-
Alternate to AJA System Test for MAC
Hi –
I wish someone smart (Steve) would write a commercially available alternate to AJA System Test. IOMeter only runs on PC’s, and the ATTO Drive Utility is from the stone age. “Everyone” relies on AJA System Test, and “everyone” in the know says that it’s really not accurate or represent what is actually happening, yet “every” manufacturer uses it as their benchmark to show array performance on their drives.I for one would certainly pay “a couple of bucks” for a utility that was accurate, and showed an accurate representation of what is actually happening on a MAC Platform.
And Blackmagic Speed Test is no better (and worse) than AJA System Test.
Bob Zelin
-
5 Replies
-
What are you thoughts on Bonnie++ (https://en.wikipedia.org/wiki/Bonnie%2B%2B, https://www.coker.com.au/bonnie++/)? It’s very popular in the open source unix world and is in Macports. On quick inspection, it looks like it’s only linked to standard OS X libraries, so you could probably just copy the single binary around and use it on systems without the rest of Macports on it.
I’ve also done some simple benchmarks as they are with dd and reading from /dev/zero and writing to disk (typically a file of at least 2xRAM to make sure I’ve blown through any cache and buffering in at the vfs layer), or vice versa depending on what I wanted to test. The basic number from this and watching iostat can give you some decent insight into your storage system.
This is what it is– simple and quick — and like any benchmarking you need to understand all of the layers of your storage system to understand what any number or test means.
On the network side of things, I’ve found ttcp (also in Macports) to be very useful.
-
We use things like netpipe and iperf to debug drivers. They aren’t very useful for testing how the network will perform with AFP or Samba.
Apple used to have xsan_tuner which seemed like a serious attempt. I don’t know why they dropped it.
The tools small tree uses are proprietary. They give us a competitive advantage. I can setup 20 or 50 threads on a server and see how it will react. It would be very hard for someone that doesn’t understand kernel IO to setup something like this using final cut.
Steve Modica
CTO, Small Tree Communications -
has anyone tried this, and if they have, would this do anything different (as far as reliability) than AJA System Test –
https://diglloydtools.com/disktester.html
Bob ZElin
-
I read the collateral on this and I don’t think it’ll do what you want. Note that in the output for the streams test there’s no mention of latency. So assuming the streams run at a certain speed, he’s going to declare success (or at least, there’s nothing I see in the output that would indicate possible failure).
“Streams” from FCP are different depending on whether they are going over AFP, Samba, Xsan or a local HFS+ filesystem. How you measure them depends on the apps IO size and chosen API for those filesystems.
Steve Modica
CTO, Small Tree Communications -
Bob,
Did you ever find an alternative you liked?
Over the past week or so, I’ve been doing a lot of testing with iozone (https://www.izone.org) at work. It’s available in MacPorts and works just fine on OS X. It doesn’t have a GUI and isn’t perfectly suited to modeling video editing work flows, but it will give you far more data and tests that the AJA tool does. Of course like anything storage related, you really have to understand all of the different layers and what is going on with each one.
Chris
Reply to this Discussion! Login or Sign Up