Skip to content
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.

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

Added sampling functionality #85

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open
Changes from all commits
Commits
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
7 changes: 7 additions & 0 deletions cloudwatchlogs-with-dlq/cloudwatchlogs_lambda.js
Original file line number Diff line number Diff line change
@@ -17,6 +17,7 @@ var consoleFormatRegex = /^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}.\d{3}Z\s(\w+?-\w+
var requestIdRegex = /(?:RequestId:|Z)\s+([\w\d\-]+)/;
var url = require('url');
var vpcutils = require('./vpcutils');
var samplingutils = require('./samplingutils');
var SumoLogsClient = require('./sumo-dlq-function-utils').SumoLogsClient;
var Utils = require('./sumo-dlq-function-utils').Utils;

@@ -81,6 +82,7 @@ function getConfig(env) {
"LogFormat": env.LOG_FORMAT || 'Others',
"compressData": env.COMPRESS_DATA || true,
"vpcCIDRPrefix": env.VPC_CIDR_PREFIX || '',
"samplingPercent": env.SAMPLING_PERCENT || '',
"includeLogInfo": ("INCLUDE_LOG_INFO" in env) ? env.INCLUDE_LOG_INFO === "true" : false,
"includeSecurityGroupInfo": ("INCLUDE_SECURITY_GROUP_INFO" in env) ? env.INCLUDE_SECURITY_GROUP_INFO === "true" : false
};
@@ -112,10 +114,15 @@ function transformRecords(config, records) {

function filterRecords(config, records) {
var filteredRecords = records;
console.log(config)
if (config.LogFormat.startsWith("VPC") && config.vpcCIDRPrefix) {
filteredRecords = vpcutils.discardInternalTraffic(config.vpcCIDRPrefix, records);
console.log(records.length - filteredRecords.length + " records discarded as InternalTraffic");
}
if (config.samplingPercent) {
filteredRecords = samplingutils.sampleTraffic(config.samplingPercent, records);
console.log(records.length - filteredRecords.length + " records discarded via Sampling");
}
return filteredRecords;
}

2 changes: 1 addition & 1 deletion cloudwatchlogs-with-dlq/package.json
Original file line number Diff line number Diff line change
@@ -10,7 +10,7 @@
"devDependencies": {},
"scripts": {
"test": "node -e 'require('./test').test()'",
"build": "rm -f cloudwatchlogs-with-dlq.zip && zip -r cloudwatchlogs-with-dlq.zip DLQProcessor.js cloudwatchlogs_lambda.js vpcutils.js package.json sumo-dlq-function-utils/ node_modules/",
"build": "rm -f cloudwatchlogs-with-dlq.zip && zip -r cloudwatchlogs-with-dlq.zip DLQProcessor.js cloudwatchlogs_lambda.js vpcutils.js samplingutils.js package.json sumo-dlq-function-utils/ node_modules/",
"prod_deploy": "python -c 'from test_cwl_lambda import prod_deploy;prod_deploy()'"
},
"author": "Himanshu Pal",
38 changes: 38 additions & 0 deletions cloudwatchlogs-with-dlq/samplingutils.js
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
function sampleTraffic(samplingPercent, records) {
if (!samplingPercent) {
return records;
}
var filteredRecords = [];
var toBeSamplesRecords = [];
records.forEach(function (log) {
if ("logLevel" in log.message.message) {
if(Number.isInteger(log.message.message.logLevel)){
if (log.message.message.logLevel >= 4) {
filteredRecords.push(log);
} else {
toBeSamplesRecords.push(log);
}
} else {
filteredRecords.push(log);
}
} else {
filteredRecords.push(log);
}
});
if(samplingPercent == 0) {
var increment = 0;
} else {
var increment = 100/samplingPercent;
Copy link
Collaborator

Choose a reason for hiding this comment

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

let's type cast this to integer so that increment is a natural number always.
Also I think we should have a condition samplingPercent > 0 and <= 100 and then we can run a for loop inside it.
Also would be good to break this into two separate functions one for filtering and other for sampling. Filtering one returns filtered + tobesampled records and takes records as input
while sampling one takes tobesampled records and sampling percent as input and returns sampled records
later on we merge the filtered and sampled records

}

if(increment > 0) {
for (var i = 0; i < toBeSamplesRecords.length; i += increment) {
filteredRecords.push(toBeSamplesRecords[i]);
}
}
return filteredRecords;
}

module.exports = {
sampleTraffic: sampleTraffic
};