home.markdown

@@ -42,7 +42,7 @@ Figure out what's the next step:
 Well, first these two.
 
 ### Feb 26
-* Previously Result:
+- Previously Result:
     * Created a free style fakeStream for Retwis, which caused some pressure but not really.
     * Able to run YCSB on both Redis-Single and Redis-Cluster.
     * Found out that Redis-Cluster is almost 3x slower than Redis-Single
@@ -50,7 +50,7 @@ Well, first these two.
     * Tried tests on Python client using Retwis
     * Turns out Redis-Cluster is slower than Redis-Single
 
-* Current Thinking:
+- Current Thinking:
     * The performance difference between Redis-Cluster and Redis-Single is caused by the client side random redirecting when requesting the data. 
     * Demo of the situation is like this:
 
@@ -83,9 +83,12 @@ Well, first these two.
         `-> Redirected to slot [14969] located at 127.0.0.1:7002`
         
         `OK`
-    * Whatever
+    * Pending alternation for the Redis-Cluste:
+        - Using the Sharded Jedis Client, to see what will happen in order of YCSB performance
+        - Copy and paste the Redis-Cluster hash function, implement it in the client. Basically everytime we need to read/write a data, we hash first to figure out which machine we should go and directly go there and get the result we want.
+        - Set up a client which use Redis-Cluster's hash function, let it hash to the existing node. This implementation eliminated the redirecting process.
 
-* Weak point and improvement for the fakeStream:
+- Weak point and improvement for the fakeStream:
   1. Changing the functionality of Retwis
       1. Add a Retweet function:
           * post part: "Shared by" + PreviousUser's Username + OldPost