Performance Consistency

Performance consistency tells us a lot about the architecture of these SSDs and how they handle internal fragmentation. The reason we do not have consistent IO latency with SSDs is because inevitably all controllers have to do some amount of defragmentation or garbage collection in order to continue operating at high speeds. When and how an SSD decides to run its defrag or cleanup routines directly impacts the user experience as inconsistent performance results in application slowdowns.

To test IO consistency, we fill a secure erased SSD with sequential data to ensure that all user accessible LBAs (Logical Block Addresses) have data associated with them. Next we kick off a 4KB random write workload across all LBAs at a queue depth of 32 using incompressible data. The test is run for just over half an hour and we record instantaneous IOPS every second.

We are also testing drives with added over-provisioning by limiting the LBA range. This gives us a look into the drive’s behavior with varying levels of empty space, which is frankly a more realistic approach for client workloads.

Each of the three graphs has its own purpose. The first one is of the whole duration of the test in log scale. The second and third one zoom into the beginning of steady-state operation (t=1400s) but on different scales: the second one uses log scale for easy comparison whereas the third one uses linear scale for better visualization of differences between drives. Click the dropdown selections below each graph to switch the source data.

For more detailed description of the test and why performance consistency matters, read our original Intel SSD DC S3700 article.

Micron M600 256GB
Default
25% Over-Provisioning

Performance consistency is not very good, but that was expected as we are dealing with a DRAM-less design. With insufficient cache for the NAND mapping table, it is very hard to manage the table efficiently in the steady-state environment, which results in decreased performance. The good news is that Chrome OS is extremely light and a scenario like this is basically impossible, so the data here is merely an interesting piece of information.

Micron M600 256GB
Default
25% Over-Provisioning

 

Micron M600 256GB
Default
25% Over-Provisioning

TRIM Validation

To test TRIM, I filled the drive with sequential 128KB data and proceeded with a 30-minute random 4KB write (QD32) workload to put the drive into steady-state. After that I TRIM'ed the drive by issuing a quick format in Windows and ran HD Tach to produce the graph below.

It seems that TRIM is working, although there is an odd drop in read performance after the ~140GB mark.

Managing Storage in Chrome OS AnandTech Storage Bench 2013
Comments Locked

67 Comments

View All Comments

  • sligett - Wednesday, October 22, 2014 - link

    But one might instead say --

    I have zero clue why Windows laptops are so popular. I tried one and it was laughably complex compared to Chromebooks that are now pretty much priced the same. This might be ok, but for its complexity, Windows doesn't really run any faster than its Chrome OS counterparts, nor does it get much better battery life at all. I just see no reason unless you just absolutely detest ChromeOS.
  • BrokenCrayons - Tuesday, October 28, 2014 - link

    I think one of the root causes for Chrome OS drawing ire is Google's invasive data mining activities associated with the device, storage of information on their servers, and the linking of that data with web browsing habits (including sites that use Google Ad Services -- of which there are many), GPS and cellular triangulation information (if you also happen to be using Android), mail, app use, time spent in each app, and so forth. Google being behind Chrome is one of the biggest problems with uptake of the platform. Since most of Google's services are offered free of charge, you can be assured that they're generating profit by "farming" their users in the same way social networking does, by monitoring and analysing everything at all times on as many platforms as possible.
  • patel21 - Wednesday, October 22, 2014 - link

    If we can create a recovery media, then can we install it on normal PC's ?
  • Bob Todd - Wednesday, October 22, 2014 - link

    If you just want to play around and test it, you can just grab a Chromium OS build from various places.
  • daddacool - Wednesday, October 22, 2014 - link

    "While the whole netbook boom kind of died with the introduction of tablets"

    I remember the actual reason for the demise of netbooks being feature creep, obviously coupled with the associated price creep. Netbooks we're orginally known as SCCs; Small Cheap Computers. Once the price began edging up into budget laptop price, the case for them became much less compelling.
  • waldojim42 - Thursday, October 23, 2014 - link

    Yep, I thought this too. I remember netbooks reaching into the $400~$500 range while still running crap Atom processors. I don't know who they expected would be in the market for them, but it sure wasn't me.
  • a1exh - Wednesday, October 22, 2014 - link

    How well does the "chrome://imageburner" upgrade method work? If your internal 16/32GB drive is almost full (of non-compressible data) presumably you need a 16/32GB SDHC or USB stick?
  • extide - Friday, October 24, 2014 - link

    It doesnt back up your daownloaded data, just the OS.
  • abianand - Thursday, October 23, 2014 - link

    Does this SSD upgrade keep the cost of this Chromebook at $200 or increase it?
  • Suo.Eno - Thursday, October 23, 2014 - link

    Here you go bro
    http://www.anandtech.com/show/8543/upgrading-the-s...

Log in

Don't have an account? Sign up now