ZFS

You are currently browsing articles tagged ZFS.

This Pretty Much Answers That Question

Thursday, March 12, 2009 in Networking, UNIX by slowe | 8 comments

A couple of days ago I posed this question: is Sun preparing to take on Cisco? The question generated some interesting responses in the comments to the article.

Reader Bill had this to say:

How on earth would Cisco respond if Sun started introducing products with better performance, at a fraction of the price, built on high volume open source adoption?

As I responded, that’s the real $64,000 question, isn’t it? That’s the premise upon which this entire thing is built—that by using commodity hardware and open source components, Sun can produce high-quality, high-performing network equipment that they can sell for far less than Cisco.

Reader Ed, on the other hand, questioned the validity of this kind of move:

I would think that partnering with a Juniper or Foundry-type company and OEMing equipment from those companies would be a more prudent move than venturing on their own to create new network devices.

Normally, I would agree with Ed if we were talking about a company that was merely interested in entering a market in order to become a more complete supplier to their customers. That’s not Sun’s purpose. Sun’s purpose is, I think, to fundamentally change the nature of the networking hardware market. How successful they’ll be…well, that’s another question.

My original article also prompted a response elsewhere on the Internet. Christofer Hoff thought my use of the work “distracted” in describing Cisco and Project “California” wasn’t appropriate, and in one sense he’s correct—”California” is absolutely a natural evolution of Cisco’s products and technologies and it does make sense for them. As I pointed out to Hoff, though, being successful with this new solution (I can’t call it a server!) will take focus, and while Cisco is focused on “California” Sun has their opportunity.

And it looks like they are definitely going to take that opportunity:

As I’ve said before, general purpose microprocessors and operating systems are now fast enough to eliminate the need for special purpose devices. That means you can build a router out of a server – notice you cannot build a server out of a router, try as hard as you like. The same applies to storage devices.
 
To demonstrate this point, we now build our entire line of storage systems from general purpose server parts, including Solaris and ZFS, our open source file system. This allows us to innovate in software, where others have to build custom silicon or add cost. We are planning a similar line of networking platforms, based around the silicon and software you can already find in our portfolio.

The emphasis on that last sentence is mine, just to emphasize the clarity of where Sun is headed. Clearly, it is their intention to leverage OpenSolaris, Crossbow, ZFS, Solaris Zones, etc., to compete directly against Cisco. And Cisco appears to be their primary target, judging from this sentence:

That means you can build a router out of a server – notice you cannot build a server out of a router, try as hard as you like.

To me, that looks like a direct jab at “California”.

So, I guess the question of whether Sun is going to take on Cisco is settled. Hoff, get your popcorn!

Tags: , , , ,

Storage Short Take #4

Tuesday, December 2, 2008 in Storage by slowe | 2 comments

Last week I provided a list of virtualization-related items that had made their way into my Inbox in some form or another; today I’ll share storage-related items with you in Storage Short Take #4! This post will also be cross-published to the Storage Monkeys Blogs.

  • Stephen Foskett has a nice round-up of some of the storage-related changes available to users in VMWare ESX 3.5 Update 3. Of particular note to many users is the VMDK Recovery Tool. Oh, and be sure to have a look at Stephen’s list of top 10 innovative enterprise storage hardware products. He invited me to participate in creating the list, but I just didn’t feel like I would have been able to contribute anything genuinely useful. Storage is an area I enjoy, but I don’t think I’ve risen to the ranks of “storage guru” just yet.
  • And in the area of top 10 storage lists, Marc Farley shares his list of top 10 network storage innovations as well. I’ll have to be honest—I recognize more of these products than I did ones on Stephen’s list.
  • Robin Harris of StorageMojo provides some great insight into the details behind EMC’s Atmos cloud storage product. I won’t even begin to try to summarize some of that information here as it’s way past my level, but it’s fascinating reading. What’s also interesting to me is that EMC chose to require users to use an API to really interact with the Atmos (more detailed reasons why provided here by Chad Sakac), while child company VMware is seeking to prevent users from having to modify their applications to take advantage of “the cloud.” I don’t necessarily see a conflict between these two approaches as they are seeking to address two different issues. Actually, I see similarities between EMC’s Atmos approach and Microsoft’s Azure approach, both which require retooling applications to take advantage of the new technology.
  • Speaking of Chad, here’s a recent post on how to add storage to the Celerra Virtual Appliance.
  • Andy Leonard took up a concern about NetApp deduplication and volume size limits a while back. The basic gist of the concern is that in its current incarnation, NetApp deduplication limits the size of the volume that can be deduplicated. If the size of the volume ever exceeds that limit, it can’t be deduplicated—even if the volume is subsequently resized back within the limit. With that in mind, users must actively track deduplication space savings so that, in the event they need to undo the deduplication, they don’t inadvertently lose the ability to deduplicate because they exceeded the size limit. Although Larry Freeman aka “Dr Dedupe” responded in the comments to Andy’s post, I don’t think that he actually addressed the problem Andy was trying to state. Although the logical data size can grow to 16TB within a deduplicated volume, you’ll still need to watch deduplication space savings if you think you might need to undo the deduplication for whatever reason. Otherwise, you could exceed the volume size limitations and lose the ability to deduplicate that volume.
  • And while we are on the subject of NetApp, a blog post by Beth Pariseau from earlier in the year recently caught my attention; it was in regards to NetApp Snapshots in LUN environments. I’ve discussed a little bit of this before in my post about managing space requirements with LUNs. The basic question: how much additional space is recommended—or required—when using Snapshots and LUNs? Before the advent of Snapshot auto-delete and volume autogrow, the mantra from NetApp was “2x + delta”—two times the size of the LUN plus changes. With the addition of these features, deduplication, and additional thin provisioning functionality, NetApp has now moved their focus to “1x + Delta”—the size of the LUN plus space needed for changes. It’s not surprising to me that there is confusion in this area, as NetApp themselves has worked so hard to preach “2x + Delta” and now has to go back and change their message. Bottom line: You’re going to need additional space for storing Snapshots of your LUNs, and the real amount is determined by your change rate, how many Snapshots you will keep, and for how long you will keep them. 20% might be enough, or you might need 120%. It all depends upon your applications and your business needs.
  • If you’re into Solaris ZFS, be sure to have a look at this NFS performance white paper by Sun. It provides some good details on recent changes to how NFS exports are implemented in conjunction with ZFS.

That’s it for this time around, but feel free to share any interesting links and your thoughts on them in the comments!

Tags: , , , , , , , , , ,

Virtualization Short Take #20

Thursday, October 23, 2008 in Microsoft, Virtualization by slowe | 1 comment

This week’s Short Take is a collection of links and articles that I’ve seen over the last few weeks (or longer ago, in some cases!) that I thought others might find interesting or useful. Enjoy!

  • Alessandro broke the news to the general public about some anticipated new virtualization features that are expected to make their debut in Windows Server 2008 R2, expected sometime in 2010. Microsoft announced live migration for Hyper-V back at the beginning of September, so that part was already known. Now coming from Alessandro’s article is the announcement that Microsoft is developing a cluster file system, similar to VMFS, called Cluster Shared Volumes (CSV). Personally, this wasn’t a big surprise to me as a contact of mine leaked this to me a while ago. Hopefully this won’t hit Sanbolic too hard, whose Melio FS and Kayo FS solutions were intended to fill this gap (as discussed here and here).
  • As fully expected, VMware and Microsoft trade lots of barbs back and forth about VMware ESX vs. Hyper-V and vice versa. Out of the various exchanges, I found the “Too Dry and Crunchy” exchange—now quite old, having been published back at the end of September—the most entertaining. It started here with a barb from VMware about how Hyper-V with Server Core, the recommended configuration from Microsoft for virtualization hosts, is “not the Windows you know.” They compared Hyper-V on Server Core to ESXi and, not surprisingly, found ESXi to be easier and faster to install. What was really surprising though, was the response from James O’Neill in which he essentially agreed: Server Core isn’t “the Windows you know.” While he does love Server Core, James also recognizes that Server Core is not the right fit for every workload, and that management processes and procedures may need to change when using Server Core. Personally, I’m glad to see James recognizing and being honest about the limitations (or caveats) of Server Core. If only all vendors were so honest about their own products…one day, perhaps.
  • Duncan points out a great PDF on the definitions of various memory statistics. Readers may find that useful in understanding the various counters within VirtualCenter.
  • This VMware KB article outlines a potential VMware HA problem with multiple Service Console interfaces.
  • Andy Leonard picked up this VMware KB article that I bookmarked via Delicious.com and discussed how VMware’s recommendations and NetApp’s recommendations seem to run counter to each other. Personally, I’m inclined to follow VMware’s recommendations after the little snafu with NetApp’s NFS file locking suggestion.
  • This is a cool article on the use of ZFS and iSCSI to create clones in storage instead of at the virtualization layer. This is interesting because it’s being done with Solaris and ZFS, but it’s functionally equivalent to FlexClones with NetApp, which I’ve discussed before (see here, here, and here). Accordingly, ZFS clones will suffer from all the same limitations as NetApp FlexClones.
  • And while we’re on the topic of Sun and NetApp, what’s the deal with the recent patent rulings in the ZFS vs. WAFL lawsuit? If I’m reading this update correctly, it looks like some of the core WAFL patents from NetApp are being invalidated. Is Sun going to win this thing?

That does it for now. Thanks for reading!

Tags: , , , , , , , , , , ,

This is What Snow Leopard Needs

Thursday, October 23, 2008 in Macintosh by slowe | 5 comments

Before the release of Mac OS X 10.5 “Leopard,” the computing world was abuzz with the possible inclusion of ZFS—Zettabyte File System—into the new operating system. That rumor was largely fueled by the rumors swirling around about what would officially become known as Time Machine. It turns out that ZFS did make its way into Leopard, albeit on a read-only basis, and it isn’t the technology behind Time Machine.

Now, the next version of Mac OS X, version 10.6 code-named “Snow Leopard,” is said to be more evolutionary than revolutionary. Personally, I’d love to see Apple fully embrace ZFS as its file system of choice, and then throw away the goofy “flying through space” UI in Time Machine to embrace something like this. Of course, Apple can seriously turn up the UI polish, but this kind of approach makes sense and seems relatively easy to incorporate into the Finder interface.

So what do you think? Am I way out in left field here, or does anyone else think this seems like a good idea?

Tags: , ,

NetApp Suing Sun over ZFS

Wednesday, September 5, 2007 in Storage by slowe | 2 comments

I was on the road most of the day today, so I must have missed this news earlier. Apparently, Sun Microsystems and Network Appliance have had a little spat over ZFS and WAFL, and now NetApp is suing Sun for patent infringement.

Dave Hitz explained the situation in a blog entry:

This morning, NetApp filed an IP (intellectual property) lawsuit against Sun. It has two parts. The first is a “declaratory judgment”, asking the court to decide whether we infringe a set of patents that Sun claims we do. The second says that Sun infringes several of our patents with its ZFS technology.

Dave Hitz goes on to attempt to differentiate NetApp’s actions from the IP lawsuit(s) of SCO infamy. Personally, I wouldn’t place NetApp and SCO in the same situation, although I am strongly opposed to the current system of software patents. Patent reform is desperately needed, before things get worse than they already are.

In any case, this turn of events is unfortunate. I’m not technical enough to be able to provide any sort of opinion with regards to whether or not ZFS actually does infringe upon NetApp’s WAFL patents (or the other way around), but I do hope that Sun and NetApp can settle things amicably and move forward with more innovation, rather than getting stuck in an argument over who owns what. That’s the last thing either company needs right now. In addition, ZFS’ status needs to be settled quickly, before more companies decide to try to adopt a supposedly open sourced file system and incorporate it into their own products (as Apple reportedly did with ZFS and Leopard).

For more information on the lawsuit, see this eWeek article or this report from The Register. I’d also be interested in hearing anyone else’s feedback on the situation. What’s your take?

Tags: , , , , ,

Comparison of WAFL and ZFS

Monday, March 12, 2007 in Storage, UNIX by slowe | No comments

This comparison of ZFS (Zettabyte File System) and WAFL (Write Anywhere File Layout) by Network Appliance (no direct link for WAFL) is an interesting comparison of these two advanced filesystems and their feature set. Be sure to read the comments for some additional insight on the comparison of the two filesystems and some clarification about supported features.

One distinction raised in the comments that’s worthy to be noted here is that any comparison of this sort also, by its very nature, takes into account the operating system that runs the filesystem. As a result, any comparison of ZFS vs. WAFL also involves, to a lesser extent, Solaris and Data ONTAP, respectively. Similarly (and I think this may have been pointed out in the comments as well), the underlying hardware used by these filesystems (and their operating systems) also comes into play as well.

For these reasons, it’s impossible—in my mind, at least—to perform any sort of apples-to-apples comparison of these two technologies. It’s still an interesting article, though.

Tags: , , , , , ,