Encode the compressed data at the start internal buffer. This ensures
the returned slice maintains the entire capacity and is available for
subsequent use.
When we pool / reuse string buffers, this will help considerably.
Improvements over previous commit:
```
name old time/op new time/op delta
EncodeStrings/10/batch-8 542ns ± 1% 355ns ± 2% -34.53% (p=0.008 n=5+5)
EncodeStrings/100/batch-8 5.29µs ± 1% 3.58µs ± 2% -32.20% (p=0.008 n=5+5)
EncodeStrings/1000/batch-8 48.6µs ± 0% 36.2µs ± 2% -25.40% (p=0.008 n=5+5)
name old alloc/op new alloc/op delta
EncodeStrings/10/batch-8 704B ± 0% 0B -100.00% (p=0.008 n=5+5)
EncodeStrings/100/batch-8 9.47kB ± 0% 0.00kB -100.00% (p=0.008 n=5+5)
EncodeStrings/1000/batch-8 90.1kB ± 0% 0.0kB -100.00% (p=0.008 n=5+5)
name old allocs/op new allocs/op delta
EncodeStrings/10/batch-8 0.00 0.00 ~ (all equal)
EncodeStrings/100/batch-8 1.00 ± 0% 0.00 -100.00% (p=0.008 n=5+5)
EncodeStrings/1000/batch-8 1.00 ± 0% 0.00 -100.00% (p=0.008 n=5+5)
```
This commit adds a tsm1 function for encoding a batch of booleans into a
provided buffer.
The following benchmarks compare the performance of the existing
iterator based encoders, and the new batch oriented encoders using
randomly generated sets of booleans.
This commit adds a tsm1 function for encoding a batch of strings into a
provided buffer. The new function also shares the buffer between the
input data and the snappy encoded output, reducing allocations.
The following benchmarks compare the performance of the existing
iterator based encoders, and the new batch oriented encoders using
randomly generated strings.
name old time/op new time/op delta
EncodeStrings/10 2.14µs ± 4% 1.42µs ± 4% -33.56% (p=0.000 n=10+10)
EncodeStrings/100 12.7µs ± 3% 10.9µs ± 2% -14.46% (p=0.000 n=10+10)
EncodeStrings/1000 132µs ± 2% 114µs ± 2% -13.88% (p=0.000 n=10+9)
name old alloc/op new alloc/op delta
EncodeStrings/10 657B ± 0% 704B ± 0% +7.15% (p=0.000 n=10+10)
EncodeStrings/100 6.14kB ± 0% 9.47kB ± 0% +54.14% (p=0.000 n=10+10)
EncodeStrings/1000 61.4kB ± 0% 90.1kB ± 0% +46.66% (p=0.000 n=10+10)
name old allocs/op new allocs/op delta
EncodeStrings/10 3.00 ± 0% 0.00 -100.00% (p=0.000 n=10+10)
EncodeStrings/100 3.00 ± 0% 1.00 ± 0% -66.67% (p=0.000 n=10+10)
EncodeStrings/1000 3.00 ± 0% 1.00 ± 0% -66.67% (p=0.000 n=10+10)
This commit adds a tsm1 function for encoding a batch of floats into a
buffer. Further, it replaces the `bitstream` library used in the
existing encoders (and all the current decoders) with inlined bit
expressions within the encoder, significantly reducing the function call
overhead for larger batches.
The following benchmarks compare the performance of the existing
iterator based encoders, and the new batch oriented encoders. They look
at a sequential input slice and a randomly generated input slice.
name old time/op new time/op delta
EncodeFloats/10_seq 1.14µs ± 3% 0.24µs ± 3% -78.94% (p=0.000 n=10+10)
EncodeFloats/10_ran 1.69µs ± 2% 0.21µs ± 3% -87.43% (p=0.000 n=10+10)
EncodeFloats/100_seq 7.07µs ± 1% 1.72µs ± 1% -75.62% (p=0.000 n=7+9)
EncodeFloats/100_ran 15.8µs ± 4% 1.8µs ± 1% -88.60% (p=0.000 n=10+9)
EncodeFloats/1000_seq 50.2µs ± 3% 16.2µs ± 2% -67.66% (p=0.000 n=10+10)
EncodeFloats/1000_ran 174µs ± 2% 16µs ± 2% -90.77% (p=0.000 n=10+10)
name old alloc/op new alloc/op delta
EncodeFloats/10_seq 0.00B 0.00B ~ (all equal)
EncodeFloats/10_ran 0.00B 0.00B ~ (all equal)
EncodeFloats/100_seq 0.00B 0.00B ~ (all equal)
EncodeFloats/100_ran 0.00B 0.00B ~ (all equal)
EncodeFloats/1000_seq 0.00B 0.00B ~ (all equal)
EncodeFloats/1000_ran 0.00B 0.00B ~ (all equal)
name old allocs/op new allocs/op delta
EncodeFloats/10_seq 0.00 0.00 ~ (all equal)
EncodeFloats/10_ran 0.00 0.00 ~ (all equal)
EncodeFloats/100_seq 0.00 0.00 ~ (all equal)
EncodeFloats/100_ran 0.00 0.00 ~ (all equal)
EncodeFloats/1000_seq 0.00 0.00 ~ (all equal)
EncodeFloats/1000_ran 0.00 0.00 ~ (all equal)
This keeps file compatability by just writing out zeros for the
sizes and offsets. Perhaps it's ok to just nuke everything and
remove the data.
It also keeps the hll package because it seems generally useful
even if it's not currently being used.
This commit removes the remaining bits of the fields index. In doing
so, the buildCursor method on the engine would need to be updated.
It turns out, that code was statically dead, so delete it and anything
that depended on it. Additionally, delete anything as reported by
the unused tool in the tsdb package.
The generate commands have been modified to take advantage of the new
functionality in Go 1.11 that allows `go run` to execute a package
instead of individual files.
This functionality combined with Go modules allows us to execute a
package directly out of our pinned dependencies rather than accidentally
picking up another binary outside of the build environment.
This also simplifies the Makefile because they no longer have to be
responsible for installing the correct tooling since the Go command
takes care of that logic. It also makes it so that the Makefiles with
file generation can now be invoked from their appropriate subdirectories
so they are contained within the directory itself rather than relying on
values in the top level Makefile.
It is now possible to generate all files within this project by using:
go generate ./...
Or the Makefile can continue to be used.
This commit also copies over the special copy of `tmpl` that the storage
engine uses within the influxdb repository. It was never copied over so
using `go generate` on these packages did not work.
We are moving the necessary code for 2.0 from the influxdb 1.X
repository to the platform 2.0 repository. The logger is an unnecessary
dependency on the old influxdb that is making life more complicated.
This pulls in the code that allows doing reads with flux into the
platform repo, and removes extra.go.
The reusable portion is under storage/reads, where the concrete
implementation for one of the platform's engines is in
storage/readservice.
In order to make this more reusable, the cursors had to move into
their own package, decoupling it from all of the other code in the
tsdb package. tsdb/cursors is this new package, and type/function
aliases have been added to the tsdb package to point at it.
The models package already is very light on transitive dependencies
and so it was allowed to be depended on in a concrete way in the
cursors package.
Finally, the protobuf definitions for issuing GRPC reads has been
moved into its own package for two reasons:
1. It's a clean separation, and helps keep it that way.
2. Many/most consumers will not be using GRPC. We just
use the datatypes to express the API which helps making
a GRPC server easier.
It is left up to future refactorings (specifically ones that involve
GPRC) to determine if these types should remain, or if there is a
cleaner way.
There's still some dependencies on both github.com/influxdata/influxql
and github.com/influxdata/influxdb/logger that we can hopefully remove
in future refactorings.
This commit generates an additional `.tss` stats file alongside each
TSM file when it is written that contains size stats for all measurements
within the TSM file. These files can be combined to generate stats for
all measurements across all TSM files.
Edd Robinson
Mark Rushakoff
Stuart Carnie
Jeff Wendling
Chris Goller
zhulongcheng
Jacob Marble
Jonathan A. Sternberg
Ben Johnson