that's a fixed or semi fixed, non-flexible disk space allocation for "copy on write" changed blocks, right? On the Network Appliance filer, isn't' that "reserve" more of an accounting mechanism than a physical disk space allocation? I thought you could use snapshots on the network appliance system without setting any reserve if you wanted.
-----Original Message----- From: Paul Brosseau [mailto:paulb@netapp.com] Sent: Thursday, May 10, 2001 9:01 AM To: ferdberfl@netzero.net; toasters@mathworks.com Subject: RE: EMC IP4700 vs NetApp F740
Chris,
Your description of how the IP4700's Snapshot copy-on-write mechanism works is right on. The original data is copied to a new location and the new data is written to the original block. Yes this compromises performance. Yes you have to allocate physical disk space to accomplish this. No you cannot shrink the amount of disk space you have allocated for this process if you find that it is too much.
Paul Brosseau - Netapp SE Former EMC SE
-----Original Message----- From: owner-dl-toasters@netapp.com [mailto:owner-dl-toasters@netapp.com]On Behalf Of Ferd Berfl Sent: Thursday, May 10, 2001 10:02 AM To: toasters@mathworks.com Subject: RE: EMC IP4700 vs NetApp F740
re: snapshots, I thought that everyone else's snapshot functionality other than Netapp's must be based on a "copy on write" method because Netapp has a patent on continuously writing new blocks. (their WAFL filesystem intellectual property and patents). If you can't take advantage of the method of writing modified blocks as new blocks and not touching the original block pointed to by the snapshot, doesn't that mean that you have to reserve some amount of storage, that is free blocks, for holding the copy on write changed blocks to maintain the snapshots?
-----Original Message----- From: owner-dl-toasters@netapp.com [mailto:owner-dl-toasters@netapp.com]On Behalf Of Barry Lustig Sent: Wednesday, May 09, 2001 5:30 PM To: Chris_Van_Genderen@NexFlash.com Cc: sirbruce@ix.netcom.com; toasters@mathworks.com Subject: Re: EMC IP4700 vs NetApp F740
Chris,
I'm the person that started the F85 vs. IP4700 thread. Here is one data point. When we benchmarked the F85 it was able to do a single threaded read at 90-95 Mbits/sec and writes at 85-90 Mbits/sec. This was on a 100BaseT full-duplex connection to a linux box. When we tried the same benchmark with the IP4700 it showed 40-50 Mbits/sec read and 20-25 Mbits/sec write. This clinched the deal for the F85's for us. EMC compares the IP4700 to the F8xx line. If the system cannot even keep up with an F85, I think that EMC needs to take a look at what is going on. Also, you should check with EMC regarding their snapshot implementation. Netapp's snapshots don't have to copy old data when a data block is updated. A new block is allocated and then written. I've heard, but haven't verified that the IP4700's filesystem acts more like a copy on write system. First the old data block has to be copied to a new location then the modified data is written. If this is actually the case then the performance of the filesystem will be compromised. I know that there are EMC folks on this list. Maybe one of them can respond.
barry
Chris_Van_Genderen@NexFlash.com wrote:
Bruce,
One of the items that I did not mention was that we are a start up company that is using the back-end infrastructure of our parent company. I have been given the task of not only buying a NAS device for company wide storage, but also to build the entire network infrastructure and server infrastructure for our new location. So, what ever we purchase will need to go online immediately and support the company in a new location. I don't have the "test-bed" to test
anything.
As you can also guess, via my title, I am not a MIS person either. So, I've been going through a fairly steep learning curve in many areas. I am weary about compatibility issues with NFS and our engineering/CAD Sun machines. In this area, I feel because of their industry
experience,
NetApp has the edge. I've talked with EMC on this issue, and they re-assure me that the IP4700 will not have compatibility problems. However, this is much different than having users of the product claim
that their
are no compatibility problems.
My gut feeling is to go with the F740 because of the existing
installation
base, and the maturity of the product. I'm just a little miffed that
NetApp has
been trying to use my inexperience and limited knowledgebase against
me during
the sales process; it doesn't give me the feeling that I can
trust them.
Chris Van Genderen Software Engineer & Applications Manager NexFlash Technologies, Inc. chris_van_genderen@nexflash.com
"Bruce Sterling To:toasters@mathworks.com, Chris_Van_Genderen@NexFlash.com
Woodcock" cc: (bcc: ChrisVan Genderen/Santa Clara/ISSIHQ)
<sirbruce@ix.n Subject: Re: EMCIP4700 vs NetApp F740
etcom.com> 05/09/01 03:45 PMMost of what you seem to be weighing are nebulous issues of who says what. Why don't you just find out for yourself?
Ask Netapp for an F760 to try out for 2 weeks.
Ask EMC for an IP4700 *at the equivalent price and disk capacity, with RAID* to try out for 2 weeks.
See which has better performance for your users and which you can administer easier. Build large RAID groups, test simultaneous file sharing from NFS and CIFS, fail drives, do rebuilds, etc.
Bruce
_________________________________________________________ Do You Yahoo!? Get your free @yahoo.com address at http://mail.yahoo.com