In integer math, the results are nearly equal when adjusted for the almost half-as-fast CPU clock of the Sun Fire T, as an example. You can't get four dual-core Opteron processors in the same space. Because we can't modify the LMBench3 source code, we were limited to testing one, then eight instances of the test suite. Without otherwise optimizing the benchmark, we found that overall, the eight-core scenario was about eight times as fast as a single-instance result.
This means that the single CPU can do eight times the work of a single instance with very few slow-ups measured. At eight cores, performance was good, and if optimized to 32 threads logical or virtual CPUs , performance might have been spectacular, but there is little way of measuring this correctly, and few applications that can take advantage of the discrete threads.
The performance marks we did measure were very good - especially given the small form factor of the T In testing, we downloaded, recompiled and used quite a few open source applications on the T as a convenience of Solaris 10 , despite its unusual CPU arrangement. Most applications we've seen don't have specific optimizations available for either the UltraSPARC architecture or the multicore, multithreaded arrangement used by the T or any other CPU for that matter.
Multiprocessor-poised code is exceedingly rare. Optimizations that take advantage of the processor threads will range from fairly simple for example, applications that already are optimized for UltraSPARC architectures to the very difficult for example, retrofitting existing or ported applications to take advantage of the processor configuration.
It also is possible to use Solaris zoning techniques to start and execute applications on specific parts of the T1 CPU inside the T However, this virtualization technique adds significantly to the management articulation that is possible in the Sun Fire architecture.
Sun says the T is a strong performer at a low operational cost. Henderson is principal researcher at ExtremeLabs in Indianapolis. He can be reached at thenderson extremelabs. Laszlo Szenes of ExtremeLabs contributed to the testing.
Henderson is also a member of the Network World Lab Alliance, a cooperative of the premier reviewers in the network industry, each bringing to bear years of practical experience on every review. For more Lab Alliance information, including what it takes to become a member, go to www. In real numbers, this meant that the quad dual-core Opteron server served approximately 2, pages per second of an 8KB static page with 10 image elements while the T averaged 2, pages per second.
A similar test on a dual 3. My SSL tests showed the T suffering slightly as compared to the dual-core Opteron, averaging operations per second, with the Opteron server dishing out requests per second. The dual-Xeon Windows server held the middle at roughly ops per second.
The newest member of the Sun family might be considered a boutique server, but the UltraSparc T1 is truly a revolutionary processor. Paul Venezia is a veteran enterprise architect and senior contributing editor at InfoWorld, where he writes analyses and reviews. Here are the latest Insider stories. More Insider Sign Out. Sign In Register. Sign Out Sign In Register. Latest Insider. Check out the latest Insider stories here. The fans enable the system to continue operating with adequate cooling in the event that one of the fans fails.
The Sun Fire T server server features an environmental monitoring subsystem protects the server and its components against:. Temperature sensors are located throughout the system to monitor the ambient temperature of the system and internal components. The software and hardware ensure that the temperatures within the enclosure do not exceed predetermined safe operation ranges.
If the temperature observed by a sensor falls below a low-temperature threshold or rises above a high-temperature threshold, the monitoring subsystem software lights the amber Service Required LEDs on the front and back panel.
If the temperature condition persists and reaches a critical threshold, the system initiates a graceful system shutdown. In the event of a failure of the system controller, backup sensors protect the system from serious damage, by initiating a forced hardware shutdown. Service Required LEDs remain lit after an automatic system shutdown to aid in problem diagnosis.
The power subsystem is monitored in a similar fashion by monitoring power supplies and reporting any fault in the front and rear panel LEDs. Additionally, LEDs located on each power supply light to indicate failures.
You can set up a hardware RAID 1 mirroring and hardware RAID 0 striping configurations for any pair of internal hard drives, providing a high-performance solution for hard drive mirroring. The Sun Fire T server features the latest fault management technologies. The Solaris 10 OS architecture provides a means for building and deploying systems and services capable of predictive self-healing. Self-healing technology enables systems to accurately predict component failures and mitigate many serious problems before they actually occur.
This technology is incorporated into both the hardware and software of the Sun Fire T server. At the heart of the predictive self-healing capabilities is the Solaris Fault Manager, a new service that receives data relating to hardware and software errors, and automatically and silently diagnoses the underlying problem. Once a problem is diagnosed, a set of agents automatically responds by logging the event, and if necessary, takes the faulty component offline. By automatically diagnosing problems, business-critical applications and essential system services can continue uninterrupted in the event of software failures, or major hardware component failures.
The Sun Fire T server uses a space-saving 2U-high rackmountable enclosure that can be installed into a variety of industry standard racks. The following figures show the physical characteristics of the Sun Fire T server.
0コメント