In my MIX talk I told that for 2k reads, we take 3ms. It is actually the case under load where the servers are straining. Here is a latest performance shot that we got with the CTP3 bits.

Bulk APIs: Note that these numbers are without any bulk operations. With bulk gets (we are trying to add a Bulk Get in RTM timeframe within a region) we get upwards of 211,000 operations per second. (assuming a 32 key per batch).

Local Cache: None of these tests use Local Cache = true. That will again give upwards of 200K operations per second.

[Statutory Warning: These are the numbers that we got in our test labs to give you an idea of the performance characteristics of this product. There is no implicit warranty or guarantee on these numbers!]

Servers : 2

 

Server Configuration      :

Processor                       :             AMD Phenom (9600 B) Quad Core Processor

RAM size                        :              8 GB RAM

Operating System          :              64 bit win 2k3

Network                         :              1GBPS network

Secondary                      :               0

Client configuration       :              Routing with NO local cache.

No of Agents                  :              10

 

Throughput :

 

Scenario

object

Number of Clients

RC4(Ops/sec)

CTP2(Ops/sec)

 Mainly Gets

Byte[] (2kb)

100

34500

36300

Mainly Gets

Byte[](2kb to 16kb)

150

27000

27300

Put

Char[](2kb)

200

9170

6060

Put-Get

String[](1kb)

200

11500

8000

Put-Get-Remove

Byte[](4kb) wrapped in object

100

30300

29880

 

Latency :

 

Operation(byte array)

Object

RC4(In ms)

CTP2(in ms)

Add

Char [](2kb)

1.35

 

1.59

Put

Byte [](2kb)

0.63

 

0.55

Get

Byte [](2kb)

0.50

 

0.51

Remove

Byte [](2kb)

0.49

 

0.44

 

 

Servers : 2

 

Server Configuration :

 

Processor                            :             AMD Phenom (9600 B) Quad Core Processor

RAM size                            :                 8 GB RAM

Operating System               :               64 bit win 2k3

Network                              :             1GBPS network

 

Trending with and without secondary throughput on RC4:

 

Scenario

Object

with secondary

without secondary

Put-Get(2k)

String[](1k)

4300

11500

Put-Get-Remove(2k)

Byte[](4kb) wrapped in object

8280

30300

 

--

Murali