Hello Kazi,

You have to ensure connectivity between the client and the server. Make sure 
you can ping/ssh from one to another. 
I see that you are using port 80. Port 80 is dedicated to HTTP, you should 
always avoid reserved ports. Try using the 
default port (11211). 
Once you solve this and if the segmentation fault is still there, please run 
the client with gdb and send us 
the stack trace once it crashes. 

Regards,
Djordje
________________________________________
From: Kazi Sudipto Arif [[email protected]]
Sent: Tuesday, August 27, 2013 5:54 PM
To: Djordje Jevdjic
Subject: Re: running data-caching magic number error

Djordje,

           My memcached is memcached-1.4.15 with libevent-2.0.21 . Instead of 
using two servers after noting my error, I am trying to use a single server as 
I originally intended. I am running this on a vm through virtualbox. When I try 
to put only one server on the servers.txt I am recieving a segmentation fault. 
I am assuming that maybe I have not configured my servers.txt properly. The 
current contents of my servers.txt file are:

10.0.5.2, 80

and this is the result:

vagrant@server:/opt/memcached/memcached_client$ ./loader -a 
../twitter_dataset/twitter_dataset_unscaled -o 
../twitter_dataset/twitter_dataset_30x -s servers.txt -S 30 -D 4096 -j -T 1
stats_time = 1
Configuration:

nProcessors on system: 8
nWorkers: 1
runtime: -1
Get fraction: 0.900000
Naggle's algorithm: False


host: 10.0.5.2
address: 10.0.5.2
Segmentation fault

Thank you very much,

Kazi


On Tue, Aug 27, 2013 at 10:36 AM, Djordje Jevdjic 
<[email protected]<mailto:[email protected]>> wrote:
Hello Kazi,

There is no need to be a root when running this benchmark.
Could you let me know the exact Memcached version you are using?

I guess you wanted to say "-S 30" in your command, rather than -S 3.

I see that you are using two servers at the same time.  I suggest you create two
files: server1.txt and server2.txt each containing the corresponding server 
details.

Then run the following command to scale the dataset and warm up one server:
./loader -a ../twitter_dataset/twitter_dataset_unscaled -o 
../twitter_dataset/twitter_dataset_30x -s servers1.txt  -S 30 -D 4096 -j -T 1

Once it finishes, you can just warm up the other server:
./loader -a ../twitter_dataset/twitter_dataset_30x -s servers2.txt -S 1 -D 4096 
-j -T 1

Let me know what happens.

Regards,
Djordje
________________________________________
From: Kazi Sudipto Arif [[email protected]<mailto:[email protected]>]
Sent: Tuesday, August 27, 2013 9:30 AM
To: [email protected]<mailto:[email protected]>
Subject: running data-caching magic number error

Hello,

I am attempting to get the data-caching benchmark up and running on Ubuntu 
10.04 OS (x86). I receive a magic number error when attempting to scale the 
dataset. The output file is not produced and I cannot start the benchmark. I 
cannot understand why this is happening and any help in tracking the cause 
would be much appreciated.

Scaling the dataset:

root@server:/opt/memcached/memcached_client# sudo ./loader -a 
../twitter_dataset/twitter_dataset_unscaled -o ../twitter_dataset_30x -s 
servers.txt -w 2 -S 3 -D 4096 -j -T 1
stats_time = 1
Configuration:

nProcessors on system: 8
nWorkers: 2
runtime: -1
Get fraction: 0.900000
Naggle's algorithm: False


host: 10.0.5.2
address: 10.0.5.2
host: 192.168.10.116
address: 192.168.10.116
Loading key value file...Average Size = 1057.34758
Keys to Preload = 802302
created uniform distribution 1000
rps -1 cpus 2
Overridge n_connections_total because < n_workers
num_worker_connections 1
num_worker_connections 1
Creating worker on tid 1340749568
starting receive base loop
On read Incorrect magic number: 48 should be: ffffff81

Thank you,

Kazi

Reply via email to