From ce0ecde565d22cda75cd0ddeb4b92c7c0a95ca67 Mon Sep 17 00:00:00 2001
From: Maggie White <maggiewhite@google.com>
Date: Fri, 21 Jul 2017 15:33:20 -0700
Subject: [PATCH] UFS-specific runtime I/O tuning

Tested 1/2x, 1x, 2x, and 4x the current readahead buffer and noop and
cfq I/O schedulers for /dev/block/sda, which contains /data. The most
consistent performance boost was seen across all UFS vendors and storage
sizes using cfq and a readahead buffer of 1024.
Note: testing was done on Walleye, not Taimen

Bug: 38000161
Test: Compared 1P app launch times using app-launcher for schedulers
(noop, cfq) and readahead buffer sizes (128,512,1024,2048)

Change-Id: I7551a4110ad025ec7975dd39301f048f0942f585
---
 init-taimen.rc | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init-taimen.rc b/init-taimen.rc
index 1a6ddb4..13ae83e 100644
--- a/init-taimen.rc
+++ b/init-taimen.rc
@@ -15,7 +15,7 @@ on late-fs
 
 on property:sys.boot_completed=1
     # end boot time fs tune
-    write /sys/block/sda/queue/read_ahead_kb 512
+    write /sys/block/sda/queue/read_ahead_kb 1024
     write /sys/block/sda/queue/nr_requests 128
     write /sys/block/sda/queue/iostats 1
     write /sys/block/sde/queue/read_ahead_kb 512