[pbs-devel] [PATCH proxmox 1/1] proxmox: add sparse_copy(_async) to tools::io

[Dominik Csapak <d.csapak@proxmox.com>]

this is able to seek the target instead of writing zeroes, which
generates sparse files where supported

Signed-off-by: Dominik Csapak <d.csapak@proxmox.com>
---
changes from RFC:
* use minimal buffer_is_zero version that generates fast code on release
  compilation
 proxmox/src/tools/io/mod.rs | 70 +++++++++++++++++++++++++++++++++++++
 1 file changed, 70 insertions(+)

diff --git a/proxmox/src/tools/io/mod.rs b/proxmox/src/tools/io/mod.rs
index 2e92ebb..299d19c 100644
--- a/proxmox/src/tools/io/mod.rs
+++ b/proxmox/src/tools/io/mod.rs
@@ -3,8 +3,78 @@
 //! The [`ReadExt`] trait provides additional operations for handling byte buffers for types
 //! implementing [`Read`](std::io::Read).
 
+use std::io::{self, Read, Write, Seek, SeekFrom, ErrorKind};
+
 mod read;
 pub use read::*;
 
 mod write;
 pub use write::*;
+
+fn buffer_is_zero(buf: &[u8]) -> bool {
+    !buf
+        .chunks(128)
+        .map(|aa|
+            aa.iter().fold(0, |a, b| a|b) != 0
+        ).any(|a| a)
+}
+
+/// copy similar to io::copy, but seeks the target when encountering
+/// zero bytes instead of writing them
+pub fn sparse_copy<R: Read + ?Sized, W: Write + Seek + ?Sized>(
+    reader: &mut R,
+    writer: &mut W,
+) -> Result<u64, io::Error> {
+    let mut buf = crate::tools::byte_buffer::ByteBuffer::new();
+    let mut written = 0;
+    loop {
+        let len = match buf.read_from(reader) {
+            Ok(0) => return Ok(written),
+            Ok(len) => len,
+            Err(ref e) if e.kind() == ErrorKind::Interrupted => continue,
+            Err(e) => return Err(e),
+        };
+
+        if buffer_is_zero(&buf[..]) {
+            writer.seek(SeekFrom::Current(len as i64))?;
+        } else {
+            writer.write_all(&buf[..])?;
+        }
+        buf.clear();
+        written += len as u64;
+    }
+}
+
+#[cfg(feature = "tokio")]
+use tokio::io::{AsyncReadExt, AsyncWriteExt, AsyncSeekExt};
+
+#[cfg(feature = "tokio")]
+/// copy similar to tokio::io::copy, but seeks the target when encountering
+/// zero bytes instead of writing them
+pub async fn sparse_copy_async<R, W>(
+    reader: &mut R,
+    writer: &mut W,
+) -> Result<u64, io::Error>
+where
+    R: AsyncReadExt + Unpin,
+    W: AsyncWriteExt + AsyncSeekExt + Unpin,
+{
+    let mut buf = crate::tools::byte_buffer::ByteBuffer::new();
+    let mut written = 0;
+    loop {
+        let len = match buf.read_from_async(reader).await {
+            Ok(0) => return Ok(written),
+            Ok(len) => len,
+            Err(ref e) if e.kind() == ErrorKind::Interrupted => continue,
+            Err(e) => return Err(e),
+        };
+
+        if buffer_is_zero(&buf[..]) {
+            writer.seek(SeekFrom::Current(len as i64)).await?;
+        } else {
+            writer.write_all(&buf[..]).await?;
+        }
+        buf.clear();
+        written += len as u64;
+    }
+}
-- 
2.20.1