uwnetworkslab/meshinsight

MeshInsight: Dissecting Overheads of Service Mesh Sidecars

meshinsight's Issues

ValueError: Input y contains NaN

Hi
I was getting the below error after running offline profiler for meshinsight:

Traceback (most recent call last):
  File "./meshinsight/profiler/offline_profiler.py", line 604, in <module>
    latency_models = build_latency_model(latency_profile, request_sizes, p)
  File "./meshinsight/profiler/offline_profiler.py", line 271, in build_latency_model
    models['read_reg'] = linear_regression("read", read_data)
  File "./meshinsight/profiler/offline_profiler.py", line 262, in linear_regression
    reg = LinearRegression().fit(X, y)
  File "/home/ryzen02/.local/lib/python3.8/site-packages/sklearn/linear_model/_base.py", line 648, in fit
    X, y = self._validate_data(
  File "/home/ryzen02/.local/lib/python3.8/site-packages/sklearn/base.py", line 584, in _validate_data
    X, y = check_X_y(X, y, **check_params)
  File "/home/ryzen02/.local/lib/python3.8/site-packages/sklearn/utils/validation.py", line 1122, in check_X_y
    y = _check_y(y, multi_output=multi_output, y_numeric=y_numeric, estimator=estimator)
  File "/home/ryzen02/.local/lib/python3.8/site-packages/sklearn/utils/validation.py", line 1132, in _check_y
    y = check_array(
  File "/home/ryzen02/.local/lib/python3.8/site-packages/sklearn/utils/validation.py", line 921, in check_array
    _assert_all_finite(
  File "/home/ryzen02/.local/lib/python3.8/site-packages/sklearn/utils/validation.py", line 161, in _assert_all_finite
    raise ValueError(msg_err)
ValueError: Input y contains NaN.

Before this error I was also getting some runtime warnings

/home/ryzen02/.local/lib/python3.8/site-packages/numpy/core/fromnumeric.py:3464: RuntimeWarning: Mean of empty slice.
  return _methods._mean(a, axis=axis, dtype=dtype,
/home/ryzen02/.local/lib/python3.8/site-packages/numpy/core/_methods.py:192: RuntimeWarning: invalid value encountered in scalar divide
  ret = ret.dtype.type(ret / rcount)
/home/ryzen02/.local/lib/python3.8/site-packages/numpy/core/_methods.py:269: RuntimeWarning: Degrees of freedom <= 0 for slice
  ret = _var(a, axis=axis, dtype=dtype, out=out, ddof=ddof,
/home/ryzen02/.local/lib/python3.8/site-packages/numpy/core/_methods.py:226: RuntimeWarning: invalid value encountered in divide
  arrmean = um.true_divide(arrmean, div, out=arrmean,
/home/ryzen02/.local/lib/python3.8/site-packages/numpy/core/_methods.py:261: RuntimeWarning: invalid value encountered in scalar divide

I am running meshinsight on Ubuntu18.04 , kernel version 4.15 , python3.8 and istio 1.18.0.

Change call graph format from txt to Yaml/JSON

[Error] Failed to attach BPF program b'trace_func_entry' to kprobe

Hello,
I use Ubuntu 20.04, and meshinsight commit is f2e2142c5d5fe641ddc4a8675614c2d10e9eac5f

Author: lbr <[email protected]>
Date:   Sat Mar 25 21:56:20 2023 -0400

    set default CNI to flannel

wenn i run

sudo python3 ./meshinsight/profiler/offline_profiler.py --latency --cpu -v

I received the error:

29-Mar-23 22:43:10 |    DEBUG | Running cmd: python3 /home/naibaoofficial/projects/meshinsight/meshinsight/profiler/latency/funclatency_filter.py -p 114620 ep_send_events_proc -d 30 -t 0
Traceback (most recent call last):
  File "/home/naibaoofficial/projects/meshinsight/meshinsight/profiler/latency/funclatency_filter.py", line 380, in <module>
    b.attach_kprobe(event_re=pattern, fn_name="trace_func_entry")
  File "/usr/lib/python3/dist-packages/bcc/__init__.py", line 835, in attach_kprobe
    raise Exception("Failed to attach BPF program %s to kprobe %s"
Exception: Failed to attach BPF program b'trace_func_entry' to kprobe , it's not traceable (either non-existing, inlined, or marked as "notrace")

The python context is:

# load BPF program
b = BPF(text=bpf_text)

# attach probes
if not library:
    b.attach_kprobe(event_re=pattern, fn_name="trace_func_entry")
    b.attach_kretprobe(event_re=pattern, fn_name="trace_func_return")
    matched = b.num_open_kprobes()

Could anyone help me to fix it?
Thank you

Better description and example for annotated call graph

Integrate critical path analysis tools in MeshInsight

For example, https://github.com/uber-research/CRISP or https://gitlab.engr.illinois.edu/DEPEND/firm

Better failure handling in offline profiler

Add citation file

https://docs.github.com/en/repositories/managing-your-repositorys-settings-and-features/customizing-your-repository/about-citation-files

Exception: Failed to compile BPF module <text>

I am facing the following error after running the code for Meshinsight's profiler:

ryzen02@ryzen02-rs-iiitd:~/meshinsight$ sudo python3 ./meshinsight/profiler/offline_profiler.py --latency --cpu
18-Jun-23 18:35:42 |     INFO | Starting latency profiling!
In file included from /virtual/main.c:2:
In file included from include/uapi/linux/ptrace.h:143:
In file included from ./arch/x86/include/asm/ptrace.h:5:
./arch/x86/include/asm/segment.h:266:2: error: expected '(' after 'asm'
        alternative_io ("lsl %[seg],%[p]",
        ^
./arch/x86/include/asm/alternative.h:240:2: note: expanded from macro 'alternative_io'
        asm_inline volatile (ALTERNATIVE(oldinstr, newinstr, feature)   \
        ^
include/linux/compiler_types.h:214:24: note: expanded from macro 'asm_inline'
#define asm_inline asm __inline
                       ^
/virtual/main.c:53:9: error: no member named 'atomic_increment' in 'struct avg_table_t'
    avg.atomic_increment(lat, delta);
    ~~~ ^
/virtual/main.c:54:9: error: no member named 'atomic_increment' in 'struct avg_table_t'
    avg.atomic_increment(cnt);
    ~~~ ^
/virtual/main.c:59:10: error: no member named 'atomic_increment' in 'struct dist_table_t'
    dist.atomic_increment(bpf_log2l(delta));
    ~~~~ ^
4 errors generated.
Traceback (most recent call last):
  File "/home/ryzen02/meshinsight/meshinsight/profiler/latency/funclatency.py", line 345, in <module>
    b = BPF(text=bpf_text)
  File "/usr/lib/python3/dist-packages/bcc/__init__.py", line 343, in __init__
    raise Exception("Failed to compile BPF module %s" % (src_file or "<text>"))
Exception: Failed to compile BPF module <text>
Traceback (most recent call last):
  File "./meshinsight/profiler/offline_profiler.py", line 596, in <module>
    syscall_overhead  = profile_syscall(args.duration)
  File "./meshinsight/profiler/offline_profiler.py", line 41, in profile_syscall
    result = subprocess.run(cmd, stdout=subprocess.PIPE, check=True)
  File "/usr/lib/python3.8/subprocess.py", line 512, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['python3', '/home/ryzen02/meshinsight/meshinsight/profiler/latency/funclatency.py', '-p 6234', 'c:getpid', '-d 30']' returned non-zero exit status 1.

I am using Linux kernel version 5.4.0 , Ubuntu 18.04, Python 3.8, libllvm 6.0 , libclang 6.0 , llvm 6.0

I would be obliged if someone can help with this !

Add support for filters

Integrate what-if analysis into MeshInsight