Update query types to new naming convention.

Cleanup and make consistent the labels for queries.

README.md

@@ -129,7 +129,7 @@ Variables needed:
 1. the same use case, seed, # of devices, and start time as used in data generation
 1. an end time that is one second after the end time from data generation. E.g., for `2016-01-04T00:00:00Z` use `2016-01-04T00:00:01Z`
 1. the number of queries to generate. E.g., `1000`
-1. and the type of query you'd like to generate. E.g., `1-host-1-hr`
+1. and the type of query you'd like to generate. E.g., `single-groupby(1,1,1)`
 
 For the last step there are numerous queries to choose from, which are
 listed in [Appendix I](#appendix-i-query-types). Additionally, the file
@@ -143,16 +143,16 @@ For generating just one set of queries for a given type:
 $ tsbs_generate_queries -seed=123 -scale-var=4000 \
     -timestamp-start="2016-01-01T00:00:00Z" \
     -timestamp-end="2016-01-04T00:00:01Z" \
-    -queries=1000 -query-type="1-host-1-hr" -format="timescaledb" \
-    | gzip > /tmp/timescaledb-queries-1-host-1-hr.gz
+    -queries=1000 -query-type="single-groupby(1,1,1)" -format="timescaledb" \
+    | gzip > /tmp/timescaledb-queries-single-groupby(1,1,1).gz
 ```
 
 For generating sets of queries for multiple types:
 ```bash
 $ formats="timescaledb" scaleVar=4000 seed=123 \
     tsStart="2016-01-01T00:00:00Z" \
     tsEnd="2016-01-04T00:00:01Z" \
-    queries=1000 queryTypes="1-host-1-hr 1-host-12-hr groupby" \
+    queries=1000 queryTypes="single-groupby(1,1,1) single-groupby(1,1,12) double-groupby(1)" \
     dataDir="/tmp" script/generate_queries.sh
 ```
 
@@ -257,10 +257,10 @@ to run multiple query types in a row. The queries it generates should be
 put in a file with one query per line and the path given to the script.
 For example, if you had a file named `queries.txt` that looked like this:
 ```text
-high-cpu-and-field
-cpu-max-all-eight-hosts
+high-cpu(1)
+cpu-max-all(8)
 groupby-orderby-limit
-groupby
+double-groupby(1)
 ```
 
 You could generate a run script named `query_test.sh`:
@@ -275,13 +275,13 @@ And the resulting script file would look like:
 ```bash
 #!/bin/bash
 # Queries
-cat /tmp/queries/timescaledb-high-cpu-and-field-queries.gz | gunzip | query_benchmarker_timescaledb --workers=8 --limit=1000 --postgres="host=localhost user=postgres sslmode=disable"  | tee query_timescaledb_timescaledb-high-cpu-and-field-queries.out
+cat /tmp/queries/timescaledb-high-cpu(1)-queries.gz | gunzip | query_benchmarker_timescaledb --workers=8 --limit=1000 --hosts="localhost" --postgres="user=postgres sslmode=disable"  | tee query_timescaledb_timescaledb-high-cpu(1)-queries.out
 
-cat /tmp/queries/timescaledb-cpu-max-all-eight-hosts-queries.gz | gunzip | query_benchmarker_timescaledb --workers=8 --limit=1000 --postgres="host=localhost user=postgres sslmode=disable"  | tee query_timescaledb_timescaledb-cpu-max-all-eight-hosts-queries.out
+cat /tmp/queries/timescaledb-cpu-max-all(8)-queries.gz | gunzip | query_benchmarker_timescaledb --workers=8 --limit=1000 --hosts="localhost" --postgres="user=postgres sslmode=disable"  | tee query_timescaledb_timescaledb-cpu-max-all(8)-queries.out
 
-cat /tmp/queries/timescaledb-groupby-orderby-limit-queries.gz | gunzip | query_benchmarker_timescaledb --workers=8 --limit=1000 --postgres="host=localhost user=postgres sslmode=disable"  | tee query_timescaledb_timescaledb-groupby-orderby-limit-queries.out
+cat /tmp/queries/timescaledb-groupby-orderby-limit-queries.gz | gunzip | query_benchmarker_timescaledb --workers=8 --limit=1000 --hosts="localhost" --postgres="user=postgres sslmode=disable"  | tee query_timescaledb_timescaledb-groupby-orderby-limit-queries.out
 
-cat /tmp/queries/timescaledb-groupby-queries.gz | gunzip | query_benchmarker_timescaledb --workers=8 --limit=1000 --postgres="host=localhost user=postgres sslmode=disable"  | tee query_timescaledb_timescaledb-groupby-queries.out
+cat /tmp/queries/timescaledb-double-groupby(1)-queries.gz | gunzip | query_benchmarker_timescaledb --workers=8 --limit=1000 --hosts="localhost" --postgres="user=postgres sslmode=disable"  | tee query_timescaledb_timescaledb-double-groupby(1)-queries.out
 ```
 
 ### Query validation (optional)
@@ -296,18 +296,18 @@ the results.
 ### Devops / cpu-only
 |Query type|Description|
 |:---|:---|
-|1-host-1-hr| Simple aggregrate (MAX) on one metric for 1 host, every 5 mins for 1 hour
-|1-host-12-hr| Simple aggregrate (MAX) on one metric for 1 host, every 5 mins for 12 hours
-|8-host-1-hr| Simple aggregrate (MAX) on one metric for 8 hosts, every 5 mins for 1 hour
-|5-metrics-1-host-1-hr| Simple aggregrate (MAX) on 5 metrics for 1 host, every 5 mins for 1 hour
-|5-metrics-1-host-12-hr| Simple aggregrate (MAX) on 5 metrics for 1 host, every 5 mins for 12 hours
-|5-metrics-8-host-1-hr| Simple aggregrate (MAX) on 5 metrics for 8 hosts, every 5 mins for 1 hour
-|cpu-max-all-single-host| Aggregate across all CPU metrics per hour over 1 hour for a single host
-|cpu-max-all-eight-hosts| Aggregate across all CPU metrics per hour over 1 hour for eight hosts
-|groupby| Aggregate on across both time and host, giving the average of 1 CPU metric per host per hour for 24 hours
-|groupby-5| Aggregate on across both time and host, giving the average of 5 CPU metrics per host per hour for 24 hours
-|groupby-all| Aggregate on across both time and host, giving the average of all (10) CPU metrics per host per hour for 24 hours
-|high-cpu-all-hosts| All the readings where one metric is above a threshold across all hosts
-|high-cpu-1-host| All the readings where one metric is above a threshold for a particular host
+|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
+|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
+|double-groupby(5)| Aggregate on across both time and host, giving the average of 5 CPU metrics per host per hour for 24 hours
+|double-groupby(all)| Aggregate on across both time and host, giving the average of all (10) CPU metrics per host per hour for 24 hours
+|high-cpu(all)| All the readings where one metric is above a threshold across all hosts
+|high-cpu(1)| All the readings where one metric is above a threshold for a particular host
 |lastpoint| The last reading for each host
 |groupby-orderby-limit| The last 5 aggregate readings (across time) before a randomly chosen endpoint

cmd/tsbs_generate_queries/cassandra_devops_common.go

@@ -76,7 +76,7 @@ func (d *CassandraDevops) GroupByTime(qi query.Query, nHosts, numMetrics int, ti
 func (d *CassandraDevops) GroupByOrderByLimit(qi query.Query) {
 	interval := d.interval.RandWindow(time.Hour)
 
-	humanLabel := "Cassandra max cpu over last 5 min-intervals (rand end)"
+	humanLabel := "Cassandra max cpu over last 5 min-intervals (random end)"
 	q := qi.(*query.Cassandra)
 	q.HumanLabel = []byte(humanLabel)
 	q.HumanDescription = []byte(fmt.Sprintf("%s: %s", humanLabel, d.interval.StartString()))
@@ -103,7 +103,7 @@ func (d *CassandraDevops) GroupByTimeAndPrimaryTag(qi query.Query, numMetrics in
 	interval := d.interval.RandWindow(doubleGroupByDuration)
 	metrics := getCPUMetricsSlice(numMetrics)
 
-	humanLabel := fmt.Sprintf("Cassandra mean of %d metrics, all hosts, rand 1day by 1hr", numMetrics)
+	humanLabel := getDoubleGroupByLabel("Cassandra", numMetrics)
 	q := qi.(*query.Cassandra)
 	q.HumanLabel = []byte(humanLabel)
 	q.HumanDescription = []byte(fmt.Sprintf("%s: %s", humanLabel, interval.StartString()))
@@ -124,14 +124,14 @@ func (d *CassandraDevops) GroupByTimeAndPrimaryTag(qi query.Query, numMetrics in
 // FROM cpu WHERE (hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
 // AND time >= '$HOUR_START' AND time < '$HOUR_END'
 // GROUP BY hour ORDER BY hour
-func (d *CassandraDevops) MaxAllCPU(qi query.Query, nhosts int) {
-	interval := d.interval.RandWindow(8 * time.Hour)
-	tagSet := d.getHostWhere(nhosts)
+func (d *CassandraDevops) MaxAllCPU(qi query.Query, nHosts int) {
+	interval := d.interval.RandWindow(maxAllDuration)
+	tagSet := d.getHostWhere(nHosts)
 
 	tagSets := [][]string{}
 	tagSets = append(tagSets, tagSet)
 
-	humanLabel := fmt.Sprintf("Cassandra max cpu all fields, rand %4d hosts, rand 12hr by 1h", nhosts)
+	humanLabel := getMaxAllLabel("Cassandra", nHosts)
 	q := qi.(*query.Cassandra)
 	q.HumanLabel = []byte(humanLabel)
 	q.HumanDescription = []byte(fmt.Sprintf("%s: %s", humanLabel, interval.StartString()))

cmd/tsbs_generate_queries/devops.go

@@ -14,6 +14,14 @@ const (
 	allHosts              = "all hosts"
 	doubleGroupByDuration = 24 * time.Hour
 	highCPUDuration       = 24 * time.Hour
+	maxAllDuration        = 8 * time.Hour
+
+	labelSingleGroupby       = "single-groupby"
+	labelDoubleGroupby       = "double-groupby"
+	labelLastpoint           = "lastpoint"
+	labelMaxAll              = "cpu-max-all"
+	labelGroupbyOrderbyLimit = "groupby-orderby-limit"
+	labelHighCPU             = "high-cpu"
 )
 
 type devopsCore struct {
@@ -61,17 +69,6 @@ func getCPUMetricsSlice(numMetrics int) []string {
 	return cpuMetrics[:numMetrics]
 }
 
-// Devops describes a devops query generator.
-type Devops interface {
-	CPU5Metrics(query.Query, int, int, time.Duration)
-	GroupByOrderByLimit(query.Query)
-	HighCPUForHosts(query.Query, int, int)
-	LastPointPerHost(query.Query)
-	MaxAllCPU(query.Query, int, int)
-	MaxCPUUsageHourByMinute(query.Query, int, int, time.Duration)
-	MeanCPUMetricsDayByHourAllHostsGroupbyHost(query.Query, int)
-}
-
 // SingleGroupbyFiller is a type that can fill in a single groupby query
 type SingleGroupbyFiller interface {
 	GroupByTime(query.Query, int, int, time.Duration)
@@ -102,6 +99,10 @@ type HighCPUFiller interface {
 	HighCPUForHosts(query.Query, int)
 }
 
+func getDoubleGroupByLabel(dbName string, numMetrics int) string {
+	return fmt.Sprintf("%s mean of %d metrics, all hosts, random %s by 1hr", dbName, numMetrics, doubleGroupByDuration)
+}
+
 func getHighCPULabel(dbName string, nHosts int) string {
 	label := dbName + " CPU over threshold, "
 	if nHosts > 0 {
@@ -112,12 +113,16 @@ func getHighCPULabel(dbName string, nHosts int) string {
 	return label
 }
 
-func getRandomHosts(scale, nhosts int) []string {
-	if nhosts > scale {
-		log.Fatal("nhosts > scaleVar")
+func getMaxAllLabel(dbName string, nHosts int) string {
+	return fmt.Sprintf("%s max of all CPU fields, random %4d hosts, random %s by 1h", dbName, nHosts, maxAllDuration)
+}
+
+func getRandomHosts(scale, nHosts int) []string {
+	if nHosts > scale {
+		log.Fatalf("number of hosts (%d) larger than --scale-var (%d)", nHosts, scale)
 	}
 
-	nn := rand.Perm(scale)[:nhosts]
+	nn := rand.Perm(scale)[:nHosts]
 
 	hostnames := []string{}
 	for _, n := range nn {

cmd/tsbs_generate_queries/influx_devops_common.go

@@ -88,7 +88,7 @@ func (d *InfluxDevops) GroupByOrderByLimit(qi query.Query) {
 	v := url.Values{}
 	v.Set("q", fmt.Sprintf(`SELECT max(usage_user) from cpu %s group by time(1m) limit 5`, where))
 
-	humanLabel := "Influx max cpu over last 5 min-intervals (rand end)"
+	humanLabel := "Influx max cpu over last 5 min-intervals (random end)"
 	q := qi.(*query.HTTP)
 	q.HumanLabel = []byte(humanLabel)
 	q.HumanDescription = []byte(fmt.Sprintf("%s: %s", humanLabel, interval.StartString()))
@@ -116,7 +116,7 @@ func (d *InfluxDevops) GroupByTimeAndPrimaryTag(qi query.Query, numMetrics int)
 	v := url.Values{}
 	v.Set("q", fmt.Sprintf("SELECT %s from cpu where time >= '%s' and time < '%s' group by time(1h),hostname", strings.Join(selectClauses, ", "), interval.StartString(), interval.EndString()))
 
-	humanLabel := fmt.Sprintf("Influx mean of %d metrics, all hosts, rand 1day by 1hr", numMetrics)
+	humanLabel := getDoubleGroupByLabel("Influx", numMetrics)
 	q := qi.(*query.HTTP)
 	q.HumanLabel = []byte(humanLabel)
 	q.HumanDescription = []byte(fmt.Sprintf("%s: %s", humanLabel, interval.StartString()))
@@ -132,14 +132,14 @@ func (d *InfluxDevops) GroupByTimeAndPrimaryTag(qi query.Query, numMetrics int)
 // FROM cpu WHERE (hostname = '$HOSTNAME_1' OR ... OR hostname = '$HOSTNAME_N')
 // AND time >= '$HOUR_START' AND time < '$HOUR_END'
 // GROUP BY hour ORDER BY hour
-func (d *InfluxDevops) MaxAllCPU(qi query.Query, nhosts int) {
-	interval := d.interval.RandWindow(8 * time.Hour)
-	whereHosts := d.getHostWhereString(nhosts)
+func (d *InfluxDevops) MaxAllCPU(qi query.Query, nHosts int) {
+	interval := d.interval.RandWindow(maxAllDuration)
+	whereHosts := d.getHostWhereString(nHosts)
 
 	v := url.Values{}
 	v.Set("q", fmt.Sprintf("SELECT max(usage_user),max(usage_system),max(usage_idle),max(usage_nice),max(usage_iowait),max(usage_irq),max(usage_softirq),max(usage_steal),max(usage_guest),max(usage_guest_nice) from cpu where %s and time >= '%s' and time < '%s' group by time(1m)", whereHosts, interval.StartString(), interval.EndString()))
 
-	humanLabel := fmt.Sprintf("Influx max cpu all fields, rand %4d hosts, rand 12hr by 1m", nhosts)
+	humanLabel := getMaxAllLabel("Influx", nHosts)
 	q := qi.(*query.HTTP)
 	q.HumanLabel = []byte(humanLabel)
 	q.HumanDescription = []byte(fmt.Sprintf("%s: %s", humanLabel, interval.StartString()))

cmd/tsbs_generate_queries/main.go

@@ -16,21 +16,21 @@ import (
 
 var useCaseMatrix = map[string]map[string]QueryFillerMaker{
 	"devops": {
-		"1-host-1-hr":             NewDevopsSingleGroupby(1, 1, 1),
-		"1-host-12-hr":            NewDevopsSingleGroupby(1, 1, 12),
-		"8-host-1-hr":             NewDevopsSingleGroupby(1, 8, 1),
-		"5-metrics-1-host-1-hr":   NewDevopsSingleGroupby(5, 1, 1),
-		"5-metrics-1-host-12-hr":  NewDevopsSingleGroupby(5, 1, 12),
-		"5-metrics-8-host-1-hr":   NewDevopsSingleGroupby(5, 8, 1),
-		"cpu-max-all-single-host": NewDevopsMaxAllCPU(1),
-		"cpu-max-all-eight-hosts": NewDevopsMaxAllCPU(1),
-		"groupby":                 NewDevopsGroupBy(1),
-		"groupby-5":               NewDevopsGroupBy(5),
-		"groupby-all":             NewDevopsGroupBy(len(cpuMetrics)),
-		"groupby-orderby-limit":   NewDevopsGroupByOrderByLimit,
-		"high-cpu-all-hosts":      NewDevopsHighCPU(0),
-		"high-cpu-1-host":         NewDevopsHighCPU(1),
-		"lastpoint":               NewDevopsLastPointPerHost,
+		labelSingleGroupby + "(1,1,1)":  NewDevopsSingleGroupby(1, 1, 1),
+		labelSingleGroupby + "(1,1,12)": NewDevopsSingleGroupby(1, 1, 12),
+		labelSingleGroupby + "(1,8,1)":  NewDevopsSingleGroupby(1, 8, 1),
+		labelSingleGroupby + "(5,1,1)":  NewDevopsSingleGroupby(5, 1, 1),
+		labelSingleGroupby + "(5,1,12)": NewDevopsSingleGroupby(5, 1, 12),
+		labelSingleGroupby + "(5,8,1)":  NewDevopsSingleGroupby(5, 8, 1),
+		labelMaxAll + "(1)":             NewDevopsMaxAllCPU(1),
+		labelMaxAll + "(8)":             NewDevopsMaxAllCPU(1),
+		labelDoubleGroupby + "(1)":      NewDevopsGroupBy(1),
+		labelDoubleGroupby + "(5)":      NewDevopsGroupBy(5),
+		labelDoubleGroupby + "(all)":    NewDevopsGroupBy(len(cpuMetrics)),
+		labelGroupbyOrderbyLimit:        NewDevopsGroupByOrderByLimit,
+		labelHighCPU + "(all)":          NewDevopsHighCPU(0),
+		labelHighCPU + "(1)":            NewDevopsHighCPU(1),
+		labelLastpoint:                  NewDevopsLastPointPerHost,
 	},
 }
 
@@ -97,8 +97,8 @@ func init() {
 	flag.IntVar(&scaleVar, "scale-var", 1, "Scaling variable (must be the equal to the scalevar used for data generation).")
 	flag.IntVar(&queryCount, "queries", 1000, "Number of queries to generate.")
 
-	flag.BoolVar(&timescaleUseJSON, "timescale-use-json", false, "Use separate JSON tags table when querying")
-	flag.BoolVar(&timescaleUseTags, "timescale-use-tags", true, "Use separate tags table when querying")
+	flag.BoolVar(&timescaleUseJSON, "timescale-use-json", false, "TimescaleDB only: Use separate JSON tags table when querying")
+	flag.BoolVar(&timescaleUseTags, "timescale-use-tags", true, "TimescaleDB only: Use separate tags table when querying")
 
 	flag.StringVar(&timestampStartStr, "timestamp-start", "2016-01-01T00:00:00Z", "Beginning timestamp (RFC3339).")
 	flag.StringVar(&timestampEndStr, "timestamp-end", "2016-01-02T06:00:00Z", "Ending timestamp (RFC3339).")

cmd/tsbs_generate_queries/mongo_devops_common.go

@@ -167,7 +167,7 @@ func (d *MongoDevops) GroupByTime(qi query.Query, nHosts, numMetrics int, timeRa
 // AND time >= '$HOUR_START' AND time < '$HOUR_END'
 // GROUP BY hour ORDER BY hour
 func (d *MongoDevops) MaxAllCPU(qi query.Query, nHosts int) {
-	interval := d.interval.RandWindow(8 * time.Hour)
+	interval := d.interval.RandWindow(maxAllDuration)
 	hostnames := d.getRandomHosts(nHosts)
 	docs := getTimeFilterDocs(interval)
 	bucketNano := time.Hour.Nanoseconds()
@@ -219,7 +219,7 @@ func (d *MongoDevops) MaxAllCPU(qi query.Query, nHosts int) {
 	pipelineQuery = append(pipelineQuery, group)
 	pipelineQuery = append(pipelineQuery, bson.M{"$sort": bson.M{"_id": 1}})
 
-	humanLabel := fmt.Sprintf("Mongo max cpu all fields, rand %4d hosts, rand 8hr by 1h", nHosts)
+	humanLabel := getMaxAllLabel("Mongo", nHosts)
 	q := qi.(*query.Mongo)
 	q.HumanLabel = []byte(humanLabel)
 	q.BsonDoc = pipelineQuery
@@ -298,7 +298,7 @@ func (d *MongoDevops) GroupByTimeAndPrimaryTag(qi query.Query, numMetrics int) {
 		{"$sort": bson.M{"_id.time": 1}},
 	}...)
 
-	humanLabel := fmt.Sprintf("Mongo mean of %d metrics, all hosts, rand 1day by 1hr", numMetrics)
+	humanLabel := getDoubleGroupByLabel("Mongo", numMetrics)
 	q := qi.(*query.Mongo)
 	q.HumanLabel = []byte(humanLabel)
 	q.BsonDoc = pipelineQuery
@@ -492,7 +492,7 @@ func (d *MongoDevops) GroupByOrderByLimit(qi query.Query) {
 		{"$limit": 5},
 	}...)
 
-	humanLabel := "Mongo max cpu over last 5 min-intervals (rand end)"
+	humanLabel := "Mongo max cpu over last 5 min-intervals (random end)"
 	q := qi.(*query.Mongo)
 	q.HumanLabel = []byte(humanLabel)
 	q.BsonDoc = pipelineQuery

cmd/tsbs_generate_queries/mongo_naive_devops_common.go

@@ -157,7 +157,7 @@ func (d *MongoNaiveDevops) GroupByTimeAndPrimaryTag(qi query.Query, numMetrics i
 	}...)
 	pipelineQuery = append(pipelineQuery, bson.M{"$sort": bson.M{"_id.time": 1, "_id.hostname": 1}})
 
-	humanLabel := fmt.Sprintf("Mongo [NAIVE] mean of %d metrics, all hosts, rand 1day by 1hr", numMetrics)
+	humanLabel := getDoubleGroupByLabel("Mongo [NAIVE]", numMetrics)
 	q := qi.(*query.Mongo)
 	q.HumanLabel = []byte(humanLabel)
 	q.BsonDoc = pipelineQuery