Merge branch 'main' into cn/chunk-updating

datafusion/Cargo.toml

@@ -8,7 +8,7 @@ description = "Re-exports datafusion at a specific version"
 [dependencies]
 
 # Rename to workaround doctest bug
-# Turn off optional datafusion features (e.g. don't get support for crypo functions or avro)
+# Turn off optional datafusion features (e.g. don't get support for crypto functions or avro)
 upstream = { git = "https://github.com/apache/arrow-datafusion.git", rev="8ddd99c8432fdac2c236040973f984a4146f18b7", default-features = false, package = "datafusion" }
 datafusion-proto = { git = "https://github.com/apache/arrow-datafusion.git", rev="8ddd99c8432fdac2c236040973f984a4146f18b7" }
 workspace-hack = { path = "../workspace-hack"}

docs/valgrind.md

@@ -68,7 +68,7 @@ The simplest way to use the massif output is to use [massif-visualizer]:
 ![massif-visualizer screenshot](./images/screenshot_massif_visualizer.jpeg)
 
 [heappy]: https://github.com/mkmik/heappy
-[jemalloc]: ttps://github.com/jemalloc/jemalloc
+[jemalloc]: https://github.com/jemalloc/jemalloc
 [lazycell]: https://crates.io/crates/lazycell
 [Massif]: https://valgrind.org/docs/manual/ms-manual.html
 [massif-visualizer]: https://github.com/KDE/massif-visualizer

iox_data_generator/benches/point_generation.rs

@@ -77,7 +77,7 @@ pub fn agent_pre_generated(c: &mut Criterion) {
     let spec: DataSpec = toml::from_str(r#"
 name = "storage_cardinality_example"
 
-# Values are automatically generated before the agents are intialized. They generate tag key/value pairs
+# Values are automatically generated before the agents are initialized. They generate tag key/value pairs
 # with the name of the value as the tag key and the evaluated template as the value. These pairs
 # are Arc wrapped so they can be shared across tagsets and used in the agents as pre-generated data.
 [[values]]
@@ -122,7 +122,7 @@ template = "{{id}}"
 cardinality = 10
 
 # makes a tagset so every bucket appears in every partition. The other tags are descriptive and don't
-# increase the cardiality beyond count(bucket) * count(partition). Later this example will use the
+# increase the cardinality beyond count(bucket) * count(partition). Later this example will use the
 # agent and measurement generation to take this base tagset and increase cardinality on a per-agent basis.
 [[tag_sets]]
 name = "bucket_set"

iox_data_generator/schemas/big_db.toml

@@ -137,7 +137,7 @@ f64_range = [0.0, 1.0]
 
 [[database_writers]]
 agents = [
-    {name = "high", sampling_interval = "10s", count = 10}, # 5,000 meassurmeents
+    {name = "high", sampling_interval = "10s", count = 10}, # 5,000 measurements
     {name = "medium", sampling_interval = "10s", count = 20}, # 20,000 measurements
     {name = "low", sampling_interval = "10s", count = 20} # 200,000 measurements
 ]

iox_data_generator/schemas/cap-write.toml

@@ -84,7 +84,7 @@ name = "mem"
     i64_range = [0, 10000000]
 
     [[agents.measurements.fields]]
-    name = "avaiable_percent"
+    name = "available_percent"
     f64_range = [0.0, 100.0]
 
     [[agents.measurements.fields]]

iox_data_generator/schemas/full_example.toml

@@ -33,7 +33,7 @@
 
 name = "full_example"
 
-# Values are automatically generated before the agents are intialized. They generate tag key/value pairs
+# Values are automatically generated before the agents are initialized. They generate tag key/value pairs
 # with the name of the value as the tag key and the evaluated template as the value. These pairs
 # can be shared across tagsets and used in the agents as pre-generated data.
 [[values]]
@@ -55,7 +55,7 @@ template = "foo_{{guid}}_{{id}}_{{random 5}}_{{format-time \"%Y-%m-%d\"}}"
 name = "t1"
 template = "t1_{{id}}"
 cardinality = 3
-# each t1 genereated will reference one of t3 and one of foo_bar. As each t1 is generated
+# each t1 generated will reference one of t3 and one of foo_bar. As each t1 is generated
 # it will loop through the t3 and foo_bar collections. So the 3rd t1 that is generated will
 # reference the first t3 and foo_bar
 has_one = ["t3", "foo_bar"]
@@ -85,7 +85,7 @@ name = "example"
 # for_each specifies how to iterate through the values to generate tagsets. If you want to
 # use values that belong_to others or are a has_one, specify their parent first. For values
 # without relationships, you'll get a combined cardinality of each multiplied by the other.
-# In this eaxmple we get cardinality of card(t1) * card(foo_bar) * card(other). The has_one
+# In this example we get cardinality of card(t1) * card(foo_bar) * card(other). The has_one
 # members of t1 don't increase cardinality.
 for_each = [
     "t1",

iox_data_generator/schemas/storage_cardinality_example.toml

@@ -1,6 +1,6 @@
 name = "storage_cardinality_example"
 
-# Values are automatically generated before the agents are intialized. They generate tag key/value pairs
+# Values are automatically generated before the agents are initialized. They generate tag key/value pairs
 # with the name of the value as the tag key and the evaluated template as the value. These pairs
 # are Arc wrapped so they can be shared across tagsets and used in the agents as pre-generated data.
 [[values]]
@@ -45,7 +45,7 @@ template = "{{id}}"
 cardinality = 10
 
 # makes a tagset so every bucket appears in every partition. The other tags are descriptive and don't
-# increase the cardiality beyond count(bucket) * count(partition). Later this example will use the
+# increase the cardinality beyond count(bucket) * count(partition). Later this example will use the
 # agent and measurement generation to take this base tagset and increase cardinality on a per-agent basis.
 [[tag_sets]]
 name = "bucket_set"