You are currently browsing the tag archive for the ‘HP’ tag.
Both Dell and HP released their first wave of servers based on the new dual-socket Intel Xeon E5 series last week. Dell is calling their new servers “12th generation”, and HP is calling theirs “Gen8″ (generation eight). After reviewing both vendors’ offerings, my initial take is that Dell is raising the bar in terms of storage density and features, and HP is matching some of Dell’s recent gains in system manageability.
With their previous generation of servers, Dell lagged behind HP’s internal hot-plug disk capabilities. The Dell PowerEdge R710 2U server could only hold up to 8 2.5” (small form factor, or “SFF”) drives, but HP had an option to insert up to 16 in their ProLiant DL380 G7. The Dell PowerEdge T710 server could only hold up to 16 SFF drives, but HP’s ProLiant DL370 G6 could hold up to 24. My team at work ended up choosing the DL370 G6 in many cases for applications like file servers, SQL servers, and backup servers because of the large number of local disks. External disk enclosures from either vendor are very expensive. With their 12th-generation servers, Dell has increased the internal storage capabilities of their servers significantly. The PowerEdge R620 can hold up to 10 SFF drives. The PowerEdge R720 can now hold 8 or 16 SFF drives (with a two-controller 8 + 8 split-backplane option), and has added a 2U PowerEdge R720xd model that can hold up to 14 3.5″ (large form factor, or “LFF”)drives or 26 SFF drives. The PowerEdge T620 (replacing the T610 and T710 models) can hold up to 32 SFF drives. On some server models, Dell also has added the capability to address up to 4 of the hot-plug bays directly with PCI Express (PCIe) buses, which work with PCIe SSD (solid state disk) hot-plug disk options for high-performance workloads. They also carry a feature on their PERC RAID controllers called CacheCade which allows the controller to use SAS SSDs as additional read/write cache.
HP’s new servers break little new ground in the storage area compared to the models the Gen8 servers are replacing. The ProLiant DL360p Gen8 (1U rackmount server) maxes out at 8 SFF drives (same as G7), the DL380p Gen8 (2U rackmount) can hold up to 16 SFF drives (same as G7), and the ML350p Gen8 (a 5U tower/rack server similar to the Dell T620) can hold up to 24 SFF drives (same as DL370 G6). HP doesn’t have an answer for the PCIe SSDs or CacheCade feature that Dell offers. Both of the new-generation Dell PERC and HP Smart Array RAID controllers have flash-backed write cache (FBWC) as a standard feature: HP had this when their previous generation controllers launched; Dell added the feature after launch. HP has 1GB and 2GB FBWC options on their new Smart Array P421 controller; Dell shows only 512MB and 1GB options on the new PERC H710.
Both vendors’ servers have similar processor/memory options at launch. All the servers I’ve referenced here can hold up to two 8-core CPUs and have 24 DIMM slots for RAM at sizes of 2 to 32GB (maximum 768GB RAM). Other servers that use the Xeon E5 CPUs in a 4-socket configuration are due to come out later this year and will have even greater memory capacity. Memory now runs at up to 1600MHz and the lowest-speed configuration (when many DIMM sockets are populated) is 1066MHz (up from 800MHz in the Xeon 5600-based configurations).
With their previous generation of servers, Dell added a new Lifecycle Controller that provided a bootable, GUI environment for maintaining servers independently of the installed OS. HP appears to be trying to match this feature with their new “iLO Management Engine”. I’m looking forward to seeing how this works. Both vendors have evolved their lifecycle management over the last few years to be a lot more OS-agnostic, relying on Linux-based boot environments to provide easy-to-use system management/update tools.
Both vendors are driving up their feature sets, but I think Dell is poised to be a leader in direct-attached storage applications. I will have to review the systems management offerings from both vendors to see if they’re truly getting more similar.
A VMmark Review Panel comprised of several of our partners has recently been formed in order to provide additional rigor and transparency to the benchmark reviews. The founding members of the review panel are AMD, Dell, and HP, in addition to VMware. (We hope to add more partners soon.)
This broader and more open review process will produce an even greater level of confidence in the accuracy and compliance of published results.
I agree. I’ve blogged about the veracity of VMmark results before and it generated some good discussion.
VMmark is a virtualization throughput benchmark developed by VMware to test its products’ performance on compatible hardware configurations. Its job is to stress the CPU/memory subsystem of a server hosting virtual machines and index its performance at its maximum acceptable workload. Vendors document VMmark tests with VMware products (normally ESX) on a given hardware/software configuration and submit the results to VMware, who publishes them on a web site.
VMmark came out of beta with version 1.0 in July 2007. To date, Dell, HP, IBM, and Sun have submitted results that have been published by VMware. The results cover the AMD Opteron and Intel Xeon server platforms, which all four server vendors now provide to varying degrees. It’s been a useful resource for me, since the competition between AMD and Intel the last few years has resulted in each vendor taking turns leading in virtualization performance in the 2-socket and 4-socket x86 server spaces. Regardless of which vendor submits a VMmark result for a particular processor/memory/chipset combination, the result can usually be inferred to be similar to what would be obtained on another vendor’s implementation of that combination. Based on a recent conversation I had with HP, they expect that customers will make that inference. I had approached them twice about HP’s lack of up-to-date VMmark results for their flagship virtualization platforms, and was told that they hadn’t submitted recent benchmarks due to their reluctance to publish results with non-production VMware ESX builds and/or hardware that wasn’t yet available to customers. Because other vendors were publishing results on current or upcoming platforms sooner, HP apparently didn’t see much return on going though the trouble and cost of performing and documenting VMmarks on their implemenation of similar platforms.
Note that when I described VMmark, I mentioned compatible, not supported, hardware configurations; that’s because VMware has published results from vendors that used pre-release, unsupported software and/or hardware. I think this is the most likely reason Dell was the first to release a quad-core-Opteron-based VMmark. If you look at the disclosure for that submission, you’ll see that it was run on a PowerEdge R905 with 2.5GHz quad-core Opterons (model 8360 SE), a processor model that isn’t available for purchase in that server today. The fastest available R905 today has model 8356 (2.3GHz) processors. Dell’s submitted results for their PowerEdge R900 with Xeon 7350 processors used a beta version of VMware ESX Server v3.5, build 62773, and was tested on November 16, 2007: a few weeks before the production release of ESX 3.5, build 64607, on December 10th. In fact, of the 16 total VMmark results published as of today, the only vendor who submitted results with hardware or software unavailable at the time of publishing is Dell.
To better reflect the version and status of hardware and software used to obtain the published results, I think VMware should:
- refuse to publish results that use pre-release hardware and/or software
- clearly state the availability and/or versions of the tested hardware and software in the system descriptions on the results page
That would allow customers like me to better determine the veracity of a published score without having to be a detective. As VMmark evolves and future SPEC-sanctioned virtualization benchmarks come to market, it would be nice to be able to see more, relevant benchmarks from more vendors rather than gamed, dubious benchmarks from a few.