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.

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

Flush if next record would make the request size too big #9

Closed
wants to merge 5 commits into from
Closed

Flush if next record would make the request size too big #9

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
eef22e7
Flush if next record would make the request size too big
Oct 7, 2016
6231a05
Account for buffer size and properly flush if needed
Apr 4, 2017
9c9c979
Remove call to len()
Apr 4, 2017
2622d72
Take partition key into account when calculating the size of the requ…
Apr 4, 2017
47d7d7f
Keep megabyte constant private
Apr 5, 2017
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
20 changes: 16 additions & 4 deletions kinesis.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,10 +9,10 @@ import (
k "github.com/aws/aws-sdk-go/service/kinesis"
)

// Size limits as defined by http://docs.aws.amazon.com/kinesis/latest/APIReference/API_PutRecords.html.
const (
maxRecordSize = 1 << 20 // 1MiB
maxRequestSize = 5 << 20 // 5MiB
megaByte = 1 << 20
maxRecordSize = megaByte
maxRequestSize = 5 * megaByte
)

// Errors.
Expand All @@ -39,7 +39,7 @@ func New(config Config) *Producer {

// Put record `data` using `partitionKey`. This method is thread-safe.
func (p *Producer) Put(data []byte, partitionKey string) error {
if len(data) > maxRecordSize {
if len(data)+len(partitionKey) > maxRecordSize {
return ErrRecordSizeExceeded
}

Expand Down Expand Up @@ -73,6 +73,7 @@ func (p *Producer) Stop() {
// loop and flush at the configured interval, or when the buffer is exceeded.
func (p *Producer) loop() {
buf := make([]*k.PutRecordsRequestEntry, 0, p.BufferSize)
bufSize := 0
tick := time.NewTicker(p.FlushInterval)
drain := false

Expand All @@ -82,11 +83,21 @@ func (p *Producer) loop() {
for {
select {
case record := <-p.records:
recordSize := len(*record.PartitionKey) + len(record.Data)

if bufSize+recordSize > maxRequestSize {
p.flush(buf, "request size")
buf = nil
bufSize = 0
}

buf = append(buf, record)
bufSize += recordSize

if len(buf) >= p.BufferSize {
p.flush(buf, "buffer size")
buf = nil
bufSize = 0
}

if drain && len(p.records) == 0 {
Expand All @@ -97,6 +108,7 @@ func (p *Producer) loop() {
if len(buf) > 0 {
p.flush(buf, "interval")
buf = nil
bufSize = 0
}
case <-p.done:
drain = true
Expand Down