| # Copyright 2015 Webindex authors (see AUTHORS) |
| # |
| # Licensed under the Apache License, Version 2.0 (the "License"); |
| # you may not use this file except in compliance with the License. |
| # You may obtain a copy of the License at |
| # |
| # http://www.apache.org/licenses/LICENSE-2.0 |
| # |
| # Unless required by applicable law or agreed to in writing, software |
| # distributed under the License is distributed on an "AS IS" BASIS, |
| # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| # See the License for the specific language governing permissions and |
| # limitations under the License. |
| |
| # Accumulo table where indexes are exported for search |
| accumuloIndexTable: webindex_search |
| # Fluo Application Name |
| fluoApp: webindex |
| # Webindex builds multiple data sets for its computation. Each of these data |
| # sets needs to be spread across the cluster. The setting below determines how |
| # much each dataset will be split up. Ideally this would be a small multiple of |
| # the number of Accumulo tablet servers. |
| numTablets: 20 |
| # Number of buckets for collision free maps and export queue. This setting is |
| # used during initialization of the Fluo table and when Spark loads the initial |
| # data. The value of numBuckets must be the same for these two task. |
| numBuckets: 100 |
| #This determines how fast each Spark load task will load documents. Set to 0 |
| #for no limit. Setting this to 50 and running 10 conucurrent load task would |
| #limit the load rate to 500 documents/sec. |
| loadRateLimit: 0 |
| # HDFS temporary directory |
| hdfsTempDir: /cc/temp |