[pbs-devel] [PATCH proxmox-backup v3 4/5] datastore: data blob: increase compression throughput

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

by not using `zstd::stream::copy_encode`, because that has an allocation
pattern that reduces throughput if the target/source storage and the
network are faster than the chunk creation.

instead use `zstd_safe::compress` which shouldn't do any big
allocations, since we provide the target buffer.

To handle the case that the target buffer is too small, we now ignore
all zstd error and continue with the uncompressed data, logging the error
except if the target buffer is too small.

Some benchmarks on my machine from tmpfs to a datastore on tmpfs:

Type                without patches (MiB/s)  with patches (MiB/s)
.img file           ~614                     ~767
pxar one big file   ~657                     ~807
pxar small files    ~576                     ~627

Signed-off-by: Dominik Csapak <d.csapak@proxmox.com>
---
changes from v2:
* use zstd_safe instead of zstd
 pbs-datastore/src/data_blob.rs | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/pbs-datastore/src/data_blob.rs b/pbs-datastore/src/data_blob.rs
index adf5a932..4e689364 100644
--- a/pbs-datastore/src/data_blob.rs
+++ b/pbs-datastore/src/data_blob.rs
@@ -147,39 +147,40 @@ impl DataBlob {
 
             DataBlob { raw_data }
         } else {
-            let max_data_len = data.len() + std::mem::size_of::<DataBlobHeader>();
+            let header_len = std::mem::size_of::<DataBlobHeader>();
+            let max_data_len = data.len() + header_len;
+            let mut raw_data = vec![0; max_data_len];
             if compress {
-                let mut comp_data = Vec::with_capacity(max_data_len);
-
                 let head = DataBlobHeader {
                     magic: COMPRESSED_BLOB_MAGIC_1_0,
                     crc: [0; 4],
                 };
                 unsafe {
-                    comp_data.write_le_value(head)?;
+                    (&mut raw_data[0..header_len]).write_le_value(head)?;
                 }
 
-                zstd::stream::copy_encode(data, &mut comp_data, 1)?;
-
-                if comp_data.len() < max_data_len {
-                    let mut blob = DataBlob {
-                        raw_data: comp_data,
-                    };
-                    blob.set_crc(blob.compute_crc());
-                    return Ok(blob);
+                match zstd_safe::compress(&mut raw_data[header_len..], data, 1) {
+                    Ok(size) if size <= data.len() => {
+                        raw_data.truncate(header_len + size);
+                        let mut blob = DataBlob { raw_data };
+                        blob.set_crc(blob.compute_crc());
+                        return Ok(blob);
+                    }
+                    Err(err) if !zstd_error_is_target_too_small(err) => {
+                        log::warn!("zstd compression error: {err}");
+                    }
+                    _ => {}
                 }
             }
 
-            let mut raw_data = Vec::with_capacity(max_data_len);
-
             let head = DataBlobHeader {
                 magic: UNCOMPRESSED_BLOB_MAGIC_1_0,
                 crc: [0; 4],
             };
             unsafe {
-                raw_data.write_le_value(head)?;
+                (&mut raw_data[0..header_len]).write_le_value(head)?;
             }
-            raw_data.extend_from_slice(data);
+            (&mut raw_data[header_len..]).write_all(data)?;
 
             DataBlob { raw_data }
         };
-- 
2.39.2



_______________________________________________
pbs-devel mailing list
pbs-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pbs-devel