Paper: a few more graphs.

paper/graph_fifo_query_index.grap

@@ -1,8 +1,8 @@
 .G1
 copy "legend.grap"
 frame invis ht 3 wid 4 left solid bot solid
-coord y 0,500
-ticks left out from 0 to 500 by 50
+coord y 0,300
+ticks left out from 0 to 300 by 50
 ticks bot out at 50000 "50,000", 100000 "100,000", 150000 "150,000", 200000 "200,000", 250000 "250,000"
 
 label left "Request duration with" unaligned "an index (ns)" "(Median)" left 0.8
@@ -11,10 +11,10 @@ label bot "Number of cars in the database" down 0.1
 obfifo1 = obfifo5 = obfifo10 = obfifo20 = 0 # old bullets
 cbfifo1 = cbfifo5 = cbfifo10 = cbfifo20 = 0 # current bullets
 
-legendxleft  = 180000
-legendxright = 240000
-legendyup    = 400
-legendydown  = 300
+legendxleft  = 120000
+legendxright = 180000
+legendyup    = 120
+legendydown  = 20
 
 boite(legendxleft,legendxright,legendyup,legendydown)
 legend_common(legendxleft,legendxright,legendyup,legendydown)

paper/graph_fifo_query_partition.grap

@@ -1,8 +1,9 @@
 .G1
 copy "legend.grap"
 frame invis ht 3 wid 4 left solid bot solid
-coord x 0,5000*2 y 0,5000
-ticks left out from 0 to 5000 by 1000
+coord x 0,5000*2 y 0,4000
+ticks left out from 0 to 4000 by 400
+ticks bot  out from 1000 to 10000 by 1000
 
 label left "Request duration" unaligned "for a partition (µs)" "(Median)" left 0.8
 label bot "Number of cars matching the partition" down 0.1

paper/graph_fifo_query_tag.grap

@@ -0,0 +1,68 @@
+.G1
+copy "legend.grap"
+frame invis ht 3 wid 4 left solid bot solid
+coord x 0,5000 y 0,3000
+ticks left out from 0 to 5000 by 200
+ticks bot  out from 1000 to 5000 by 1000
+label left "Request duration" unaligned "for a tag (µs)" "(Median)" left 0.8
+label bot "Number of cars matching the tag" down 0.1
+
+obfifo1 = obfifo5 = obfifo10 = obfifo20 = 0
+cbfifo1 = cbfifo5 = cbfifo10 = cbfifo20 = 0
+
+legendxleft  = 2000
+legendxright = 3500
+legendyup    = 2500
+legendydown  = 1500
+
+boite(legendxleft,legendxright,legendyup,legendydown)
+legend_common(legendxleft,legendxright,legendyup,legendydown)
+
+copy "../data/fifo_tags.d" thru X
+	cx = $1
+
+	y_scale = 1000
+
+	## fifo1 fifo5 fifo10 fifo20
+	#line from cx,$2/y_scale  to cx,$4/y_scale
+	#line from cx,$5/y_scale  to cx,$7/y_scale
+	#line from cx,$8/y_scale  to cx,$10/y_scale
+	#line from cx,$11/y_scale to cx,$13/y_scale
+
+	#ty = $3
+
+	cbfifo1  = $3/y_scale
+	cbfifo5  = $6/y_scale
+	cbfifo10 = $9/y_scale
+	cbfifo20 = $12/y_scale
+
+.gcolor red
+	if (obfifo1 > 0) then {line from cx,cbfifo1 to ox,obfifo1}
+.gcolor
+.gcolor green
+	if (obfifo5 > 0) then {line from cx,cbfifo5 to ox,obfifo5}
+.gcolor
+	if (obfifo10 > 0) then {line from cx,cbfifo10 to ox,obfifo10}
+.gcolor pink
+	if (obfifo20 > 0) then {line from cx,cbfifo20 to ox,obfifo20}
+.gcolor
+
+	obfifo1 = cbfifo1
+	obfifo5 = cbfifo5
+	obfifo10 = cbfifo10
+	obfifo20 = cbfifo20
+	ox = cx
+
+	# fifo1 fifo5 fifo10 fifo20
+.gcolor red
+	bullet at cx,cbfifo1
+.gcolor
+.gcolor green
+	bullet at cx,cbfifo5
+.gcolor
+	bullet at cx,cbfifo10
+.gcolor pink
+	bullet at cx,cbfifo20
+.gcolor
+X
+.G2

paper/graph_query_partition.grap

@@ -3,6 +3,7 @@ copy "legend.grap"
 frame invis ht 3 wid 4 left solid bot solid
 coord x 0,5000*2 y 0,350
 ticks left out from 0 to 350 by 50
+ticks bot  out from 1000 to 10000 by 1000
 
 label left "Request duration" unaligned "for a partition (ms)" "(Median)" left 0.8
 label bot "Number of cars matching the partition" down 0.1

paper/graph_query_tag.grap

@@ -3,6 +3,7 @@ copy "legend.grap"
 frame invis ht 3 wid 4 left solid bot solid
 coord x 0,5000 y 0,170
 ticks left out from 0 to 170 by 20
+ticks bot  out from 1000 to 5000 by 1000
 label left "Request duration" unaligned "for a tag (ms)" "(Median)" left 0.8
 label bot "Number of cars matching the tag" down 0.1
 

paper/paper.ms

@@ -39,6 +39,7 @@
 .I \\$1 \\$2 \\$3
 ..
 .
+.
 . \" The document starts here.
 .
 .TITLE Document Oriented DataBase (DODB)
@@ -941,6 +942,9 @@ The experiment starts with a database containing 1,000 cars and goes up to 250,0
 .ps -2
 .so graph_query_index.grap
 .ps \n[PS]
+.QP
+This first figure shows the request durations to retrieve data based on a basic index with a database containing up to 250k entries.
+.QE
 
 Since there is only one value to retrieve, the request is quick and time is almost constant.
 When the value and the index are kept in memory (see \f[CW]RAM only\f[] and \f[CW]Cached db\f[]), the retrieval is almost instantaneous (about 50 to 120 ns).
@@ -1045,10 +1049,41 @@ Since this implementation of DODB is related to the Crystal language (which isn'
 .so graph_addition_fifo.grap
 .ps \n[PS]
 
-.APPENDIX Common database
+.APPENDIX Common database performance
+The
+.I Common
+database enables to configure the number of allowed entries in the cache.
+The following figures show the performance of the common database depending on the cache size.
+
 .ps -2
 .so graph_fifo_query_index.grap
 .ps \n[PS]
+.QP
+This first figure shows the request durations to retrieve data based on a basic index with a database containing up to 250k entries.
+.QE
+.EQ
+delim $$
+.EN
+This figure shows a value being requested and since there is only a single value being requested in the test, it is immediately put in the cache and is never evicted.
+For that reason, the result is stable amongst all
+.I common
+database instances:
+.vp 2p
+$+-$ 170 ns.
+.EQ
+delim off
+.EN
 .ps -2
 .so graph_fifo_query_partition.grap
 .ps \n[PS]
+.QP
+This first figure shows the request durations to retrieve data based on a partition containing up to 10k entries.
+.QE
+As we see in the figure, the duration for data retrieval grows almost linearly for databases with a sufficient cache size (starting with 10k entries).
+When the cache size is not sufficient, the requests are hundred times slower, which explain why the database with a cache size of one thousand entries isn't even represented in the graph, and why the 5k database has great results up to 5k partitions.
+.ps -2
+.so graph_fifo_query_tag.grap
+.ps \n[PS]
+.QP
+This first figure shows the request durations to retrieve data based on a tag containing up to 5k entries.
+.QE