fix clickhouse benchmark to work with latest clickhouse

.github/workflows/go.yml

@@ -10,12 +10,12 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
 
     - name: Set up Go
-      uses: actions/setup-go@v2
+      uses: actions/setup-go@v4
       with:
-        go-version: 1.15
+        go-version: '1.20'
 
     - name: Test
       run: go test -v -race ./...

.gitignore

@@ -4,6 +4,7 @@
 .idea
 .vscode
 *~
+/bin
 
 # High Dynamic Range (HDR) Histogram files
 *.hdr

Dockerfile

@@ -1,12 +1,12 @@
 # Build stage
-FROM golang:1.13.1-alpine AS builder
+FROM golang:1.20.8-alpine AS builder
 WORKDIR /tsbs
 COPY ./ ./
 RUN apk update && apk add --no-cache git
 RUN go mod download && go install ./...
 
 # Final stage
-FROM alpine:3.8.5
+FROM alpine:3.18
 RUN apk update && apk add --no-cache bash
 COPY --from=builder /go/bin /
 COPY --from=builder /tsbs/scripts /

README.md

@@ -1,8 +1,22 @@
 # Time Series Benchmark Suite (TSBS)
+
 This repo contains code for benchmarking several time series databases,
-including TimescaleDB, MongoDB, InfluxDB, CrateDB and Cassandra.
-This code is based on a fork of work initially made public by InfluxDB
-at https://github.com/influxdata/influxdb-comparisons.
+including QuestDB, TimescaleDB, MongoDB, InfluxDB, CrateDB, and Cassandra.
+This code is based on a fork of TSBS from TimescaleDB available at
+https://github.com/timescale/tsbs. Read
+[this post](https://questdb.io/blog/optimizing-optimizer-time-series-benchmark-suite/)
+to understand why we (QuestDB) created it.
+
+This fork derives from the original TSBS and includes a number of changes
+such as:
+* Loader optimizations for QuestDB making it capable of 4M+ rows/s
+ingestion.
+* A number of bugfixes in query generation.
+* InfluxDB v2 support based on
+[this PR](https://github.com/timescale/tsbs/pull/209). Original TSBS
+supports InfluxDB v1 only.
+
+All kinds of pull requests are welcome.
 
 Current databases supported:
 
@@ -35,6 +49,7 @@ database in the TSBS, feel free to open a pull request to add it!
 Currently, TSBS supports two use cases.
 
 ### Dev ops
+
 A 'dev ops' use case, which comes in two forms. The full form is used to
 generate, insert, and measure data from 9 'systems' that could be monitored
 in a real world dev ops scenario (e.g., CPU, memory, disk, etc).
@@ -49,6 +64,7 @@ one host in the dataset and the number of different hosts generated is
 defined by the `scale` flag (see below).
 
 ### Internet of Things (IoT)
+
 The second use case is meant to simulate the data load in an IoT
 environment. This use case simulates data streaming from a set of trucks
 belonging to a fictional trucking company. This use case simulates
@@ -76,14 +92,15 @@ cases are implemented for each database:
 |CrateDB|X||
 |InfluxDB|X|X|
 |MongoDB|X|
-|QuestDB|X|X
+|QuestDB|X|X²|
 |SiriDB|X|
 |TimescaleDB|X|X|
 |Timestream|X||
-|VictoriaMetrics|X²||
+|VictoriaMetrics|X³||
 
 ¹ Does not support the `groupby-orderby-limit` query
-² Does not support the `groupby-orderby-limit`, `lastpoint`, `high-cpu-1`, `high-cpu-all` queries
+² Supports ingestion only
+³ Does not support the `groupby-orderby-limit`, `lastpoint`, `high-cpu-1`, `high-cpu-all` queries
 
 ## What the TSBS tests
 
@@ -107,8 +124,8 @@ scripts). The easiest way to get and install the Go programs is to use
 `go get` and then `make all` to install all binaries:
 ```bash
 # Fetch TSBS and its dependencies
-$ go get github.com/timescale/tsbs
-$ cd $GOPATH/src/github.com/timescale/tsbs
+$ go get github.com/questdb/tsbs
+$ cd $GOPATH/src/github.com/questdb/tsbs
 $ make
 ```
 
@@ -396,12 +413,12 @@ the results.
 ### Devops / cpu-only
 |Query type|Description|
 |:---|:---|
-|single-groupby-1-1-1| Simple aggregrate (MAX) on one metric for 1 host, every 5 mins for 1 hour
-|single-groupby-1-1-12| Simple aggregrate (MAX) on one metric for 1 host, every 5 mins for 12 hours
-|single-groupby-1-8-1| Simple aggregrate (MAX) on one metric for 8 hosts, every 5 mins for 1 hour
-|single-groupby-5-1-1| Simple aggregrate (MAX) on 5 metrics for 1 host, every 5 mins for 1 hour
-|single-groupby-5-1-12| Simple aggregrate (MAX) on 5 metrics for 1 host, every 5 mins for 12 hours
-|single-groupby-5-8-1| Simple aggregrate (MAX) on 5 metrics for 8 hosts, every 5 mins for 1 hour
+|single-groupby-1-1-1| Simple aggregate (MAX) on one metric for 1 host, every 5 mins for 1 hour
+|single-groupby-1-1-12| Simple aggregate (MAX) on one metric for 1 host, every 5 mins for 12 hours
+|single-groupby-1-8-1| Simple aggregate (MAX) on one metric for 8 hosts, every 5 mins for 1 hour
+|single-groupby-5-1-1| Simple aggregate (MAX) on 5 metrics for 1 host, every 5 mins for 1 hour
+|single-groupby-5-1-12| Simple aggregate (MAX) on 5 metrics for 1 host, every 5 mins for 12 hours
+|single-groupby-5-8-1| Simple aggregate (MAX) on 5 metrics for 8 hosts, every 5 mins for 1 hour
 |cpu-max-all-1| Aggregate across all CPU metrics per hour over 1 hour for a single host
 |cpu-max-all-8| Aggregate across all CPU metrics per hour over 1 hour for eight hosts
 |double-groupby-1| Aggregate on across both time and host, giving the average of 1 CPU metric per host per hour for 24 hours
@@ -433,11 +450,6 @@ the results.
 We welcome contributions from the community to make TSBS better!
 
 You can help either by opening an
-[issue](https://github.com/timescale/tsbs/issues) with
+[issue](https://github.com/questdb/tsbs/issues) with
 any suggestions or bug reports, or by forking this repository,
 making your own contribution, and submitting a pull request.
-
-Before we accept any contributions, Timescale contributors need to
-sign the [Contributor License Agreement](https://cla-assistant.io/timescale/tsbs) (CLA).
-By signing a CLA, we can ensure that the community is free and confident in its
-ability to use your contributions.

cmd/tsbs_generate_data/main.go

@@ -10,7 +10,9 @@
 
 // Supported use cases:
 // devops: scale is the number of hosts to simulate, with log messages
-//         every log-interval seconds.
+//
+//	every log-interval seconds.
+//
 // cpu-only: same as `devops` but only generate metrics for CPU
 package main
 
@@ -22,11 +24,11 @@ import (
 	"runtime/pprof"
 
 	"github.com/blagojts/viper"
+	"github.com/questdb/tsbs/internal/inputs"
+	"github.com/questdb/tsbs/internal/utils"
+	"github.com/questdb/tsbs/pkg/data/usecases/common"
+	"github.com/questdb/tsbs/pkg/targets/initializers"
 	"github.com/spf13/pflag"
-	"github.com/timescale/tsbs/internal/inputs"
-	"github.com/timescale/tsbs/internal/utils"
-	"github.com/timescale/tsbs/pkg/data/usecases/common"
-	"github.com/timescale/tsbs/pkg/targets/initializers"
 )
 
 var (

cmd/tsbs_generate_queries/databases/akumuli/common.go

@@ -3,9 +3,9 @@ package akumuli
 import (
 	"time"
 
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/uses/devops"
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/utils"
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/uses/devops"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/utils"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 // BaseGenerator contains settings specific for Akumuli database.

cmd/tsbs_generate_queries/databases/akumuli/devops.go

@@ -6,8 +6,8 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/uses/devops"
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/uses/devops"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 // Devops produces Influx-specific queries for all the devops query types.
@@ -70,9 +70,11 @@ type tsdbAggregateAllQuery struct {
 // SELECT minute, max(metric1), ..., max(metricN)
 // FROM cpu
 // WHERE
-// 		(hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
-// 	AND time >= '$HOUR_START'
-// 	AND time < '$HOUR_END'
+//
+//		(hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
+//	AND time >= '$HOUR_START'
+//	AND time < '$HOUR_END'
+//
 // GROUP BY minute
 // ORDER BY minute ASC
 //
@@ -176,17 +178,19 @@ func (d *Devops) HighCPUForHosts(qi query.Query, nHosts int) {
 // SELECT MAX(metric1), ..., MAX(metricN)
 // FROM cpu
 // WHERE
-// 		(hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
-// 		AND time >= '$HOUR_START'
-// 		AND time < '$HOUR_END'
+//
+//	(hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
+//	AND time >= '$HOUR_START'
+//	AND time < '$HOUR_END'
+//
 // GROUP BY hour
 // ORDER BY hour
 //
 // Resultsets:
 // cpu-max-all-1
 // cpu-max-all-8
-func (d *Devops) MaxAllCPU(qi query.Query, nHosts int) {
-	interval := d.Interval.MustRandWindow(devops.MaxAllDuration)
+func (d *Devops) MaxAllCPU(qi query.Query, nHosts int, duration time.Duration) {
+	interval := d.Interval.MustRandWindow(duration)
 	hostnames, err := d.GetRandomHosts(nHosts)
 	panicIfErr(err)
 	startTimestamp := interval.StartUnixNano()

cmd/tsbs_generate_queries/databases/cassandra/common.go

@@ -4,10 +4,10 @@ import (
 	"strings"
 	"time"
 
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/uses/devops"
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/utils"
-	internalutils "github.com/timescale/tsbs/internal/utils"
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/uses/devops"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/utils"
+	internalutils "github.com/questdb/tsbs/internal/utils"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 // BaseGenerator contains settings specific for Cassandra database.

cmd/tsbs_generate_queries/databases/cassandra/devops.go

@@ -4,9 +4,9 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/uses/devops"
-	"github.com/timescale/tsbs/internal/utils"
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/uses/devops"
+	"github.com/questdb/tsbs/internal/utils"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 // TODO: Remove the need for this by continuing to bubble up errors

cmd/tsbs_generate_queries/databases/cassandra/devops_test.go

@@ -5,7 +5,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 func TestDevopsGetHostWhereWithHostnames(t *testing.T) {

cmd/tsbs_generate_queries/databases/clickhouse/common.go

@@ -3,9 +3,9 @@ package clickhouse
 import (
 	"time"
 
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/uses/devops"
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/utils"
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/uses/devops"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/utils"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 // BaseGenerator contains settings specific for ClickHouse.

cmd/tsbs_generate_queries/databases/clickhouse/devops.go

@@ -5,8 +5,8 @@ import (
 	"strings"
 	"time"
 
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/uses/devops"
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/uses/devops"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 // TODO: Remove the need for this by continuing to bubble up errors
@@ -76,9 +76,11 @@ const clickhouseTimeStringFormat = "2006-01-02 15:04:05"
 // SELECT MAX(metric1), ..., MAX(metricN)
 // FROM cpu
 // WHERE
-// 		(hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
-// 		AND time >= '$HOUR_START'
-// 		AND time < '$HOUR_END'
+//
+//	(hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
+//	AND time >= '$HOUR_START'
+//	AND time < '$HOUR_END'
+//
 // GROUP BY hour
 // ORDER BY hour
 //
@@ -290,9 +292,11 @@ func (d *Devops) LastPointPerHost(qi query.Query) {
 // SELECT minute, max(metric1), ..., max(metricN)
 // FROM cpu
 // WHERE
-// 		(hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
-// 	AND time >= '$HOUR_START'
-// 	AND time < '$HOUR_END'
+//
+//		(hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
+//	AND time >= '$HOUR_START'
+//	AND time < '$HOUR_END'
+//
 // GROUP BY minute
 // ORDER BY minute ASC
 //

cmd/tsbs_generate_queries/databases/clickhouse/devops_test.go

@@ -6,8 +6,8 @@ import (
 	"testing"
 	"time"
 
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/uses/devops"
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/uses/devops"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 func TestDevopsGetHostWhereWithHostnames(t *testing.T) {

cmd/tsbs_generate_queries/databases/cratedb/common.go

@@ -3,9 +3,9 @@ package cratedb
 import (
 	"time"
 
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/uses/devops"
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/utils"
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/uses/devops"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/utils"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 // BaseGenerator contains settings specific for CrateDB

cmd/tsbs_generate_queries/databases/cratedb/devops.go

@@ -5,8 +5,8 @@ import (
 	"strings"
 	"time"
 
-	"github.com/timescale/tsbs/cmd/tsbs_generate_queries/uses/devops"
-	"github.com/timescale/tsbs/pkg/query"
+	"github.com/questdb/tsbs/cmd/tsbs_generate_queries/uses/devops"
+	"github.com/questdb/tsbs/pkg/query"
 )
 
 // TODO: Remove the need for this by continuing to bubble up errors
@@ -28,7 +28,8 @@ const hostnameField = "tags['hostname']"
 // a set of column idents.
 //
 // For instance:
-//      max(cpu_time) AS max_cpu_time
+//
+//	max(cpu_time) AS max_cpu_time
 func (d *Devops) getSelectAggClauses(aggFunc string, idents []string) []string {
 	selectAggClauses := make([]string, len(idents))
 	for i, ident := range idents {
@@ -44,8 +45,8 @@ func (d *Devops) getSelectAggClauses(aggFunc string, idents []string) []string {
 // Queries:
 // cpu-max-all-1
 // cpu-max-all-8
-func (d *Devops) MaxAllCPU(qi query.Query, nHosts int) {
-	interval := d.Interval.MustRandWindow(devops.MaxAllDuration)
+func (d *Devops) MaxAllCPU(qi query.Query, nHosts int, duration time.Duration) {
+	interval := d.Interval.MustRandWindow(duration)
 	selectClauses := d.getSelectAggClauses("max", devops.GetAllCPUMetrics())
 	hosts, err := d.GetRandomHosts(nHosts)
 	panicIfErr(err)