[jira] [Assigned] (GIRAPH-174) ConnectedComponentsVertex for loops can be replaced with for-each loops
[ https://issues.apache.org/jira/browse/GIRAPH-174?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Hyunsik Choi reassigned GIRAPH-174: --- Assignee: Roman K ConnectedComponentsVertex for loops can be replaced with for-each loops --- Key: GIRAPH-174 URL: https://issues.apache.org/jira/browse/GIRAPH-174 Project: Giraph Issue Type: Improvement Reporter: Jakob Homan Assignee: Roman K Priority: Trivial Labels: newbie Attachments: GIRAPH-174.patch {code}// First superstep is special, because we can simply look at the neighbors if (getSuperstep() == 0) { for (IteratorIntWritable edges = iterator(); edges.hasNext();) { int neighbor = edges.next().get(); if (neighbor currentComponent) { currentComponent = neighbor; } } // Only need to send value if it is not the own id if (currentComponent != getVertexValue().get()) { setVertexValue(new IntWritable(currentComponent)); for (IteratorIntWritable edges = iterator(); edges.hasNext();) { int neighbor = edges.next().get(); if (neighbor currentComponent) { sendMsg(new IntWritable(neighbor), getVertexValue()); } } }{code} Both of the for loops in this chunk from ConnectedComponentsVertex can be replaced with for(IntWritable i : iterator()) loops to be more idiomatic. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-185) Improve concurrency of putMsg / putMsgList
[ https://issues.apache.org/jira/browse/GIRAPH-185?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13262278#comment-13262278 ] Hyunsik Choi commented on GIRAPH-185: - If there is a trade-off relationship between the performance and memory consumption, the memory consumption seems more important in the current giraph implementation. Also, I agree that some benchmarks are necessary. Improve concurrency of putMsg / putMsgList -- Key: GIRAPH-185 URL: https://issues.apache.org/jira/browse/GIRAPH-185 Project: Giraph Issue Type: Improvement Components: graph Affects Versions: 0.2.0 Reporter: Bo Wang Assignee: Bo Wang Fix For: 0.2.0 Attachments: GIRAPH-185.patch, GIRAPH-185.patch Original Estimate: 2h Remaining Estimate: 2h Currently in putMsg / putMsgList, a synchronized closure is used to protect the whole transientInMessages when adding the new message. This lock prevents other concurrent calls to putMsg/putMsgList and increases the response time. We should use fine-grain locks to allow high concurrency in message communication. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13114646#comment-13114646 ] Hyunsik Choi commented on GIRAPH-12: I'm sorry too for late response. I was out of town due to my personal work. I just come to home. The previous experiments are too simple. Actually, that experiment cannot show any meaningful result. I sorry for that. As to the question 3, this issue was originated from the memory usage. I should have measured the memory usage. Sooner, I'll answer your 3 questions :) Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Components: bsp Reporter: Avery Ching Assignee: Hyunsik Choi Priority: Minor Attachments: GIRAPH-12_1.patch, GIRAPH-12_2.patch Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13114709#comment-13114709 ] Hyunsik Choi commented on GIRAPH-12: I have thought about question 3. That is, how we can measure the memory usage while Giraph is running. Probably, the most basic way is to use the hadoop metrics (http://www.cloudera.com/blog/2009/03/hadoop-metrics/). However, this way needs to change _hadoop-metrics.properties_ file. So, it may be restricted for most large clusters; e.g., Yahoo! cluster that Avery can access. If the above way is impossible, we can implement a thread class mimic to hadoop metric in order to measure the memory usage on JVM periodically and sends that to a specific remote server. What do you think about that? Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Components: bsp Reporter: Avery Ching Assignee: Hyunsik Choi Priority: Minor Attachments: GIRAPH-12_1.patch, GIRAPH-12_2.patch Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Hyunsik Choi updated GIRAPH-12: --- Attachment: GIRAPH-12_2.patch I attach the second patch. I have benchmarked this patch via GIRAPH-32. The results are shown as the below. In the results, the improved version is slightly better than current implementation. As Avery mentioned, the improved one makes threads controllable, so it is an improve. Users can adjust the number of core threads and max threads by using GiraphJob's constants, such as MSG_FLUSHER_CORE_SIZE and MSG_FLUSHER_MAX_SIZE. This setting can affect the performance. So, we may need to guide users to find the best parameters. But, this experiment may be not enough to evaluate this approach because this experiment is conducted in small cluster. *the result of original version* {noformat} org.apache.giraph.benchmark.RandomMessageBenchmark -e 2 -s 3 -w 6 -b 4 -n 150 -V 30 -v = 1st = 11/09/22 00:55:06 INFO mapred.JobClient: Total (milliseconds)=63096 11/09/22 00:55:06 INFO mapred.JobClient: Superstep 3 (milliseconds)=551 11/09/22 00:55:06 INFO mapred.JobClient: Setup (milliseconds)=1331 11/09/22 00:55:06 INFO mapred.JobClient: Shutdown (milliseconds)=1008 11/09/22 00:55:06 INFO mapred.JobClient: Vertex input superstep (milliseconds)=516 11/09/22 00:55:06 INFO mapred.JobClient: Superstep 0 (milliseconds)=16079 11/09/22 00:55:06 INFO mapred.JobClient: Superstep 2 (milliseconds)=25657 11/09/22 00:55:06 INFO mapred.JobClient: Superstep 1 (milliseconds)=17950 = 2rd = 11/09/22 00:58:13 INFO mapred.JobClient: Total (milliseconds)=62771 11/09/22 00:58:13 INFO mapred.JobClient: Superstep 3 (milliseconds)=600 11/09/22 00:58:13 INFO mapred.JobClient: Setup (milliseconds)=1290 11/09/22 00:58:13 INFO mapred.JobClient: Shutdown (milliseconds)=950 11/09/22 00:58:13 INFO mapred.JobClient: Vertex input superstep (milliseconds)=614 11/09/22 00:58:13 INFO mapred.JobClient: Superstep 0 (milliseconds)=15654 11/09/22 00:58:13 INFO mapred.JobClient: Superstep 2 (milliseconds)=25157 11/09/22 00:58:13 INFO mapred.JobClient: Superstep 1 (milliseconds)=18499 {noformat} *the result of patched version* {noformat} = 1st = 11/09/22 00:59:41 INFO mapred.JobClient: Total (milliseconds)=60068 11/09/22 00:59:41 INFO mapred.JobClient: Superstep 3 (milliseconds)=542 11/09/22 00:59:41 INFO mapred.JobClient: Setup (milliseconds)=1219 11/09/22 00:59:41 INFO mapred.JobClient: Shutdown (milliseconds)=1025 11/09/22 00:59:41 INFO mapred.JobClient: Vertex input superstep (milliseconds)=616 11/09/22 00:59:41 INFO mapred.JobClient: Superstep 0 (milliseconds)=15887 11/09/22 00:59:41 INFO mapred.JobClient: Superstep 2 (milliseconds)=23149 11/09/22 00:59:41 INFO mapred.JobClient: Superstep 1 (milliseconds)=17626 = 2rd = 11/09/22 01:01:05 INFO mapred.JobClient: Total (milliseconds)=60359 11/09/22 01:01:05 INFO mapred.JobClient: Superstep 3 (milliseconds)=510 11/09/22 01:01:05 INFO mapred.JobClient: Setup (milliseconds)=1399 11/09/22 01:01:05 INFO mapred.JobClient: Shutdown (milliseconds)=956 11/09/22 01:01:05 INFO mapred.JobClient: Vertex input superstep (milliseconds)=550 11/09/22 01:01:05 INFO mapred.JobClient: Superstep 0 (milliseconds)=16054 11/09/22 01:01:05 INFO mapred.JobClient: Superstep 2 (milliseconds)=23049 11/09/22 01:01:05 INFO mapred.JobClient: Superstep 1 (milliseconds)=17835 {noformat} Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Components: bsp Reporter: Avery Ching Assignee: Hyunsik Choi Priority: Minor Attachments: GIRAPH-12_1.patch, GIRAPH-12_2.patch Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Resolved] (GIRAPH-32) Implement benchmarks to evaluate the performance of message passing
[ https://issues.apache.org/jira/browse/GIRAPH-32?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Hyunsik Choi resolved GIRAPH-32. Resolution: Fixed Because this issue got +1, I just committed. Implement benchmarks to evaluate the performance of message passing Key: GIRAPH-32 URL: https://issues.apache.org/jira/browse/GIRAPH-32 Project: Giraph Issue Type: Task Components: benchmark Reporter: Hyunsik Choi Assignee: Hyunsik Choi Fix For: 0.70.0 Attachments: GIRAPH-32.patch, GIRAPH-32_2.patch Message passing framework plays an important role in Giraph. We need some benchmark programs to evaluate the improvement related to message passing method. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (GIRAPH-32) Implement benchmarks to evaluate the performance of message passing
[ https://issues.apache.org/jira/browse/GIRAPH-32?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Hyunsik Choi updated GIRAPH-32: --- Attachment: GIRAPH-32_2.patch Good idea! According to which InputFormat we use, we could choose the distribution of destination vertices. I attach the patch that corrected coding convention. Implement benchmarks to evaluate the performance of message passing Key: GIRAPH-32 URL: https://issues.apache.org/jira/browse/GIRAPH-32 Project: Giraph Issue Type: Task Components: benchmark Reporter: Hyunsik Choi Assignee: Hyunsik Choi Fix For: 0.70.0 Attachments: GIRAPH-32.patch, GIRAPH-32_2.patch Message passing framework plays an important role in Giraph. We need some benchmark programs to evaluate the improvement related to message passing method. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (GIRAPH-32) Implement benchmarks to evaluate the performance of message passing
[ https://issues.apache.org/jira/browse/GIRAPH-32?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Hyunsik Choi updated GIRAPH-32: --- Attachment: GIRAPH-32.patch I attach the patch about this issue. This patch includes a benchmark class. In this benchmark, for each vertex, the compute function sends a meaningless message into all edges of the vertex. Actually, I intend this benchmark to send messages into random workers. PseudoRandomVertexInputFormat already generates random edges. I employed it. This benchmark allows users to set the size of message bytes and the number of sending messages per edge. This is because I think they are basic factors to evaluate the behavior and performance of some message delivery system. Besides, users can adjust the number of edges per vertex rather than adjusting the number of sending messages per. It allows users to make the sending pattern either more spread or more skewed. Anyone can review this? Implement benchmarks to evaluate the performance of message passing Key: GIRAPH-32 URL: https://issues.apache.org/jira/browse/GIRAPH-32 Project: Giraph Issue Type: Task Components: benchmark Reporter: Hyunsik Choi Assignee: Hyunsik Choi Fix For: 0.70.0 Attachments: GIRAPH-32.patch Message passing framework plays an important role in Giraph. We need some benchmark programs to evaluate the improvement related to message passing method. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13107061#comment-13107061 ] Hyunsik Choi commented on GIRAPH-12: (a note for sharing) Graph mutation functions (e.g., addVertexRequest, addEdgeRequest..) directly invoke RPC functions. This approach incurs RPC round-trip overheads during processing. Especially when many workers try to mutate vertices or edges, synchronization overheads may also occur in receiving sides. It may be severe as the size of cluster increases. If we change graph mutation API to asynchronous messages, it would be more efficient. If possible, graph mutation messages and value messages (i.e., sendMsg) can be integrated into one message passing API. Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Components: bsp Reporter: Avery Ching Assignee: Hyunsik Choi Priority: Minor Attachments: GIRAPH-12_1.patch Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13107063#comment-13107063 ] Hyunsik Choi commented on GIRAPH-12: (a note for sharing) In current implementation, outgoing messages are sent to other peers in only two triggers: 1) When the number of outgoing messages for a specific peer exceeds the a threshold (i.e., maxSize), the outgoing messages for the peer are transmitted to the peer. 2) When one super step is finished, the entire messages are flushed to other peers. In the case 1, however, the current implementation only consider the number of messages instead of the size of messages. The outgoing messages reside in main memory until they are sent to other peers. It is another important factor to consume main memory. It would be good to consider not only the number of messages but also the size of messages. Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Components: bsp Reporter: Avery Ching Assignee: Hyunsik Choi Priority: Minor Attachments: GIRAPH-12_1.patch Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-35) Modifying the site to indicated that Jake Mannix and Dmitriy Ryaboy are now Giraph committers
[ https://issues.apache.org/jira/browse/GIRAPH-35?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13105795#comment-13105795 ] Hyunsik Choi commented on GIRAPH-35: +1 Welcome new committers :) Modifying the site to indicated that Jake Mannix and Dmitriy Ryaboy are now Giraph committers - Key: GIRAPH-35 URL: https://issues.apache.org/jira/browse/GIRAPH-35 Project: Giraph Issue Type: Task Reporter: Avery Ching Assignee: Avery Ching Attachments: GIRAPH-35.patch -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13104340#comment-13104340 ] Hyunsik Choi commented on GIRAPH-12: You mean that we need some benchmark program to test the performance and scalability of message passing methods. If so, I'll add two benchmarking programs, which are sending messages to peers in random and skewed distribution respectively. For this, I'll create another issue. Let me know what you think :) Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Components: bsp Reporter: Avery Ching Assignee: Hyunsik Choi Priority: Minor Attachments: GIRAPH-12_1.patch Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Created] (GIRAPH-32) Implement benchmarks to evaluate the performance of message passing
Implement benchmarks to evaluate the performance of message passing Key: GIRAPH-32 URL: https://issues.apache.org/jira/browse/GIRAPH-32 Project: Giraph Issue Type: Task Components: benchmark Reporter: Hyunsik Choi Assignee: Hyunsik Choi Fix For: 0.70.0 Message passing framework plays an important role in Giraph. We need some benchmark programs to evaluate the improvement related to message passing method. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Created] (GIRAPH-33) Missing license header of GraphState.java
Missing license header of GraphState.java - Key: GIRAPH-33 URL: https://issues.apache.org/jira/browse/GIRAPH-33 Project: Giraph Issue Type: Task Components: graph Reporter: Hyunsik Choi Priority: Trivial Fix For: 0.70.0 GraphState.java doesn't contain apache license header. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (GIRAPH-33) Missing license header of GraphState.java
[ https://issues.apache.org/jira/browse/GIRAPH-33?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Hyunsik Choi updated GIRAPH-33: --- Attachment: GIRAPH-33.patch This patch adds apache license header. Missing license header of GraphState.java - Key: GIRAPH-33 URL: https://issues.apache.org/jira/browse/GIRAPH-33 Project: Giraph Issue Type: Task Components: graph Reporter: Hyunsik Choi Priority: Trivial Fix For: 0.70.0 Attachments: GIRAPH-33.patch GraphState.java doesn't contain apache license header. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Resolved] (GIRAPH-33) Missing license header of GraphState.java
[ https://issues.apache.org/jira/browse/GIRAPH-33?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Hyunsik Choi resolved GIRAPH-33. Resolution: Fixed This is a trivial fix. I just committed. Missing license header of GraphState.java - Key: GIRAPH-33 URL: https://issues.apache.org/jira/browse/GIRAPH-33 Project: Giraph Issue Type: Task Components: graph Reporter: Hyunsik Choi Priority: Trivial Fix For: 0.70.0 Attachments: GIRAPH-33.patch GraphState.java doesn't contain apache license header. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13102682#comment-13102682 ] Hyunsik Choi commented on GIRAPH-12: Like the current PeerThread, initially each PeerConnection gets one established RPC proxy. These connections are kept during whole processing. So, there is no connection overhead. If you test this code on Yahoo!'s clusters, I'll appreciate your help. And, next week I can access to my lab's hadoop cluster. At that time, I'll also do some tests. Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Components: bsp Reporter: Avery Ching Assignee: Hyunsik Choi Priority: Minor Attachments: GIRAPH-12_1.patch Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Hyunsik Choi updated GIRAPH-12: --- Attachment: GIRAPH-12_1.patch As Avery mentioned, in the current architecture, each worker requires N threads that communicate with N remote peers. This may incur severe context-switching overheads (especially when all messages are flushed) and more memory consumption. Firstly, I considered about replacing RPC system to another one. However, it is not simple work. I need more time. Instead, I have considered an alternative way to employ ThreadPoolExecutor in order to adjust active threads. When Giraph deals with large graphs, the performance of Giraph is usually bounded on network bandwidth. I think that this approach would be effective. In addition, I tried to reduce the synchronization area, where BasicRPCCommunicator (374-394 lines) sends large buffered messages to specific peers. I attached the patch in progress. Now, I cannot access to real hadoop cluster for one week. I didn't test this in real cluster. Besides, all unit test are passed. How about this approach? Could you review this? Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Reporter: Avery Ching Assignee: Hyunsik Choi Priority: Minor Attachments: GIRAPH-12_1.patch Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Updated] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ] Hyunsik Choi updated GIRAPH-12: --- Component/s: bsp Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Components: bsp Reporter: Avery Ching Assignee: Hyunsik Choi Priority: Minor Attachments: GIRAPH-12_1.patch Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-29) Implement TextVertexInputFormat for text-format graph data
[ https://issues.apache.org/jira/browse/GIRAPH-29?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13102111#comment-13102111 ] Hyunsik Choi commented on GIRAPH-29: I'm sorry for my big mistake. I overlookd org.apache.giraph.lib package. I have a question. When a program use TextVertexInputFormat, the active workers are determined by the number of blocks? How does giraph work when the blocks are more than numWorkers? Should the numWorkers is set by user by considering both the length of input data and the number of numWorkers. Implement TextVertexInputFormat for text-format graph data -- Key: GIRAPH-29 URL: https://issues.apache.org/jira/browse/GIRAPH-29 Project: Giraph Issue Type: New Feature Components: bsp Reporter: Hyunsik Choi Assignee: Hyunsik Choi Priority: Minor Fix For: 0.70.0 Supporting text-format graph data would be nice. It is helpful for developing graph algorithms and debugging because text-format graph data are human-readable and enable users to easily write sample data sets. Furthermore, text-format data are exchangeable regardless of operating systems or programming languages. So, we need a basic InputFormat to help users develop user-defined InputFormat classes to deal text-represented graph data sets. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-29) Implement TextVertexInputFormat for text-format graph data
[ https://issues.apache.org/jira/browse/GIRAPH-29?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13102177#comment-13102177 ] Hyunsik Choi commented on GIRAPH-29: Thank you for your kind reply. Implement TextVertexInputFormat for text-format graph data -- Key: GIRAPH-29 URL: https://issues.apache.org/jira/browse/GIRAPH-29 Project: Giraph Issue Type: New Feature Components: bsp Reporter: Hyunsik Choi Assignee: Hyunsik Choi Priority: Minor Fix For: 0.70.0 Supporting text-format graph data would be nice. It is helpful for developing graph algorithms and debugging because text-format graph data are human-readable and enable users to easily write sample data sets. Furthermore, text-format data are exchangeable regardless of operating systems or programming languages. So, we need a basic InputFormat to help users develop user-defined InputFormat classes to deal text-represented graph data sets. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-9) Change Yahoo License Header to Apache License Header
[ https://issues.apache.org/jira/browse/GIRAPH-9?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13092619#comment-13092619 ] Hyunsik Choi commented on GIRAPH-9: --- Unfortunately, I didn't know that there exists such a tool. I changed them in hand :) Change Yahoo License Header to Apache License Header Key: GIRAPH-9 URL: https://issues.apache.org/jira/browse/GIRAPH-9 Project: Giraph Issue Type: Task Reporter: Hyunsik Choi Assignee: Hyunsik Choi Fix For: 0.1.0 Attachments: GIRAPH-9.patch All source codes contains Yahoo License Header as follows {noformat} Licensed to Yahoo! under one or more contributor license agreements. ... {noformat} These license header should be as follows {noformat} Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. ... {noformat} -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira
[jira] [Commented] (GIRAPH-12) Investigate communication improvements
[ https://issues.apache.org/jira/browse/GIRAPH-12?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanelfocusedCommentId=13092622#comment-13092622 ] Hyunsik Choi commented on GIRAPH-12: Netty seems to be good solution. Now, Apache Avro provides the netty-based server. If we use Avro as a rpc mechanism among workers, we could solve this problem easily. Investigate communication improvements -- Key: GIRAPH-12 URL: https://issues.apache.org/jira/browse/GIRAPH-12 Project: Giraph Issue Type: Improvement Reporter: Avery Ching Priority: Minor Currently every worker will start up a thread to communicate with every other workers. Hadoop RPC is used for communication. For instance if there are 400 workers, each worker will create 400 threads. This ends up using a lot of memory, even with the option -Dmapred.child.java.opts=-Xss64k. It would be good to investigate using frameworks like Netty or custom roll our own to improve this situation. By moving away from Hadoop RPC, we would also make compatibility of different Hadoop versions easier. -- This message is automatically generated by JIRA. For more information on JIRA, see: http://www.atlassian.com/software/jira