Skip to content

Instantly share code, notes, and snippets.

@rjzamora
Last active July 25, 2024 20:08
Show Gist options
  • Save rjzamora/860ce8ee7a7bcf931917496e20940c74 to your computer and use it in GitHub Desktop.
Save rjzamora/860ce8ee7a7bcf931917496e20940c74 to your computer and use it in GitHub Desktop.
Splitting IO and compute onto different resources.
Display the source blob
Display the rendered blob
Raw
{
"cells": [
{
"cell_type": "markdown",
"id": "1c01dc89-8876-4d84-a8d4-f6a7397c91e0",
"metadata": {},
"source": [
"```\n",
"$ dask scheduler > scheduler.out 2>&1 &\n",
"\n",
"$ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 dask cuda worker 127.0.0.1:8786 --resources \"GPU=1\" > gpu_workers.out 2>&1 &\n",
"\n",
"$ dask worker 127.0.0.1:8786 --nworkers 10 --nthreads 8 --resources \"CPU=1\" > cpu_workers.out 2>&1 &\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "e38829c7-c580-4f69-899c-71825bb2ed2b",
"metadata": {},
"outputs": [],
"source": [
"import dask\n",
"import dask.dataframe as dd\n",
"\n",
"from pyarrow import dataset\n",
"import cudf\n",
"\n",
"from distributed import Client"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "127f32fd-da3d-4581-9b74-13ad237a15e7",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
" <div style=\"width: 24px; height: 24px; background-color: #e1e1e1; border: 3px solid #9D9D9D; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <h3 style=\"margin-bottom: 0px;\">Client</h3>\n",
" <p style=\"color: #9D9D9D; margin-bottom: 0px;\">Client-9edf07be-4ac0-11ef-b71b-d8c49764f70a</p>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
"\n",
" <tr>\n",
" \n",
" <td style=\"text-align: left;\"><strong>Connection method:</strong> Direct</td>\n",
" <td style=\"text-align: left;\"></td>\n",
" \n",
" </tr>\n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:8787/status\" target=\"_blank\">http://127.0.0.1:8787/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
"\n",
" \n",
"\n",
" \n",
" <details>\n",
" <summary style=\"margin-bottom: 20px;\"><h3 style=\"display: inline;\">Scheduler Info</h3></summary>\n",
" <div style=\"\">\n",
" <div>\n",
" <div style=\"width: 24px; height: 24px; background-color: #FFF7E5; border: 3px solid #FF6132; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <h3 style=\"margin-bottom: 0px;\">Scheduler</h3>\n",
" <p style=\"color: #9D9D9D; margin-bottom: 0px;\">Scheduler-105c5d9f-b628-4717-ad28-3ef961a9635e</p>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm:</strong> tcp://10.33.227.164:8786\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Workers:</strong> 18\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard:</strong> <a href=\"http://10.33.227.164:8787/status\" target=\"_blank\">http://10.33.227.164:8787/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads:</strong> 88\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Started:</strong> 36 minutes ago\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total memory:</strong> 1.97 TiB\n",
" </td>\n",
" </tr>\n",
" </table>\n",
" </div>\n",
" </div>\n",
"\n",
" <details style=\"margin-left: 48px;\">\n",
" <summary style=\"margin-bottom: 20px;\">\n",
" <h3 style=\"display: inline;\">Workers</h3>\n",
" </summary>\n",
"\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:33193</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:33193\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 1\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:33397/status\" target=\"_blank\">http://127.0.0.1:33397/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 125.97 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:33589\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-gc0qywew\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 683.79 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 251.99 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 360.95 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:34121</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:34121\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:42851/status\" target=\"_blank\">http://127.0.0.1:42851/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:40513\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-6g6lvzmk\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 398.06 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 221.67 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 323.87 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:35039</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:35039\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:44617/status\" target=\"_blank\">http://127.0.0.1:44617/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:44147\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-3ddmttcv\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 386.24 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 232.58 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 334.53 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:35047</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:35047\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 1\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:34501/status\" target=\"_blank\">http://127.0.0.1:34501/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 125.97 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:45571\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-ityr0amb\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 0.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 717.38 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 229.29 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 339.35 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:36533</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:36533\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 1\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:37667/status\" target=\"_blank\">http://127.0.0.1:37667/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 125.97 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:45497\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-u8_acuyn\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 701.49 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 247.91 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 356.73 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:37455</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:37455\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:42947/status\" target=\"_blank\">http://127.0.0.1:42947/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:46095\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-m1izlpds\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 385.09 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 221.59 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 324.27 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:37577</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:37577\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:41559/status\" target=\"_blank\">http://127.0.0.1:41559/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:37615\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-zvi06n6z\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 386.70 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 245.52 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 350.40 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:38295</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:38295\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:37173/status\" target=\"_blank\">http://127.0.0.1:37173/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:41503\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-x7hl3hm7\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 386.17 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 248.19 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 347.79 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:39795</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:39795\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:44999/status\" target=\"_blank\">http://127.0.0.1:44999/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:40807\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-xhp6i1z_\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 392.82 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 246.26 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 343.43 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:40001</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:40001\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 1\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:39873/status\" target=\"_blank\">http://127.0.0.1:39873/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 125.97 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:33795\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-2d6lkol8\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 705.52 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 252.12 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 360.90 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:40019</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:40019\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 1\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:46269/status\" target=\"_blank\">http://127.0.0.1:46269/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 125.97 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:44371\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-4wo22_tm\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 711.04 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 224.56 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 326.76 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:40361</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:40361\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 1\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:42001/status\" target=\"_blank\">http://127.0.0.1:42001/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 125.97 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:32861\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-ndg5fol2\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 694.39 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 222.34 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 332.15 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:41643</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:41643\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:40425/status\" target=\"_blank\">http://127.0.0.1:40425/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:43355\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-nl5_t2u9\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 389.00 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 235.27 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 345.53 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:42093</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:42093\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 1\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:38333/status\" target=\"_blank\">http://127.0.0.1:38333/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 125.97 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:42141\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-tf6erj7o\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 4.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 714.17 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 253.01 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 362.20 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:42701</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:42701\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:41163/status\" target=\"_blank\">http://127.0.0.1:41163/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:41549\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-_l2fndij\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 391.42 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 223.05 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 322.48 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:43155</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:43155\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:40371/status\" target=\"_blank\">http://127.0.0.1:40371/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:37179\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-mj_e4j36\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 388.55 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 221.86 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 326.72 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:44755</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:44755\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 8\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:35981/status\" target=\"_blank\">http://127.0.0.1:35981/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 100.78 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:36419\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-vd001ram\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 4.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 386.34 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 247.96 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 353.16 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
" <div style=\"margin-bottom: 20px;\">\n",
" <div style=\"width: 24px; height: 24px; background-color: #DBF5FF; border: 3px solid #4CC9FF; border-radius: 5px; position: absolute;\"> </div>\n",
" <div style=\"margin-left: 48px;\">\n",
" <details>\n",
" <summary>\n",
" <h4 style=\"margin-bottom: 0px; display: inline;\">Worker: tcp://127.0.0.1:46055</h4>\n",
" </summary>\n",
" <table style=\"width: 100%; text-align: left;\">\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Comm: </strong> tcp://127.0.0.1:46055\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Total threads: </strong> 1\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Dashboard: </strong> <a href=\"http://127.0.0.1:40791/status\" target=\"_blank\">http://127.0.0.1:40791/status</a>\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory: </strong> 125.97 GiB\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Nanny: </strong> tcp://127.0.0.1:33391\n",
" </td>\n",
" <td style=\"text-align: left;\"></td>\n",
" </tr>\n",
" <tr>\n",
" <td colspan=\"2\" style=\"text-align: left;\">\n",
" <strong>Local directory: </strong> /raid/dask-space/rzamora/dask-space/dask-scratch-space/worker-u3copcgb\n",
" </td>\n",
" </tr>\n",
"\n",
" \n",
"\n",
" \n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks executing: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in memory: </strong> \n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks ready: </strong> \n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Tasks in flight: </strong>\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>CPU usage:</strong> 2.0%\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Last seen: </strong> Just now\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Memory usage: </strong> 713.12 MiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Spilled bytes: </strong> 0 B\n",
" </td>\n",
" </tr>\n",
" <tr>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Read bytes: </strong> 235.09 kiB\n",
" </td>\n",
" <td style=\"text-align: left;\">\n",
" <strong>Write bytes: </strong> 349.77 kiB\n",
" </td>\n",
" </tr>\n",
" \n",
"\n",
" </table>\n",
" </details>\n",
" </div>\n",
" </div>\n",
" \n",
"\n",
" </details>\n",
"</div>\n",
" </details>\n",
" \n",
"\n",
" </div>\n",
"</div>"
],
"text/plain": [
"<Client: 'tcp://10.33.227.164:8786' processes=18 threads=88, memory=1.97 TiB>"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"client = Client(\"127.0.0.1:8786\")\n",
"client"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "e435d805-643c-424e-9516-3339571d4813",
"metadata": {},
"outputs": [],
"source": [
"# Path and column selection\n",
"path = \"s3://coiled-data/tpch/scale-1000/customer\"\n",
"columns = [\"c_custkey\"]\n",
"ds = dataset.dataset(path, format=\"parquet\")\n",
"paths = [\"s3://\" + path for path in ds.files]"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "40d2ae52-840d-429e-a932-a03c5004cd03",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 778 ms, sys: 355 ms, total: 1.13 s\n",
"Wall time: 40.6 s\n"
]
}
],
"source": [
"%%time\n",
"\n",
"# IO phase (cpu)\n",
"df = dd.read_parquet(\n",
" path,\n",
" filesystem=\"arrow\",\n",
" columns=columns,\n",
").persist(resources={'CPU': 1})\n",
"\n",
"# Compute phase (gpu)\n",
"res = df.to_backend(\"cudf\").max().compute(resources={'GPU': 1})"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "7dbe7016-0802-4130-aacd-fab17edf057a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 288 ms, sys: 27.9 ms, total: 316 ms\n",
"Wall time: 47.8 s\n"
]
}
],
"source": [
"%%time\n",
"\n",
"# CPU only\n",
"df = dd.read_parquet(\n",
" path,\n",
" filesystem=\"arrow\",\n",
" columns=columns,\n",
").max().compute(resources={'CPU': 1})"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "86d38653-ffed-4eee-9e66-d0abfa84f642",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 577 ms, sys: 330 ms, total: 907 ms\n",
"Wall time: 1min 36s\n"
]
}
],
"source": [
"%%time\n",
"\n",
"def read_daft_partition(path, columns):\n",
" import daft\n",
"\n",
" return daft.read_parquet(path).select(*columns).to_arrow()\n",
"\n",
"def from_arrow_partition(part):\n",
" return cudf.DataFrame.from_arrow(part)\n",
"\n",
"df = dd.from_map(\n",
" read_daft_partition,\n",
" paths,\n",
" meta=ds.schema.empty_table().to_pandas()[columns],\n",
" enforce_metadata=False,\n",
").persist(resources={'CPU': 1})\n",
"\n",
"meta = cudf.DataFrame.from_pandas(\n",
" ds.schema.empty_table().to_pandas()[columns]\n",
")\n",
"result = df.map_partitions(\n",
" from_arrow_partition,\n",
" meta=meta,\n",
" enforce_metadata=False,\n",
").max().compute(resources={'GPU': 1})"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "3e47bea2-d3c3-4e5b-9c77-39304c6e93c9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 146 ms, sys: 22.2 ms, total: 168 ms\n",
"Wall time: 1min 47s\n"
]
}
],
"source": [
"%%time\n",
"\n",
"def read_daft_partition_pandas(path, columns):\n",
" import daft\n",
"\n",
" return daft.read_parquet(path).select(*columns).to_pandas()\n",
"\n",
"result = dd.from_map(\n",
" read_daft_partition_pandas,\n",
" paths,\n",
" meta=ds.schema.empty_table().to_pandas()[columns],\n",
" enforce_metadata=False,\n",
").max().compute(resources={'CPU': 1})"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "1551045e-493a-4af8-82b4-e15e63b40612",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 977 ms, sys: 211 ms, total: 1.19 s\n",
"Wall time: 2min 24s\n"
]
}
],
"source": [
"%%time\n",
"\n",
"# GPU only\n",
"with dask.config.set({\"dataframe.backend\": \"cudf\"}):\n",
" df = dd.read_parquet(\n",
" path,\n",
" columns=columns,\n",
" ).max().compute(resources={'GPU': 1})"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c08ed5e0-6cc3-41ad-a627-1210ac62a6ba",
"metadata": {},
"outputs": [],
"source": [
"# #VERY SLOW\n",
"# %%time\n",
"# \n",
"# GPU only (aggregate_files=True)\n",
"# with dask.config.set({\"dataframe.backend\": \"cudf\"}):\n",
"# df = dd.read_parquet(\n",
"# path,\n",
"# aggregate_files=True,\n",
"# columns=columns,\n",
"# ).max().compute(resources={'GPU': 1})\n",
"# \n",
"# #CPU times: user 2.08 s, sys: 624 ms, total: 2.7 s\n",
"# #Wall time: 10min 31s"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c99f15b3-25c2-40bf-9c91-4a0903b8b499",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment