When I run my app in debug mode, whenever a time consuming task is run (like a core data fetch request) there is a time indication appearing on top of the view. I am unable to find the meaning of this and how it is named.
It looks like:
"appName NNNN ms"
(it is not caught by the screen shot)
Can someone tell if it is possible to get rid of it and how ? Thanks for your help !
Instruments
RSS for tagInstruments is a performance-analysis and testing tool for iOS, iPadOS, watchOS, tvOS, and macOS apps.
Posts under Instruments tag
94 Posts
Sort by:
Post
Replies
Boosts
Views
Activity
I have the Vision Pro developer strap, do I need to do anything to make Instruments transfer the data over it rather than wifi? Or will it do that automatically?
It seems incredibly slow for transferring and then analysing data.
I can see the Vision Pro recognised in Configurator, so assume it's working.
Otherwise.. Any tips for speeding up Instruments? Capturing 5 mins of gameplay (high-freq) then takes 30-40+ mins to appear in Instruments on an M2 Max 32gb.
Thanks!
I'm currently supporting an app where one of the dependencies we use had an update. The app is an iPad only app that is meant to be run as a kiosk (guided access, single app mode). After the dependency update for the casing of the tablet / kiosk, we noticed an uptick in errors that may or may not have been associated with the recent 3rd party software update.
I wanted to verify if the update had an impact on our production kiosks. To get a good idea of whether or not the update for casework's library had a negative impact, though, I would need to run instruments on a tablet while it's in the case. There's only one power cable to the iPad and the cable that would be used to connect directly to a Mac / Xcode is the same cable that connects to the casework.
Is it possible to run instruments, and then retrieve data, from an app that's not directly connected to Xcode? Or is it possible for Xcode to somehow connect via a running instance of an app remotely?
We're planning to integrate performance profiling tool into our own Application.
The standard tool is Xcode Instruments, which is great but requires Xcode to be installed.
I have couple of queries related to that.
Is there a way to use Instruments without clients needing to install Xcode?
If not, then can we include Xcode installation as part of my application installation in the customer machine?
I saved a trace from the Leaks tool. However when I try to open the saved file, I get an error that says, "The document 'Generations.trace' could not be opened. Trace is malformed - run data is missing." This happens every time I try to save from Instruments.
I'm using Instruments 15.3. Any ideas?
We are getting crash issue in our WKWebkit based Cordova application due to memory issues. However, for debugging the memory issue we are trying to use JavaScript allocations in the memory profiler of instruments. and while using it, the profiler automatically closes within few seconds, and we are not able to debug the underlaying memory issue in the WKWebKit. I
Is there way to identify process which is handling a global keyboard shortcut? Let's say I press some CMD-ALT-L in any application, some file shows up on disk and there is no any kind of visual indication of where it's coming from. How do I find the offender?
I've been seeing warning like the following with my Apple Watch app:
=== AttributeGraph: cycle detected through attribute 140952 ===
=== AttributeGraph: cycle detected through attribute 131640 ===
=== AttributeGraph: cycle detected through attribute 131640 ===
=== AttributeGraph: cycle detected through attribute 131640 ===
=== AttributeGraph: cycle detected through attribute 131640 ===
=== AttributeGraph: cycle detected through attribute 131640 ===
=== AttributeGraph: cycle detected through attribute 131640 ===
I've done some debugging with Instruments and Xcode, I've determined that its caused by adding a
.toolbar {
ToolbarItemGroup(placement: .topBarTrailing) {
Label("Stop", systemImage: "xmark")
}
}
to an item within my NavigationSplitView List Destination view.
To aid reproduction of this issue even more, I've verified the same warning occurs with the Apple sample code from the WWDC23 Backyard Birds app.
https://developer.apple.com/documentation/swiftui/backyard-birds-sample?changes=_9
If you take the Apple sample code, open it in Xcode 15.4 and run it in the Apple Watch WatchOS 10.5 simulator, then select the Bird Springs item, all is well.
If you then add the above toolbar code to the BackyardSummaryTab file at the bottom of the VStack, you'll see the same AttributeGraph issues I'm seeing in my app.
Is this a bug? I can't understand why adding a static ToolBarItem in WatchOS is causing this.
I've seen this issue in the simulator and also on device.
Error when trying to generate CoreML performance report, message says
The data couldn't be written because it isn't in the correct format.
Here is the code to replicate the issue
import numpy as np
import coremltools as ct
from coremltools.converters.mil import Builder as mb
import coremltools.converters.mil as mil
w = np.random.normal(size=(256, 128, 1))
wemb = np.random.normal(size=(1, 32000, 128)) # .astype(np.float16)
rope_emb = np.random.normal(size=(1, 2048, 128))
shapes = [(1, seqlen) for seqlen in (32, 64)]
enum_shape = mil.input_types.EnumeratedShapes(shapes=shapes)
fixed_shape = (1, 128)
max_length = 2048
dtype = np.float32
@mb.program(
input_specs=[
# mb.TensorSpec(enum_shape.symbolic_shape, dtype=mil.input_types.types.int32),
mb.TensorSpec(enum_shape.symbolic_shape, dtype=mil.input_types.types.int32),
],
opset_version=mil.builder.AvailableTarget.iOS17,
)
def flex_like(input_ids):
indices = mb.fill_like(ref_tensor=input_ids, value=np.array(1, dtype=np.int32))
causal_mask = np.expand_dims(
np.triu(np.full((max_length, max_length), -np.inf, dtype=dtype), 1),
axis=0,
)
mask = mb.gather(
x=causal_mask,
indices=indices,
axis=2,
batch_dims=1,
name="mask_gather_0",
)
# mask = mb.gather(
# x=mask, indices=indices, axis=1, batch_dims=1, name="mask_gather_1"
# )
rope = mb.gather(x=rope_emb.astype(dtype), indices=indices, axis=1, batch_dims=1, name="rope")
hidden_states = mb.gather(x=wemb.astype(dtype), indices=input_ids, axis=1, batch_dims=1, name="embedding")
return (
hidden_states,
mask,
rope,
)
cml_flex_like = ct.convert(
flex_like,
compute_units=ct.ComputeUnit.ALL,
compute_precision=ct.precision.FLOAT32,
minimum_deployment_target=ct.target.iOS17,
inputs=[
ct.TensorType(name="input_ids", shape=enum_shape),
],
)
cml_flex_like.save("flex_like_32")
If I remove the hidden states from the return it does work, and it also works if I keep the hidden states, but remove both mask, and rope, i.e, the report is generated for both programs with either these returns:
return (
# hidden_states,
mask,
rope,
)
and
return (
hidden_states,
# mask,
# rope,
)
It also works if I use a static shape instead of an EnumeratedShape
I'm using macOS 15.0 and Xcode 16.0
Edit 1:
Forgot to mention that although the performance report fails, the model is still able to make predictions
the downloads button in safari keeps flickering and cannot be pressed no matter what.
I have been able to get rid of reported memory leaks in Instruments not by fixing a leak but by adding some lines (like releasing a previous nil object) that convinced Instruments it is not a leak.
But I am stuck are some I cannot stop Instruments from reporting. It reports a leak in this code
if(expr.length>0)
{ // add previous Atomic
Atomic *atom = [[Atomic alloc] initWithString:[string substringWithRange:expr] isNumber:aNum];
[exprTokens addObject:atom];
[atom release];
}
}
and it underlines the substringWithRange method. I changed code to explicitly release atom and I assumed substringWithRange would return an autoreleased new string. I am aware Instruments tells you where the leaked object is created and not where it is leak, but only things created here are atom and a sub string and atom is released immediately.
The initWithString method might do it, but I don't find anything there. Also, while running instruments, this code is 8542 times (I am pretty sure always in the same context) and Instruments says it only leaks 61 times.
I don't now if there is misunderstanding are a code problem?
We have observed for a few months that the Instruments tool in Xcode does not show correct memory allocation for the PacketTunnelProvider process on iOS 17. The memory allocation does not exceed 6-7 MB, which is not the case with iOS 16 or 15. Additionally, Instruments crashes the PacketTunnelProvider process after profiling for a few minutes.
Please note that I am not running Xcode in debugger mode for the PacketTunnelProvider process along with instruments, as this is a known issue that causes the PacketTunnelProvider to be killed when both Instruments and the Xcode debugger are running.
Is anyone else facing this issue and have a workaround?
Good day.
I'm having problems debugging hangs. Watched the video WWDC Analyze hangs with Instruments. Apparently the main thread is blocked. It’s just not possible to analyze what exactly is blocking the flow. Please help me figure it out.
https://drive.google.com/file/d/1QvFK4y79CG0fBMrJPOrBCTuWsOaqichY/view?usp=share_link <- trace
Hello,
I see the Instruments app has gotten a nice upgrade for Xcode 16. There is one issue left that has been bothering me though.
If my app is installed inside the "Application" folder, and I then try to launch Instruments for a new build of the same app from within XCode, Instruments will run the app installed in "Applications" instead of running the app I just built.
The problem with this, is that it's very easy to accidentally profile an old version of your app, and come to the wrong conclusions.
I've created a video showing this issue: https://youtu.be/IloFsQQFgSw