To fit or not to fit

artifacts/2022-09-23-s3lat/plot.R

@@ -19,7 +19,7 @@ ggplot(c, aes(x=endpoint,y=time_mean,fill=daemon,ymin=time_min,ymax=time_max)) +
       coord_flip() +
       labs(
         x="S3 Endpoint",
-        y="Latency (ms)",
+        y="Request duration (ms)",
         fill="Daemon",
         caption="Get the code to reproduce this graph at https://git.deuxfleurs.fr/Deuxfleurs/mknet",
         title="S3 endpoint latency in a simulated geo-distributed cluster",

artifacts/2022-09-24-s3billion/plot.R

@@ -1,12 +1,25 @@
 library(tidyverse)
+library(ggpmisc)
 
 
-read_csv("garage-v0.8-beta2-lmdb.csv") %>% mutate(batch_dur_sec = batch_dur_nanoseconds / 1000 / 1000 / 1000 ) -> s
+read_csv("garage-v0.8-beta2-lmdb.csv") %>% mutate(batch_dur_sec = batch_dur_nanoseconds / 1000 / 1000 / 1000) %>% filter(total_objects != 0) -> s
+
+reg1 <- lm(s$batch_dur_sec~s$total_objects)
+reg2 <- lm(s$batch_dur_sec ~ log(s$total_objects))
+
+f1 <- y~log(x)
+f2 <- y~x
+
 ggplot(s, aes(x=total_objects, y=batch_dur_sec)) +
   geom_point() +
-  geom_smooth(method = "gam", se = FALSE) + 
+  #geom_smooth(method="lm",formula=f1,  se = FALSE, color="red") + 
+  #geom_smooth(method="lm",formula=f2,  se = FALSE, color="blue") +
+  #stat_poly_eq(formula = f1, label.y = 0.9, color = "red", aes(label=paste(..eq.label..,..rr.label..,..adj.rr.label..,..AIC.label..,..BIC.label.., sep = "~~~"))) +
+  #stat_poly_eq(formula = f2, label.y = 0.8, color="blue",aes(label=paste(..eq.label..,..rr.label..,..adj.rr.label..,..AIC.label..,..BIC.label.., sep = "~~~"))) +
+  #geom_smooth(method = "gam", se = FALSE) + 
   scale_x_continuous(expand=c(0,0), breaks = scales::pretty_breaks(n = 10))+
   scale_y_continuous(expand=c(0,0), breaks = scales::pretty_breaks(n = 10))+
+  coord_cartesian(ylim=c(0,60)) +
   labs(
     y="Time (in sec) spent sending a batch (8192 objects)",
     x="Total number of objects stored in the cluster",
@@ -15,6 +28,7 @@ ggplot(s, aes(x=total_objects, y=batch_dur_sec)) +
     subtitle="Daemon: Garage v0.8 beta 2 with LMDB as db_engine\nBenchmark: 128 batch. 8192 objects/batch. 32 threads/batch. 256 objects/thread. 16-byte/objects.\nEnvironment: mknet (Ryzen 5 1400, 16GB RAM, SSD). DC topo (3 nodes, 1Gb/s, 1ms latency).") +
   theme_classic()
 ggsave("./garage.png", width=200, height=120, units="mm")
+#ggsave("./garage-regression.png", width=200, height=120, units="mm")