Apple Bug? 2017 MacBook Pro Has Impaired Performance Using Apple Power Brick vs OWC Thunderbolt 3 Dock + Why Does 800% CPU Usage Go Into Idle Clock Speed Mode?
Mac wish list • all 15" Apple MacBook Pro 2017 models • MPG gets credit if you buy through those links.
MPG tested a fully-loaded 2017 MacBook Pro with 1TB SSD.
Suggested accessories include the OWC Thunderbolt 3 Dock, the 1TB Envoy Pro EX.
I came across a curious thing: when measuring power usage @AMAZONfor the 2017 MacBook Pro, I found that the total power draw at 800% CPU usage was 58 watts with the OWC Thunderbolt 3 Docks, but only 24 watts with the Apple power brick. The OWC TB3 Dock did not even get warm even aas the MacBook Pro ran its fan much louder and got much hotter than when powered by the Apple power brick!
What it confirms is that the OWC Thunderbolt 3 Dock somehow persuades the 2017 MacBook Pro to run at higher performance! Surely this is an Apple bug of some kind related to the disappointing performance; see 2017 MacBook Pro: Severely Degraded Performance for More than Short Usage (and also applies to 2016 MBP).
Power draw will vary by application load and the Thunderbolt 3 Dock doesn't cause the MacBook Pro to draw more*, but it appears that the OWC Thunderbolt 3 Docks enables higher performance versus the Apple power brick. Since the Apple power brick is rated at 85 watts this is a strange finding; it suggests an Apple power management bug.
* Measured power draw of the OWC Thunderbolt 3 Dock is about 11 watts when the MacBook Pro is idle.
Lower performance with the Apple power brick is consistent with but does not fully explain the performance drop under load seen in prior tests. It suggests an Apple power management bug that throttles performance with the Apple power brick, but not the OWC Thunderbolt 3 Dock.
Supporting this contention are the following:
- Performance (memory bandwidth) is higher by 8.5% using the OWC Thunderbolt 3 Dock.
- A this higher performance the MacBook Pro gets hotter (determined by feeling bottom of the MBP case), and runs its fans at an higher/louder level—the difference is easy to hear.
- Swapping the OWC TB3 cable out for the Apple-supplied cable immediately droppedthe TB3 Dock power usage by 10 watts, and produced the same lower performance as with the Apple power brick. The Apple cable is useless for the Dock as well, since it is not a TB3 cable (system message pops up saying can't use Thunderbolt).
- OWC TB3 cable on Apple power brick also delivers the lower performance. So it seems that the *both* the Apple power brick and its cable suck.
Tests were repeated half a dozen times, swapping the power sources into the same port on the MacBook Pro—100% repeatable. At this time, there is no evidence that Photoshop and other benchmarks and/or IntegrityChecker will run faster with OWC Thunderbolt 3 Dock power. But the differing memory bandwidth and power draw are 100% reproducible every time the power source is switched. Strange. Reader Jeffrey L suggests Intel’s Power Gadget tool.
Clock speed drop to about 1.8 GHz
Check out these two graphs, obtained via the Intel Power Gadget.
Running the verify command in IntegrityChecker (part of diglloydTools), all 8 virtual CPU cores were running full tilt (800% CPU usage or close to it). As the test started, power consumption rose sharply to 72 watts, then declined. The reason becomes clear from the graphs below.
The graphs raise more questions than they answer. In particular, why does a 3.2 GHz CPU (turbo boost to 3.6 GHz) suddenly plumet to about 1.8 GHz and stay there for a long time? And why at other times does it stick nicely at 3.6 GHz?
From what I can tell, there is some kind of performance bug in which macOS takes the CPU speed down to 1.8 GHz or so even when 800% CPU usage is constant. That behavior is seen in the two leftmost graphs. For the graph at right, the dip is an end to the job and some idle time, then the job is repeated. Note that clock speed when idle is similar to clock speed under 800% CPU load! This would explain the weird sluggishness that I’ve experienced all too often with the 2016 and 2017 MacBook Pro—strange sluggish pauses. That would make sense if the CPU clock speed were throttled down to half speed or so.
There is another possible explanation, but it’s a guess: could it be that the clock speed is dropp during the MemoryTester stress command because memory bandwidth won’t support any faster execution speed? That would make sense: 8 virtual CPUs running on a 2133 MHz memory bus. Some techo-nerd out there might be able to confirm that as a theory. Reader Greg writes that it might have to do with introduction of Intel SpeedShift.