Changes between Version 7 and Version 8 of GENIExperimenter/Tutorials/HadoopInASlice/ExecuteExperiment
- Timestamp:
- 01/07/14 21:17:52 (10 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
GENIExperimenter/Tutorials/HadoopInASlice/ExecuteExperiment
v7 v8 22 22 Now that you have reserved your resources, you are ready to... 23 23 24 == 9. Login to nodes==24 == 1. Login to Hadoop Master == 25 25 {{{ 26 26 #!html … … 31 31 32 32 <td > 33 <ol >34 <li>Login (ssh) to the hadoop-master using a yourself usingthe key you associated with the33 <ol type="A"> 34 <li>Login (ssh) to the hadoop-master using the key you associated with the 35 35 GENI Portal and the IP address displayed by Flack. The ssh application you use will 36 36 depend on the configuration of laptop/desktop that you are using.</li> 37 <li>Check the status/properties of the VMs.</li> 38 39 <ol type="a"> 37 </op> 38 </td></tr> 39 </table> 40 }}} 41 42 == 2. Check the status/properties of the VMs. == 43 44 {{{ 45 #!html 46 47 48 <table border="0"> 49 <tr> 50 51 <td > 52 <ol type="A"> 53 40 54 <li> Observe the properties of the network interfaces </li> 41 55 … … 168 182 rtt min/avg/max/mdev = 0.468/0.607/0.852/0.174 ms 169 183 </code></pre> 170 171 172 <li> Check the status of the Hadoop filesystem</li> 184 </op> 185 186 </td></tr> 187 </table> 188 }}} 189 190 == 3. Check the status of the Hadoop filesystem. == 191 192 {{{ 193 #!html 194 195 196 <table border="0"> 197 <tr> 198 199 <td > 200 <ol type="A"> 201 202 203 <li> Query for the status of the filesystem and its associated workers. </li> 173 204 <pre><code> 174 205 # hadoop dfsadmin -report … … 210 241 211 242 243 212 244 <li> Test the filesystem with a small file </li> 213 245 … … 237 269 238 270 </ol> 239 240 241 <li> Test the true power of the Hadoop filesystem by creating and sorting a large random dataset. It may be useful/interesting to login to the master and/or worker VMs and use tools like \verb$top$, \verb$iotop$, and \verb$iftop$ to observe the resource utilization on each of the VMs during the sort test. </li> 242 243 244 <ol type="a"> 271 </op> 272 273 </td></tr> 274 </table> 275 }}} 276 277 == 4. Run the Hadoop Sort Testcase == 278 279 Test the true power of the Hadoop filesystem by creating and sorting a large random dataset. It may be useful/interesting to login to the master and/or worker VMs and use tools like \verb$top$, \verb$iotop$, and \verb$iftop$ to observe the resource utilization on each of the VMs during the sort test. 280 281 {{{ 282 #!html 283 284 285 <table border="0"> 286 <tr> 287 288 <td > 289 <ol type="A"> 245 290 <li> Create a 1 GB random data set. After the data is created, use the \verb$ls$ functionally to confirm the data exists. Note that the data is composed of several files in a directory. </li> 246 291 <pre><code> … … 331 376 </ol> 332 377 333 <li>Re-do tutorial with a different number of workers, amount of bandwidth, and/or worker instance types. Warning: Be courteous to other users and do not take all the resources. </li> 334 335 <ol type="a"> 378 </td></tr> 379 </table> 380 }}} 381 382 == 5. Advanced Example == 383 384 Re-do the tutorial with a different number of workers, amount of bandwidth, and/or worker instance types. Warning: Be courteous to other users and do not take all the resources. 385 386 {{{ 387 #!html 388 389 390 <table border="0"> 391 <tr> 392 393 <td > 394 <ol type="A"> 395 396 336 397 <li> Time the performance of runs with different resources </li> 337 398 <li> Observe largest size file you can create with different settings. </li>