I had this problem too, and it’s a typo in the direction. Basically you need to change the name of the output (it’s supposed to be a file, not a directory, or a file name conflicting with an existing directory).
So instead of ./loader -a ../twitter_dataset/twitter_dataset_unscaled -o ../twitter_dataset/ -s servers.txt -w 1 -S 1 -D 4096 -j -T 1 Do: ./loader -a ../twitter_dataset/twitter_dataset_unscaled -o ../twitter_dataset/twitter_dataset_scaled -s servers.txt -w 1 -S 1 -D 4096 -j -T 1 You’d then change the following directions according to the new file name Tri From: Yarong Guo Sent: July 1, 2013 3:00 PM To: cloudsuite Subject: Segmentation Fault while running Data Caching Hello, After building the benchmark, I tried to run the client by: ./loader -a ../twitter_dataset/twitter_dataset_unscaled -o ../twitter_dataset/ -s servers.txt -w 1 -S 1 -D 4096 -j -T 1 It gives me a segmentation fault: stats_time = 1 Configuration: nProcessors on system: 8 nWorkers: 1 runtime: -1 Get fraction: 0.900000 Naggle's algorithm: False host: 131.179.116.101 address: 131.179.116.101 Segmentation fault Anyone have met a similar situation? Thank you! Yarong
