Commit 6efc4f62 authored by Ryan Randles Jones's avatar Ryan Randles Jones
Browse files

added jobs vs users graphs

parent 9bfd57c5
%% Cell type:code id: tags:
```
# must run
import sqlite3
import slurm2sql
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import seaborn as sns
import plotly.express as px
```
%% Cell type:code id: tags:
```
# must run
# creates database of info from March 2020 using sqlite 3
db = sqlite3.connect('/data/rc/rc-team/slurm-since-March.sqlite3')
```
%% Cell type:code id: tags:
```
# creates database of allocation info from March 2020 using sqlite 3
# not using this right now, but is here as an option
#db_allocation = sqlite3.connect('/data/rc/rc-team/slurm-since-March-allocation.sqlite3')
```
%% Cell type:code id: tags:
```
# must run
# variable for to be used in names of plots to describe the max gigs measured
UpperlimitGB = 5
# variable for max gigs of RAM requested - Charts range from 0 to upperRAMlimit gigs
upperRAMlimit = UpperlimitGB * 10e+10 # 5 gigs
```
%% Cell type:code id: tags:
```
# must run
# df_1 is starting database
df_1 = pd.read_sql('SELECT * FROM slurm', db)
```
%% Cell type:code id: tags:
```
# voluntary
# for displaying all available column options
pd.set_option('display.max_columns', None)
df_1.head(5)
```
%% Cell type:code id: tags:
```
# must run
# df_2 is database with only ReqMemCpu and ReqMemNode, and ArrayTaskID
df_2 = df_1.loc[:,['JobName','ReqMemCPU', 'ReqMemNode', 'ArrayJobID','ArrayTaskID']]
df_2 = df_1.loc[:,['JobStep','User', 'JobName','ReqMemCPU', 'ReqMemNode', 'ArrayJobID','ArrayTaskID']]
#df_2.head(5)
```
%% Cell type:code id: tags:
```
# must run
# df_batch is df_2 with only batch jobs
df_batch = df_1.JobName.str.contains('batch')
#df_2[df_batch]
# df_user is df_2 with only user defined jobs
df_3 = df_2[df_2['JobStep'].isnull()] # jobs where jobstep is None
df_3
```
%% Cell type:code id: tags:
```
# must run
# creates database from df_batch of ReqMemCPU batch jobs that are < or = a given point
CPU_cutoff = df_2[df_batch][(df_2[df_batch].ReqMemCPU <= upperRAMlimit)]
#CPU_cutoff
Node_cutoff = df_2[df_batch][(df_2[df_batch].ReqMemNode <= upperRAMlimit)]
df_user = df_3.loc[:,['User', 'JobName', 'ReqMemCPU', 'ReqMemNode', 'ArrayJobID','ArrayTaskID']]
df_user
```
%% Cell type:code id: tags:
```
# voluntary
# must run
# gives mean, min, max, std, and 3 percentiles for cutoff data
# can change what to include or exclude
CPU_cutoff.describe(include=None, exclude=None)
# df_batch is df_2 with only batch jobs
df_batch = df_2.JobName.str.contains('batch')
#df_batch
```
%% Cell type:code id: tags:
```
# voluntary
# gives mean, min, max, std, and 3 percentiles for cutoff data
# can change what to include or exclude
Node_cutoff.describe(include=None, exclude=None)
```
# must run
%% Cell type:code id: tags:
# creates database from df_batch of ReqMemCPU batch jobs that are < or = a given point
JobsCPU_cutoff = df_2[df_batch][(df_2[df_batch].ReqMemCPU <= upperRAMlimit)]
#JobsCPU_cutoff
JobsNode_cutoff = df_2[df_batch][(df_2[df_batch].ReqMemNode <= upperRAMlimit)]
UsersCPU_cutoff = df_user[(df_user.ReqMemCPU <= upperRAMlimit)]
#UsersCPU_cutoff
UsersNode_cutoff = df_user[(df_user.ReqMemCPU <= upperRAMlimit)]
```
# msut run
# creates databases of Requested Ram per CPU and per Node that have an array task id using the upper RAM limit cutoff
CPU_arraytask = CPU_cutoff.dropna(subset=['ArrayTaskID'])
Node_arraytask = Node_cutoff.dropna(subset=['ArrayTaskID'])
```
%% Cell type:code id: tags:
```
# must run
# voluntary
# creates databases of Requested Ram per CPU and per Node that do not have an array task id using the upper RAM limit cutoff
CPU_nonarraytask = CPU_cutoff[CPU_cutoff['ArrayTaskID'].isnull()]
Node_nonarraytask = Node_cutoff[Node_cutoff['ArrayTaskID'].isnull()]
#CPU_nonarraytask.head(5)
# gives mean, min, max, std, and 3 percentiles for cutoff data
# can change what to include or exclude
JobsCPU_cutoff.describe(include=None, exclude=None)
```
%% Cell type:markdown id: tags:
Graphs: <br>
User Requested RAM per CPU for all Jobs
<br>
User Requested RAM per Node for all Jobs
<br>
User Requested RAM per CPU and per Node together for all Jobs
<br>
User Requested RAM per CPU for Array Jobs vs Not Array Jobs
<br>
User Requested RAM per Node for Array Jobs vs Not Array Jobs
<br>
These graphs create histograms using the data for the month of March 2020.
The x axis measures the amount of requested RAM in gigs per CPU/Node, from 0 to the max declared in the upperRAMlimit variable above - 5 gigs.
The y axis measures how many users requested that amount RAM per CPU or Node.
%% Cell type:code id: tags:
```
# shows all user requested cpu memory for array and non array jobs
CPU_fig = sns.distplot(CPU_cutoff['ReqMemCPU'], kde=False, label='User Requested RAM per CPU for Array and Non Array Jobs', color = "green")
CPU_fig.set_yscale('log')
plt.legend(prop={'size': 12},loc='upper right',bbox_to_anchor=(2.25, 1.0),ncol=1)
plt.title('User Requested RAM per CPU for all Jobs %i gigs or less'%UpperlimitGB)
plt.xlabel('Requested Gigs of RAM')
plt.ylabel('Number of Jobs Requesting')
# voluntary
# gives mean, min, max, std, and 3 percentiles for cutoff data
# can change what to include or exclude
JobsNode_cutoff.describe(include=None, exclude=None)
```
%% Cell type:code id: tags:
```
# shows all user requested node memory for array and non array jobs
Node_fig = sns.distplot(Node_cutoff['ReqMemNode'], kde=False, label='User Requested RAM per Node for Array and Non Array Jobs')
Node_fig.set_yscale('log')
# voluntary
plt.legend(prop={'size': 12},loc='upper right',bbox_to_anchor=(2.25, 1.0),ncol=1)
plt.title('User Requested RAM per Node for all Jobs %i gigs or less'%UpperlimitGB)
plt.xlabel('Requested Gigs of RAM')
plt.ylabel('Number of Jobs Requesting')
# gives mean, min, max, std, and 3 percentiles for cutoff data
# can change what to include or exclude
UsersCPU_cutoff.describe(include=None, exclude=None)
```
%% Cell type:code id: tags:
```
#shows requested cpu and node for all job types (array and non array jobs) side by side for easy comparison.
CPU_fig = sns.distplot(CPU_cutoff['ReqMemCPU'], kde=False, label='User Requested RAM per CPU for Array and Non Array Jobs', color = "green")
CPU_fig.set_yscale('log')
Node_fig = sns.distplot(Node_cutoff['ReqMemNode'], kde=False, label='User Requested RAM per Node for Array and Non Array Jobs') #color = 'darkblue')
Node_fig.set_yscale('log')
# voluntary
plt.legend(prop={'size': 12},loc='upper right',bbox_to_anchor=(2.25, 1.0),ncol=1)
plt.title('User Requested RAM per CPU and per Node together for all Jobs %i gigs or less'%UpperlimitGB)
plt.xlabel('Requested Gigs of RAM')
plt.ylabel('Number of Jobs Requesting')
# gives mean, min, max, std, and 3 percentiles for cutoff data
# can change what to include or exclude
UsersNode_cutoff.describe(include=None, exclude=None)
```
%% Cell type:code id: tags:
```
#shows requested cpu memory for array jobs alongside requested cpu memory for non array jobs for easy comparison.
CPU_arraytask_fig = sns.distplot(CPU_arraytask['ReqMemCPU'], kde=False, label='User Requested RAM per CPU for Array Jobs', color = "green")
CPU_arraytask_fig.set_yscale('log')
# msut run
CPU_nonarraytask_fig = sns.distplot(CPU_nonarraytask['ReqMemCPU'], kde=False, label='User Requested RAM per CPU for Non Array Jobs')
CPU_nonarraytask_fig.set_yscale('log')
# creates databases of Requested Ram per CPU and per Node that have an array task id using the upper RAM limit cutoff
JobsCPU_arraytask = JobsCPU_cutoff.dropna(subset=['ArrayTaskID'])
JobsNode_arraytask = JobsNode_cutoff.dropna(subset=['ArrayTaskID'])
plt.legend(prop={'size': 12},loc='upper right',bbox_to_anchor=(2.05, 1.0),ncol=1)
plt.title('User Requested RAM per CPU for Array Jobs vs Not Array Jobs %i gigs or less'%UpperlimitGB)
plt.xlabel('Requested Gigs of RAM')
plt.ylabel('Number of Jobs Requesting')
UsersCPU_arraytask = UsersCPU_cutoff.dropna(subset=['ArrayTaskID'])
UsersNode_arraytask = UsersNode_cutoff.dropna(subset=['ArrayTaskID'])
```
%% Cell type:code id: tags:
```
#shows requested node memory for array jobs alongside requested node memory for non array jobs for easy comparison.
Node_arraytask_fig = sns.distplot(Node_arraytask['ReqMemCPU'], kde=False, label='User Requested RAM per Node for Array Jobs', color = "green")
Node_arraytask_fig.set_yscale('log')
Node_nonarraytask_fig = sns.distplot(Node_nonarraytask['ReqMemNode'], kde=False, label='User Requested RAM per Node for Non Array Jobs')
Node_nonarraytask_fig.set_yscale('log')
# must run
plt.legend(prop={'size': 12},loc='upper right',bbox_to_anchor=(2.10, 1.0),ncol=1)
plt.title('User Requested RAM per Node for Array Jobs vs Not Array Jobs %i gigs or less'%UpperlimitGB)
plt.xlabel('Requested Gigs of RAM')
plt.ylabel('Number of Jobs Requesting')
# creates databases of Requested Ram per CPU and per Node that do not have an array task id using the upper RAM limit cutoff
JobsCPU_nonarraytask = JobsCPU_cutoff[JobsCPU_cutoff['ArrayTaskID'].isnull()]
JobsNode_nonarraytask = JobsNode_cutoff[JobsNode_cutoff['ArrayTaskID'].isnull()]
#JobsCPU_nonarraytask.head(5)
UsersCPU_nonarraytask = UsersCPU_cutoff[UsersCPU_cutoff['ArrayTaskID'].isnull()]
UsersNode_nonarraytask = UsersNode_cutoff[UsersNode_cutoff['ArrayTaskID'].isnull()]
#UsersCPU_nonarraytask.head(5)
```
%% Cell type:markdown id: tags:
# These are Plotly Express Graphs of the some of the above Seaborn graphs. Run them only if you need more details about the data in the graph. They will make your notebook run slower.
# Number of Jobs vs Users Requesting RAM per CPU
%% Cell type:markdown id: tags:
Graphs: <br>
User Requested RAM per CPU for all Jobs
<br>
User Requested RAM per CPU for Non Array Jobs
Jobs Requesting RAM per CPU for all Jobs
<br>
User Requested RAM per CPU for Array Jobs
Users Requesting RAM per CPU for all Jobs
<br>
User Requested RAM per Node for all Jobs
Jobs Requesting RAM per CPU for Array Jobs vs Not Array Jobs
<br>
User Requested RAM per Node for Non Array Jobs
<br>
User Requested RAM per Node for Array Jobs
Users Requesting RAM per CPU for Array Jobs vs Not Array Jobs
<br>
These graphs create histograms using the data for the month of March 2020.
The x axis measures the amount of requested RAM in gigs per CPU/Node, from 0 to the max declared in the upperRAMlimit variable above - 5 gigs.
The y axis measures how many users requested that amount RAM per CPU or Node.
Can also show box or violin graph above to show where min, max, median, and 3rd quartile is.
The x axis measures the amount of requested RAM in gigs per CPU, from 0 to the max declared in the upperRAMlimit variable above - 5 gigs.
The y axis measures how many jobs requested that amount RAM per CPU.
%% Cell type:code id: tags:
```
CPU_fig = px.histogram(CPU_cutoff, x="ReqMemCPU",
title='User Requested RAM per CPU for all Jobs %i gigs or less'%UpperlimitGB,
labels={'ReqMemCPU':'ReqMemCPU'}, # can specify one label per df column
opacity=0.8,
log_y=True, # represent bars with log scale
marginal="box", # can be `box`, `violin`
hover_data=CPU_cutoff.columns,
nbins=30,
color_discrete_sequence=['goldenrod'] # color of histogram bars
)
CPU_fig.show()
# shows all user requested cpu memory for array and non array jobs
Jobs_fig = sns.distplot(JobsCPU_cutoff['ReqMemCPU'], kde=False, label='Jobs Requesting RAM per CPU for Array and Non Array Jobs', color = "green")
Jobs_fig.set_yscale('log')
plt.legend(prop={'size': 12},loc='upper right',bbox_to_anchor=(2.25, 1.0),ncol=1)
plt.title('Jobs Requesting RAM per CPU for all Jobs %i gigs or less'%UpperlimitGB)
plt.xlabel('Requested Gigs of RAM')
plt.ylabel('Number of Jobs Requesting')
```
%% Cell type:code id: tags:
```
CPU_nonarraytask_fig = px.histogram(CPU_nonarraytask, x="ReqMemCPU",
title='User Requested RAM per CPU for Non Array Jobs %i gigs or less'%UpperlimitGB,
labels={'ReqMemCPU':'ReqMemCPU'}, # can specify one label per df column
opacity=0.8,
log_y=True, # represent bars with log scale
marginal="box", # can be `box`, `violin`
hover_data=CPU_nonarraytask.columns,
nbins=30,
color_discrete_sequence=['goldenrod'] # color of histogram bars
)
CPU_nonarraytask_fig.show()
# shows all user requested cpu memory for array and non array jobs
Users_fig = sns.distplot(UsersCPU_cutoff['ReqMemCPU'], kde=False, label='Users Requesting RAM per CPU for Array and Non Array Jobs', color = "green")
Users_fig.set_yscale('log')
plt.legend(prop={'size': 12},loc='upper right',bbox_to_anchor=(2.25, 1.0),ncol=1)
plt.title('Users Requesting RAM per CPU for all Jobs %i gigs or less'%UpperlimitGB)
plt.xlabel('Requested Gigs of RAM')
plt.ylabel('Number of Users Requesting')
```
%% Cell type:code id: tags:
```
CPU_arraytask_fig = px.histogram(CPU_arraytask, x="ReqMemCPU",
title='User Requested RAM per CPU for Array Jobs %i gigs or less'%UpperlimitGB,
labels={'ReqMemCPU':'ReqMemCPU'}, # can specify one label per df column
opacity=0.8,
log_y=True, # represent bars with log scale
marginal="box", # can be `box`, `violin`
hover_data=CPU_arraytask.columns,
nbins=30,
color_discrete_sequence=['goldenrod'] # color of histogram bars
)
CPU_arraytask_fig.show()
```
#shows requested cpu memory for array jobs alongside requested cpu memory for non array jobs for easy comparison.
Jobs_arraytask_fig = sns.distplot(JobsCPU_arraytask['ReqMemCPU'], kde=False, label='Jobs Requesting RAM per CPU for Array Jobs', color = "green")
Jobs_arraytask_fig.set_yscale('log')
%% Cell type:code id: tags:
Jobs_nonarraytask_fig = sns.distplot(JobsCPU_nonarraytask['ReqMemCPU'], kde=False, label='Jobs Requesting RAM per CPU for Non Array Jobs')
Jobs_nonarraytask_fig.set_yscale('log')
```
Node_fig = px.histogram(Node_cutoff, x="ReqMemNode",
title='User Requested RAM per Node for all Jobs %i gigs or less'%UpperlimitGB,
labels={'ReqMemNode':'ReqMemNode'}, # can specify one label per df column
opacity=0.8,
log_y=True, # represent bars with log scale
marginal="box", # can be `box`, `violin`
hover_data=Node_cutoff.columns,
nbins=30,
color_discrete_sequence=['darkblue'] # color of histogram bars
)
Node_fig.show()
plt.legend(prop={'size': 12},loc='upper right',bbox_to_anchor=(2.05, 1.0),ncol=1)
plt.title('Jobs Requesting RAM per CPU for Array Jobs vs Not Array Jobs %i gigs or less'%UpperlimitGB)
plt.xlabel('Requested Gigs of RAM')
plt.ylabel('Number of Jobs Requesting')
```
%% Cell type:code id: tags:
```
Node_nonarraytask_fig = px.histogram(Node_nonarraytask, x="ReqMemNode",
title='User Requested RAM per Node for Non Array Jobs %i gigs or less'%UpperlimitGB,
labels={'ReqMemNode':'ReqMemNode'}, # can specify one label per df column
opacity=0.8,
log_y=True, # represent bars with log scale
marginal="box", # can be `box`, `violin`
hover_data=Node_nonarraytask.columns,
nbins=30,
color_discrete_sequence=['darkblue'] # color of histogram bars
)
Node_nonarraytask_fig.show()
```
#shows requested cpu memory for array jobs alongside requested cpu memory for non array jobs for easy comparison.
Users_arraytask_fig = sns.distplot(UsersCPU_arraytask['ReqMemCPU'], kde=False, label='Jobs Requesting RAM per CPU for Array Jobs', color = "green")
Users_arraytask_fig.set_yscale('log')
%% Cell type:code id: tags:
Users_nonarraytask_fig = sns.distplot(UsersCPU_nonarraytask['ReqMemCPU'], kde=False, label='Jobs Requesting RAM per CPU for Non Array Jobs')
Users_nonarraytask_fig.set_yscale('log')
```
Node_arraytask_fig = px.histogram(Node_arraytask, x="ReqMemNode",
title='User Requested RAM per Node for Array Jobs %i gigs or less'%UpperlimitGB,
labels={'ReqMemNode':'ReqMemNode'}, # can specify one label per df column
opacity=0.8,
log_y=True, # represent bars with log scale
marginal="box", # can be `box`, `violin`
hover_data=Node_arraytask.columns,
nbins=30,
color_discrete_sequence=['darkblue'] # color of histogram bars
)
Node_arraytask_fig.show()
plt.legend(prop={'size': 12},loc='upper right',bbox_to_anchor=(2.05, 1.0),ncol=1)
plt.title('Users Requesting RAM per CPU for Array Jobs vs Not Array Jobs %i gigs or less'%UpperlimitGB)
plt.xlabel('Requested Gigs of RAM')
plt.ylabel('Number of Jobs Requesting')
```
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment