the root filesystem and/or C: drive on an AoE SAN
4) No multipath (that I can see). Perhaps I misunderstand this, but it seems like there is no way to do multipath IO with this system. That is, all the drives are single-connected to a network. If that network switch goes down, all drives on that network are inaccessible.
So AoE looks like a neat technology for pushing drives out of the box and potentially sharing them among hosts, but there is no intelligence there. It is just dumb block addressable storage with no added availability or management, and therefore is far from being an iSCSI or FC killer.
Re:Not an iSCSI killer, here are the reasons why n (Score:4, Interesting)
AoE is a COOL thing exactly because it's a 'dumb' technology. You can buy a switch, a bunch of disk drives and AoE adapters, a small Linux PC - and your storage system is ready. There is a lot of existing RAID manipulation and monitoring tools for Linux, so RAID configuration is not a problem.
You also can boot from SAN, it's not a problem. Just add required modules and configs to initrd and place it on a USB drive.
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
I am looking for an affordable storage box for my home network, but for this kind of money I expect SMB/NFS functionality, not a dumb ATA interface over ethernet.
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
It may be cool, but it is WAY too expensive. 4000 dollars for a 15-disk box without disks, come on!
Have you prices rack-mountable boxes with space, airflow and power for that many drives? They cost clost to that much even without the AoE adapters.
I am looking for an affordable storage box for my home network, but for this kind of money I expect SMB/NFS functionality, not a dumb ATA interface over ethernet.
Coraid's stuff is obviously not for home use. For home use, use an old PC filled with disks.
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
However, all solutions I have looked at (the Coraid included) have this useless (for me) feature.
Currently I am looking at a 3E high 19" cabinet I have, to construct some disk mounting hardware (horizontal rails across top and bottom) and put a small board (ITX) in it. The thing can then run as a (Linux) server and export the disks as SMB or NFS instead of AoE, so they are directly accessible to my satel
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
Plain PC with Linux doesn't suit me because there are only 3 or 4 ATA controllers on a typical motherboard. Additional RAID controllers help but not much.
AoE solution allows to install literally dozens of cheap disks in a cheap gigabit switch.
Price on AoE should go down - electronics in AoE controller should cost no more than $20-$30.
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
1) The "server", or drive array, handles the RAID, and all space carving (LVM, EVMS). AoE tools then export block devices.
2) Yup, no argument there.
3) VMs can boot from AoE, unless you use RedHat in which case it's not stable.
4) Multipath ethernet (or bonding) can be done trivially at the kernel level on all connected devices. Both to double the throughput, or just increase th
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
SAN's management capability is also it's downfall. Expensive, complicated and vendor-specific.
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
The holy grail of SAN's is unified SAN management and the number one complaint of SAN's is that management is too complicated and causes vendor lockin. No doubt that a centralized place for storage management is frequently desirable. If it weren't SANs would never exist in the first place.
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
Thanks.
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
Re:Not an iSCSI killer, here are the reasons why n (Score:2)
Not so much cheaper (Score:2, Insightful)
question (Score:2)
Maybe I dont get it... (Score:2)
I dont see what the point is other than the fact that they are offering yet another transport protocol. Given that one can install iSCSI target software on linux/solaris/windows... whats the point? Anybody who read the article
Re:Maybe I dont get it... (Score:2)
ATAoE is a crock, it's no better than iSCSI (Score:4, Informative)
They'll give excuses about the cost of iSCSI hardware offload.. but you don't need that. ATAoE is all software anyway it's just a protocol over ethernet, rather than layered on top of TCP/IP.
What is wrong with using TCP/IP - which is already standard and reliable? Nothing. We know TCP/IP provides certain things for us.. resilience (through retransmits), and routing, are a good couple, and what about QoS?
ATAoE needs to be all the same network, close together, they're reimplemented the resilience, you can't use inbuilt common TCP checksum, segmentation and other offloads in major ethernet chipsets because they're a layer too low for it.
No point in it. Just trying to gain a niche. They could have implemented products around iSCSI, gotten the same performance with the same features, for the same price. Bunkum!
Re:ATAoE is a crock, it's no better than iSCSI (Score:2)
Trouble is that I'd assume all 10GigE NIC's will come with offload engines anyway so there's no savings.
There is no functional problem with making the product non-routable. Servers need physical security and physical proximity. What you seem to think is a liability is not one.
Re:ATAoE is a crock, it's no better than iSCSI (Score:2)
Do you actually have an ATA RAID array that can perform 10 Gigabits/s full-duplex? I would love to see that, I really don't think those disks really exist though (maybe a couple or 10 10Krpm WD ones..
Right, so in the article this one guy says that "using the second network port and a dedicated switch adds more security". So despite being non-routable he gave it a dedicated network anyway. There's also a guy in the article talking about that he "believes" that iSCSI would have been harder to configure. I
Re:ATAoE is a crock, it's no better than iSCSI (Score:2)
Bare boards? (Score:2)
I can't tell if this is clever or stupid... (Score:3, Interesting)
ATA is a crappy protocol, even when local. It's only good for squeezing that last $0.03 out of the controller cost. Once you are using ethernet cables ($1) and links and PHYs on each end ($4 each), it makes a lot more sense to put some brains back in. Use SCSI. Heck, even ATAPI optical drives (the optical drive in your computer) uses ATAPI, which is SCSI in packetized ATA transfers.
Also, I'm a bit nervous about the packet CRC validation being done in the ethernet controller/layer itself. The problem is that if an ethernet switch between you and the storage device stores packs and forwards them (as all smart switches do), it may also chose to regenerate the CRC on the way. If it corrupts the packet internally and generates a new, valid CRC for the new, corrupt packet, you have undetected corruption. I'd be a bit nervous about that for my hard drive.
I do think using GigE is a smart way to attach hard drives to servers. I look at the back of an Apple XServe and see two GigE ports and a fibre channel card. Why can't one GigE port be used to attach to the network and one to the XServe RAID? Why do I need to get a multi hundred dollar card to attach to the XServe RAID when that GigE port is fast enough? It'd sure save a lot of cost, and hopefully reduce the price ot the end user.
Anyway. I'm pro GigE attachment, not sure I'm for this AoE.
Re:I can't tell if this is clever or stupid... (Score:2)
I'm pretty confident that you can prevent unintended data corruption. TCP/IP manages it so there's your proof of concept
GigE is not a good choice for disk attachment since it is easily outrun by a small number of disks. 10GigE is where it
Not Routable? (Score:2)
If I'm reading the Wikipedia AoE article [wikipedia.org] right... AoE is a L2 protocol that can not cross routers. That would immediately rule out the office I work in, in which floors and the data centre are on separate TCP/IP subnets. Small offices only, then?
But, as noted above, if they are claiming that they avoid the cost of ToE NICs for iSCSI, that's a spurious claim, since they are an optional performance enhancer, not a requirement for iSCSI. I've seen surprisingly decent performance without them, with the HP EV
What about vblade? (Score:2)
Does anyone here have experienc
Ultimate Proof (Score:2, Offtopic)
Re:(-1, Get Off My Lawn) (Score:2)
iSCSI needs killing? (Score:2)
I just deployed an AoE SAN (Score:5, Informative)
So far I am very pleased. Just make sure you get hardware that can do jumbo frames as this will increase your performance by 50%.
NBD and Raid1 (Score:2)
put it back in the oven (Score:2, Insightful)
Also, consider management of one of these AoE boxes. What sort of tools are out there to simplify provisioning, deployment, snapshots and backup, etc. In order for this to go an
AoE works, and it is cheaper (Score:2, Informative)
the only thing that bothers me about AoE is there is only a single vendor supporting it at the moment. other than that, it is great stuff. while it is not routable in the sense ip is routable, you can do creative things with ethernet switch
what about the low-hanging fruit? (Score:2)
Right now the cost of entry discourages experimentation. Having to buy a $3,000+ chassis plus all the drives is going to require funding that I have to fight for. If I can implement a proof of concept for under $500, I don't even need my manager to sign off on the expense. I can just d
Re:Another "Killer" (Score:5, Informative)
In the case of AoE, a single remote block device can be shared between multiple systems. Each client could issue it's own write/reads. in combination with a distributed file system, each node could mount the same FS.
It's the same as NBD, iSCSI, Shared SCSI, and Fiber Channel.
Re:Another "Killer" (Score:2, Insightful)