Skip to content
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

Upgrade to object_store 0.9.0 and arrow 50.0.0 #8758

Merged
merged 14 commits into from
Jan 14, 2024
Merged

Upgrade to object_store 0.9.0 and arrow 50.0.0 #8758

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
7e7a57a
Prepare object_store 0.9.0
tustvold Jan 5, 2024
17c1a23
Update test
tustvold Jan 5, 2024
6a861df
Update to arrow 50.0.0
tustvold Jan 8, 2024
46bec97
Update sqllogictest
tustvold Jan 8, 2024
9f723ac
Merge remote-tracking branch 'upstream/main' into prepare-object-stor…
tustvold Jan 9, 2024
4851323
Update sqllogictests
tustvold Jan 9, 2024
285fb33
Format
tustvold Jan 9, 2024
1e4eca2
Use nullif
tustvold Jan 9, 2024
8353982
Merge remote-tracking branch 'apache/main' into prepare-object-store-…
alamb Jan 12, 2024
99c7177
Use released version of arrow-rs
alamb Jan 12, 2024
727b881
Update README to remove references to SIMD
alamb Jan 12, 2024
89cb067
unpatch datafusion-cli
alamb Jan 12, 2024
0c4a8a1
Adjust memory sizes in tests
alamb Jan 12, 2024
5a6d80d
Restore test without explicit region
alamb Jan 12, 2024
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
28 changes: 19 additions & 9 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,13 +32,13 @@ rust-version = "1.70"
version = "34.0.0"

[workspace.dependencies]
arrow = { version = "49.0.0", features = ["prettyprint"] }
arrow-array = { version = "49.0.0", default-features = false, features = ["chrono-tz"] }
arrow-buffer = { version = "49.0.0", default-features = false }
arrow-flight = { version = "49.0.0", features = ["flight-sql-experimental"] }
arrow-ipc = { version = "49.0.0", default-features = false, features = ["lz4"] }
arrow-ord = { version = "49.0.0", default-features = false }
arrow-schema = { version = "49.0.0", default-features = false }
arrow = { version = "50.0.0", features = ["prettyprint"] }
arrow-array = { version = "50.0.0", default-features = false, features = ["chrono-tz"] }
arrow-buffer = { version = "50.0.0", default-features = false }
arrow-flight = { version = "50.0.0", features = ["flight-sql-experimental"] }
arrow-ipc = { version = "50.0.0", default-features = false, features = ["lz4"] }
arrow-ord = { version = "50.0.0", default-features = false }
arrow-schema = { version = "50.0.0", default-features = false }
async-trait = "0.1.73"
bigdecimal = "0.4.1"
bytes = "1.4"
Expand All @@ -64,9 +64,9 @@ indexmap = "2.0.0"
itertools = "0.12"
log = "^0.4"
num_cpus = "1.13.0"
object_store = { version = "0.8.0", default-features = false }
object_store = { version = "0.9.0", default-features = false }
parking_lot = "0.12"
parquet = { version = "49.0.0", default-features = false, features = ["arrow", "async", "object_store"] }
parquet = { version = "50.0.0", default-features = false, features = ["arrow", "async", "object_store"] }
rand = "0.8"
rstest = "0.18.0"
serde_json = "1"
Expand All @@ -92,3 +92,13 @@ opt-level = 3
overflow-checks = false
panic = 'unwind'
rpath = false

[patch.crates-io]
arrow = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-array = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-buffer = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-flight = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-ipc = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-ord = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-schema = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
parquet = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
1 change: 0 additions & 1 deletion benchmarks/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,6 @@ rust-version = "1.70"
[features]
ci = []
default = ["mimalloc"]
simd = ["datafusion/simd"]
Copy link
Contributor

Choose a reason for hiding this comment

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

arrow 50 removed the manual SIMD implementation and now relies on auto vectorization - apache/arrow-rs#5184

snmalloc = ["snmalloc-rs"]

[dependencies]
Expand Down
113 changes: 54 additions & 59 deletions datafusion-cli/Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

15 changes: 12 additions & 3 deletions datafusion-cli/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ rust-version = "1.70"
readme = "README.md"

[dependencies]
arrow = "49.0.0"
arrow = "50.0.0"
async-trait = "0.1.41"
aws-config = "0.55"
aws-credential-types = "0.55"
Expand All @@ -40,9 +40,9 @@ dirs = "4.0.0"
env_logger = "0.9"
futures = "0.3"
mimalloc = { version = "0.1", default-features = false }
object_store = { version = "0.8.0", features = ["aws", "gcp"] }
object_store = { version = "0.9.0", features = ["aws", "gcp"] }
parking_lot = { version = "0.12" }
parquet = { version = "49.0.0", default-features = false }
parquet = { version = "50.0.0", default-features = false }
regex = "1.8"
rustyline = "11.0"
tokio = { version = "1.24", features = ["macros", "rt", "rt-multi-thread", "sync", "parking_lot", "signal"] }
Expand All @@ -53,3 +53,12 @@ assert_cmd = "2.0"
ctor = "0.2.0"
predicates = "3.0"
rstest = "0.17"

[patch.crates-io]
arrow = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-array = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-buffer = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-ipc = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-ord = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
arrow-schema = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
parquet = { git = "https://github.com/tustvold/arrow-rs.git", rev = "06490e8ab2b986784d2998cfcf74cbf9c025ef10" }
8 changes: 0 additions & 8 deletions datafusion-cli/src/exec.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -340,14 +340,6 @@ mod tests {
let session_token = "fake_session_token";
let location = "s3://bucket/path/file.parquet";

// Missing region
alamb marked this conversation as resolved.
Show resolved Hide resolved
let sql = format!("CREATE EXTERNAL TABLE test STORED AS PARQUET
OPTIONS('access_key_id' '{access_key_id}', 'secret_access_key' '{secret_access_key}') LOCATION '{location}'");
let err = create_external_table_test(location, &sql)
.await
.unwrap_err();
assert!(err.to_string().contains("Missing region"));

// Should be OK
let sql = format!("CREATE EXTERNAL TABLE test STORED AS PARQUET
OPTIONS('access_key_id' '{access_key_id}', 'secret_access_key' '{secret_access_key}', 'region' '{region}', 'session_token' '{session_token}') LOCATION '{location}'");
Expand Down
1 change: 0 additions & 1 deletion datafusion/core/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,6 @@ parquet = ["datafusion-common/parquet", "dep:parquet"]
pyarrow = ["datafusion-common/pyarrow", "parquet"]
regex_expressions = ["datafusion-physical-expr/regex_expressions", "datafusion-optimizer/regex_expressions"]
serde = ["arrow-schema/serde"]
simd = ["arrow/simd"]
alamb marked this conversation as resolved.
Show resolved Hide resolved
unicode_expressions = ["datafusion-physical-expr/unicode_expressions", "datafusion-optimizer/unicode_expressions", "datafusion-sql/unicode_expressions"]

[dependencies]
Expand Down
2 changes: 1 addition & 1 deletion datafusion/core/src/datasource/physical_plan/csv.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -375,7 +375,7 @@ impl FileOpener for CsvOpener {

let range = match calculated_range {
RangeCalculation::Range(None) => None,
RangeCalculation::Range(Some(range)) => Some(range),
RangeCalculation::Range(Some(range)) => Some(range.into()),
RangeCalculation::TerminateEarly => {
return Ok(
futures::stream::poll_fn(move |_| Poll::Ready(None)).boxed()
Expand Down
Loading
Loading