Lightweight and efficient Rust gcs rsync for Google Cloud Storage.
gcs-rsync is faster than gsutil rsync according to the following benchmarks.
no hard limit to 32K objects or specific conf to compute state.
This crate can be used as a library or CLI. The API managing objects (download, upload, delete, ...) can be used independently.
Cargo.toml
[dependencies]
gcs-rsync = "0.4"cargo install --example gcs-rsync gcs-rsync
~/.cargo/bin/gcs-rsync
docker run --rm -it -v ${GOOGLE_APPLICATION_CREDENTIALS}:/creds.json:ro -v <YourFolderToUpload>:/source:ro superbeeeeeee/gcs-rsync -r -m /source gs://<YourBucket>/<YourFolderToUpload>/docker run --rm -it -v ${GOOGLE_APPLICATION_CREDENTIALS}:/creds.json:ro -v <YourFolderToDownloadTo>:/dest superbeeeeeee/gcs-rsync -r -m gs://<YourBucket>/<YourFolderToUpload>/ /destdocker run --rm -it -v ${GOOGLE_APPLICATION_CREDENTIALS}:/creds.json:ro -v <YourFolderToDownloadTo>:/dest superbeeeeeee/gcs-rsync -r -m gs://<YourBucket>/<YourFolderToUpload>/<YourPrefix> /dest-i (include glob pattern) and -x (exclude glob pattern) multiple times.
An example where any json or toml are included recursively except any test.json or test.toml recursively
docker run --rm -it -v ${GOOGLE_APPLICATION_CREDENTIALS}:/creds.json:ro -v <YourFolderToDownloadTo>:/dest superbeeeeeee/gcs-rsync -r -m -i **/*.json -i **/*.toml -x **/test.json -x **/test.toml
gs://<YourBucket>/YourFolderToUpload>/ /destwith_includes and with_excludes client builders are used to fill includes and excludes glob patterns.
Important note about gsutil: The gsutil ls command does not list all object items by default but instead list all prefixes while adding the -r flag slowdown gsutil performance. The ls performance command is very different to the rsync implementation.
- gcs-rsync: 2.2s/7MB
- gsutil: 9.93s/47MB
winner: gcs-rsync
rm -rf ~/Documents/test4 && cargo build --release --examples && /usr/bin/time -lp -- ./target/release/examples/bucket_to_folder_syncreal 2.20
user 0.13
sys 0.21
7606272 maximum resident set size
0 average shared memory size
0 average unshared data size
0 average unshared stack size
1915 page reclaims
0 page faults
0 swaps
0 block input operations
0 block output operations
394 messages sent
1255 messages received
0 signals received
54 voluntary context switches
5814 involuntary context switches
636241324 instructions retired
989595729 cycles elapsed
3895296 peak memory footprint
rm -rf ~/Documents/gsutil_test4 && mkdir ~/Documents/gsutil_test4 && /usr/bin/time -lp -- gsutil -m -q rsync -r gs://dev-bucket/sync_test4/ ~/Documents/gsutil_test4/Operation completed over 215 objects/50.3 KiB.
real 9.93
user 8.12
sys 2.35
47108096 maximum resident set size
0 average shared memory size
0 average unshared data size
0 average unshared stack size
196391 page reclaims
1 page faults
0 swaps
0 block input operations
0 block output operations
36089 messages sent
87309 messages received
5 signals received
38401 voluntary context switches
51924 involuntary context switches
12986389 instructions retired
12032672 cycles elapsed
593920 peak memory footprint
- gcs-rsync: 0.78s/8MB
- gsutil: 2.18s/47MB
winner: gcs-rsync (due to size and mtime check before crc32c like gsutil does)
cargo build --release --examples && /usr/bin/time -lp -- ./target/release/examples/bucket_to_folder_syncreal 1.79
user 0.13
sys 0.12
7864320 maximum resident set size
0 average shared memory size
0 average unshared data size
0 average unshared stack size
1980 page reclaims
0 page faults
0 swaps
0 block input operations
0 block output operations
397 messages sent
1247 messages received
0 signals received
42 voluntary context switches
4948 involuntary context switches
435013936 instructions retired
704782682 cycles elapsed
4141056 peak memory footprint
/usr/bin/time -lp -- gsutil -m -q rsync -r gs://test-bucket/sync_test4/ ~/Documents/gsutil_test4/real 2.18
user 1.37
sys 0.66
46899200 maximum resident set size
0 average shared memory size
0 average unshared data size
0 average unshared stack size
100108 page reclaims
1732 page faults
0 swaps
0 block input operations
0 block output operations
6311 messages sent
12752 messages received
4 signals received
6145 voluntary context switches
14219 involuntary context switches
13133297 instructions retired
13313536 cycles elapsed
602112 peak memory footprint
gsutil -m -q rsync -r -d ./your-dir gs://your-bucket/usr/bin/time -lp -- gsutil -m -q rsync -r gs://dev-bucket/sync_test4/ ~/Documents/gsutil_test4/All default functions related to authentication use GOOGLE_APPLICATION_CREDENTIALS env var as default conf like official Google libraries do on other languages (golang, dotnet)
Other functions (from and from_file) provide the custom integration mode.
For more info about OAuth2, see the related README in the oauth2 mod.
cargo test --libTEST_SERVICE_ACCOUNT=<PathToAServiceAccount> TEST_BUCKET=<BUCKET> TEST_PREFIX=<PREFIX> cargo test --no-fail-fastuse std::path::Path;
use gcs_rsync::storage::{credentials, Object, ObjectClient, StorageResult};
use tokio_util::codec::{BytesCodec, FramedRead};
#[tokio::main]
async fn main() -> StorageResult<()> {
let args = std::env::args().collect::<Vec<_>>();
let bucket = args[1].as_str();
let prefix = args[2].to_owned();
let file_path = args[3].to_owned();
let auc = Box::new(credentials::authorizeduser::default().await?);
let object_client = ObjectClient::new(auc).await?;
let file_path = Path::new(&file_path);
let name = file_path.file_name().unwrap().to_string_lossy();
let file = tokio::fs::File::open(file_path).await.unwrap();
let stream = FramedRead::new(file, BytesCodec::new());
let name = format!("{}/{}", prefix, name);
let object = Object::new(bucket, name.as_str())?;
object_client.upload(&object, stream).await.unwrap();
println!("object {} uploaded", &object);
Ok(())
}cargo run --release --example upload_object "<YourBucket>" "<YourPrefix>" "<YourFilePath>"use std::path::Path;
use futures::TryStreamExt;
use gcs_rsync::storage::{credentials, Object, ObjectClient, StorageResult};
use tokio::{
fs::File,
io::{AsyncWriteExt, BufWriter},
};
#[tokio::main]
async fn main() -> StorageResult<()> {
let args = std::env::args().collect::<Vec<_>>();
let bucket = args[1].as_str();
let name = args[2].as_str();
let output_path = args[3].to_owned();
let auc = Box::new(credentials::authorizeduser::default().await?);
let object_client = ObjectClient::new(auc).await?;
let file_name = Path::new(&name).file_name().unwrap().to_string_lossy();
let file_path = format!("{}/{}", output_path, file_name);
let object = Object::new(bucket, name)?;
let mut stream = object_client.download(&object).await.unwrap();
let file = File::create(&file_path).await.unwrap();
let mut buf_writer = BufWriter::new(file);
while let Some(data) = stream.try_next().await.unwrap() {
buf_writer.write_all(&data).await.unwrap();
}
buf_writer.flush().await.unwrap();
println!("object {} downloaded to {:?}", &object, file_path);
Ok(())
}cargo run --release --example download_object "<YourBucket>" "<YourObjectName>" "<YourAbsoluteExistingDirectory>"use std::path::Path;
use futures::TryStreamExt;
use gcs_rsync::storage::{Object, ObjectClient, StorageResult};
use tokio::{
fs::File,
io::{AsyncWriteExt, BufWriter},
};
#[tokio::main]
async fn main() -> StorageResult<()> {
let bucket = "gcs-rsync-dev-public";
let name = "hello.txt";
let object_client = ObjectClient::no_auth();
let file_name = Path::new(&name).file_name().unwrap().to_string_lossy();
let file_path = file_name.to_string();
let object = Object::new(bucket, "hello.txt")?;
let mut stream = object_client.download(&object).await.unwrap();
let file = File::create(&file_path).await.unwrap();
let mut buf_writer = BufWriter::new(file);
while let Some(data) = stream.try_next().await.unwrap() {
buf_writer.write_all(&data).await.unwrap();
}
buf_writer.flush().await.unwrap();
println!("object {} downloaded to {:?}", &object, file_path);
Ok(())
}cargo run --release --example download_public_object "<YourBucket>" "<YourObjectName>" "<YourAbsoluteExistingDirectory>"use gcs_rsync::storage::{credentials, Object, ObjectClient, StorageResult};
#[tokio::main]
async fn main() -> StorageResult<()> {
let args = std::env::args().collect::<Vec<_>>();
let bucket = args[1].as_str();
let name = args[2].as_str();
let object = Object::new(bucket, name)?;
let auc = Box::new(credentials::authorizeduser::default().await?);
let object_client = ObjectClient::new(auc).await?;
object_client.delete(&object).await?;
println!("object {} uploaded", &object);
Ok(())
}cargo run --release --example delete_object "<YourBucket>" "<YourPrefix>/<YourFileName>"use futures::TryStreamExt;
use gcs_rsync::storage::{credentials, ObjectClient, ObjectsListRequest, StorageResult};
#[tokio::main]
async fn main() -> StorageResult<()> {
let args = std::env::args().collect::<Vec<_>>();
let bucket = args[1].as_str();
let prefix = args[2].to_owned();
let auc = Box::new(credentials::authorizeduser::default().await?);
let object_client = ObjectClient::new(auc).await?;
let objects_list_request = ObjectsListRequest {
prefix: Some(prefix),
fields: Some("items(name),nextPageToken".to_owned()),
..Default::default()
};
object_client
.list(bucket, &objects_list_request)
.await
.try_for_each(|x| {
println!("{}", x.name.unwrap());
futures::future::ok(())
})
.await?;
Ok(())
}cargo run --release --example list_objects "<YourBucket>" "<YourPrefix>"use futures::TryStreamExt;
use gcs_rsync::storage::{credentials, ObjectClient, ObjectsListRequest, StorageResult};
#[tokio::main]
async fn main() -> StorageResult<()> {
let args = std::env::args().collect::<Vec<_>>();
let bucket = args[1].as_str();
let prefix = args[2].to_owned();
let auc = Box::new(
credentials::serviceaccount::default(
"https://www.googleapis.com/auth/devstorage.full_control",
)
.await?,
);
let object_client = ObjectClient::new(auc).await?;
let objects_list_request = ObjectsListRequest {
prefix: Some(prefix),
fields: Some("items(name),nextPageToken".to_owned()),
..Default::default()
};
object_client
.list(bucket, &objects_list_request)
.await
.try_for_each(|x| {
println!("{}", x.name.unwrap());
futures::future::ok(())
})
.await?;
Ok(())
}GOOGLE_APPLICATION_CREDENTIALS=<PathToJson> cargo r --release --example list_objects_service_account "<YourBucket>" "<YourPrefix>"list a bucket having more than 60K objects
time cargo run --release --example list_objects "<YourBucket>" "<YourPrefixHavingMoreThan60K>" | wc -lHumans are terrible at guessing-about-performance
export CARGO_PROFILE_RELEASE_DEBUG=true
sudo -- cargo flamegraph --example list_objects "<YourBucket>" "<YourPrefixHavingMoreThan60K>"cargo build --release --examples && /usr/bin/time -lp -- ./target/release/examples/list_objects "<YourBucket>" "<YourPrefixHavingMoreThan60K>"docker rust rust:alpine3.14
apk add --no-cache musl-dev pkgconfig openssl-dev
LDFLAGS="-static -L/usr/local/musl/lib" LD_LIBRARY_PATH=/usr/local/musl/lib:$LD_LIBRARY_PATH CFLAGS="-I/usr/local/musl/include" PKG_CONFIG_PATH=/usr/local/musl/lib/pkgconfig cargo build --release --target=x86_64-unknown-linux-musl --example bucket_to_folder_sync