Just spit-balling here....
-
@Dashrender said:
@dafyre
From memory, and it's been a few years, Scott always seemed to really want Tier 1 if possible, but if you had to be budget friendly, then yes, Tier 2 like SuperMicro was definitely usable.Using a white box as @DustinB3403 suggests to me indicates that you don't value your data. The cost of the hardware for a Teir 1/2 NAS should be significantly lower than the value of your data, unless you just don't care about your data.
You nailed it. Tier 1 and Tier 2 only. Going with low quality parts saves almost zero money but creates a lot of risk both in failure and compatibility not to mention performance and an inability to get support.
-
@DustinB3403 said:
I've generally respected Intels product lines and never had any issues with them in the past.
So being Part Agnostic then the Topic will be revised.
Intel makes middle of the road processors (nothing compared to IBM Power or Oracle Sparc) and quite good SSDs and some excellent support chipsets but their quality pretty much ends there. Their motherboards are generic and their RAID cards are literally the example of customers being tricked to get FakeRAID, nearly all Intel RAID products are FakeRAID and some of the worst in that category.
-
Moving to big name ENTERPRISE parts turns this into a SAM-SD discussion and, yes, I recommend that heavily.
-
As does the Oracle ZFS team who worked with Eric McAlvin and I to develop the SAM-SD model in 2007.
-
The SAM-SD approach was based on the work that Sun (now Oracle) did on Thumper.
-
Sun Thumper.... the predecessor to the SAM-SD
-
The HP Proliant DL585 G2, the first machine that McAlvin and I designed to take on NetApp in a 10,000 node compute cluster for NFS performance in 2007. Used RHEL 5 and NFS 3. Crushed a half million dollar NetApp tuned by the NetApp team directly for the test. This is the SAM-SD 0, it wasn't called a SAM-SD until years later.
-
@scottalanmiller It was somebody at SW that gave it that name, isn't it?
-
OK so Scott for the purpose of this topic, what hardware vendors meet your Criteria for ENTERPRISE grade equipment that business might build in house?
IBM Power / Oracle Sparc
Supermicro / Dell / HP
LSI or AdaptecAny others?
-
@dafyre said:
@scottalanmiller It was somebody at SW that gave it that name, isn't it?
Yes "Limey", Marin Peverly from PA.
-
The original Reference Design SAM-SD "Model 1" from 2009. The HP Proliant DL185 G5. 14x 3.5" LDD HDs, dual AMD Opterons, SmartArray P400 512MB RAID Controller.
@ntg still has the original unit.
-
@DustinB3403 said:
OK so Scott for the purpose of this topic, what hardware vendors meet your Criteria for ENTERPRISE grade equipment that business might build in house?
IBM Power / Oracle Sparc
Supermicro / Dell / HP
LSI or AdaptecAny others?
While I'm not fan, Cisco would make the list as well. As would Fujitsu.
-
@scottalanmiller ROFL... If I didn't know better, my first guess would be that is the same model used in the HP / LeftHand P4300 SAN series...
-
@dafyre said:
@scottalanmiller ROFL... If I didn't know better, my first guess would be that is the same model used in the HP / LeftHand P4300 SAN series...
It is, we've often mentioned that the Lefthand was HP's response to the SAM-SD reference design. They actually took the parts and design that we had been promoting and built a fully supported proprietary product based on the open design that we had done.
-
New SAM-SD discussion group created as the official place to discuss the SAM-SD concept. We will eventually direct here from the SAM-SD website.
-
@scottalanmiller said:
The HP Proliant DL585 G2, the first machine that McAlvin and I designed to take on NetApp in a 10,000 node compute cluster for NFS performance in 2007. Used RHEL 5 and NFS 3. Crushed a half million dollar NetApp tuned by the NetApp team directly for the test. This is the SAM-SD 0, it wasn't called a SAM-SD until years later.
what about your setup do you think allowed this box to crush them?
-
@Dashrender said:
what about your setup do you think allowed this box to crush them?
We know very well what it was - vastly higher threading performance provided by the combination of the Opterons and the RHEL OS. NetApp is built of FreeBSD and does not thread as well as Linux and is not tuned as well for storage performance (FreeBSD shines at network performance over Linux and the reverse for storage.) And the NetApp devices are disk heavy but did not have particularly powerful CPUs. The combination meant that the NFS layer would literally demand more from the CPUs than the platform could provide. The $20K Proliant with Linux was able to crush the $500K NetApp with the NetApp actually crashing and dying while the Proliant was able to complete all of the tests.
It was all predicted ahead of time and the DL585 chosen because of its ability to vastly "outthread" the NetApp.
-
Sun's ZFS team had helped us to identify why the NetApps that we had were unable to supply NFS reliably or quickly to our server cluster (10,000 HP Proliant DL145 G2s) and the design was based around addressing that issue cost effectively. We knew when the NetApps that we had would fail and invited NetApp to provide a solution, which they failed to do. The test harness that we used to gauge the NetApp vs. the SAM-SD was 3,000 compute nodes pulled out of production. The NetApp was unable to complete the test, the SAM-SD completed it with ease showing that it could handle, when used in a storage cluster, the entire compute cluster without a problem.
-
@Dashrender said:
@scottalanmiller said:
The HP Proliant DL585 G2, the first machine that McAlvin and I designed to take on NetApp in a 10,000 node compute cluster for NFS performance in 2007. Used RHEL 5 and NFS 3. Crushed a half million dollar NetApp tuned by the NetApp team directly for the test. This is the SAM-SD 0, it wasn't called a SAM-SD until years later.
what about your setup do you think allowed this box to crush them?
NetApp was pretty weak in performance back then. They were designed around massive scale out, which broke into the performance.
As someone who works in various "cloud" providers, using this kind of method would not really be worthwhile for us. I've used 3par and NetApp, and now Pure and Compellant for storage. But for SMB, this is absolutely perfect. I used a Dell PE2950 stacked with a bunch of SATA drives for a SAM-SD once. I needed file server space and backup destinations, not SQL IOPS. Thats the beauty of it, stack it with SSDs, you got something close to what Pure can supply. Stack it with SATA, you have a "NAS" that rivals anything out there. It's flexible and customize-able. You just have to decide what is most important for your organization.
-
@scottalanmiller said:
@Dashrender said:
what about your setup do you think allowed this box to crush them?
We know very well what it was - vastly higher threading performance provided by the combination of the Opterons and the RHEL OS. NetApp is built of FreeBSD and does not thread as well as Linux and is not tuned as well for storage performance (FreeBSD shines at network performance over Linux and the reverse for storage.) And the NetApp devices are disk heavy but did not have particularly powerful CPUs. The combination meant that the NFS layer would literally demand more from the CPUs than the platform could provide. The $20K Proliant with Linux was able to crush the $500K NetApp with the NetApp actually crashing and dying while the Proliant was able to complete all of the tests.
It was all predicted ahead of time and the DL585 chosen because of its ability to vastly "outthread" the NetApp.
With solutions like this, why isn't someone crushing the NAS/SAN market with these types of much lower cost solutions than the competition? Seems like these would fly off the shelf at 1/10 or less the cost of the competition.
