Bloglg

1. Atto Disk Benchmark For Mac
2. Disk Benchmark Mac Os X
3. Mac Benchmark Tool

Close unresponsive apps and processes

When your system is acting sluggish or simply not responding, an app or process may be the source of the problem. You can use Activity Monitor to locate the troublesome app or process and force it to quit.

CrystalDiskMark by Hiyohiyo is a free to use HDD benchmarking tool that will help you measure the read/write speeds of your hard drives. Even though there is no version of CrystalDiskMark for Mac available at the moment, you can download other programs that can help you test and monitor the speed of your hard drives. Download this app from Microsoft Store for Windows 10, Windows 8.1. See screenshots, read the latest customer reviews, and compare ratings for Disk Benchmark.

• General Mac Performance Test. There are apps available in the market that are mainly used for Mac speed test. However, the easiest to use and the most widely recommended is the Geekbench 4 or GB4 by Primate Labs. Aside from Mac, you can also use it to benchmark iPhones and iPads.
• The Only Bench You'll Ever Need. Xbench was developed by Spiny Software to provide a comprehensive benchmarking solution for Mac OS X. Xbench is useful not only for comparing the relative speeds of two different Macintoshes, but also for optimizing performance on a single machine.

See how much energy your Mac is using

You can find out how much energy your Mac is using, and see which apps or processes are using the most energy.

See real-time CPU, network, or disk status in the Dock

It’s easy to keep an eye on your system status without even looking at the Activity Monitor window—you can monitor your CPU, network, or disk usage as a live graph right in the Dock.

To browse the Activity Monitor User Guide, click Table of Contents at the top of the page.

Thanks. The submission had the same command twice, and as it was anonymous, I couldn't contact the poster. I did some Googling and found that second command. It seemed to work for me, but I've changed it in the hint.

The read speed test is flawed as written. Using /dev/zero as dd's input and output file doesn't hit the disk at all and will return ridiculous speeds like 15-20 GB/sec. The proper way to do the read test is to be to dd the tstfile created by the write benchmark into /dev/null (but only after clearing the RAM cache by using the 'purge' command).
This one-liner will test the write speed, clear the cache, properly test the read speed, and then remove tstfile to reclaim disk space:
dd if=/dev/zero bs=1024k of=tstfile count=1024 && purge && dd if=tstfile bs=1024k of=/dev/null count=1024 && rm tstfile

Here's what I get using this method (and dividing by 1048576 to get Mb/sec):
Internal laptop hd (7200 rpm, sata): Write=42.99 Mb/sec, Read=38.09 Mb/sec
External G-Raid (esata): Write=134.76 Mb/sec, Read=192.32 Mb/sec
External Seagate hd (laptop drive, USB-2): Write=33.59 Mb/sec, Read=36.38 Mb/sec
External G-Raid (Firewire 800): Write=60.79 Mb/sec, Read=66.17 Mb/sec
Encrypted sparsebundle image on external G-Raid above (esata): Write=68.66 Mb/sec, Read=81.33 Mb/sec

That's not really very fast for Thunderbolt.
I bought a Factory Refurb LaCie Little Big Drive for $229 (LaCie.com), removed the drives and the fan, and replaced the drives with a pair of SSDs. Using RAID0, I get around 450MB/s read and 360MB/s write speeds with every test I've tried. It's much faster than the internal SSD in my 2011 iMac.

The freeware Xbench's Disk Test offers a nice method for getting a few different kinds of disk benchmarks.

Atto Disk Benchmark For Mac

Also keep in mind it's only as fast as your system's slowest bottleneck. I realized this myself when I recently upgraded my internal HDD to SSD. Obviously I didn't do proper research. I got a top of the line model and was expecting super fast speeds around 460MB/s on SATA-III, only to realize that my 2008 MBP only has SATA-I so I get about 120 MB/s.
Probably still faster than HDD, but I never did measure the speed before I upgraded.

You wouldn't save a great deal of money going sata-I or II ssd and this way you are future proof if you'll get a new mac.

That thought had occurred to me too. However if I was going to upgrade my Macbook Pro the new one would probably already have SSD and wouldn't be user-replaceable (like in the new Retina Display version)

When I tried:
time dd if=/dev/zero bs=1024k of=tstfile count=1024 2>&1 | grep sec | awk '{print 'scale = 2 ; '$(NF-1048576) '}' | bc
I got:
awk: non-terminated string }cale = 2 ... at source line 1
context is
>>> <<<
awk: giving up
source line number 2
Mac OS X Lion 10.7.4

Disk Benchmark Mac Os X

That awk line has an extra quote, it appears.
Any way, I found that this works:
time dd if=/dev/zero bs=1024k of=tstfile count=1024 2>&1 | grep sec | awk '{print $1 / 1024 / 1024 / $5, 'MB/sec' }'
You don't need bc at all, awk can do the arithmetic. I am dividing the total bytes by the total seconds and by
By the way, my standard internal drive in my 27' iMac (2.8GHz, a couple of years old) did the writing at 91 MB/sec.

Mac Benchmark Tool

Even better, leave out grep also. Awk can do its own pattern matching:
time dd if=/dev/zero bs=1024k of=tstfile count=1024 2>&1 | awk '/sec/ {print $1 / $5 / 1048576, 'MB/sec' }'


One additional thing that might be worth mentioning...your test file (tstfile) should be larger than the amount of physical ram.
This prevents caching and artificially inflated read speeds. Allow me to demo this on my snazzy new iMac with the PCI-e drive...
The system has 16GB of ram, a 3.5 GHz i7 and 512 GB PCI-e SSD:
madht@host (]> 01:19:24
~> time dd if=/dev/zero bs=2048k of=tstfile count=1024 2>&1 | awk '/sec/ {print $1 / $5 / 1048576, 'MB/sec' }'
732.213 MB/sec
real 0m3.278s
user 0m0.002s
sys 0m1.155s
Wow faaaast writes - love this drive...
now check the file size
madht@host (]> 01:20:12
~>ls -al tstfile
-rw-r--r--+ 1 user staff 2147483648 Jan 4 13:30 tstfile
2GB, way less than 16GB.
Now lets Read it back...
madht@host (]> 01:30:19
~> time dd if=tstfile bs=2048k of=/dev/null count=1024 2>&1 | awk '/sec/ {print $1 / $5 / 1048576, 'MB/sec' }'
6262.12 MB/sec
real 0m0.329s
user 0m0.002s
sys 0m0.329s
Mother of God!! 6.2 GB/sec!!
Hmmm....that can't be right.
So lets try a much larger test file.
NOTE: The file size does not *need* to exceed your total ram, just the amount you have free. If you feel this is a valuable use of your time ;) hint, hint -- then adjust block sizes and counts to just exceed the amount of free memory you have available.
Here Goes with a 16GB file:
madht@host (]> 01:30:44
~> time dd if=/dev/zero bs=2048k of=tstfile count=8192 2>&1 | awk '/sec/ {print $1 / $5 / 1048576, 'MB/sec' }'
728.792 MB/sec
real 0m22.583s
user 0m0.007s
sys 0m5.543s
Still bloody fast writes, yum.
Check the size (I always do)
madht@host (]> 01:42:45
~>ls -al tstfile
-rw-r--r--+ 1 user staff 17179869184 Jan 4 13:42 tstfile
Yep, that one there is a whale that can't be crammed into my ram.
madht@host (]> 01:42:49
~> time dd if=tstfile bs=2048k of=/dev/null count=8192 2>&1 | awk '/sec/ {print $1 / $5 / 1048576, 'MB/sec' }'
779.598 MB/sec
real 0m21.018s
user 0m0.006s
sys 0m4.323s
Aaaah much more like it. And still pretty performant, yo.
One more thing to add and I don't know if was already mentioned or not tl:dr -- this is a sequential test only. iow - this is as fast as it gets and in no way indicative of how your drive performs when ~30-50% of its reads and writes are random - i.e. during regular multi application usage of the OS. ioMeter is the best open source benchmarker out there however they don't fully support OSX, just the worker engine binaries -- so iometer itself would have to run on a separate machine. But it's doable ;)

Would anyone be able to tell me how to use these commands to test my USB 3.0 drives or Thunderbolt drives?