Skip to content

Sky's Chunking #188

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

Closed
jacomago wants to merge 2 commits into from
Closed

Sky's Chunking #188

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3126ff9
Adds chunking to the processing
jacomago Oct 8, 2025
9bb7ef5
Add chunking to saveAll
jacomago Oct 8, 2025
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
94 changes: 56 additions & 38 deletions src/main/java/org/phoebus/channelfinder/ChannelRepository.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,12 +45,15 @@

import java.io.IOException;
import java.text.MessageFormat;
import java.util.ArrayList;
import java.util.Collection;
import java.util.Collections;
import java.util.Comparator;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Optional;
import java.util.Spliterator;
import java.util.logging.Level;
import java.util.logging.Logger;
import java.util.stream.Collectors;
Expand Down Expand Up @@ -187,53 +190,68 @@ public Channel save(Channel channel) {
@SuppressWarnings("unchecked")
@Override
public <S extends Channel> Iterable<S> saveAll(Iterable<S> channels) {
// Create a list of all channel names
List<String> ids = StreamSupport.stream(channels.spliterator(), false).map(Channel::getName).collect(Collectors.toList());

try {
Map<String, Channel> existingChannels = findAllById(ids).stream().collect(Collectors.toMap(Channel::getName, c -> c));

BulkRequest.Builder br = new BulkRequest.Builder();

for (Channel channel : channels) {
if (existingChannels.containsKey(channel.getName())) {
// merge with existing channel
Channel updatedChannel = existingChannels.get(channel.getName());
if (channel.getOwner() != null && !channel.getOwner().isEmpty())
updatedChannel.setOwner(channel.getOwner());
updatedChannel.addProperties(channel.getProperties());
updatedChannel.addTags(channel.getTags());
br.operations(op -> op.index(i -> i.index(esService.getES_CHANNEL_INDEX())
.id(updatedChannel.getName())
.document(JsonData.of(updatedChannel, new JacksonJsonpMapper(objectMapper)))));
Spliterator<S> split = channels.spliterator();
int chunkSize = Integer.parseInt(System.getProperty("repository.chunking.size"));

// Create a list of all channel names
List<S> resultList = new ArrayList<>();
while(true) {
List<Channel> chunk = new ArrayList<>(chunkSize);
for (int i = 0; i < chunkSize && split.tryAdvance(chunk::add); i++){};
if (chunk.isEmpty()) break;
try {
List<String> ids = StreamSupport.stream(channels.spliterator(), false)
.map(Channel::getName)
.toList();

BulkResponse result = getBulkResponseForChannels(chunk, ids);
// Log errors, if any
if (result.errors()) {
logger.log(Level.SEVERE, TextUtil.BULK_HAD_ERRORS);
for (BulkResponseItem item : result.items()) {
if (item.error() != null) {
logger.log(Level.SEVERE, () -> item.error().reason());
}
}
// TODO cleanup? or throw exception?
} else {
br.operations(op -> op.index(i -> i.index(esService.getES_CHANNEL_INDEX())
.id(channel.getName())
.document(JsonData.of(channel, new JacksonJsonpMapper(objectMapper)))));
resultList.addAll((Collection<? extends S>) findAllById(ids));
}
} catch (IOException e) {
String message = MessageFormat.format(TextUtil.FAILED_TO_INDEX_CHANNELS, channels);
logger.log(Level.SEVERE, message, e);
throw new ResponseStatusException(HttpStatus.INTERNAL_SERVER_ERROR, message, null);

}
BulkResponse result = null;
result = client.bulk(br.refresh(Refresh.True).build());
// Log errors, if any
if (result.errors()) {
logger.log(Level.SEVERE, TextUtil.BULK_HAD_ERRORS);
for (BulkResponseItem item : result.items()) {
if (item.error() != null) {
logger.log(Level.SEVERE, () -> item.error().reason());
}
}
// TODO cleanup? or throw exception?
}
return resultList;
}

private <S extends Channel> BulkResponse getBulkResponseForChannels(Iterable<S> channels, List<String> ids) throws IOException {
Map<String, Channel> existingChannels = findAllById(ids).stream().collect(Collectors.toMap(Channel::getName, c -> c));

BulkRequest.Builder br = new BulkRequest.Builder();

for (Channel channel : channels) {
if (existingChannels.containsKey(channel.getName())) {
// merge with existing channel
Channel updatedChannel = existingChannels.get(channel.getName());
if (channel.getOwner() != null && !channel.getOwner().isEmpty())
updatedChannel.setOwner(channel.getOwner());
updatedChannel.addProperties(channel.getProperties());
updatedChannel.addTags(channel.getTags());
br.operations(op -> op.index(i -> i.index(esService.getES_CHANNEL_INDEX())
.id(updatedChannel.getName())
.document(JsonData.of(updatedChannel, new JacksonJsonpMapper(objectMapper)))));
} else {
return (Iterable<S>) findAllById(ids);
br.operations(op -> op.index(i -> i.index(esService.getES_CHANNEL_INDEX())
.id(channel.getName())
.document(JsonData.of(channel, new JacksonJsonpMapper(objectMapper)))));
}
} catch (IOException e) {
String message = MessageFormat.format(TextUtil.FAILED_TO_INDEX_CHANNELS, channels);
logger.log(Level.SEVERE, message, e);
throw new ResponseStatusException(HttpStatus.INTERNAL_SERVER_ERROR, message, null);

}
return null;
return client.bulk(br.refresh(Refresh.True).build());
}

/**
Expand Down
14 changes: 13 additions & 1 deletion src/main/java/org/phoebus/channelfinder/processors/ChannelProcessorService.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,9 @@
import org.springframework.core.task.TaskExecutor;
import org.springframework.stereotype.Service;

import java.util.ArrayList;
import java.util.List;
import java.util.Spliterator;
import java.util.logging.Level;
import java.util.logging.Logger;
import java.util.stream.Collectors;
Expand Down Expand Up @@ -44,9 +46,19 @@ public void sendToProcessors(List<Channel> channels) {
}
taskExecutor.execute(() -> channelProcessors.stream()
.filter(ChannelProcessor::enabled)

.forEach(channelProcessor -> {
try {
channelProcessor.process(channels);
Spliterator<Channel> split = channels.stream().spliterator();
int chunkSize = Integer.parseInt(System.getProperty("processors.chunking.size"));

while(true) {
List<Channel> chunk = new ArrayList<>(chunkSize);
for (int i = 0; i < chunkSize && split.tryAdvance(chunk::add); i++){};
if (chunk.isEmpty()) break;
channelProcessor.process(chunk);
}

} catch (Exception e) {
logger.log(Level.WARNING, "ChannelProcessor " + channelProcessor.getClass().getName() + " throws exception", e);
}
Expand Down
6 changes: 6 additions & 0 deletions src/main/resources/application.properties
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -114,6 +114,12 @@ [email protected]@
# DEBUG level will log all requests and responses to and from the REST end points
logging.level.org.springframework.web.filter.CommonsRequestLoggingFilter=INFO

################ Repository ##################################################
repository.chunking.size=10000

################ Processor ##################################################
processors.chunking.size=10000

################ Archiver Appliance Configuration Processor #################
aa.urls={'default': 'http://localhost:17665'}
# Comma-separated list of archivers to use if archiver_property_name is null
Expand Down
Loading