# Put this at the top of the Python script
import os
from nvitop import select_devices

os.environ['CUDA_VISIBLE_DEVICES'] = ','.join(
    select_devices(format='uuid', min_count=4, min_free_memory='8GiB')
)

from tensorflow.python.keras.utils.multi_gpu_utils import multi_gpu_model
from tensorflow.python.keras.callbacks import TensorBoard
from nvitop.callbacks.keras import GpuStatsLogger
gpus = ['/gpu:0', '/gpu:1']  # or `gpus = [0, 1]` or `gpus = 2`
model = Xception(weights=None, ..)
model = multi_gpu_model(model, gpus)  # optional
model.compile(..)
tb_callback = TensorBoard(log_dir='./logs')  # or `keras.callbacks.CSVLogger`
gpu_stats = GpuStatsLogger(gpus)
model.fit(.., callbacks=[gpu_stats, tb_callback])

from lightning.pytorch import Trainer
from nvitop.callbacks.lightning import GpuStatsLogger
gpu_stats = GpuStatsLogger()
trainer = Trainer(gpus=[..], logger=True, callbacks=[gpu_stats])

from nvitop import Device

devices = Device.all()  # or `Device.cuda.all()` to use CUDA ordinal instead
for device in devices:
    processes = device.processes()  # type: Dict[int, GpuProcess]
    sorted_pids = sorted(processes.keys())

    print(device)
    print(f'  - Fan speed:       {device.fan_speed()}%')
    print(f'  - Temperature:     {device.temperature()}C')
    print(f'  - GPU utilization: {device.gpu_utilization()}%')
    print(f'  - Total memory:    {device.memory_total_human()}')
    print(f'  - Used memory:     {device.memory_used_human()}')
    print(f'  - Free memory:     {device.memory_free_human()}')
    print(f'  - Processes ({len(processes)}): {sorted_pids}')
    for pid in sorted_pids:
        print(f'    - {processes[pid]}')
    print('-' * 120)

import time

from nvitop import Device, GpuProcess, NA, colored

print(colored(time.strftime('%a %b %d %H:%M:%S %Y'), color='red', attrs=('bold',)))

devices = Device.cuda.all()  # or `Device.all()` to use NVML ordinal instead
separator = False
for device in devices:
    processes = device.processes()  # type: Dict[int, GpuProcess]

    print(colored(str(device), color='green', attrs=('bold',)))
    print(colored('  - Fan speed:       ', color='blue', attrs=('bold',)) + f'{device.fan_speed()}%')
    print(colored('  - Temperature:     ', color='blue', attrs=('bold',)) + f'{device.temperature()}C')
    print(colored('  - GPU utilization: ', color='blue', attrs=('bold',)) + f'{device.gpu_utilization()}%')
    print(colored('  - Total memory:    ', color='blue', attrs=('bold',)) + f'{device.memory_total_human()}')
    print(colored('  - Used memory:     ', color='blue', attrs=('bold',)) + f'{device.memory_used_human()}')
    print(colored('  - Free memory:     ', color='blue', attrs=('bold',)) + f'{device.memory_free_human()}')
    if len(processes) > 0:
        processes = GpuProcess.take_snapshots(processes.values(), failsafe=True)
        processes.sort(key=lambda process: (process.username, process.pid))

        print(colored(f'  - Processes ({len(processes)}):', color='blue', attrs=('bold',)))
        fmt = '    {pid:<5}  {username:<8} {cpu:>5}  {host_memory:>8} {time:>8}  {gpu_memory:>8}  {sm:>3}  {command:<}'.format
        print(colored(fmt(pid='PID', username='USERNAME',
                          cpu='CPU%', host_memory='HOST-MEM', time='TIME',
                          gpu_memory='GPU-MEM', sm='SM%',
                          command='COMMAND'),
                      attrs=('bold',)))
        for snapshot in processes:
            print(fmt(pid=snapshot.pid,
                      username=snapshot.username[:7] + ('+' if len(snapshot.username) > 8 else snapshot.username[7:8]),
                      cpu=snapshot.cpu_percent, host_memory=snapshot.host_memory_human,
                      time=snapshot.running_time_human,
                      gpu_memory=(snapshot.gpu_memory_human if snapshot.gpu_memory_human is not NA else 'WDDM:N/A'),
                      sm=snapshot.gpu_sm_utilization,
                      command=snapshot.command))
    else:
        print(colored('  - No Running Processes', attrs=('bold',)))

    if separator:
        print('-' * 120)
    separator = True

In [1]: from nvitop import take_snapshots, Device
   ...: import os
   ...: os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID'
   ...: os.environ['CUDA_VISIBLE_DEVICES'] = '1,0'  # comma-separated integers or UUID strings

In [2]: take_snapshots()  # equivalent to `take_snapshots(Device.all())`
Out[2]:
SnapshotResult(
    devices=[
        DeviceSnapshot(
            real=Device(index=0, ...),
            ...
        ),
        ...
    ],
    gpu_processes=[
        GpuProcessSnapshot(
            real=GpuProcess(pid=xxxxxx, device=Device(index=0, ...), ...),
            ...
        ),
        ...
    ]
)

In [3]: device_snapshots, gpu_process_snapshots = take_snapshots(Device.all())  # type: Tuple[List[DeviceSnapshot], List[GpuProcessSnapshot]]

In [4]: device_snapshots, _ = take_snapshots(gpu_processes=False)  # ignore process snapshots

In [5]: take_snapshots(Device.cuda.all())  # use CUDA device enumeration
Out[5]:
SnapshotResult(
    devices=[
        CudaDeviceSnapshot(
            real=CudaDevice(cuda_index=0, nvml_index=1, ...),
            ...
        ),
        CudaDeviceSnapshot(
            real=CudaDevice(cuda_index=1, nvml_index=0, ...),
            ...
        ),
    ],
    gpu_processes=[
        GpuProcessSnapshot(
            real=GpuProcess(pid=xxxxxx, device=CudaDevice(cuda_index=0, ...), ...),
            ...
        ),
        ...
    ]
)

In [6]: take_snapshots(Device.cuda(1))  # <CUDA 1> only
Out[6]:
SnapshotResult(
    devices=[
        CudaDeviceSnapshot(
            real=CudaDevice(cuda_index=1, nvml_index=0, ...),
            ...
        )
    ],
    gpu_processes=[
        GpuProcessSnapshot(
            real=GpuProcess(pid=xxxxxx, device=CudaDevice(cuda_index=1, ...), ...),
            ...
        ),
        ...
    ]
)

In [1]: from nvitop import ResourceMetricCollector, Device
   ...: import os
   ...: os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID'
   ...: os.environ['CUDA_VISIBLE_DEVICES'] = '3,2,1,0'  # comma-separated integers or UUID strings

In [2]: collector = ResourceMetricCollector()                                   # log all devices and descendant processes of the current process on the GPUs
In [3]: collector = ResourceMetricCollector(root_pids={1})                      # log all devices and all GPU processes
In [4]: collector = ResourceMetricCollector(devices=Device(0), root_pids={1})   # log <GPU 0> and all GPU processes on <GPU 0>
In [5]: collector = ResourceMetricCollector(devices=Device.cuda.all())          # use the CUDA ordinal

In [6]: with collector(tag='<tag>'):
   ...:     # Do something
   ...:     collector.collect()  # -> Dict[str, float]
# key -> '<tag>/<scope>/<metric (unit)>/<mean/min/max>'
{
    '<tag>/host/cpu_percent (%)/mean': 8.967849777683456,
    '<tag>/host/cpu_percent (%)/min': 6.1,
    '<tag>/host/cpu_percent (%)/max': 28.1,
    ...,
    '<tag>/host/memory_percent (%)/mean': 21.5,
    '<tag>/host/swap_percent (%)/mean': 0.3,
    '<tag>/host/memory_used (GiB)/mean': 91.0136418208109,
    '<tag>/host/load_average (%) (1 min)/mean': 10.251427386878328,
    '<tag>/host/load_average (%) (5 min)/mean': 10.072539414569503,
    '<tag>/host/load_average (%) (15 min)/mean': 11.91126970422139,
    ...,
    '<tag>/cuda:0 (gpu:3)/memory_used (MiB)/mean': 3.875,
    '<tag>/cuda:0 (gpu:3)/memory_free (MiB)/mean': 11015.562499999998,
    '<tag>/cuda:0 (gpu:3)/memory_total (MiB)/mean': 11019.437500000002,
    '<tag>/cuda:0 (gpu:3)/memory_percent (%)/mean': 0.0,
    '<tag>/cuda:0 (gpu:3)/gpu_utilization (%)/mean': 0.0,
    '<tag>/cuda:0 (gpu:3)/memory_utilization (%)/mean': 0.0,
    '<tag>/cuda:0 (gpu:3)/fan_speed (%)/mean': 22.0,
    '<tag>/cuda:0 (gpu:3)/temperature (C)/mean': 25.0,
    '<tag>/cuda:0 (gpu:3)/power_usage (W)/mean': 19.11166264116916,
    ...,
    '<tag>/cuda:1 (gpu:2)/memory_used (MiB)/mean': 8878.875,
    ...,
    '<tag>/cuda:2 (gpu:1)/memory_used (MiB)/mean': 8182.875,
    ...,
    '<tag>/cuda:3 (gpu:0)/memory_used (MiB)/mean': 9286.875,
    ...,
    '<tag>/pid:12345/host/cpu_percent (%)/mean': 151.34342772112265,
    '<tag>/pid:12345/host/host_memory (MiB)/mean': 44749.72373447514,
    '<tag>/pid:12345/host/host_memory_percent (%)/mean': 8.675082352111717,
    '<tag>/pid:12345/host/running_time (min)': 336.23803206741576,
    '<tag>/pid:12345/cuda:1 (gpu:4)/gpu_memory (MiB)/mean': 8861.0,
    '<tag>/pid:12345/cuda:1 (gpu:4)/gpu_memory_percent (%)/mean': 80.4,
    '<tag>/pid:12345/cuda:1 (gpu:4)/gpu_memory_utilization (%)/mean': 6.711118172407917,
    '<tag>/pid:12345/cuda:1 (gpu:4)/gpu_sm_utilization (%)/mean': 48.23283397736476,
    ...,
    '<tag>/duration (s)': 7.247399162035435,
    '<tag>/timestamp': 1655909466.9981883
}

import os

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.tensorboard import SummaryWriter

from nvitop import CudaDevice, ResourceMetricCollector
from nvitop.callbacks.tensorboard import add_scalar_dict

# Build networks and prepare datasets
...

# Logger and status collector
writer = SummaryWriter()
collector = ResourceMetricCollector(devices=CudaDevice.all(),  # log all visible CUDA devices and use the CUDA ordinal
                                    root_pids={os.getpid()},   # only log the descendant processes of the current process
                                    interval=1.0)              # snapshot interval for background daemon thread

# Start training
global_step = 0
for epoch in range(num_epoch):
    with collector(tag='train'):
        for batch in train_dataset:
            with collector(tag='batch'):
                metrics = train(net, batch)
                global_step += 1
                add_scalar_dict(writer, 'train', metrics, global_step=global_step)
                add_scalar_dict(writer, 'resources',      # tag='resources/train/batch/...'
                                collector.collect(),
                                global_step=global_step)

        add_scalar_dict(writer, 'resources',              # tag='resources/train/...'
                        collector.collect(),
                        global_step=epoch)

    with collector(tag='validate'):
        metrics = validate(net, validation_dataset)
        add_scalar_dict(writer, 'validate', metrics, global_step=epoch)
        add_scalar_dict(writer, 'resources',              # tag='resources/validate/...'
                        collector.collect(),
                        global_step=epoch)

import datetime
import time

import pandas as pd

from nvitop import ResourceMetricCollector

collector = ResourceMetricCollector(root_pids={1}, interval=2.0)  # log all devices and all GPU processes
df = pd.DataFrame()

with collector(tag='resources'):
    for _ in range(60):
        # Do something
        time.sleep(60)

        metrics = collector.collect()
        df_metrics = pd.DataFrame.from_records(metrics, index=[len(df)])
        df = pd.concat([df, df_metrics], ignore_index=True)
        # Flush to CSV file ...

df.insert(0, 'time', df['resources/timestamp'].map(datetime.datetime.fromtimestamp))
df.to_csv('results.csv', index=False)

from nvitop import Device, ResourceMetricCollector, collect_in_background

logger = ...

def on_collect(metrics):  # will be called periodically
    if logger.is_closed():  # closed manually by user
        return False
    logger.log(metrics)
    return True

def on_stop(collector):  # will be called only once at stop
    if not logger.is_closed():
        logger.close()  # cleanup

# Record metrics to the logger in the background every 5 seconds.
# It will collect 5-second mean/min/max for each metric.
collect_in_background(
    on_collect,
    ResourceMetricCollector(Device.cuda.all()),
    interval=5.0,
    on_stop=on_stop,
)

ResourceMetricCollector(Device.cuda.all()).daemonize(
    on_collect,
    interval=5.0,
    on_stop=on_stop,
)

In [1]: from nvitop import (
   ...:     host,
   ...:     Device, PhysicalDevice, CudaDevice,
   ...:     parse_cuda_visible_devices, normalize_cuda_visible_devices
   ...:     HostProcess, GpuProcess,
   ...:     NA,
   ...: )
   ...: import os
   ...: os.environ['CUDA_DEVICE_ORDER'] = 'PCI_BUS_ID'
   ...: os.environ['CUDA_VISIBLE_DEVICES'] = '9,8,7,6'  # comma-separated integers or UUID strings

In [2]: Device.driver_version()
Out[2]: '525.60.11'

In [3]: Device.cuda_driver_version()  # the maximum CUDA version supported by the driver (can be different from the CUDA Runtime version)
Out[3]: '12.0'

In [4]: Device.cuda_runtime_version()  # the CUDA Runtime version
Out[4]: '11.8'

In [5]: Device.count()
Out[5]: 10

In [6]: CudaDevice.count()  # or `Device.cuda.count()`
Out[6]: 4

In [7]: all_devices      = Device.all()                 # all devices on board (physical device)
   ...: nvidia0, nvidia1 = Device.from_indices([0, 1])  # from physical device indices
   ...: all_devices
Out[7]: [
    PhysicalDevice(index=0, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    PhysicalDevice(index=1, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    PhysicalDevice(index=2, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    PhysicalDevice(index=3, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    PhysicalDevice(index=4, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    PhysicalDevice(index=5, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    PhysicalDevice(index=6, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    PhysicalDevice(index=7, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    PhysicalDevice(index=8, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    PhysicalDevice(index=9, name="GeForce RTX 2080 Ti", total_memory=11019MiB)
]

In [8]: # NOTE: The function results might be different between calls when the `CUDA_VISIBLE_DEVICES` environment variable has been modified
   ...: cuda_visible_devices = Device.from_cuda_visible_devices()  # from the `CUDA_VISIBLE_DEVICES` environment variable
   ...: cuda0, cuda1         = Device.from_cuda_indices([0, 1])    # from CUDA device indices (might be different from physical device indices if `CUDA_VISIBLE_DEVICES` is set)
   ...: cuda_visible_devices = CudaDevice.all()                    # shortcut to `Device.from_cuda_visible_devices()`
   ...: cuda_visible_devices = Device.cuda.all()                   # `Device.cuda` is aliased to `CudaDevice`
   ...: cuda_visible_devices
Out[8]: [
    CudaDevice(cuda_index=0, nvml_index=9, name="NVIDIA GeForce RTX 2080 Ti", total_memory=11019MiB),
    CudaDevice(cuda_index=1, nvml_index=8, name="NVIDIA GeForce RTX 2080 Ti", total_memory=11019MiB),
    CudaDevice(cuda_index=2, nvml_index=7, name="NVIDIA GeForce RTX 2080 Ti", total_memory=11019MiB),
    CudaDevice(cuda_index=3, nvml_index=6, name="NVIDIA GeForce RTX 2080 Ti", total_memory=11019MiB)
]

In [9]: nvidia0 = Device(0)  # from device index (or `Device(index=0)`)
   ...: nvidia0
Out[9]: PhysicalDevice(index=0, name="GeForce RTX 2080 Ti", total_memory=11019MiB)

In [10]: nvidia1 = Device(uuid='GPU-01234567-89ab-cdef-0123-456789abcdef')  # from UUID string (or just `Device('GPU-xxxxxxxx-...')`)
    ...: nvidia2 = Device(bus_id='00000000:06:00.0')                        # from PCI bus ID
    ...: nvidia1
Out[10]: PhysicalDevice(index=1, name="GeForce RTX 2080 Ti", total_memory=11019MiB)

In [11]: cuda0 = CudaDevice(0)                        # from CUDA device index (equivalent to `CudaDevice(cuda_index=0)`)
    ...: cuda1 = CudaDevice(nvml_index=8)             # from physical device index
    ...: cuda3 = CudaDevice(uuid='GPU-xxxxxxxx-...')  # from UUID string
    ...: cuda4 = Device.cuda(4)                       # `Device.cuda` is aliased to `CudaDevice`
    ...: cuda0
Out[11]:
CudaDevice(cuda_index=0, nvml_index=9, name="NVIDIA GeForce RTX 2080 Ti", total_memory=11019MiB)

In [12]: nvidia0.memory_used()  # in bytes
Out[12]: 9293398016

In [13]: nvidia0.memory_used_human()
Out[13]: '8862MiB'

In [14]: nvidia0.gpu_utilization()  # in percentage
Out[14]: 5

In [15]: nvidia0.processes()  # type: Dict[int, GpuProcess]
Out[15]: {
    52059: GpuProcess(pid=52059, gpu_memory=7885MiB, type=C, device=PhysicalDevice(index=0, name="GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=52059, name='ipython3', status='sleeping', started='14:31:22')),
    53002: GpuProcess(pid=53002, gpu_memory=967MiB, type=C, device=PhysicalDevice(index=0, name="GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=53002, name='python', status='running', started='14:31:59'))
}

In [16]: nvidia1_snapshot = nvidia1.as_snapshot()
    ...: nvidia1_snapshot
Out[16]: PhysicalDeviceSnapshot(
    real=PhysicalDevice(index=1, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    bus_id='00000000:05:00.0',
    compute_mode='Default',
    clock_infos=ClockInfos(graphics=1815, sm=1815, memory=6800, video=1680),  # in MHz
    clock_speed_infos=ClockSpeedInfos(current=ClockInfos(graphics=1815, sm=1815, memory=6800, video=1680), max=ClockInfos(graphics=2100, sm=2100, memory=7000, video=1950)),  # in MHz
    cuda_compute_capability=(7, 5),
    current_driver_model='N/A',
    decoder_utilization=0,              # in percentage
    display_active='Disabled',
    display_mode='Disabled',
    encoder_utilization=0,              # in percentage
    fan_speed=22,                       # in percentage
    gpu_utilization=17,                 # in percentage (NOTE: this is the utilization rate of SMs, i.e. GPU percent)
    index=1,
    max_clock_infos=ClockInfos(graphics=2100, sm=2100, memory=7000, video=1950),  # in MHz
    memory_clock=6800,                  # in MHz
    memory_free=10462232576,            # in bytes
    memory_free_human='9977MiB',
    memory_info=MemoryInfo(total=11554717696, free=10462232576, used=1092485120)  # in bytes
    memory_percent=9.5,                 # in percentage (NOTE: this is the percentage of used GPU memory)
    memory_total=11554717696,           # in bytes
    memory_total_human='11019MiB',
    memory_usage='1041MiB / 11019MiB',
    memory_used=1092485120,             # in bytes
    memory_used_human='1041MiB',
    memory_utilization=7,               # in percentage (NOTE: this is the utilization rate of GPU memory bandwidth)
    mig_mode='N/A',
    name='GeForce RTX 2080 Ti',
    pcie_rx_throughput=1000,            # in KiB/s
    pcie_rx_throughput_human='1000KiB/s',
    pcie_throughput=ThroughputInfo(tx=1000, rx=1000),  # in KiB/s
    pcie_tx_throughput=1000,            # in KiB/s
    pcie_tx_throughput_human='1000KiB/s',
    performance_state='P2',
    persistence_mode='Disabled',
    power_limit=250000,                 # in milliwatts (mW)
    power_status='66W / 250W',          # in watts (W)
    power_usage=66051,                  # in milliwatts (mW)
    sm_clock=1815,                      # in MHz
    temperature=39,                     # in Celsius
    total_volatile_uncorrected_ecc_errors='N/A',
    utilization_rates=UtilizationRates(gpu=17, memory=7, encoder=0, decoder=0),  # in percentage
    uuid='GPU-01234567-89ab-cdef-0123-456789abcdef',
)

In [17]: nvidia1_snapshot.memory_percent  # snapshot uses properties instead of function calls
Out[17]: 9.5

In [18]: nvidia1_snapshot['memory_info']  # snapshot also supports `__getitem__` by string
Out[18]: MemoryInfo(total=11554717696, free=10462232576, used=1092485120)

In [19]: nvidia1_snapshot.bar1_memory_info  # snapshot will automatically retrieve not presented attributes from `real`
Out[19]: MemoryInfo(total=268435456, free=257622016, used=10813440)

>>> from nvitop import NA
>>> NA
'N/A'

>>> 'memory usage: {}'.format(NA)  # NA is an instance of `str`
'memory usage: N/A'
>>> NA.lower()                     # NA is an instance of `str`
'n/a'
>>> NA.ljust(5)                    # NA is an instance of `str`
'N/A  '
>>> NA + 'str'                     # string contamination if the operand is a string
'N/Astr'

>>> float(NA)                      # explicit conversion to float (`math.nan`)
nan
>>> NA + 1                         # auto-casting to float if the operand is a number
nan
>>> NA * 1024                      # auto-casting to float if the operand is a number
nan
>>> NA / (1024 * 1024)             # auto-casting to float if the operand is a number
nan

memory_used: Union[int, NaType] = device.memory_used()            # memory usage in bytes or `'N/A'`
memory_used_in_mib: float       = float(memory_used) / (1 << 20)  # memory usage in Mebibytes (MiB) or `math.nan`

devices_by_used_memory = sorted(Device.all(), key=Device.memory_used, reverse=True)  # it's safe to compare `'N/A'` with numbers
devices_by_free_memory = sorted(Device.all(), key=Device.memory_free, reverse=True)  # please add `memory_free != 'N/A'` checks if sort in descending order here

In [20]: processes = nvidia1.processes()  # type: Dict[int, GpuProcess]
    ...: processes
Out[20]: {
    23266: GpuProcess(pid=23266, gpu_memory=1031MiB, type=C, device=Device(index=1, name="GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=23266, name='python3', status='running', started='2021-05-10 21:02:40'))
}

In [21]: process = processes[23266]
    ...: process
Out[21]: GpuProcess(pid=23266, gpu_memory=1031MiB, type=C, device=Device(index=1, name="GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=23266, name='python3', status='running', started='2021-05-10 21:02:40'))

In [22]: process.status()  # GpuProcess will automatically inherit attributes from GpuProcess.host
Out[22]: 'running'

In [23]: process.cmdline()  # type: List[str]
Out[23]: ['python3', 'rllib_train.py']

In [24]: process.command()  # type: str
Out[24]: 'python3 rllib_train.py'

In [25]: process.cwd()  # GpuProcess will automatically inherit attributes from GpuProcess.host
Out[25]: '/home/xxxxxx/Projects/xxxxxx'

In [26]: process.gpu_memory_human()
Out[26]: '1031MiB'

In [27]: process.as_snapshot()
Out[27]: GpuProcessSnapshot(
    real=GpuProcess(pid=23266, gpu_memory=1031MiB, type=C, device=PhysicalDevice(index=1, name="GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=23266, name='python3', status='running', started='2021-05-10 21:02:40')),
    cmdline=['python3', 'rllib_train.py'],
    command='python3 rllib_train.py',
    compute_instance_id='N/A',
    cpu_percent=98.5,                       # in percentage
    device=PhysicalDevice(index=1, name="GeForce RTX 2080 Ti", total_memory=11019MiB),
    gpu_encoder_utilization=0,              # in percentage
    gpu_decoder_utilization=0,              # in percentage
    gpu_instance_id='N/A',
    gpu_memory=1081081856,                  # in bytes
    gpu_memory_human='1031MiB',
    gpu_memory_percent=9.4,                 # in percentage (NOTE: this is the percentage of used GPU memory)
    gpu_memory_utilization=5,               # in percentage (NOTE: this is the utilization rate of GPU memory bandwidth)
    gpu_sm_utilization=0,                   # in percentage (NOTE: this is the utilization rate of SMs, i.e. GPU percent)
    host=HostProcessSnapshot(
        real=HostProcess(pid=23266, name='python3', status='running', started='2021-05-10 21:02:40'),
        cmdline=['python3', 'rllib_train.py'],
        command='python3 rllib_train.py',
        cpu_percent=98.5,                   # in percentage
        host_memory=9113627439,             # in bytes
        host_memory_human='8691MiB',
        is_running=True,
        memory_percent=1.6849018430285683,  # in percentage
        name='python3',
        running_time=datetime.timedelta(days=1, seconds=80013, microseconds=470024),
        running_time_human='46:13:33',
        running_time_in_seconds=166413.470024,
        status='running',
        username='panxuehai',
    ),
    host_memory=9113627439,                 # in bytes
    host_memory_human='8691MiB',
    is_running=True,
    memory_percent=1.6849018430285683,      # in percentage (NOTE: this is the percentage of used host memory)
    name='python3',
    pid=23266,
    running_time=datetime.timedelta(days=1, seconds=80013, microseconds=470024),
    running_time_human='46:13:33',
    running_time_in_seconds=166413.470024,
    status='running',
    type='C',                               # 'C' for Compute / 'G' for Graphics / 'C+G' for Both
    username='panxuehai',
)

In [28]: process.uids()  # GpuProcess will automatically inherit attributes from GpuProcess.host
Out[28]: puids(real=1001, effective=1001, saved=1001)

In [29]: process.kill()  # GpuProcess will automatically inherit attributes from GpuProcess.host

In [30]: list(map(Device.processes, all_devices))  # all processes
Out[30]: [
    {
        52059: GpuProcess(pid=52059, gpu_memory=7885MiB, type=C, device=PhysicalDevice(index=0, name="GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=52059, name='ipython3', status='sleeping', started='14:31:22')),
        53002: GpuProcess(pid=53002, gpu_memory=967MiB, type=C, device=PhysicalDevice(index=0, name="GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=53002, name='python', status='running', started='14:31:59'))
    },
    {},
    {},
    {},
    {},
    {},
    {},
    {},
    {
        84748: GpuProcess(pid=84748, gpu_memory=8975MiB, type=C, device=PhysicalDevice(index=8, name="GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=84748, name='python', status='running', started='11:13:38'))
    },
    {
        84748: GpuProcess(pid=84748, gpu_memory=8341MiB, type=C, device=PhysicalDevice(index=9, name="GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=84748, name='python', status='running', started='11:13:38'))
    }
]

In [31]: this = HostProcess(os.getpid())
    ...: this
Out[31]: HostProcess(pid=35783, name='python', status='running', started='19:19:00')

In [32]: this.cmdline()  # type: List[str]
Out[32]: ['python', '-c', 'import IPython; IPython.terminal.ipapp.launch_new_instance()']

In [33]: this.command()  # not simply `' '.join(cmdline)` but quotes are added
Out[33]: 'python -c "import IPython; IPython.terminal.ipapp.launch_new_instance()"'

In [34]: this.memory_info()
Out[34]: pmem(rss=83988480, vms=343543808, shared=12079104, text=8192, lib=0, data=297435136, dirty=0)

In [35]: import cupy as cp
    ...: x = cp.zeros((10000, 1000))
    ...: this = GpuProcess(os.getpid(), cuda0)  # construct from `GpuProcess(pid, device)` explicitly rather than calling `device.processes()`
    ...: this
Out[35]: GpuProcess(pid=35783, gpu_memory=N/A, type=N/A, device=CudaDevice(cuda_index=0, nvml_index=9, name="NVIDIA GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=35783, name='python', status='running', started='19:19:00'))

In [36]: this.update_gpu_status()  # update used GPU memory from new driver queries
Out[36]: 267386880

In [37]: this
Out[37]: GpuProcess(pid=35783, gpu_memory=255MiB, type=C, device=CudaDevice(cuda_index=0, nvml_index=9, name="NVIDIA GeForce RTX 2080 Ti", total_memory=11019MiB), host=HostProcess(pid=35783, name='python', status='running', started='19:19:00'))

In [38]: id(this) == id(GpuProcess(os.getpid(), cuda0))  # IMPORTANT: the instance will be reused while the process is running
Out[38]: True

In [39]: host.cpu_count()
Out[39]: 88

In [40]: host.cpu_percent()
Out[40]: 18.5

In [41]: host.cpu_times()
Out[41]: scputimes(user=2346377.62, nice=53321.44, system=579177.52, idle=10323719.85, iowait=28750.22, irq=0.0, softirq=11566.87, steal=0.0, guest=0.0, guest_nice=0.0)

In [42]: host.load_average()
Out[42]: (14.88, 17.8, 19.91)

In [43]: host.virtual_memory()
Out[43]: svmem(total=270352478208, available=192275968000, percent=28.9, used=53350518784, free=88924037120, active=125081112576, inactive=44803993600, buffers=37006450688, cached=91071471616, shared=23820632064, slab=8200687616)

In [44]: host.memory_percent()
Out[44]: 28.9

In [45]: host.swap_memory()
Out[45]: sswap(total=65534947328, used=475136, free=65534472192, percent=0.0, sin=2404139008, sout=4259434496)

In [46]: host.swap_percent()
Out[46]: 0.0

import nvitop
import nvitop as alias
import nvitop.api as api
import nvitop.device as device
from nvitop import *
from nvitop.api import *
from nvitop import Device, ResourceMetricCollector

from nvitop import cli
from nvitop import gui
import nvitop.cli
import nvitop.gui