Skip to content

GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO#34461

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
Hor911 wants to merge 2 commits into from
Closed

GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO #34461

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
308af41
Split arrow::FileReader::ReadRowGroups() for flexible async IO
Hor911 Mar 5, 2023
a82d751
Clang formatting
Hor911 Mar 6, 2023
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
30 changes: 27 additions & 3 deletions cpp/src/parquet/arrow/reader.cc
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -311,6 +311,13 @@ class FileReaderImpl : public FileReader {
return ReadTable(Iota(reader_->metadata()->num_columns()), table);
}

Status WillNeedRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& column_indices) override;

Status DecodeRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& column_indices,
std::shared_ptr<::arrow::Table>* out) override;

Status ReadRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& indices,
std::shared_ptr<Table>* table) override;
Expand DownExpand Up@@ -1216,9 +1223,8 @@ Status FileReaderImpl::GetColumn(int i, FileColumnIteratorFactory iterator_facto
return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& column_indices,
std::shared_ptr<Table>* out) {
Status FileReaderImpl::WillNeedRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& column_indices) {
RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

// PARQUET-1698/PARQUET-1820: pre-buffer row groups/column chunks if enabled
Expand All@@ -1229,6 +1235,24 @@ Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
reader_properties_.cache_options());
END_PARQUET_CATCH_EXCEPTIONS
}
return Status::OK();
}

Status FileReaderImpl::DecodeRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& column_indices,
std::shared_ptr<::arrow::Table>* out) {
RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
/*cpu_executor=*/nullptr);
ARROW_ASSIGN_OR_RAISE(*out, fut.MoveResult());
return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& column_indices,
std::shared_ptr<Table>* out) {
RETURN_NOT_OK(WillNeedRowGroups(row_groups, column_indices));

auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
/*cpu_executor=*/nullptr);
Expand Down
7 changes: 7 additions & 0 deletions cpp/src/parquet/arrow/reader.h
View file
Open in desktop
Original file line numberDiff line numberDiff line change
Expand Up@@ -249,6 +249,13 @@ class PARQUET_EXPORT FileReader {

virtual ::arrow::Status ReadRowGroup(int i, std::shared_ptr<::arrow::Table>* out) = 0;

virtual ::arrow::Status WillNeedRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& column_indices) = 0;
Comment on lines +252 to +253

@wjones127wjones127Mar 6, 2023

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

How does the caller know when the row groups are loaded? Should this return a Future instead?

@Hor911Hor911Mar 6, 2023

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

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

It can't be expressed in this API. This method is translated into call of arrow::io::RandomAccessFile::WillNeed()

No-op is default and valid implementation of WillNeed. It means that no preload/prefetch is provided in this RAF implementation. All work will be done when ReadAt or ReadAsync is called.

Current Arrow API expect tight coupling between FileReader, ParquetFileReader and intermediate Cache. It is not possible to provide true async decoupling w/o significant API changes (it was discussed somewhere).

For my technique to work, one should provide special implementation of arrow::io::RandomAccessFile which will receive WillNeed, download the data and signals it in some "hidden" way. Not perfect, but possible to reach what I needed w/o API changes and any other side effects.

I think I'll be able to provide you link ro real use case tomorrow.

@westonpacewestonpaceMar 6, 2023

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

#14723 adds a filesystem method for "read many". I would like to see this method support plugging and splitting in the same way that ReadRangeCache does today (then, ReadRangeCache will only be needed if you need true "caching"). Then I think we can use that instead of the ReadRangeCache.

This will allow local filesystems to rely on the OS for plugging & splitting and will allow remote filesystems like S3 to adapt the algorithm to their needs. It's also async and returns a future reliably so you can then return a future from this method (I agree that would be desired).

@wgtmacwgtmacMar 7, 2023

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

+1 for @westonpace's suggestion.

In addition, what if WillNeedRowGroups (w/ or w/o same inputs) has been called more than once? Maintaining the state is rather tricky according to my experience. If the new function only issues I/O hints to the RandomAccessFile, probably it is much easier to reason about the behavior directly from RandomAccessFile.


virtual ::arrow::Status DecodeRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& column_indices,
std::shared_ptr<::arrow::Table>* out) = 0;

virtual ::arrow::Status ReadRowGroups(const std::vector<int>& row_groups,
const std::vector<int>& column_indices,
std::shared_ptr<::arrow::Table>* out) = 0;
Expand Down
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all 
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO by Hor911 · Pull Request #34461 · apache/arrow · GitHub
Skip to content
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO#34461

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

Hor911
wants to merge
2
commits into

from

 Closed


GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO
#34461
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
308af41

Split arrow::FileReader::ReadRowGroups() for flexible async IO


Hor911 Mar 5, 2023
a82d751

Clang formatting


Hor911 Mar 6, 2023

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


30 changes: 27 additions & 3 deletions
cpp/src/parquet/arrow/reader.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -311,6 +311,13 @@ class FileReaderImpl : public FileReader {
 return ReadTable(Iota(reader_->metadata()->num_columns()), table);
 }

 Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) override;

 Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) override;

 Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& indices,
 std::shared_ptr<Table>* table) override;
Expand DownExpand Up@@ -1216,9 +1223,8 @@ Status FileReaderImpl::GetColumn(int i, FileColumnIteratorFactory iterator_facto
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
Status FileReaderImpl::WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 // PARQUET-1698/PARQUET-1820: pre-buffer row groups/column chunks if enabled
Expand All@@ -1229,6 +1235,24 @@ Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 reader_properties_.cache_options());
 END_PARQUET_CATCH_EXCEPTIONS
 }
 return Status::OK();
}

Status FileReaderImpl::DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
 ARROW_ASSIGN_OR_RAISE(*out, fut.MoveResult());
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
 RETURN_NOT_OK(WillNeedRowGroups(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
Expand Down

7 changes: 7 additions & 0 deletions
cpp/src/parquet/arrow/reader.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -249,6 +249,13 @@ class PARQUET_EXPORT FileReader {

 virtual ::arrow::Status ReadRowGroup(int i, std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) = 0;

Comment on lines

+252
 to 
+253

@wjones127wjones127Mar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

How does the caller know when the row groups are loaded? Should this return a Future instead?
@Hor911Hor911Mar 6, 2023

Copy link


Copy Markdown

Author
Choose a reason for hiding this comment

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

It can't be expressed in this API. This method is translated into call of arrow::io::RandomAccessFile::WillNeed()
No-op is default and valid implementation of WillNeed. It means that no preload/prefetch is provided in this RAF implementation. All work will be done when ReadAt or ReadAsync is called.
Current Arrow API expect tight coupling between FileReader, ParquetFileReader and intermediate Cache. It is not possible to provide true async decoupling w/o significant API changes (it was discussed somewhere).
For my technique to work, one should provide special implementation of arrow::io::RandomAccessFile which will receive WillNeed, download the data and signals it in some "hidden" way. Not perfect, but possible to reach what I needed w/o API changes and any other side effects.
I think I'll be able to provide you link ro real use case tomorrow.
@westonpacewestonpaceMar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

#14723 adds a filesystem method for "read many". I would like to see this method support plugging and splitting in the same way that ReadRangeCache does today (then, ReadRangeCache will only be needed if you need true "caching"). Then I think we can use that instead of the ReadRangeCache.
This will allow local filesystems to rely on the OS for plugging & splitting and will allow remote filesystems like S3 to adapt the algorithm to their needs. It's also async and returns a future reliably so you can then return a future from this method (I agree that would be desired).
@wgtmacwgtmacMar 7, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

+1 for @westonpace's suggestion.
In addition, what if WillNeedRowGroups (w/ or w/o same inputs) has been called more than once? Maintaining the state is rather tricky according to my experience. If the new function only issues I/O hints to the RandomAccessFile, probably it is much easier to reason about the behavior directly from RandomAccessFile.

 virtual ::arrow::Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Force GitHub README to respect dark mode
(function() {
var style = document.createElement('style');
style.textContent = '
.markdown-body {
color-scheme: dark light;
}
.markdown-body pre { background: #161b22 !important; }
.markdown-body code { background: rgba(110, 118, 129, 0.4) !important; }
.markdown-body table th, .markdown-body table td { border-color: #30363d !important; }
.markdown-body img { background: #0d1117; }
.markdown-body blockquote { border-left-color: #8b949e; }
.markdown-body hr { border-color: #30363d; }
';
document.head.appendChild(style);
})();
}
} catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO by Hor911 · Pull Request #34461 · apache/arrow · GitHub
Skip to content
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO#34461

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

Hor911
wants to merge
2
commits into

from

 Closed


GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO
#34461
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
308af41

Split arrow::FileReader::ReadRowGroups() for flexible async IO


Hor911 Mar 5, 2023
a82d751

Clang formatting


Hor911 Mar 6, 2023

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


30 changes: 27 additions & 3 deletions
cpp/src/parquet/arrow/reader.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -311,6 +311,13 @@ class FileReaderImpl : public FileReader {
 return ReadTable(Iota(reader_->metadata()->num_columns()), table);
 }

 Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) override;

 Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) override;

 Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& indices,
 std::shared_ptr<Table>* table) override;
Expand DownExpand Up@@ -1216,9 +1223,8 @@ Status FileReaderImpl::GetColumn(int i, FileColumnIteratorFactory iterator_facto
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
Status FileReaderImpl::WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 // PARQUET-1698/PARQUET-1820: pre-buffer row groups/column chunks if enabled
Expand All@@ -1229,6 +1235,24 @@ Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 reader_properties_.cache_options());
 END_PARQUET_CATCH_EXCEPTIONS
 }
 return Status::OK();
}

Status FileReaderImpl::DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
 ARROW_ASSIGN_OR_RAISE(*out, fut.MoveResult());
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
 RETURN_NOT_OK(WillNeedRowGroups(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
Expand Down

7 changes: 7 additions & 0 deletions
cpp/src/parquet/arrow/reader.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -249,6 +249,13 @@ class PARQUET_EXPORT FileReader {

 virtual ::arrow::Status ReadRowGroup(int i, std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) = 0;

Comment on lines

+252
 to 
+253

@wjones127wjones127Mar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

How does the caller know when the row groups are loaded? Should this return a Future instead?
@Hor911Hor911Mar 6, 2023

Copy link


Copy Markdown

Author
Choose a reason for hiding this comment

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

It can't be expressed in this API. This method is translated into call of arrow::io::RandomAccessFile::WillNeed()
No-op is default and valid implementation of WillNeed. It means that no preload/prefetch is provided in this RAF implementation. All work will be done when ReadAt or ReadAsync is called.
Current Arrow API expect tight coupling between FileReader, ParquetFileReader and intermediate Cache. It is not possible to provide true async decoupling w/o significant API changes (it was discussed somewhere).
For my technique to work, one should provide special implementation of arrow::io::RandomAccessFile which will receive WillNeed, download the data and signals it in some "hidden" way. Not perfect, but possible to reach what I needed w/o API changes and any other side effects.
I think I'll be able to provide you link ro real use case tomorrow.
@westonpacewestonpaceMar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

#14723 adds a filesystem method for "read many". I would like to see this method support plugging and splitting in the same way that ReadRangeCache does today (then, ReadRangeCache will only be needed if you need true "caching"). Then I think we can use that instead of the ReadRangeCache.
This will allow local filesystems to rely on the OS for plugging & splitting and will allow remote filesystems like S3 to adapt the algorithm to their needs. It's also async and returns a future reliably so you can then return a future from this method (I agree that would be desired).
@wgtmacwgtmacMar 7, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

+1 for @westonpace's suggestion.
In addition, what if WillNeedRowGroups (w/ or w/o same inputs) has been called more than once? Maintaining the state is rather tricky according to my experience. If the new function only issues I/O hints to the RandomAccessFile, probably it is much easier to reason about the behavior directly from RandomAccessFile.

 virtual ::arrow::Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Highlight search terms from Google/DuckDuckGo/Bing referrer
(function() {
var ref = document.referrer;
var terms = [];
if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) {
var url = new URL(ref);
var q = url.searchParams.get('q') || url.searchParams.get('p');
if (q) {
terms = q.split(/\s+/).filter(function(t) { return t.length > 2; });
}
}
if (terms.length === 0) return;
var style = document.createElement('style');
style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }';
document.head.appendChild(style);
function highlight(node) {
if (node.nodeType === 3) { // text node
var text = node.textContent;
var found = false;
terms.forEach(function(term) {
var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi');
if (regex.test(text)) {
found = true;
var frag = document.createDocumentFragment();
var parts = text.split(regex);
parts.forEach(function(part, i) {
if (i % 2 === 0) {
frag.appendChild(document.createTextNode(part));
} else {
var span = document.createElement('span');
span.className = 'userscript-highlight';
span.textContent = part;
frag.appendChild(span);
}
});
node.parentNode.replaceChild(frag, node);
}
});
} else if (node.nodeType === 1 && node.childNodes) { // element
var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT'];
if (!skipTags.includes(node.tagName)) {
Array.from(node.childNodes).forEach(highlight);
}
}
}
highlight(document.body);
// Re-highlight on dynamic content
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1 || node.nodeType === 3) highlight(node);
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO by Hor911 · Pull Request #34461 · apache/arrow · GitHub
Skip to content
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO#34461

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

Hor911
wants to merge
2
commits into

from

 Closed


GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO
#34461
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
308af41

Split arrow::FileReader::ReadRowGroups() for flexible async IO


Hor911 Mar 5, 2023
a82d751

Clang formatting


Hor911 Mar 6, 2023

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


30 changes: 27 additions & 3 deletions
cpp/src/parquet/arrow/reader.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -311,6 +311,13 @@ class FileReaderImpl : public FileReader {
 return ReadTable(Iota(reader_->metadata()->num_columns()), table);
 }

 Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) override;

 Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) override;

 Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& indices,
 std::shared_ptr<Table>* table) override;
Expand DownExpand Up@@ -1216,9 +1223,8 @@ Status FileReaderImpl::GetColumn(int i, FileColumnIteratorFactory iterator_facto
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
Status FileReaderImpl::WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 // PARQUET-1698/PARQUET-1820: pre-buffer row groups/column chunks if enabled
Expand All@@ -1229,6 +1235,24 @@ Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 reader_properties_.cache_options());
 END_PARQUET_CATCH_EXCEPTIONS
 }
 return Status::OK();
}

Status FileReaderImpl::DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
 ARROW_ASSIGN_OR_RAISE(*out, fut.MoveResult());
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
 RETURN_NOT_OK(WillNeedRowGroups(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
Expand Down

7 changes: 7 additions & 0 deletions
cpp/src/parquet/arrow/reader.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -249,6 +249,13 @@ class PARQUET_EXPORT FileReader {

 virtual ::arrow::Status ReadRowGroup(int i, std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) = 0;

Comment on lines

+252
 to 
+253

@wjones127wjones127Mar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

How does the caller know when the row groups are loaded? Should this return a Future instead?
@Hor911Hor911Mar 6, 2023

Copy link


Copy Markdown

Author
Choose a reason for hiding this comment

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

It can't be expressed in this API. This method is translated into call of arrow::io::RandomAccessFile::WillNeed()
No-op is default and valid implementation of WillNeed. It means that no preload/prefetch is provided in this RAF implementation. All work will be done when ReadAt or ReadAsync is called.
Current Arrow API expect tight coupling between FileReader, ParquetFileReader and intermediate Cache. It is not possible to provide true async decoupling w/o significant API changes (it was discussed somewhere).
For my technique to work, one should provide special implementation of arrow::io::RandomAccessFile which will receive WillNeed, download the data and signals it in some "hidden" way. Not perfect, but possible to reach what I needed w/o API changes and any other side effects.
I think I'll be able to provide you link ro real use case tomorrow.
@westonpacewestonpaceMar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

#14723 adds a filesystem method for "read many". I would like to see this method support plugging and splitting in the same way that ReadRangeCache does today (then, ReadRangeCache will only be needed if you need true "caching"). Then I think we can use that instead of the ReadRangeCache.
This will allow local filesystems to rely on the OS for plugging & splitting and will allow remote filesystems like S3 to adapt the algorithm to their needs. It's also async and returns a future reliably so you can then return a future from this method (I agree that would be desired).
@wgtmacwgtmacMar 7, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

+1 for @westonpace's suggestion.
In addition, what if WillNeedRowGroups (w/ or w/o same inputs) has been called more than once? Maintaining the state is rather tricky according to my experience. If the new function only issues I/O hints to the RandomAccessFile, probably it is much easier to reason about the behavior directly from RandomAccessFile.

 virtual ::arrow::Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Strip utm_, fbclid, gclid, etc. from all links on page
(function() {
var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content',
'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid',
'ref', 'ref_src', 'source', 'medium', 'campaign'];
function cleanUrl(url) {
try {
var u = new URL(url, window.location.origin);
var changed = false;
trackingParams.forEach(function(p) {
if (u.searchParams.has(p)) {
u.searchParams.delete(p);
changed = true;
}
});
return changed ? u.toString() : url;
} catch (e) {
return url;
}
}
function cleanLinks() {
document.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
cleanLinks();
var observer = new MutationObserver(function(mutations) {
mutations.forEach(function(m) {
m.addedNodes.forEach(function(node) {
if (node.nodeType === 1) {
if (node.tagName === 'A') cleanLinks();
node.querySelectorAll('a[href]').forEach(function(a) {
var clean = cleanUrl(a.href);
if (clean !== a.href) a.href = clean;
});
}
});
});
});
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); }
})();
(function(){
try {
var __m = "youtube.com";
var __re = new RegExp('^' + "youtube\\.com" + '
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO by Hor911 · Pull Request #34461 · apache/arrow · GitHub
Skip to content
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO#34461

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

Hor911
wants to merge
2
commits into

from

 Closed


GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO
#34461
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
308af41

Split arrow::FileReader::ReadRowGroups() for flexible async IO


Hor911 Mar 5, 2023
a82d751

Clang formatting


Hor911 Mar 6, 2023

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


30 changes: 27 additions & 3 deletions
cpp/src/parquet/arrow/reader.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -311,6 +311,13 @@ class FileReaderImpl : public FileReader {
 return ReadTable(Iota(reader_->metadata()->num_columns()), table);
 }

 Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) override;

 Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) override;

 Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& indices,
 std::shared_ptr<Table>* table) override;
Expand DownExpand Up@@ -1216,9 +1223,8 @@ Status FileReaderImpl::GetColumn(int i, FileColumnIteratorFactory iterator_facto
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
Status FileReaderImpl::WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 // PARQUET-1698/PARQUET-1820: pre-buffer row groups/column chunks if enabled
Expand All@@ -1229,6 +1235,24 @@ Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 reader_properties_.cache_options());
 END_PARQUET_CATCH_EXCEPTIONS
 }
 return Status::OK();
}

Status FileReaderImpl::DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
 ARROW_ASSIGN_OR_RAISE(*out, fut.MoveResult());
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
 RETURN_NOT_OK(WillNeedRowGroups(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
Expand Down

7 changes: 7 additions & 0 deletions
cpp/src/parquet/arrow/reader.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -249,6 +249,13 @@ class PARQUET_EXPORT FileReader {

 virtual ::arrow::Status ReadRowGroup(int i, std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) = 0;

Comment on lines

+252
 to 
+253

@wjones127wjones127Mar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

How does the caller know when the row groups are loaded? Should this return a Future instead?
@Hor911Hor911Mar 6, 2023

Copy link


Copy Markdown

Author
Choose a reason for hiding this comment

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

It can't be expressed in this API. This method is translated into call of arrow::io::RandomAccessFile::WillNeed()
No-op is default and valid implementation of WillNeed. It means that no preload/prefetch is provided in this RAF implementation. All work will be done when ReadAt or ReadAsync is called.
Current Arrow API expect tight coupling between FileReader, ParquetFileReader and intermediate Cache. It is not possible to provide true async decoupling w/o significant API changes (it was discussed somewhere).
For my technique to work, one should provide special implementation of arrow::io::RandomAccessFile which will receive WillNeed, download the data and signals it in some "hidden" way. Not perfect, but possible to reach what I needed w/o API changes and any other side effects.
I think I'll be able to provide you link ro real use case tomorrow.
@westonpacewestonpaceMar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

#14723 adds a filesystem method for "read many". I would like to see this method support plugging and splitting in the same way that ReadRangeCache does today (then, ReadRangeCache will only be needed if you need true "caching"). Then I think we can use that instead of the ReadRangeCache.
This will allow local filesystems to rely on the OS for plugging & splitting and will allow remote filesystems like S3 to adapt the algorithm to their needs. It's also async and returns a future reliably so you can then return a future from this method (I agree that would be desired).
@wgtmacwgtmacMar 7, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

+1 for @westonpace's suggestion.
In addition, what if WillNeedRowGroups (w/ or w/o same inputs) has been called more than once? Maintaining the state is rather tricky according to my experience. If the new function only issues I/O hints to the RandomAccessFile, probably it is much easier to reason about the behavior directly from RandomAccessFile.

 virtual ::arrow::Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Auto-enable theater mode on YouTube
(function() {
function tryTheater() {
var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]');
if (btn && !btn.classList.contains('activated')) {
btn.click();
}
}
// Try immediately
tryTheater();
// Try after navigation (SPA)
var lastUrl = location.href;
setInterval(function() {
if (location.href !== lastUrl) {
lastUrl = location.href;
setTimeout(tryTheater, 500);
}
}, 1000);
// Also try on player load
var observer = new MutationObserver(tryTheater);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO by Hor911 · Pull Request #34461 · apache/arrow · GitHub
Skip to content
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO#34461

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

Hor911
wants to merge
2
commits into

from

 Closed


GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO
#34461
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
308af41

Split arrow::FileReader::ReadRowGroups() for flexible async IO


Hor911 Mar 5, 2023
a82d751

Clang formatting


Hor911 Mar 6, 2023

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


30 changes: 27 additions & 3 deletions
cpp/src/parquet/arrow/reader.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -311,6 +311,13 @@ class FileReaderImpl : public FileReader {
 return ReadTable(Iota(reader_->metadata()->num_columns()), table);
 }

 Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) override;

 Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) override;

 Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& indices,
 std::shared_ptr<Table>* table) override;
Expand DownExpand Up@@ -1216,9 +1223,8 @@ Status FileReaderImpl::GetColumn(int i, FileColumnIteratorFactory iterator_facto
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
Status FileReaderImpl::WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 // PARQUET-1698/PARQUET-1820: pre-buffer row groups/column chunks if enabled
Expand All@@ -1229,6 +1235,24 @@ Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 reader_properties_.cache_options());
 END_PARQUET_CATCH_EXCEPTIONS
 }
 return Status::OK();
}

Status FileReaderImpl::DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
 ARROW_ASSIGN_OR_RAISE(*out, fut.MoveResult());
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
 RETURN_NOT_OK(WillNeedRowGroups(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
Expand Down

7 changes: 7 additions & 0 deletions
cpp/src/parquet/arrow/reader.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -249,6 +249,13 @@ class PARQUET_EXPORT FileReader {

 virtual ::arrow::Status ReadRowGroup(int i, std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) = 0;

Comment on lines

+252
 to 
+253

@wjones127wjones127Mar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

How does the caller know when the row groups are loaded? Should this return a Future instead?
@Hor911Hor911Mar 6, 2023

Copy link


Copy Markdown

Author
Choose a reason for hiding this comment

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

It can't be expressed in this API. This method is translated into call of arrow::io::RandomAccessFile::WillNeed()
No-op is default and valid implementation of WillNeed. It means that no preload/prefetch is provided in this RAF implementation. All work will be done when ReadAt or ReadAsync is called.
Current Arrow API expect tight coupling between FileReader, ParquetFileReader and intermediate Cache. It is not possible to provide true async decoupling w/o significant API changes (it was discussed somewhere).
For my technique to work, one should provide special implementation of arrow::io::RandomAccessFile which will receive WillNeed, download the data and signals it in some "hidden" way. Not perfect, but possible to reach what I needed w/o API changes and any other side effects.
I think I'll be able to provide you link ro real use case tomorrow.
@westonpacewestonpaceMar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

#14723 adds a filesystem method for "read many". I would like to see this method support plugging and splitting in the same way that ReadRangeCache does today (then, ReadRangeCache will only be needed if you need true "caching"). Then I think we can use that instead of the ReadRangeCache.
This will allow local filesystems to rely on the OS for plugging & splitting and will allow remote filesystems like S3 to adapt the algorithm to their needs. It's also async and returns a future reliably so you can then return a future from this method (I agree that would be desired).
@wgtmacwgtmacMar 7, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

+1 for @westonpace's suggestion.
In addition, what if WillNeedRowGroups (w/ or w/o same inputs) has been called more than once? Maintaining the state is rather tricky according to my experience. If the new function only issues I/O hints to the RandomAccessFile, probably it is much easier to reason about the behavior directly from RandomAccessFile.

 virtual ::arrow::Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Remove or un-stick sticky/fixed headers that block content
(function() {
function unstick() {
document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) {
if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') {
el.style.position = 'static';
el.style.top = 'auto';
el.style.zIndex = 'auto';
}
});
}
unstick();
var observer = new MutationObserver(unstick);
observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] });
})();
}
} catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); }
})();
(function(){
try {
var __m = "*";
var __re = new RegExp('^' + ".*" + '
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO by Hor911 · Pull Request #34461 · apache/arrow · GitHub
Skip to content
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO#34461

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

Hor911
wants to merge
2
commits into

from

 Closed


GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO
#34461
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
308af41

Split arrow::FileReader::ReadRowGroups() for flexible async IO


Hor911 Mar 5, 2023
a82d751

Clang formatting


Hor911 Mar 6, 2023

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


30 changes: 27 additions & 3 deletions
cpp/src/parquet/arrow/reader.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -311,6 +311,13 @@ class FileReaderImpl : public FileReader {
 return ReadTable(Iota(reader_->metadata()->num_columns()), table);
 }

 Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) override;

 Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) override;

 Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& indices,
 std::shared_ptr<Table>* table) override;
Expand DownExpand Up@@ -1216,9 +1223,8 @@ Status FileReaderImpl::GetColumn(int i, FileColumnIteratorFactory iterator_facto
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
Status FileReaderImpl::WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 // PARQUET-1698/PARQUET-1820: pre-buffer row groups/column chunks if enabled
Expand All@@ -1229,6 +1235,24 @@ Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 reader_properties_.cache_options());
 END_PARQUET_CATCH_EXCEPTIONS
 }
 return Status::OK();
}

Status FileReaderImpl::DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
 ARROW_ASSIGN_OR_RAISE(*out, fut.MoveResult());
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
 RETURN_NOT_OK(WillNeedRowGroups(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
Expand Down

7 changes: 7 additions & 0 deletions
cpp/src/parquet/arrow/reader.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -249,6 +249,13 @@ class PARQUET_EXPORT FileReader {

 virtual ::arrow::Status ReadRowGroup(int i, std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) = 0;

Comment on lines

+252
 to 
+253

@wjones127wjones127Mar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

How does the caller know when the row groups are loaded? Should this return a Future instead?
@Hor911Hor911Mar 6, 2023

Copy link


Copy Markdown

Author
Choose a reason for hiding this comment

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

It can't be expressed in this API. This method is translated into call of arrow::io::RandomAccessFile::WillNeed()
No-op is default and valid implementation of WillNeed. It means that no preload/prefetch is provided in this RAF implementation. All work will be done when ReadAt or ReadAsync is called.
Current Arrow API expect tight coupling between FileReader, ParquetFileReader and intermediate Cache. It is not possible to provide true async decoupling w/o significant API changes (it was discussed somewhere).
For my technique to work, one should provide special implementation of arrow::io::RandomAccessFile which will receive WillNeed, download the data and signals it in some "hidden" way. Not perfect, but possible to reach what I needed w/o API changes and any other side effects.
I think I'll be able to provide you link ro real use case tomorrow.
@westonpacewestonpaceMar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

#14723 adds a filesystem method for "read many". I would like to see this method support plugging and splitting in the same way that ReadRangeCache does today (then, ReadRangeCache will only be needed if you need true "caching"). Then I think we can use that instead of the ReadRangeCache.
This will allow local filesystems to rely on the OS for plugging & splitting and will allow remote filesystems like S3 to adapt the algorithm to their needs. It's also async and returns a future reliably so you can then return a future from this method (I agree that would be desired).
@wgtmacwgtmacMar 7, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

+1 for @westonpace's suggestion.
In addition, what if WillNeedRowGroups (w/ or w/o same inputs) has been called more than once? Maintaining the state is rather tricky according to my experience. If the new function only issues I/O hints to the RandomAccessFile, probably it is much easier to reason about the behavior directly from RandomAccessFile.

 virtual ::arrow::Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;
Expand Down

, 'i');
if (__m === '*' || __re.test(location.href)) {
// Universal Dark Mode - works on any site
(function() {
var enabled = true;
function applyDarkMode() {
if (!enabled) return;
// Create style element if it doesn't exist
var style = document.getElementById('universal-dark-mode-style');
if (!style) {
style = document.createElement('style');
style.id = 'universal-dark-mode-style';
document.head.appendChild(style);
}
// Dark mode CSS - inverts colors but preserves images/video
style.textContent = '
/* Invert everything except media */
html {
filter: invert(1) hue-rotate(180deg) !important;
background: #1a1a2e !important;
}
/* Restore images, videos, iframes, canvas */
img, video, iframe, canvas, svg, picture, [style*="background-image"] {
filter: invert(1) hue-rotate(180deg) !important;
}
/* Preserve specific elements that should not be inverted */
.no-dark-mode, .no-dark-mode *,
[data-theme="light"], [data-theme="light"],
.ace_editor, .ace_editor *,
.CodeMirror, .CodeMirror *,
.monaco-editor, .monaco-editor *,
.markdown-body pre, .markdown-body pre *,
.highlight, .highlight *,
pre code, pre code * {
filter: none !important;
}
/* Fix common UI elements */
.modal, .popup, .dropdown-menu, .tooltip, .popover {
filter: invert(1) hue-rotate(180deg) !important;
background: #2d2d44 !important;
border-color: #444 !important;
}
/* Scrollbars */
::-webkit-scrollbar { background: #1a1a2e !important; }
::-webkit-scrollbar-thumb { background: #444 !important; }
::-webkit-scrollbar-thumb:hover { background: #555 !important; }
/* Selection */
::selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; }
';
}
function removeDarkMode() {
var style = document.getElementById('universal-dark-mode-style');
if (style) style.remove();
}
// Toggle with Alt+Shift+D
document.addEventListener('keydown', function(e) {
if (e.altKey && e.shiftKey && e.key === 'D') {
e.preventDefault();
enabled = !enabled;
if (enabled) {
applyDarkMode();
console.log('[Universal Dark Mode] Enabled');
} else {
removeDarkMode();
console.log('[Universal Dark Mode] Disabled');
}
}
});
// Apply on load
applyDarkMode();
// Re-apply on dynamic content
var observer = new MutationObserver(function(mutations) {
if (enabled && !document.getElementById('universal-dark-mode-style')) {
applyDarkMode();
}
});
observer.observe(document.head, { childList: true });
console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle');
})();
}
} catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); }
})();
})();
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO by Hor911 · Pull Request #34461 · apache/arrow · GitHub
Skip to content
GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO#34461

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

Hor911
wants to merge
2
commits into

from

 Closed


GH-34460: [C++][Parquet] Split arrow::FileReader::ReadRowGroups() for flexible async IO
#34461
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
308af41

Split arrow::FileReader::ReadRowGroups() for flexible async IO


Hor911 Mar 5, 2023
a82d751

Clang formatting


Hor911 Mar 6, 2023

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


30 changes: 27 additions & 3 deletions
cpp/src/parquet/arrow/reader.cc

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -311,6 +311,13 @@ class FileReaderImpl : public FileReader {
 return ReadTable(Iota(reader_->metadata()->num_columns()), table);
 }

 Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) override;

 Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) override;

 Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& indices,
 std::shared_ptr<Table>* table) override;
Expand DownExpand Up@@ -1216,9 +1223,8 @@ Status FileReaderImpl::GetColumn(int i, FileColumnIteratorFactory iterator_facto
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
Status FileReaderImpl::WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 // PARQUET-1698/PARQUET-1820: pre-buffer row groups/column chunks if enabled
Expand All@@ -1229,6 +1235,24 @@ Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 reader_properties_.cache_options());
 END_PARQUET_CATCH_EXCEPTIONS
 }
 return Status::OK();
}

Status FileReaderImpl::DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) {
 RETURN_NOT_OK(BoundsCheck(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
 ARROW_ASSIGN_OR_RAISE(*out, fut.MoveResult());
 return Status::OK();
}

Status FileReaderImpl::ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<Table>* out) {
 RETURN_NOT_OK(WillNeedRowGroups(row_groups, column_indices));

 auto fut = DecodeRowGroups(/*self=*/nullptr, row_groups, column_indices,
 /*cpu_executor=*/nullptr);
Expand Down

7 changes: 7 additions & 0 deletions
cpp/src/parquet/arrow/reader.h

View file


Open in desktop

Original file line numberDiff line numberDiff line change
Expand Up@@ -249,6 +249,13 @@ class PARQUET_EXPORT FileReader {

 virtual ::arrow::Status ReadRowGroup(int i, std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status WillNeedRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices) = 0;

Comment on lines

+252
 to 
+253

@wjones127wjones127Mar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

How does the caller know when the row groups are loaded? Should this return a Future instead?
@Hor911Hor911Mar 6, 2023

Copy link


Copy Markdown

Author
Choose a reason for hiding this comment

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

It can't be expressed in this API. This method is translated into call of arrow::io::RandomAccessFile::WillNeed()
No-op is default and valid implementation of WillNeed. It means that no preload/prefetch is provided in this RAF implementation. All work will be done when ReadAt or ReadAsync is called.
Current Arrow API expect tight coupling between FileReader, ParquetFileReader and intermediate Cache. It is not possible to provide true async decoupling w/o significant API changes (it was discussed somewhere).
For my technique to work, one should provide special implementation of arrow::io::RandomAccessFile which will receive WillNeed, download the data and signals it in some "hidden" way. Not perfect, but possible to reach what I needed w/o API changes and any other side effects.
I think I'll be able to provide you link ro real use case tomorrow.
@westonpacewestonpaceMar 6, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

#14723 adds a filesystem method for "read many". I would like to see this method support plugging and splitting in the same way that ReadRangeCache does today (then, ReadRangeCache will only be needed if you need true "caching"). Then I think we can use that instead of the ReadRangeCache.
This will allow local filesystems to rely on the OS for plugging & splitting and will allow remote filesystems like S3 to adapt the algorithm to their needs. It's also async and returns a future reliably so you can then return a future from this method (I agree that would be desired).
@wgtmacwgtmacMar 7, 2023

Copy link


Copy Markdown

Member
Choose a reason for hiding this comment

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

+1 for @westonpace's suggestion.
In addition, what if WillNeedRowGroups (w/ or w/o same inputs) has been called more than once? Maintaining the state is rather tricky according to my experience. If the new function only issues I/O hints to the RandomAccessFile, probably it is much easier to reason about the behavior directly from RandomAccessFile.

 virtual ::arrow::Status DecodeRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;

 virtual ::arrow::Status ReadRowGroups(const std::vector<int>& row_groups,
 const std::vector<int>& column_indices,
 std::shared_ptr<::arrow::Table>* out) = 0;
Expand Down