The most common usage scenario is transfer of large amounts of photos and videos to and from the unit. Our testing methodology for storage bridges / direct-attached storage units takes into consideration the usual use-case for such devices. AnandTech DAS Suite - Benchmarking for Performance Consistency The firmware is perhaps configured differently, and is an aspect that we will continue to focus in the other subsections of the review. On a comparative basis, the performance comes up a bit short against the Kingston DTMAX A. The increase in random IOPS with queue depth shows that both UASP and NCQ are supported, as indicated in the CrystalDiskInfo report. However, as queue depth increases further, the benefits diminish. For a queue depth of 8, the reads cross the 1000 MBps barrier, and the writes are near the 950 MBps mark. The numbers here are much closer to Transcend's advertised claims. This assumes that the host port / drivers on the PC support UASP. If the numbers for the two access traces are in the same ballpark, NCQ / UASP is not supported. Comparing the '4K Q32T16' and '4K Q1T1' numbers can quickly tell us whether the storage device supports NCQ (native command queuing) / UASP (USB-attached SCSI protocol). The plain 'Rnd4K' one uses only a single queue and single thread. The 'Seq1M' traces use a 1MiB block size. The 'Seq128K Q32T1' sequential traces use 128K block size with a queue depth of 32 from a single thread, while the '4K Q32T16' one does random 4K accesses with the same queue configuration, but from multiple threads. Internally, CrystalDiskMark uses the Microsoft DiskSpd storage testing tool. Two of the traces are sequential accesses, while two are 4K random accesses. Our CrystalDiskMark benchmark configuration uses four different access traces for reads and writes over a configurable region size. It does allow the visualization of change in transfer rates as the I/O size changes, with optimal performance being reached around 512 KB for a queue depth of 4. In any case, ATTO benchmarking is restricted to a single configuration in terms of queue depth, and is only representative of a small sub-set of real-world workloads. While these numbers are not hit with our ATTO benchmark settings (bypassing the write cache and using a queue depth of 4 for sequential accesses), we find that the writes are faster than a similarly built Kingston DataTraveler MAX A, with read performance being almost the same. Transcend claims read and write speeds of 1050 MBps and 950 MBps respectively. Yet another use of these synthetic benchmarks is the ability to gather information regarding support for specific storage device features that affect performance. The results translate to the instantaneous performance numbers that consumers can expect for specific workloads, but do not account for changes in behavior when the unit is subject to long-term conditioning and/or thermal throttling. Benchmarks such as ATTO and CrystalDiskMark help provide a quick look at the performance of the direct-attached storage device.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |