Skip to content

Redesign of performance logging and support for Graylog #213

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Jun 20, 2018
Merged

Redesign of performance logging and support for Graylog #213

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
88095a6
Adding support graylog performance logging
victorusu Mar 21, 2018
501694d
Merge branch 'master' into feature/graylog-perf-support
May 24, 2018
e27c532
Redesign of performance logging.
May 25, 2018
9231954
Decouple regression tests from logging logic
May 29, 2018
59aceb1
Documentation for new performance logging feature
Jun 4, 2018
c8149e5
Merge branch 'master' into feature/graylog-perf-support
Jun 7, 2018
f6edec3
More unit tests for logging.
Jun 11, 2018
9670422
Address PR comments
Jun 14, 2018
a48bf1c
Fix Graylog logging
Jun 19, 2018
ecda652
Merge branch 'master' into feature/graylog-perf-support
vkarak Jun 20, 2018
71f4e30
Ignore performance logging if not configured
Jun 20, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
80 changes: 37 additions & 43 deletions config/cscs-pbs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,12 @@


class ReframeSettings:
_reframe_module = 'reframe'
_job_poll_intervals = [1, 2, 3]
_job_submit_timeout = 60
_checks_path = ['checks/']
_checks_path_recurse = True
_site_configuration = {
reframe_module = 'reframe'
job_poll_intervals = [1, 2, 3]
job_submit_timeout = 60
checks_path = ['checks/']
checks_path_recurse = True
site_configuration = {
'systems': {
'dom': {
'descr': 'Dom TDS',
Expand Down Expand Up @@ -102,60 +102,54 @@ class ReframeSettings:
},
}

_logging_config = {
logging_config = {
'level': 'DEBUG',
'handlers': {
'reframe.log': {
'handlers': [
{
'type': 'file',
'name': 'reframe.log',
'level': 'DEBUG',
'format': '[%(asctime)s] %(levelname)s: '
'%(check_info)s: %(message)s',
'append': False,
},

# Output handling
'&1': {
{
'type': 'stream',
'name': 'stdout',
'level': 'INFO',
'format': '%(message)s'
},
'reframe.out': {
{
'type': 'file',
'name': 'reframe.out',
'level': 'INFO',
'format': '%(message)s',
'append': False,
}
}
]
}

@property
def version(self):
return self._version

@property
def reframe_module(self):
return self._reframe_module

@property
def job_poll_intervals(self):
return self._job_poll_intervals

@property
def job_submit_timeout(self):
return self._job_submit_timeout

@property
def checks_path(self):
return self._checks_path

@property
def checks_path_recurse(self):
return self._checks_path_recurse

@property
def site_configuration(self):
return self._site_configuration

@property
def logging_config(self):
return self._logging_config
perf_logging_config = {
'level': 'DEBUG',
'handlers': [
{
'type': 'filelog',
'prefix': '%(check_system)s/%(check_partition)s',
'level': 'INFO',
'format': (
'%(asctime)s|reframe %(version)s|'
'%(check_info)s|jobid=%(check_jobid)s|'
'%(check_perf_var)s=%(check_perf_value)s|'
'ref=%(check_perf_ref)s '
'(l=%(check_perf_lower_thres)s, '
'u=%(check_perf_upper_thres)s)'
),
'append': True
}
]
}


settings = ReframeSettings()
95 changes: 50 additions & 45 deletions config/cscs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,12 @@


class ReframeSettings:
_reframe_module = 'reframe'
_job_poll_intervals = [1, 2, 3]
_job_submit_timeout = 60
_checks_path = ['checks/']
_checks_path_recurse = True
_site_configuration = {
reframe_module = 'reframe'
job_poll_intervals = [1, 2, 3]
job_submit_timeout = 60
checks_path = ['checks/']
checks_path_recurse = True
site_configuration = {
Copy link
Contributor

@vkarak vkarak May 25, 2018

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I made all these attributes public and removed properties. See the PR description for a rationale. Opinions?

'systems': {
'daint': {
'descr': 'Piz Daint',
Expand Down Expand Up @@ -324,7 +324,7 @@ class ReframeSettings:
'--exec-policy=async',
'--strict',
'--output=$APPS/UES/$USER/regression/maintenance',
'--logdir=$APPS/UES/$USER/regression/maintenance/logs',
'--perflogdir=$APPS/UES/$USER/regression/maintenance/logs',
'--stage=$SCRATCH/regression/maintenance/stage',
'--reservation=maintenance',
'--save-log-files',
Expand All @@ -335,7 +335,7 @@ class ReframeSettings:
'--exec-policy=async',
'--strict',
'--output=$APPS/UES/$USER/regression/production',
'--logdir=$APPS/UES/$USER/regression/production/logs',
'--perflogdir=$APPS/UES/$USER/regression/production/logs',
'--stage=$SCRATCH/regression/production/stage',
'--save-log-files',
'--tag=production',
Expand All @@ -345,60 +345,65 @@ class ReframeSettings:
}
}

_logging_config = {
logging_config = {
'level': 'DEBUG',
'handlers': {
'reframe.log': {
'handlers': [
{
'type': 'file',
'name': 'reframe.log',
'level': 'DEBUG',
'format': '[%(asctime)s] %(levelname)s: '
'%(check_info)s: %(message)s',
'append': False,
},

# Output handling
'&1': {
{
'type': 'stream',
'name': 'stdout',
'level': 'INFO',
'format': '%(message)s'
},
'reframe.out': {
{
'type': 'file',
'name': 'reframe.out',
'level': 'INFO',
'format': '%(message)s',
'append': False,
}
}
]
}

@property
def version(self):
return self._version

@property
def reframe_module(self):
return self._reframe_module

@property
def job_poll_intervals(self):
return self._job_poll_intervals

@property
def job_submit_timeout(self):
return self._job_submit_timeout

@property
def checks_path(self):
return self._checks_path

@property
def checks_path_recurse(self):
return self._checks_path_recurse

@property
def site_configuration(self):
return self._site_configuration

@property
def logging_config(self):
return self._logging_config
perf_logging_config = {
'level': 'DEBUG',
'handlers': [
{
'type': 'graylog',
'host': 'your-server-here',
'port': 12345,
'level': 'INFO',
'format': '%(message)s',
'extras': {
'facility': 'reframe',
'data-version': '1.0',
}
},
{
'type': 'filelog',
'prefix': '%(check_system)s/%(check_partition)s',
'level': 'INFO',
'format': (
'%(asctime)s|reframe %(version)s|'
'%(check_info)s|jobid=%(check_jobid)s|'
'%(check_perf_var)s=%(check_perf_value)s|'
'ref=%(check_perf_ref)s '
'(l=%(check_perf_lower_thres)s, '
'u=%(check_perf_upper_thres)s)'
Copy link
Contributor

@vkarak vkarak May 25, 2018

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is the produced performance log. Let me know if you like it:

2018-05-25T17:17:40|reframe 2.13-dev0|magma_zsymmetrize_prod on dom:gpu using PrgEnv-gnu|jobid=746609|cpu_perf=0.916756|ref=0.93 (l=None, u=0.05)
2018-05-25T17:17:40|reframe 2.13-dev0|magma_zsymmetrize_prod on dom:gpu using PrgEnv-gnu|jobid=746609|gpu_perf=158.9385|ref=158.4 (l=None, u=0.05)

),
'append': True
}
]
}


settings = ReframeSettings()
Loading