2017-07-16 - SEND FEEDBACK
Search for:
Macs,
how-to,
MacBook Pro,
2017 iMac 5K,
MacBook Pro and MacBook,
Thunderbolt,
Photoshop,
Lightroom Related:
Macs,
how-to,
software,
MacBook Pro,
iMac,
2017 iMac 5K,
MacBook Pro and MacBook,
Thunderbolt,
Photoshop,
LightroomI came across a curious thing: when measuring power usage for 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!
How could this be that there is 2.5X increased power draw with the OWC TB3 Dock? MemoryTester is part of diglloydTools; its stress command shows memory bandwidth as it runs.
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.
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.
Memory bandwidth varies by power source in 2017 MacBook Pro: Apple power brick vs OWC Thunderbolt 3 Dock
Figures obtained using diglloydTools MemoryTester
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.
View iMac 5K at B&H Photo and see also MPG’s computer gear wishlist. Not sure which Mac to get or how to configure it? Consult with MPG.
Testing Adobe Photoshop Lightroom (or Photoshop) often shows modest speed gaps between computers that ought to diverge more strongly, e.g., an 8 core system runs only 20% faster than a 4 core system—or more slowly.
Some of the unharvested speed potential seen in applications is due to clock speed differences (e.g., 3.5 vs 4.2 GHz), but that is not enough to explain why 6 or 8 or 10 or 12 cores run only marginally faster than 4 cores.
Speaking in general, here are just a few reasons that speed is not faster on machines with more CPU cores (these comments are not about Adobe software, but many do apply in at least some cases):
- Serializing I/O with computation
- Serializing computational steps that could run in parallel.
- Failure to use more than one CPU core at all. Or at certain steps of the computation, thus creating a choke point that limits peak speed.
- Busy waiting (Topaz InFocus with 2 cores = 12 cores due to this severe bug).
- Failing to use large enough memory buffers for disk I/O or other purposes.
- Allocating and disposing of memory at high frequency, instead of maintaining a cache.
- Failing to cache computational results that can be re-used.
- Inappropriate queuing mechanisms or simply a lack not using job or I/O queues.
- Using less than optimal algorithms e.g., an O(n^2) algorithm instead of an O(nLog(n)) algorithm, even for a short while, creating choke points that throttle performance.
- Failure to do obvious things, like process 8 files in parallel on an 8 core CPU, together with appropriate I/O queues.
The reason for impaired performance that does not scale on machines it ought to is algorithmic inefficiency, that is, a failure optimize the computational process and even a failure to take trivially easy steps, like using appropriate I/O sizes for exploiting the full speed of today’s flash drives (SSDs). If Adobe did the job better, we’d all get a free speed boost.
Shown below is CPU usage during an Export job (see the test results). Notice how there is a regular spiky dip or valley in the CPU usage, indicating that the CPU cores go idle on a periodic basis.
Checking Activity Monitor as well as a Watts Up electricity meter, these dips appear to correspond to I/O activity. Even though the iMac 5K SSD is very fast, there are at least two reasons the CPU cores are forced to idle:
- Lightroom appears to serialize I/O with computation (akin to stop lights smack dab in the interstate highway) instead of using separate work queues and an I/O read-ahead queue and an I/O write queue. The result is that CPU cores are forced to idle while waiting for I/O to complete. That’s a beginner mistake in my book.
- While the iMac 5K SSD is very fast, its speed is only half of its peak speed up to 2MB I/O sizes, that is, I/O sizes of 64MB or so are required for maximum seed. And yet Lightroom apparently never uses I/O sizes larger than 1MB, thus cutting the peak I/O speak to less than half of what is possible. See the iostat figures further below. So the I/O takes more than double the time necessary and it is apparently serialized with computation.
The I/O speed thing is a trivial fix: at the least, read the raw file in a single read—that’s a no-brainer. Then use I/O queues for both input and input (hard to do but not very hard).
CPU usage during Lightroom Export
2017 iMac 5K
What iostat shows about Lightoom I/O
The iostat results show that Lightroom never performs I/O in sizes larger than 1MB, which means using less than half the speed potential of the SSD.
Half-speed I/O creates a choke point that manifests in the failure of an 8-core 3.3 GHz Mac Pro to run more than modestly faster than a 4-core 4.2 GHz iMac 5K, indeed, slower for an Import operation. How much the I/O is the issue cannot be easily told, but it is surely a factor and those running hard drive of Fusion drive will be impacted much more severely.
As a crude measure of CPU cores and clock speed:
8 * 3.3 = 26.4 GHz of CPU core = 1.57X more cycles (but slower SSD)
4 * 4.2 = 16.8 GHz of CPU core
iMac:DIGLLOYD lloyd$ iostat -dK -w 1
disk0
KB/t tps MB/s
298.59 13 3.79
88.00 3 0.26
4.00 2 0.01
0.00 0 0.00
18.00 4 0.07
32.00 1 0.03
72.00 2 0.14
8.00 1 0.01
29.00 4 0.11
932.42 122 111.54
197.87 395 76.31
8.00 2 0.02
0.00 0 0.00
28.00 6 0.16
8.00 3 0.02
4.00 2 0.01
30.05 39 1.14
64.62 13 0.82
36.00 1 0.03
12.71 56 0.69
disk0
KB/t tps MB/s
686.95 198 132.81
880.80 30 25.67
6.67 3 0.02
4.00 2 0.01
5.78 9 0.05
4.00 1 0.00
0.00 0 0.00
28.00 3 0.08
17.33 3 0.05
0.00 0 0.00
1024.00 32 31.96
907.16 151 134.06
30.00 2 0.06
4.80 5 0.02
8.00 3 0.02
4.00 1 0.00
4.00 1 0.00
8.00 1 0.01
256.00 1 0.25
0.00 0 0.00
disk0
KB/t tps MB/s
14.23 95 1.32
782.66 165 125.97
917.48 62 55.53
5.00 4 0.02
0.00 0 0.00
5.60 5 0.03
4.00 1 0.00
4.00 1 0.00
6.00 2 0.01
4.00 1 0.00
1024.00 24 23.97
628.74 129 79.11
904.27 89 78.50
988.57 7 6.75
6.00 2 0.01
4.00 1 0.00
0.00 0 0.00
4.00 1 0.00
256.00 2 0.50
0.00 0 0.00
Well optimized
Below, this is what one ought to see with a well optimized program that is CPU intensive. Note the lack of any dropouts in CPU usage. The graph is from an IntegrityChecker verify invocation (IntegrityChecker is part of diglloydTools).
CPU usage during Lightroom Export
2017 iMac 5K
SEARCH
diglloydTools™
