|
Vanilla posted:Anyone had a good look at Pure yet? What do you want to do with it? It's pretty feature rich compared to other AFAs, but their architecture lends itself better to some things than others. They can have issues with write latencies in high throughput scenarios due to NVRAM (really just SSD) limitations and their inline/post-process dedupe, compression and garbage collection. It's also active/passive, which seems to be a point of confusion for some. There's nothing wrong with that, of course, but given that it's an AFA you're going to be CPU bound long before you're disk bound so it's worth knowing that you've only got one controller to work with.
|
#
?
Jan 31, 2014 06:47
|
|
|
|
| # ? May 14, 2024 11:26 |
|
|
NippleFloss posted:What do you want to do with it? It's pretty feature rich compared to other AFAs, but their architecture lends itself better to some things than others. They can have issues with write latencies in high throughput scenarios due to NVRAM (really just SSD) limitations and their inline/post-process dedupe, compression and garbage collection. It's also active/passive, which seems to be a point of confusion for some. There's nothing wrong with that, of course, but given that it's an AFA you're going to be CPU bound long before you're disk bound so it's worth knowing that you've only got one controller to work with. Thanks for the info, i'm not looking at them but just gauging how people are finding them.
|
|
#
?
Jan 31, 2014 11:06
|
|
|
Can we steer this train back to backups? Tapes! They still exist. They still suck. They are still the best at solving their target solution, namely, super cheap, long term, offline, remote storage. I have a challenge which my usual goto partners seem to have a problem with. (I don't know if they are just trying to upsell or what as I don't know jack squat about tape) UseCase: 120TB in an internet connected environemnt, clients want exports of their datasets (25-30TB/client) to put in their fire safes on a regular basis. Let's call it quarterly. 40TB in an isolated, no internet environment, other side of the world, clients want the same. All this means tape is in my future. Currently we use d2d replication to handle the backups for the internet based data. We currently also do a d2d for that in the offline environment on a local basis (separate server) but the size and network architecture however has made that ridiculously unfeasible. The trick is that the bigger environment is iSCSI. So, what do I do? It seems that the tape libraries are all FC/SAS. Is this as simple as setting a backup server to be the driver of the tape unit and connecting it via FC/SAS and then allowing the server to bridge back to the network for backups? Do I need an iSCSI:FC bridge? Given our hardware partnerships and account setups I really like the spec sheet of the Dell PowerVault ML6010 (also it would allow an add on in the future as my larger environment scales) Also, tell me about software.  Simpana 
|
|
#
?
Jan 31, 2014 14:07
|
|
|
Dell and Spectra Logic sell iscsi tape libraries. I can't vouch for the quality of either of them, but I researched it last year before ultimately ditching tape entirely.
|
|
#
?
Jan 31, 2014 17:01
|
|
|
Speaking of backup storage, looks like facebook wants to jumpstart using blu-rays for long term cold storage rather than tape or slow disks. http://arstechnica.com/information-technology/2014/01/why-facebook-thinks-blu-ray-discs-are-perfect-for-the-data-center/
|
|
#
?
Jan 31, 2014 19:33
|
|
|
bull3964 posted:Speaking of backup storage, looks like facebook wants to jumpstart using blu-rays for long term cold storage rather than tape or slow disks. They say you can get discs "certified for 1000 years". Most of the CD's I burned 10 years ago when people still burned CD's don't work for poo poo today. Even some commercial ones are unreadable. Presumably these enterprise grade Blu-Rays would be higher quality than the CD-R's you buy in 50-packs for $5 or whatever, but still, that would make me nervous.
|
|
#
?
Jan 31, 2014 19:46
|
|
|
Other than the cost of the drives being cheaper than tape, isn't Blu-ray more expensive in every way?
|
|
#
?
Jan 31, 2014 19:51
|
|
|
Caged posted:Other than the cost of the drives being cheaper than tape, isn't Blu-ray more expensive in every way? The guy from Facebook addresses that in the article. He feels that if a bunch of large enterprises start ordering hundreds of thousands of Blu-Rays, the economies of scale would reduce the per-disc cost to basically nothing.
|
|
#
?
Jan 31, 2014 19:56
|
|
|
Docjowles posted:The guy from Facebook addresses that in the article. He feels that if a bunch of large enterprises start ordering hundreds of thousands of Blu-Rays, the economies of scale would reduce the per-disc cost to basically nothing. Yeah, the cost is high right now because the volume is really low. BD-R production never reached what DVD-R or CD-R did because everyone just bought a flash drive for portable storage and everyone had large enough hard drives that they didn't need to offload files to disk. The big drivers for this are power and the fact that the moving parts are confined to a single reader rather than the things storing the data. As far as shelf life, there's no reason why a quality manufactured disc couldn't have a high shelf life in a controlled environment, most of the crap that's in use for home is just that, crap. BD-R, in general, is supposed to be better than CDR or DVDR right off the bat anyways. That, combined with some sort of cross disc error correction should be good to ensure integrity of the data.
|
|
#
?
Jan 31, 2014 20:06
|
|
|
I'm just cynical these days, all I see is media manufacturers slapping the work "Enterprise" on some BD-R's and selling them for 15 times the normal price of a BD-R because they're "Enterprise"
|
|
#
?
Jan 31, 2014 20:08
|
|
|
Mr Shiny Pants posted:We have two datacentres that are close by and we run fiber to them. The Metrocluster gives us the ability to have a stretched VMware cluster on top. The idea is to have it physically separated but logically one cluster. Below is a great resource if you haven't seen it: TR-3548 http://www.netapp.com/us/system/pdf-reader.aspx?pdfuri=tcm:10-59919-16&m=tr-3548.pdf
|
|
#
?
Jan 31, 2014 20:14
|
|
|
Docjowles posted:The guy from Facebook addresses that in the article. He feels that if a bunch of large enterprises start ordering hundreds of thousands of Blu-Rays, the economies of scale would reduce the per-disc cost to basically nothing. That's a hell of a gamble to take though.
|
|
#
?
Jan 31, 2014 20:20
|
|
|
Well, that's the beauty of some of the stuff Facebook is doing. They are assuming the risks and hopefully it paves the way for innovation. A big chunk that's driving this is power. You really don't want to be spinning disks up and down or storing them powered off as it affects their lifespan. However, keeping them spun up and ready all that time is a huge power draw. So, there really is a need here for SOME sort of near zero power cold storage with a high reliability and long shelf life. It makes sense to start with off the shelf tech first and refine it.
|
|
#
?
Jan 31, 2014 20:41
|
|
|
Presumably another reason for them to do this is that the robotics for a jukebox holding 100,000 Blu-Ray discs would be a lot cheaper than a comparable tape library.
|
|
#
?
Jan 31, 2014 22:11
|
|
|
KennyG posted:Backup stuff You don't need an iSCSI library to back up iSCSI attached storage. The library is attached to the media servers through SCSI/SAS/FC/Infiniband/whatever. You can direct attach if you'd really like, no switch required. Backups run from client to the media server over the network, with the media server handling communication with the tape library. Whether you need one more more media servers and tape libraries will be determined by your backup requirements, but you don't need a full FC infrastructure or an iSCSI library to meet your requirements, just a master server, a media server (can be the same server in smaller deployments), a library that can connect to the media server, and backup software to manage all of the pieces.
|
|
#
?
Jan 31, 2014 22:31
|
|
|
I assume he was thinking of something like NDMP over iSCSI. Sounds ghastly.
|
|
#
?
Jan 31, 2014 22:45
|
|
|
Docjowles posted:They say you can get discs "certified for 1000 years". Most of the CD's I burned 10 years ago when people still burned CD's don't work for poo poo today. Even some commercial ones are unreadable. Presumably these enterprise grade Blu-Rays would be higher quality than the CD-R's you buy in 50-packs for $5 or whatever, but still, that would make me nervous.
|
|
#
?
Feb 1, 2014 00:25
|
|
|
OldPueblo posted:Below is a great resource if you haven't seen it: Thanks, I was just wondering if it works as advertised. I've seen a lot of solutions over the years that over promise and under deliver.  Especially if it makes regular administration harder, or some other gotchas that they won't tell you about until you start using it. Mr Shiny Pants fucked around with this message at 10:15 on Feb 1, 2014 |
|
#
?
Feb 1, 2014 09:46
|
|
|
KennyG posted:Can we steer this train back to backups? Well we do about 40TB a week to take (2 copies of 20TB of data) using Simpana. Great software but gently caress me it's expensive and don't even get me started on the corporate side. Basically you setup your storage policy with the concept of "Copies" which can be "Primary" (you say "Backup Client X" and this is where the data goes to) then you have "Auxiliary" copies which are additional copies of all, or of a subset of the data (might be only full backups, might be only backups of Client Z). So in our case our primary backup goes to a disk library, with auxiliary copies going to a SAS connected tape library. They do global dedupe and their replication is dedupe aware so it only replicates changed blocks. The nice thing with Simpana is that it doesn't give a poo poo who you use for the hardware (tape drives need to be compatible of course), so you just go buy a bunch of Dell or HP and BYO rather than needing to pay a markup for their appliances - though like I said the software isn't cheap.
|
|
#
?
Feb 1, 2014 12:38
|
|
|
Mr Shiny Pants posted:We are looking at a NetApp Metrocluster for our VMWare cluster and will be using commvault for backups. Take it you're quite a big shop? Only ask as we're look at Metro and aint cheap with NetApp - HP do it with StoreVirtual which costs peanuts but is iSCSI only and way behind the 3PAR and NetApp in terms of features and integration with 3rd party stuff. Veeam is probably better if all you're doing is backing up VMs, the moment you want to start involving tape or physicals, well Commvault is kind of the Rolls Royce there, with a price tag to match.
|
|
#
?
Feb 1, 2014 12:42
|
|
|
parid posted:Anyone have recommendations for backup storage target systems? Commvault's software dedupe and compression tech continues its march to mediocrity. I'm getting real tired of them moving the goal posts for dedupe database's system requirements (it's now: just put it on FusionIO). Their storage efficiency has been poor. Including compression were seeing worse than 4:1, 420TB stored in 116TB of disk. Throughput has also been abysmal. If you add in the FusionIO cards, Commvault's very high support costs (we have capacity base licensing), and the cost of FAS2240's that we currently use, this environment has become very expensive and performs poorly in just about every measure. If you're on capacity licensing, Commvault license off front-end not back AFAIK so you'll be paying the same for Commvault regardless of the back-end won't you? What I'm getting at there, is that presumably any kind of inline dedupe backup target is going to be an order of magnitude more than throwing in additional shelves full of "dumb" bulk disk and letting Commvault do the dedupe?
|
|
#
?
Feb 1, 2014 12:57
|
|
|
Mr Shiny Pants posted:Thanks, I was just wondering if it works as advertised. I've seen a lot of solutions over the years that over promise and under deliver. We have essentially the same environmental you are looking at. Living with it is only slightly different than any other 7mode NetApp. SyncMirror (aggregate mirroring, which is what makes it a metro cluster) is solid, easy to work with, and functions as advertised. Since installed 4 years ago, our fabric metrocluster has never had a service outage (even for maintenance). In that time, we have done controller upgrades, a complete back end fabric upgrade, major ontap upgrade (from 7 to 8), and but numerous bugs and the like. There are only two major downsides. The first is the price. No hidden costs but you are buying twice the disk and paying for the fabric. The second is whatever they are doing with clustered ontap. NetApp has announced end of life on 7 mode. They stopped adding new features some time ago. All the effort is being put into cdot. There is no timeline for cdot support for metroclusters. parid fucked around with this message at 17:53 on Feb 1, 2014 |
|
#
?
Feb 1, 2014 17:45
|
|
|
Bitch Stewie posted:If you're on capacity licensing, Commvault license off front-end not back AFAIK so you'll be paying the same for Commvault regardless of the back-end won't you? There are different levels of capacity based licensing. We would have "Standard" licenses if we didn't do commvault dedupe but since we do, we have "Enterprise". If I remember correctly it was in the range of twice as expensive. Don't forget to add in the cost of all the flash cards for the DDBs. There's also a significant difference in the ability of the dedupe engines to compress. If commvault only gets us 4:1 and one of the storage appliances gets 8:1, we only need half as much disk.
|
|
#
?
Feb 1, 2014 17:52
|
|
|
parid posted:The second is whatever they are doing with clustered ontap. NetApp has announced end of life on 7 mode. They stopped adding new features some time ago. All the effort is being put into cdot. There is no timeline for cdot support for metroclusters. Request an NDA to get more exact information, but there is definitely a timeline for MetroCluster on CDOT and it's not TOO far off.
|
|
#
?
Feb 1, 2014 19:27
|
|
|
NippleFloss posted:Request an NDA to get more exact information, but there is definitely a timeline for MetroCluster on CDOT and it's not TOO far off. It still leaves potential new customers in a hard spot. They have to buy a new storage system who's OS has already stopped development. Its replacement's timeline is so far out its NDA and the only migration path currently out is a complete forklift... NetApp is still great to work with but this is a hard position they have put their (metrocluster) customers in.
|
|
#
?
Feb 1, 2014 19:56
|
|
|
parid posted:It still leaves potential new customers in a hard spot. They have to buy a new storage system who's OS has already stopped development. Its replacement's timeline is so far out its NDA and the only migration path currently out is a complete forklift... Agreed, I didn't mean to imply that it was a solution. We really shouldn't even be selling 7-mode anymore, given that it's a dead end and we don't have a (good) in place upgrade path. I was just letting you know that it is on the roadmap and you can expect to see it before too long. Being NDA doesn't mean much as we don't publicly announce ONTAP releases until basically the day they drop.
|
|
#
?
Feb 1, 2014 20:50
|
|
|
We are not a big shop compared to American standards I guess, we are buying a whole new infrastructure that is going to last us at least 4 - 5 years. Can you explain the CDOT compared to 7 mode some more? I don't want us to choose a solution and needing to do a forklift upgrade, needing to buy new hardware later on, or having a dead-end solution. We also looked at 3Par and they are also pretty nice, especially the licensing. Need replication? You buy it for the array and if you want to do sync or async it is totally up to you. Much better than the IBM per TB licensing.
|
|
#
?
Feb 1, 2014 21:49
|
|
|
I checked Google Analytics on my blog for the first time in a few years; my post on recovering a deleted LUN on an IBM DS storage array has been receiving at least 100 hits a month for the past 3 years. Who are these people?
|
|
#
?
Feb 2, 2014 01:18
|
|
|
Misogynist posted:I checked Google Analytics on my blog for the first time in a few years; my post on recovering a deleted LUN on an IBM DS storage array has been receiving at least 100 hits a month for the past 3 years. Who are these people? Very sad people.
|
|
#
?
Feb 2, 2014 02:37
|
|
|
Link to said blog? If it's in your profile it doesn't seem to show in the Awful app. nm found it, google is hard ok Docjowles fucked around with this message at 23:07 on Feb 3, 2014 |
|
#
?
Feb 2, 2014 02:57
|
|
|
Mr Shiny Pants posted:We are not a big shop compared to American standards I guess, we are buying a whole new infrastructure that is going to last us at least 4 - 5 years. They are completely separate OS's but there's no denying that CDOT is a direct descendant of 7mode. Its more of an evolution with some large changes. CDOT adds another layer of abstraction between the storage and there presentation of that storage. It essentially compartmentalises the NFS/cifs/iSCSI/fc servers into their own instance. They then also allow you to run multiple of these instances (called vservers). It let's you do things like delegate roles, setup test instances, join multiple ad domains, ext. They also added the ability to join multiple controller pairs to a larger cluster. Any presentation node can make any storage in the cluster available. Adding this layer of abstraction and flexibility means you can do all sorts of neat virtualization tricks. For example you can move a live volume between disk sets (aggregates) on completely separate controller pairs live. Think VMware vmotion for netapp volumes. CDOT also adds all the modern features SMB3, pNFS, ect. They have a great new command line interface. There's hope for a smoother upgrade paths in the future but right now its total forklift. Do you have any downtime at all? Christmas/Thanksgiving or the like? If so you can probably work out some kind of transition with your sales team. They have the ability to loan "swing gear" out to help with these kinds of transitions. We did that with our first CDOT system. It was more complicated than a normal upgrade and we had a couple hours of downtime during the cutover. We got there in the end and the impact on our customers wasn't serious. Previously mentioned NDAs might be able to help you understand what's coming in the future. I personally don't make purchasing decisions on the promises of any vendor. The situation may or may not get better but you should make sure that the current constraints are something you can live with. You aren't going to want to be on 7mode in 2-3 years. This is a problem you would have to address into the lifespan of the system. My environment is about 50/50 7mode and CDOT. Other than our fabric metrocluster I'm making plans to get everything over to CDOT in the next 1.5 years. The future is murky for our metrocluster. We don't have needs pressing us to upgrade.... yet. My hope is that NetApp has an answer for us before they do.
|
|
#
?
Feb 2, 2014 17:47
|
|
|
parid posted:Awesome stuff. Thanks man, that is exactly the information I am looking for. So if I understand correctly, Metro Cluster is a 7 Mode feature but 7 Mode is not actively developed anymore. Cdot is the future and has all the SMB3 and Pnfs goodness. They can't tell when the MetroCluster featureset will be added to Cdot. drat, we really like the Metro Cluster because it is an awesome fit for our situation. We like the idea of one logical system divided over two physical locations, what can Cdot do right now? And is it comparable?
|
|
#
?
Feb 2, 2014 20:00
|
|
|
Mr Shiny Pants posted:Thanks man, that is exactly the information I am looking for. So if I understand correctly, Metro Cluster is a 7 Mode feature but 7 Mode is not actively developed anymore. Cdot is the future and has all the SMB3 and Pnfs goodness. They can't tell when the MetroCluster featureset will be added to Cdot. Each cdot cluster can't span sites. Two sites, two clusters. That was the very first question I asked when I got my first cdot pitch. How physically close do the nodes in a cdot cluster have to be? Unfortunetly right now, they have to be in the same data center. In cdot, you still have the traditional controller pairs. You just now have the ability to link them. This is done over a pair of dedicated 10gig Ethernet connections to a pair of Cisco switches. The links to this switch have to be the short rage sx modules. I asked about the longer range stuff. Apparently the latencies involved in the longer distance fiver modules are an issue. I bet if you plugged it all in, it work work. Its not supported though. I suspect this is what they are planning to replace metroclusters with but that's just a guess. I'd bring your concern to your sales team to discuss. They might have ways of mitigating the problem for you that might still make this a viable solution for you. You might just have to be creative with a solution.
|
|
#
?
Feb 2, 2014 22:17
|
|
|
If metrocluster is the solution that fits your needs, I wouldn't hesitate on it specifically just because of the 7-mode/cDot transition. I know of huge corporations that rely on metrocluster solutions that are just refreshing theirs to newer 7-mode platforms right now. It's perfect for them and they're moving forward knowing the future roadmap and knowing that the future is cDot. That's anecdotal of course and it may not serve you best in your future, but as said above you can get information on the metrocluster roadmap by contacting your sales team. Find out what your options are then apply it to your personal timeline. I'm not trying to talk you into it, just trying to put it into perspective. It's not orphaned or in limbo really, it's just whether or not the transition fits your timeline.
|
|
#
?
Feb 3, 2014 03:30
|
|
|
OldPueblo posted:If metrocluster is the solution that fits your needs, I wouldn't hesitate on it specifically just because of the 7-mode/cDot transition. I know of huge corporations that rely on metrocluster solutions that are just refreshing theirs to newer 7-mode platforms right now. It's perfect for them and they're moving forward knowing the future roadmap and knowing that the future is cDot. That's anecdotal of course and it may not serve you best in your future, but as said above you can get information on the metrocluster roadmap by contacting your sales team. Find out what your options are then apply it to your personal timeline. I'm not trying to talk you into it, just trying to put it into perspective. It's not orphaned or in limbo really, it's just whether or not the transition fits your timeline. True, it fits perfectly and we'll probably go with such a setup and a smaller FAS in our DR site for backups. One other thing, does NetApp sell lemons? I mean models we should avoid because they are underpowered and the like? Thanks guys, much appreciated.
|
|
#
?
Feb 3, 2014 07:57
|
|
|
Mr Shiny Pants posted:True, it fits perfectly and we'll probably go with such a setup and a smaller FAS in our DR site for backups. Underpowered is relative to your needs, but the entire model lineup has been refreshed to account for the increased memory requirements in more recent ONTAP versions, and there are no single core systems left. The model lineup is wide enough that there's something to fit just about every workload, so it's really a question of making sure it's sized properly. As far as 7-mode goes, it's a dead end as far as new features go, but it will still be supported for a long time to come and will continue to receive bug fixes and patches for security findings. So if you're happy enough with the feature set as it stands now then 7-mode will be fine for you for a while. In addition to non-disruptive operations (volume moves between aggregates, indirect data access, aggregate relocation) there are some new features that are CDOT only like infinite volumes (volumes striped across multiple aggregates using a single namespace) and QOS that will never make it to 7-mode. In the future you can expect to see the QOS feature expanded to provide auto-tuning and possibly even online data migration between different aggregates to ensure that QOS targets are met. Likewise infinite volumes will continue to see development to make them usable for a larger number of workloads. They may even become the default volume style at some point down the road. But a lot of that stuff is a ways off and 7-mode already has a ton of features, so it's not like you're going to be stuck using a bargain basement array. If you like what 7-mode with metrocluster provides then go for it. By the time you're ready to refresh it Clustered ONTAP will have metrocluster support and a lot of those first generation features will be fully fleshed out so you will be able to see their full benefit. Or you'll go to an AFA or something completely different because the storage market is changing a LOT right now and in 5 years things could look completely different.
|
|
#
?
Feb 3, 2014 20:38
|
|
|
Misogynist posted:I checked Google Analytics on my blog for the first time in a few years; my post on recovering a deleted LUN on an IBM DS storage array has been receiving at least 100 hits a month for the past 3 years. Who are these people? Semi-comedic answer: IBM Support reps because your blog post is more useful than their internal documentation.
|
|
#
?
Feb 3, 2014 21:24
|
|
|
skipdogg posted:Semi-comedic answer: IBM Support reps because your blog post is more useful than their internal documentation.
|
|
#
?
Feb 3, 2014 23:04
|
|
|
KennyG posted:Can we steer this train back to backups? Dell has some amazingly cheap dedupe appliances the DR4000 / DR4100 but I should warn you they're not very pleasant to use. I had a lot of issues with replication, cleanup, storage space displayed and used. We're using it as basically a CIFS dump, not NDMP because no one bought the dedupe option for BackupExec2012. (Which is itself a huge piece of crap. Baby's first backup for sure. If you've got more than the smallest of small business environments, it'll make you miserable. I wouldn't use it with more than 10 servers.) I think the Dell software is maturing though. I suspect Dell is going to jump into backups in a huge way now that they own Quest and Quest owned NetVault, vRanger, and LiteSpeed. Litespeed for SQL + vRanger for all VMs + NetVault for any physical boxes left + a cheap dedupe appliance like the DR4000 / 4100 is a decent combo. That is, assuming the integration works well and they continue rock bottom pricing. If not, go buy the NetBackup appliances from Symantec and call it a day. El_Matarife fucked around with this message at 20:08 on Feb 4, 2014 |
|
#
?
Feb 4, 2014 20:05
|
|
|
|
| # ? May 14, 2024 11:26 |
|
|
parid posted:I had a positive experience with DataDomain in the past (2+ years ago). I got decent throughput but excellent compression ratios (>10:1). I hear that EMC is messing with their backup products and the future is mirky for the DataDomain product line. They are trying to integrate all these disparate products they purchased and drive people into their complete data protection stack. Considering were a NetApp\Commvault shop right now that would lead to many complications for us. Disclaimer - EMC'er here. Data Domain is here to stay. Also the entirety of the mid-range and upper-mid-range systems were just refreshed. The DD2500 and DD4200 are in the same capacity range as you're current Commvault environment. If you're hearing about product integration it could be one of a couple of things. There is a relatively new software stack/suite (Data Protection Suite) which provides access to a number of software products in one bundle. That said there is no requirement to purchase this suite, all the products are still available as standalone. Secondly Avamar integration with Data Domain has continued to develop since the last time you used Data Domain.
|
|
#
?
Feb 8, 2014 17:03
|
|