Sequential Performance – HDTach, HDTune, File Copy, YAPT (sequential)
We have shifted over to combining our results into two groupings for consumer reviews. First up is sequential performance:
HD Tach will test the sequential read, random access and interface burst speeds of your attached storage device (hard drive, flash drive, removable drive, etc). All drive technologies such as SCSI, IDE/ATA, 1394, USB, SATA and RAID are supported. HDTach tests sequential performance by issuing reads in a manner that was optimized more for HDD access, but this unique method has proven useful in evaluating the sequential response time of SSDs. The accesses are relatively small in size (2k), and are issued with a single working thread (QD=1). The end result is that devices with relatively IO high latency will not reach their ultimate rated speed.
The 600p had a *huge* distaste for HDTach's 2KB sequential access pattern. Fortunately, modern system's do not use this particular pattern. We include HDTach for as an FYI as its pattern has proven inconsistent with many SSDs that otherwise perform well.
HDTune tests a similar level of features as compared with HDTach, but with a different access pattern. Thus provides us with an additional set of benchmark numbers to compare between storage configurations. CPU utilization has proven negligible with modern processing horsepower, and is no longer included. Additionally, we do not include write performance due to HDTune's write access pattern not playing nicely with most SSDs we have tested it on.
HDTune's read pattern is a bit more realistic, and the 600p turns in decent figures here. Not spectacular, but respectable.
PCPer File Copy Test
Our custom PCPer-FC test does some fairly simple file creation and copy routines in order to test the storage system for speed. The script creates a set of files of varying sizes, times the creation process, then copies the same files to another partition on the same hard drive and times the copy process. There are four file sizes that we used to try and find any strong or weak points in the hardware: 10 files @ 1000 MB each, 100 files @ 100 MB each, 500 files @ 10 MB each and 1000 files at 1 MB each.
…and then it all fell apart. The 600p barely escapes being beaten by the WD VelociRaptor (yes, a HDD) in our file creation and copy tests. To better understand what's going on here, lets take a look at Task Manager during this test:
This capture shows the first part of the test, with 10x 1GB files being written, followed by the start of the file copy, where those 10 files are copied between two equal partitions on the 600p. After ~6GB of file creation, the 600p's SLC cache was saturated, and once that happened, it slipped into a stuttery behavior where short bursts of 300 MB/s were sprinkled among multiple seconds of very low (<20 MB/s) write speeds. I've done a lot of additional back-end testing and reported all of my findings to Intel, who are currently looking into the issue.
Historically, SLC/TLC SSDs (like Samsung's EVO series parts) will write at SLC speed until their cache fills, then transition to writing directly to the TLC for the remainder of that heavy write operation. Most SSDs handle this very smoothly, but the 600p has a very hard time with this particular condition. Fortunately for the 600p, regular folks doing regular things with their systems won't hit the sustained conditions present in the majority of our legacy benchmarks, but man is it going to make the rest of this and the next page rough…
YAPT (yet another performance test) is a benchmark recommended by a pair of drive manufacturers and was incredibly difficult to locate as it hasn't been updated or used in quite some time. That doesn't make it irrelevant by any means though, as the benchmark is quite useful. It creates a test file of about 100 MB in size and runs both random and sequential read and write tests with it while changing the data I/O size in the process. The misaligned nature of this test exposes the read-modify-write performance of SSDs and Advanced Format HDDs.
YAPT does its reads and writes in a non-4k-aligned manner, and some SSDs end up being highly sensitive to that type of workload. While it is a relatively short 'bursty' test, the 600p simply did not mesh well with the misaligned IO of this test.