12 posts • joined 8 Jan 2009
The most recent IDC research on the topic gives Data Domain 64.2% of revenue and more than *half* of all capacity shipped in the purpose built backup appliance (PBBA) market and those numbers have been increasing, not decreasing, over time.
Think about that, out of every Terabyte shipped in the PBBA market more than half of it ships in a Data Domain capacity optimised protection system. And that number is increasing.
Neither Centera nor Atmos (Nor ViPR or Isilon, just to be clear) have ever been part of EMC Backup Recovery Systems. Centera and Atmos are Advanced Software Division products sold by Backup Recovery Systems to support compliance and long term Archiving workloads. I’ve been reading ‘Centera is dead’ articles since 2001 and 12 years on there’s still new hardware and software being released for the product so it’s going to be a while yet before anyone gets to say ‘I told you so’ on any object storage products reaching the end of their market demand.
I'm not going to comment on Isilon's roadmap as that's for them to speak about but I'd see 'merging' Isilon & Atmos as not being on the table. ViPR uses a significant amount of Atmos intellectual property to provide object storage services for EMC, third party and commodity NAS systems. Isilon spoke about their integration plans with ViPR at EMC World.
All the other complaints repeated in the article are a mixture of speculation, opinion and more than a few sour grapes.
Data Domain Enterprise Manager
Mark Twomey here.
And just to be clear, EMC does offer Enterprise Manager for Data Domain which can manage 20 appliances from a single pane of glass.
I'd rather marketing not claim 620TB/hr throughput in such a case, but since HP appear to have decided it would be okay to do so...
"According to NetApp, VFCache can hold stale data if the backend array has data restored on it, but there is no reliable data coherency end-to-end."
purge -source_dev #
Run array commands
The equivalent of purging data cached in DRAM on a server. You expire the LUN cache for the LUN(s) you're making changes to.
NetApp obviously have no idea what they are talking about. Not surprising as this is from the same company who claimed 'tiering was dead' (1.3 Exabytes of Data under FAST management) and were the industry leader in Flash shipments...until it was shown EMC shipped 3x their number in teh same year.
NetApp don't rate in Flash. At all.
Regardless of what they do over the next 12 months EMC will deliver 1TB cards, the ability to use SSDs in server drive slots as cache and enhanced VMware support. On top of distributed cache coherency, enhanced FAST integration and the Thunder Server Networked Flash appliance.
SFS97 is a retired benchmark.
The SPEC SFS_97 benchmark was retired by SPEC three years ago and replaced by the redesigned SFS2008 benchmark featuring improved benchmarking workloads.
As stated by SPEC themselves neither benchmark is comparable to the other, though it's interesting to note NetApp never submitted a CIFS benchmark with their NFS submission.
To show the linear scalability and system resource aggregation of OneFS 6.5, Isilon tested 7, 14, 28, 56 and 140 nodes for both SPECsfs2008_CIFS & SPECsfs2008_NFS. The results of which can be seen on SPEC.org.
Frank wasn't sidelined or pushed out. After running Backup Recovery Systems through it's formative stages he passed control over to BJ and stayed on in an advisory capacity for a few months before starting the new year at Data Domain investor Greylock Partners.
I wish him the best of luck and I'm sure he'll be back looking to sell EMC another Greylock investment in the near future.
EMC Celerra deduplicates active files on primary storage
Disclosure: I'm an EMC employee.
NetApp isn't the only one in the market doing capacity reduction of primary storage.
EMC Celerra Deduplication will perform file level single instancing and compression of multi-terabyte active files (VMDK, VDI, or other wise) and it'll do so at the file level.
Doing it at the file level means you can force specific files to always be space reduced regardless of the reduction schedule for the volume or decided to exclude various file types if you so choose.
Backup is not Dead
While NetApp's tape augmentation market has declined Data Domain and Avamar's *tape replacement* business grew 50% year over year in the last quarter alone and has been up every quarter.
Now that they're not getting any of that action it's back to the old NetApp chestnut that "Backup is Dead".
No, no. Only their VTL is dead. Backup and Recovery is as important as ever.
Yes, Brutus too.
You forgot to include your name and title at Symantec in that comment.
Technical facts now available
Detailed technical facts about the Enterprise Vault data loss bug are now available over at The Storage Anarchist's blog.
It should be noted these are verified facts and not opinions of a competitor with a FUD agenda.
Consider this FUD attack "Exposed"
Val said: "There is no Symantec (or any other popular archiving ISV for that matter) KB article warning of potential risks with archiving to NetApp SnapLock. Will there every be? Who knows, but I like NetApp's odds due to one key difference - SIMPLICITY."
Continuing the pattern of not doing any research and hoping no one will notice I see.
Lets look at Symantec KBase article 316205.
"Data loss may occur when two or more Vault Store Partitions are located on the same physical location..."
"The following scenarios do not perform a check and will allow the same location to be created:
When a NetApp is used, this check is not performed."
Note: This does NOT affect an EMC Centera device in terms of data loss."
You've been on the wrong side of this since the very first moment Val. I told you as much in the first comment on your post where after paragraphs of FUD you still couldn't identify the problem with Enterprise Vault not archiving the data to Centera, even though it was all in the advisory if you understood what you were reading. I explained it in what? Two sentences?
What I lack in word count I make up for with accuracy and hands on experience.
But one must ask is this what goes on in the NetApp CTO Office? They trot out partner's tech advisories in public, read them incorrectly and when the partner publicly says they're wrong they then claim a Google search is proof enough as in the absence of verifiable fact they now have nothing else to support the opinion they're pushing?
Regardless of that, none of the verifiable facts (Verifiable by a third party you dragged into this) support your initial or current opinions Val leaving us with this ongoing FUD campaign of yours.
The industry equivalent of Quixote tilting at windmills.
There is no data integrity issue with Centera, you made it up. Now having caused a public incident with a partner you appear to have moved on to embarrassing your employer.
Backup, Recovery and Archiving Subject Matter Expert. EMC Corporation.
That's because they have archiving functions or act as archive targets, but they're not owned or developed by CMA and their revenue isn't recorded as such. If CMA was carrying the Centera number alone their revenue numbers would be higher.
CMA doesn't develop storage devices, NAS virtualization products/NAS software or such. It does develop the entire suite of Documentum, CenterStage, and Captiva products.
What sits where.
Centera, DX/EX, Celerra FileMover (As well as Celerra) and Rainfinity are not part of CMA they're part of the EMC Storage Division.