# Elasticsearch process dies when using G1GC **URL:** \ **Category:** Elasticsearch\ **Created:** [June 4, 2013, 12:44am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247 "2013-06-04T00:44:17Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![Christopher\_J\_Bottar](https://avatars.discourse-cdn.com/v4/letter/c/e0b2c6/32.png) [@Christopher\_J\_Bottar](https://discuss.elastic.co/u/Christopher_J_Bottar)\ **Post date:** [June 4, 2013, 12:44am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/1 "2013-06-04T00:44:17Z")
When I enable G1GC, Elasticsearch won't stay running for more than a few minutes. When it dies, nothing is output in the logs. All I see is an entry in syslog: init: elasticsearch main process (17253) terminated with status 134 Here are my G1 settings: JAVA\_OPTS="$JAVA\_OPTS -XX:+UseG1GC" JAVA\_OPTS="$JAVA\_OPTS -XX:+UnlockExperimentalVMOptions" JAVA\_OPTS="$JAVA\_OPTS -XX:MaxGCPauseMillis=400" JAVA\_OPTS="$JAVA\_OPTS -XX:GCPauseIntervalMillis=8000" I've also tried 50/100 (pause/interval). My Java version: java version "1.7.0\_21" Java(TM) SE Runtime Environment (build 1.7.0\_21-b11) Java HotSpot(TM) 64-Bit Server VM (build 23.21-b01, mixed mode) I'm running on EC2, using a cluster of 4 m1.xlarge with 5 gb allocated to Elasticsearch and mlockall true. The workload is distributed bulk indexing. I have 600 processes each in a loop, submitting bulk index requests of 200 documents at a time. As a side note, if I use UseParNewGC and UseConcMarkSweepGC, eventually I get stop-the-world pauses (of ~5s) every few seconds on each node. Which renders the cluster useless. How can I get G1 to work? Or how can I stop CMS from stopping the world several times per minute? Thank for the help. -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![jprante](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jprante/32/44941_2.png) [@jprante](https://discuss.elastic.co/u/jprante)\ **Post date:** [June 4, 2013, 7:33am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/2 "2013-06-04T07:33:28Z")
Do not use -XX:+UnlockExperimentalVMOptions or you will trigger bugs. This is for developers living on bleeding edge. Jörg Am 04.06.13 02:44, schrieb Christopher J. Bottaro: > JAVA\_OPTS="$JAVA\_OPTS -XX:+UnlockExperimentalVMOptions" -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![zerocoolys](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/zerocoolys/32/44918_2.png) [@zerocoolys](https://discuss.elastic.co/u/zerocoolys)\ **Post date:** [June 4, 2013, 8:53am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/3 "2013-06-04T08:53:55Z")
I found when using the G1 GC, elasticsearch will core dump for a few minutes. The root cause from thread dump shows # Problematic frame: # J org.elasticsearch.common.io.stream.HandlesStreamOutput.writeString(Ljava/lang/String;)V This problem only happen during indexing. When change back to CMS GC , everything goes well. ---
**Author:** ![Christopher\_J\_Bottar](https://avatars.discourse-cdn.com/v4/letter/c/e0b2c6/32.png) [@Christopher\_J\_Bottar](https://discuss.elastic.co/u/Christopher_J_Bottar)\ **Post date:** [June 4, 2013, 3:06pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/4 "2013-06-04T15:06:15Z")
Exact same result, with or without -XX:+UnlockExperimentalVMOptions. Thanks for the help. On Tuesday, June 4, 2013 2:33:28 AM UTC-5, Jörg Prante wrote: > Do not use -XX:+UnlockExperimentalVMOptions or you will trigger bugs. > This is for developers living on bleeding edge. > > Jörg > > Am 04.06.13 02:44, schrieb Christopher J. Bottaro: > > > JAVA\_OPTS="$JAVA\_OPTS -XX:+UnlockExperimentalVMOptions" -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![Jon\_Shea](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jon_shea/32/2263_2.png) [@Jon\_Shea](https://discuss.elastic.co/u/Jon_Shea)\ **Post date:** [June 4, 2013, 7:58pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/5 "2013-06-04T19:58:00Z")
Hi Christopher, I’ve had the best results using ParallelGC. We haven’t profiled the G1 yet, but I have done fairly extensive profiling of CMS (which I expect behaves similarly to G1). We’ve found that as we increase query volume ParallelGC tends to gradually degrade in performance, and an increasing percentage of queries would get caught by our 2s timeout. In contrast, when we run CMS we find that the cluster behaves pretty well under increasing load, and then suddenly at some critical level, machines will start experiencing multi-second stop-the-world garbage collections and the cluster would totally falls apart. Our CMS cluster would fall apart at about 60-70% of the traffic that our ParallelGC cluster could do while still timing out fewer than 0.5% of requests. Some people disagree with me about this, but I recommend you give ParallelGC a try. ParallelGC gives us more query throughput, mostly better query latency (worse at the 99%+ quantile), and more warning when our cluster is over-stressed and approaching failure. That said, 600 processes each running bulk inserts could be very aggressive. I’m not surprised that can knock over your cluster. I normally backfill batches of 1000 1kb documents in one single-threaded process, and I have a dynamically tunable sleep period after each insert so that I can dial back the insert rate if my cluster starts to look like it is over stressed. Are these live updates you’re processing? How many documents do you need to index per minute? If this index rate is a hard constraint, then you may need to scale your write capacity by running more shards on more machines, or by using machines with better IO throughput (ie, SSDs). -Jon -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![jprante](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jprante/32/44941_2.png) [@jprante](https://discuss.elastic.co/u/jprante)\ **Post date:** [June 4, 2013, 8:59pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/6 "2013-06-04T20:59:31Z")
G1 GC is a totally different beast. See Fig. 6 in [http://blog.mgm-tp.com/2013/03/garbage-collection-tuning/](http://blog.mgm-tp.com/2013/03/garbage-collection-tuning/) Jörg Am 04.06.13 21:58, schrieb Jon Shea: > We haven’t profiled the G1 yet, but I have done fairly extensive > profiling of CMS (which I expect behaves similarly to G1). -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![otisg](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/otisg/32/492_2.png) [@otisg](https://discuss.elastic.co/u/otisg)\ **Post date:** [June 4, 2013, 11:03pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/7 "2013-06-04T23:03:44Z")
Hi, For what it's worth, we helped a client the other day deal with ES 0.20.4 and issues around shard recovery and performance. We switched from \ to G1 and "things worked better", both with updated 17 and 21 of Oracle's Java 1.7. There were certainly no crashes. ## Otis ELASTICSEARCH Performance Monitoring - [Sematext Monitoring | Infrastructure Monitoring Service](http://sematext.com/spm/index.html) On Monday, June 3, 2013 8:44:17 PM UTC-4, Christopher J. Bottaro wrote: > When I enable G1GC, Elasticsearch won't stay running for more than a few > minutes. When it dies, nothing is output in the logs. All I see is an > entry in syslog: > > init: elasticsearch main process (17253) terminated with status 134 > > Here are my G1 settings: > > JAVA\_OPTS="$JAVA\_OPTS -XX:+UseG1GC" > JAVA\_OPTS="$JAVA\_OPTS -XX:+UnlockExperimentalVMOptions" > JAVA\_OPTS="$JAVA\_OPTS -XX:MaxGCPauseMillis=400" > JAVA\_OPTS="$JAVA\_OPTS -XX:GCPauseIntervalMillis=8000" > > I've also tried 50/100 (pause/interval). > > My Java version: > > java version "1.7.0\_21" > Java(TM) SE Runtime Environment (build 1.7.0\_21-b11) > Java HotSpot(TM) 64-Bit Server VM (build 23.21-b01, mixed mode) > > I'm running on EC2, using a cluster of 4 m1.xlarge with 5 gb allocated to > Elasticsearch and mlockall true. > > The workload is distributed bulk indexing. I have 600 processes each in a > loop, submitting bulk index requests of 200 documents at a time. > > As a side note, if I use UseParNewGC and UseConcMarkSweepGC, eventually I > get stop-the-world pauses (of ~5s) every few seconds on each node. Which > renders the cluster useless. > > How can I get G1 to work? Or how can I stop CMS from stopping the world > several times per minute? > > Thank for the help. -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![shadyabhi](https://avatars.discourse-cdn.com/v4/letter/s/edb3f5/32.png) [@shadyabhi](https://discuss.elastic.co/u/shadyabhi)\ **Post date:** [June 5, 2013, 4:00pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/8 "2013-06-05T16:00:10Z")
Hi Otis, Sorry to hop in and hijack the thread. Can you provide the exact JAVA OPTS that you used for using G1?Thanks On Wed, Jun 5, 2013 at 4:33 AM, Otis Gospodnetic \<[otis.gospodnetic@gmail.com](mailto:otis.gospodnetic@gmail.com) > wrote: > Hi, > > For what it's worth, we helped a client the other day deal with ES 0.20.4 > and issues around shard recovery and performance. We switched from \ don't recall which JVM params and collector\> to G1 and "things worked > better", both with updated 17 and 21 of Oracle's Java 1.7. There were > certainly no crashes. > > ## Otis > > ELASTICSEARCH Performance Monitoring - [Sematext Monitoring | Infrastructure Monitoring Service](http://sematext.com/spm/index.html) > > On Monday, June 3, 2013 8:44:17 PM UTC-4, Christopher J. Bottaro wrote: > > > When I enable G1GC, Elasticsearch won't stay running for more than a few > > minutes. When it dies, nothing is output in the logs. All I see is an > > entry in syslog: > > > > init: elasticsearch main process (17253) terminated with status 134 > > > > Here are my G1 settings: > > > > JAVA\_OPTS="$JAVA\_OPTS -XX:+UseG1GC" > > JAVA\_OPTS="$JAVA\_OPTS -XX:+\*\*UnlockExperimentalVMOptions" > > JAVA\_OPTS="$JAVA\_OPTS -XX:MaxGCPauseMillis=400" > > JAVA\_OPTS="$JAVA\_OPTS -XX:GCPauseIntervalMillis=\*\*8000" > > > > I've also tried 50/100 (pause/interval). > > > > My Java version: > > > > java version "1.7.0\_21" > > Java(TM) SE Runtime Environment (build 1.7.0\_21-b11) > > Java HotSpot(TM) 64-Bit Server VM (build 23.21-b01, mixed mode) > > > > I'm running on EC2, using a cluster of 4 m1.xlarge with 5 gb allocated to > > Elasticsearch and mlockall true. > > > > The workload is distributed bulk indexing. I have 600 processes each in > > a loop, submitting bulk index requests of 200 documents at a time. > > > > As a side note, if I use UseParNewGC and UseConcMarkSweepGC, eventually I > > get stop-the-world pauses (of ~5s) every few seconds on each node. Which > > renders the cluster useless. > > > > How can I get G1 to work? Or how can I stop CMS from stopping the world > > several times per minute? > > > > Thank for the help. > > -- > You received this message because you are subscribed to the Google Groups > "elasticsearch" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). -- Regards, Abhijeet Rastogi (shadyabhi) [http://blog.abhijeetr.com](http://blog.abhijeetr.com) -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![otisg](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/otisg/32/492_2.png) [@otisg](https://discuss.elastic.co/u/otisg)\ **Post date:** [June 9, 2013, 4:46am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/9 "2013-06-09T04:46:16Z")
Hi, I don't have access to that server at the moment, but I believe it was -XX:+UseG1GC -server -Xms... -Xmx... -- i.e., nothing exotic. ## Otis Performance Monitoring - [Sematext Monitoring | Infrastructure Monitoring Service](http://sematext.com/spm/index.html) Solr & Elasticsearch Support - [http://sematext.com/](http://sematext.com/) On Wednesday, June 5, 2013 12:00:10 PM UTC-4, Abhijeet Rastogi wrote: > Hi Otis, > > Sorry to hop in and hijack the thread. Can you provide the exact JAVA OPTS > that you used for using G1?Thanks > > On Wed, Jun 5, 2013 at 4:33 AM, Otis Gospodnetic \<[otis.gos...@gmail.com](mailto:otis.gos...@gmail.com)\ > > > wrote: > > > Hi, > > > > For what it's worth, we helped a client the other day deal with ES 0.20.4 > > and issues around shard recovery and performance. We switched from \ > don't recall which JVM params and collector\> to G1 and "things worked > > better", both with updated 17 and 21 of Oracle's Java 1.7. There were > > certainly no crashes. > > > > ## Otis > > > > ELASTICSEARCH Performance Monitoring - [Sematext Monitoring | Infrastructure Monitoring Service](http://sematext.com/spm/index.html) > > > > On Monday, June 3, 2013 8:44:17 PM UTC-4, Christopher J. Bottaro wrote: > > > > > When I enable G1GC, Elasticsearch won't stay running for more than a few > > > minutes. When it dies, nothing is output in the logs. All I see is an > > > entry in syslog: > > > > > > init: elasticsearch main process (17253) terminated with status 134 > > > > > > Here are my G1 settings: > > > > > > JAVA\_OPTS="$JAVA\_OPTS -XX:+UseG1GC" > > > JAVA\_OPTS="$JAVA\_OPTS -XX:+\*\*UnlockExperimentalVMOptions" > > > JAVA\_OPTS="$JAVA\_OPTS -XX:MaxGCPauseMillis=400" > > > JAVA\_OPTS="$JAVA\_OPTS -XX:GCPauseIntervalMillis=\*\*8000" > > > > > > I've also tried 50/100 (pause/interval). > > > > > > My Java version: > > > > > > java version "1.7.0\_21" > > > Java(TM) SE Runtime Environment (build 1.7.0\_21-b11) > > > Java HotSpot(TM) 64-Bit Server VM (build 23.21-b01, mixed mode) > > > > > > I'm running on EC2, using a cluster of 4 m1.xlarge with 5 gb allocated > > > to Elasticsearch and mlockall true. > > > > > > The workload is distributed bulk indexing. I have 600 processes each in > > > a loop, submitting bulk index requests of 200 documents at a time. > > > > > > As a side note, if I use UseParNewGC and UseConcMarkSweepGC, eventually > > > I get stop-the-world pauses (of ~5s) every few seconds on each node. Which > > > renders the cluster useless. > > > > > > How can I get G1 to work? Or how can I stop CMS from stopping the world > > > several times per minute? > > > > > > Thank for the help. > > > > -- > > You received this message because you are subscribed to the Google Groups > > "elasticsearch" group. > > To unsubscribe from this group and stop receiving emails from it, send an > > email to [elasticsearc...@googlegroups.com](mailto:elasticsearc...@googlegroups.com) \. > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). > > -- > Regards, > Abhijeet Rastogi (shadyabhi) > [http://blog.abhijeetr.com](http://blog.abhijeetr.com) -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![Klaus\_Brunner](https://avatars.discourse-cdn.com/v4/letter/k/9fc29f/32.png) [@Klaus\_Brunner](https://discuss.elastic.co/u/Klaus_Brunner)\ **Post date:** [June 10, 2013, 9:59am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/10 "2013-06-10T09:59:16Z")
FWIW, I've also run extensive load tests using G1GC (OpenJDK 7uSomething, 64 bits on Linux) a few months ago, and it worked nicely. As expected from my earlier tests with application servers, throughput dropped a bit but latency was a lot more stable, i.e. no long pauses. Didn't use hundreds of threads for indexing, though, just about 50. Klaus On Sunday, 9 June 2013 06:46:16 UTC+2, Otis Gospodnetic wrote: > Hi, > > I don't have access to that server at the moment, but I believe it was -XX:+UseG1GC > -server -Xms... -Xmx... -- i.e., nothing exotic. > > ## Otis > > Performance Monitoring - [Sematext Monitoring | Infrastructure Monitoring Service](http://sematext.com/spm/index.html) > Solr & Elasticsearch Support - [http://sematext.com/](http://sematext.com/) > > On Wednesday, June 5, 2013 12:00:10 PM UTC-4, Abhijeet Rastogi wrote: > > > Hi Otis, > > > > Sorry to hop in and hijack the thread. Can you provide the exact JAVA > > OPTS that you used for using G1?Thanks > > > > On Wed, Jun 5, 2013 at 4:33 AM, Otis Gospodnetic [otis.gos...@gmail.com](mailto:otis.gos...@gmail.com)wrote: > > > > > Hi, > > > > > > For what it's worth, we helped a client the other day deal with ES > > > 0.20.4 and issues around shard recovery and performance. We switched from > > > \ to G1 and "things worked > > > better", both with updated 17 and 21 of Oracle's Java 1.7. There were > > > certainly no crashes. > > > > > > ## Otis > > > > > > ELASTICSEARCH Performance Monitoring - > > > [Sematext Monitoring | Infrastructure Monitoring Service](http://sematext.com/spm/index.html) > > > > > > On Monday, June 3, 2013 8:44:17 PM UTC-4, Christopher J. Bottaro wrote: > > > > > > > When I enable G1GC, Elasticsearch won't stay running for more than a > > > > few minutes. When it dies, nothing is output in the logs. All I see is an > > > > entry in syslog: > > > > > > > > init: elasticsearch main process (17253) terminated with status 134 > > > > > > > > Here are my G1 settings: > > > > > > > > JAVA\_OPTS="$JAVA\_OPTS -XX:+UseG1GC" > > > > JAVA\_OPTS="$JAVA\_OPTS -XX:+\*\*UnlockExperimentalVMOptions" > > > > JAVA\_OPTS="$JAVA\_OPTS -XX:MaxGCPauseMillis=400" > > > > JAVA\_OPTS="$JAVA\_OPTS -XX:GCPauseIntervalMillis=\*\*8000" > > > > > > > > I've also tried 50/100 (pause/interval). > > > > > > > > My Java version: > > > > > > > > java version "1.7.0\_21" > > > > Java(TM) SE Runtime Environment (build 1.7.0\_21-b11) > > > > Java HotSpot(TM) 64-Bit Server VM (build 23.21-b01, mixed mode) > > > > > > > > I'm running on EC2, using a cluster of 4 m1.xlarge with 5 gb allocated > > > > to Elasticsearch and mlockall true. > > > > > > > > The workload is distributed bulk indexing. I have 600 processes each > > > > in a loop, submitting bulk index requests of 200 documents at a time. > > > > > > > > As a side note, if I use UseParNewGC and UseConcMarkSweepGC, eventually > > > > I get stop-the-world pauses (of ~5s) every few seconds on each node. Which > > > > renders the cluster useless. > > > > > > > > How can I get G1 to work? Or how can I stop CMS from stopping the > > > > world several times per minute? > > > > > > > > Thank for the help. > > > > > > -- > > > You received this message because you are subscribed to the Google > > > Groups "elasticsearch" group. > > > To unsubscribe from this group and stop receiving emails from it, send > > > an email to [elasticsearc...@googlegroups.com](mailto:elasticsearc...@googlegroups.com). > > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). > > > > -- > > Regards, > > Abhijeet Rastogi (shadyabhi) > > [http://blog.abhijeetr.com](http://blog.abhijeetr.com) -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![Dan\_Everton](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/dan_everton/32/1865_2.png) [@Dan\_Everton](https://discuss.elastic.co/u/Dan_Everton)\ **Post date:** [July 22, 2013, 5:44am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/11 "2013-07-22T05:44:41Z")
On Sunday, June 9, 2013 2:46:16 PM UTC+10, Otis Gospodnetic wrote: > I don't have access to that server at the moment, but I believe it was -XX:+UseG1GC > -server -Xms... -Xmx... -- i.e., nothing exotic. What heap size? We're trying to use G1GC but a few seconds after startup, the JVM process running the Elasticsearch instance crashes. The only clue is that it's crashing at # J org.elasticsearch.common.trove.impl.hash.TObjectHash.insertKey(Ljava/lang/Object;)I But that's not all that helpful. We're on the latest JDK 7 (update 25 I believe) from Oracle and with a Xms/Xmx of 16 GB on a 12-core AMD machine. Searching for bug reports doesn't turn up much apart from this > which indicates the problem has been around for a long time and isn't ES specific. Cheers, Dan > -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![Runar\_Myklebust](https://avatars.discourse-cdn.com/v4/letter/r/a6a055/32.png) [@Runar\_Myklebust](https://discuss.elastic.co/u/Runar_Myklebust)\ **Post date:** [July 22, 2013, 9:01am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/12 "2013-07-22T09:01:36Z")
Ive experienced the same behaviour in our embedded ES installations, with the same results, and it seems that trove is the reason. Doesnt really help us and our customers though, I would hope that the ES team would address this, or at least make an official statement that G1GC is not supported. On Mon, Jul 22, 2013 at 7:44 AM, Dan Everton [dan@iocaine.org](mailto:dan@iocaine.org) wrote: > On Sunday, June 9, 2013 2:46:16 PM UTC+10, Otis Gospodnetic wrote: > > > I don't have access to that server at the moment, but I believe it was -XX:+UseG1GC > > -server -Xms... -Xmx... -- i.e., nothing exotic. > > What heap size? We're trying to use G1GC but a few seconds after startup, > the JVM process running the Elasticsearch instance crashes. The only clue > is that it's crashing at > > # J > > org.elasticsearch.common.trove.impl.hash.TObjectHash.insertKey(Ljava/lang/Object;)I > > But that's not all that helpful. We're on the latest JDK 7 (update 25 I > believe) from Oracle and with a Xms/Xmx of 16 GB on a 12-core AMD machine. > > Searching for bug reports doesn't turn up much apart from this > [http://stackoverflow.com/questions/11293384/jvm-crash-with-g1-gc-and-trove-librarywhich](http://stackoverflow.com/questions/11293384/jvm-crash-with-g1-gc-and-trove-librarywhich) indicates the problem has been around for a long time and isn't ES > specific. > > Cheers, > > Dan > > > -- > > You received this message because you are subscribed to the Google Groups > > "elasticsearch" group. > > To unsubscribe from this group and stop receiving emails from it, send an > > email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ## -- mvh Runar Myklebust -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![jprante](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jprante/32/44941_2.png) [@jprante](https://discuss.elastic.co/u/jprante)\ **Post date:** [July 22, 2013, 9:35am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/13 "2013-07-22T09:35:42Z")
My extensive load tests with ES index and query under Java with G1GC are passing succesfully, both Java 7 and Java 8. What you found is a bug triggered by trove, not related to Elasticsearch. Nevertheless I would be glad to help and I wonder what trove jar was used. From [https://bitbucket.org/robeden/trove/src/c59d0ed735f0824cca851743e070d065509cf219/pom.xml?at=masterI](https://bitbucket.org/robeden/trove/src/c59d0ed735f0824cca851743e070d065509cf219/pom.xml?at=masterI) conclude the Maven artifact is in Java 5 class format. Probably a new trove build or some trove fixes could help to get it run with G1GC. Jörg On Mon, Jul 22, 2013 at 11:01 AM, Runar Myklebust [runar.a.m@gmail.com](mailto:runar.a.m@gmail.com)wrote: > Ive experienced the same behaviour in our embedded ES installations, with > the same results, and it seems that trove is the reason. Doesnt really help > us and our customers though, I would hope that the ES team would address > this, or at least make an official statement that G1GC is not supported. > > On Mon, Jul 22, 2013 at 7:44 AM, Dan Everton [dan@iocaine.org](mailto:dan@iocaine.org) wrote: > > > On Sunday, June 9, 2013 2:46:16 PM UTC+10, Otis Gospodnetic wrote: > > > > > I don't have access to that server at the moment, but I believe it was -XX:+UseG1GC > > > -server -Xms... -Xmx... -- i.e., nothing exotic. > > > > What heap size? We're trying to use G1GC but a few seconds after startup, > > the JVM process running the Elasticsearch instance crashes. The only clue > > is that it's crashing at > > > > # J > > > > org.elasticsearch.common.trove.impl.hash.TObjectHash.insertKey(Ljava/lang/Object;)I > > > > But that's not all that helpful. We're on the latest JDK 7 (update 25 I > > believe) from Oracle and with a Xms/Xmx of 16 GB on a 12-core AMD machine. > > > > Searching for bug reports doesn't turn up much apart from this > > [java - JVM Crash with G1 GC and trove library - Stack Overflow](http://stackoverflow.com/questions/11293384/jvm-crash-with-g1-gc-and-trove-librarywhich) indicates the problem has been around for a long time and isn't ES > > specific. > > > > Cheers, > > > > Dan > > > > > -- > > > You received this message because you are subscribed to the Google Groups > > > "elasticsearch" group. > > > To unsubscribe from this group and stop receiving emails from it, send an > > > email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). > > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). > > ## -- mvh > > Runar Myklebust > > -- > You received this message because you are subscribed to the Google Groups > "elasticsearch" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![jprante](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jprante/32/44941_2.png) [@jprante](https://discuss.elastic.co/u/jprante)\ **Post date:** [July 22, 2013, 9:52pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/14 "2013-07-22T21:52:49Z")
On Maven repo, I found this gnu/trove/Version.class: compiled Java class data, version 49.0 (Java 1.5) built with 1.6.0\_31-b04-415-11M3646 (Apple Inc.) I have copied over the source for a Java 1.6 (class file format 50) mavenized build of trove here (using Java 1.7.0\_21): [https://github.com/xbib/trove](https://github.com/xbib/trove) If you want to try out if this binary works better with ES and G1GC, you may include trove jar from ``` github-release-repo https://github.com/xbib/maven-repo/raw/master/releases ``` net.sf.trove4j trove4j 3.0.3 or by manual download [https://github.com/xbib/maven-repo/tree/master/releases/net/sf/trove4j/trove4j/3.0.3](https://github.com/xbib/maven-repo/tree/master/releases/net/sf/trove4j/trove4j/3.0.3) Best, Jörg On Mon, Jul 22, 2013 at 11:35 AM, [joergprante@gmail.com](mailto:joergprante@gmail.com) \< [joergprante@gmail.com](mailto:joergprante@gmail.com)\> wrote: > My extensive load tests with ES index and query under Java with G1GC are > passing succesfully, both Java 7 and Java 8. > > What you found is a bug triggered by trove, not related to Elasticsearch. > Nevertheless I would be glad to help and I wonder what trove jar was used. > From > [https://bitbucket.org/robeden/trove/src/c59d0ed735f0824cca851743e070d065509cf219/pom.xml?at=masterI](https://bitbucket.org/robeden/trove/src/c59d0ed735f0824cca851743e070d065509cf219/pom.xml?at=masterI) conclude the Maven artifact is in Java 5 class format. Probably a new > trove build or some trove fixes could help to get it run with G1GC. > > Jörg > > On Mon, Jul 22, 2013 at 11:01 AM, Runar Myklebust [runar.a.m@gmail.com](mailto:runar.a.m@gmail.com)wrote: > > > Ive experienced the same behaviour in our embedded ES installations, with > > the same results, and it seems that trove is the reason. Doesnt really help > > us and our customers though, I would hope that the ES team would address > > this, or at least make an official statement that G1GC is not supported. > > > > On Mon, Jul 22, 2013 at 7:44 AM, Dan Everton [dan@iocaine.org](mailto:dan@iocaine.org) wrote: > > > > > On Sunday, June 9, 2013 2:46:16 PM UTC+10, Otis Gospodnetic wrote: > > > > > > > I don't have access to that server at the moment, but I believe it was -XX:+UseG1GC > > > > -server -Xms... -Xmx... -- i.e., nothing exotic. > > > > > > What heap size? We're trying to use G1GC but a few seconds after > > > startup, the JVM process running the Elasticsearch instance crashes. The > > > only clue is that it's crashing at > > > > > > # J > > > > > > org.elasticsearch.common.trove.impl.hash.TObjectHash.insertKey(Ljava/lang/Object;)I > > > > > > But that's not all that helpful. We're on the latest JDK 7 (update 25 I > > > believe) from Oracle and with a Xms/Xmx of 16 GB on a 12-core AMD machine. > > > > > > Searching for bug reports doesn't turn up much apart from this > > > [java - JVM Crash with G1 GC and trove library - Stack Overflow](http://stackoverflow.com/questions/11293384/jvm-crash-with-g1-gc-and-trove-librarywhich) indicates the problem has been around for a long time and isn't ES > > > specific. > > > > > > Cheers, > > > > > > Dan > > > > > > > -- > > > > You received this message because you are subscribed to the Google > > > > Groups "elasticsearch" group. > > > > To unsubscribe from this group and stop receiving emails from it, send > > > > an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). > > > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). > > > > ## -- mvh > > > > Runar Myklebust > > > > -- > > You received this message because you are subscribed to the Google Groups > > "elasticsearch" group. > > To unsubscribe from this group and stop receiving emails from it, send an > > email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![Dan\_Everton](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/dan_everton/32/1865_2.png) [@Dan\_Everton](https://discuss.elastic.co/u/Dan_Everton)\ **Post date:** [July 23, 2013, 11:22pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/15 "2013-07-23T23:22:10Z")
On Tuesday, July 23, 2013 7:52:49 AM UTC+10, Jörg Prante wrote: > On Maven repo, I found this gnu/trove/Version.class: compiled Java class > data, version 49.0 (Java 1.5) built with 1.6.0\_31-b04-415-11M3646 (Apple > Inc.) > > I have copied over the source for a Java 1.6 (class file format 50) > mavenized build of trove here (using Java 1.7.0\_21): I wouldn't expect recompiling the JAR with Java 7 would make any difference but I'll see if we can get it tested. Switching to mmapfs from niofs helped a little bit with G1GC enabled. The nodes survive for a few minutes instead of dying immediately. There's no load on them during this time so I've no idea what the cause might be. But at this point it looks like G1GC is completely unusable for us. Cheers, Dan -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![jprante](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/jprante/32/44941_2.png) [@jprante](https://discuss.elastic.co/u/jprante)\ **Post date:** [July 24, 2013, 8:56am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/16 "2013-07-24T08:56:41Z")
I could reproduce the issue, both on JDK 7 and 8. Trying to build a reproducible test case. Jörg On Wed, Jul 24, 2013 at 1:22 AM, Dan Everton [dan@iocaine.org](mailto:dan@iocaine.org) wrote: > On Tuesday, July 23, 2013 7:52:49 AM UTC+10, Jörg Prante wrote: > > > On Maven repo, I found this gnu/trove/Version.class: compiled Java class > > data, version 49.0 (Java 1.5) built with 1.6.0\_31-b04-415-11M3646 (Apple > > Inc.) > > > > I have copied over the source for a Java 1.6 (class file format 50) > > mavenized build of trove here (using Java 1.7.0\_21): > > I wouldn't expect recompiling the JAR with Java 7 would make any > difference but I'll see if we can get it tested. > > Switching to mmapfs from niofs helped a little bit with G1GC enabled. The > nodes survive for a few minutes instead of dying immediately. There's no > load on them during this time so I've no idea what the cause might be. But > at this point it looks like G1GC is completely unusable for us. > > Cheers, > Dan > > -- > You received this message because you are subscribed to the Google Groups > "elasticsearch" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![saiprasad\_mishra](https://avatars.discourse-cdn.com/v4/letter/s/da6949/32.png) [@saiprasad\_mishra](https://discuss.elastic.co/u/saiprasad_mishra)\ **Post date:** [February 5, 2014, 7:19pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/17 "2014-02-05T19:19:55Z")
Any update on exact gc params that work with elasticsearch on G1. I am having the similar issue on ES 0.90.0 with G1 Thanks for your time on this Cheers Sai On Wednesday, July 24, 2013 1:56:41 AM UTC-7, Jörg Prante wrote: > I could reproduce the issue, both on JDK 7 and 8. Trying to build a > reproducible test case. > > Jörg > > On Wed, Jul 24, 2013 at 1:22 AM, Dan Everton \<[d...@iocaine.org](mailto:d...@iocaine.org)\ > > > wrote: > > > On Tuesday, July 23, 2013 7:52:49 AM UTC+10, Jörg Prante wrote: > > > > > On Maven repo, I found this gnu/trove/Version.class: compiled Java class > > > data, version 49.0 (Java 1.5) built with 1.6.0\_31-b04-415-11M3646 (Apple > > > Inc.) > > > > > > I have copied over the source for a Java 1.6 (class file format 50) > > > mavenized build of trove here (using Java 1.7.0\_21): > > > > I wouldn't expect recompiling the JAR with Java 7 would make any > > difference but I'll see if we can get it tested. > > > > Switching to mmapfs from niofs helped a little bit with G1GC enabled. The > > nodes survive for a few minutes instead of dying immediately. There's no > > load on them during this time so I've no idea what the cause might be. But > > at this point it looks like G1GC is completely unusable for us. > > > > Cheers, > > Dan > > > > -- > > You received this message because you are subscribed to the Google Groups > > "elasticsearch" group. > > To unsubscribe from this group and stop receiving emails from it, send an > > email to [elasticsearc...@googlegroups.com](mailto:elasticsearc...@googlegroups.com) \. > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). To view this discussion on the web visit [https://groups.google.com/d/msgid/elasticsearch/8705c21e-62da-4247-803c-d0a3c8cdcfc4%40googlegroups.com](https://groups.google.com/d/msgid/elasticsearch/8705c21e-62da-4247-803c-d0a3c8cdcfc4%40googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![Ivan](https://avatars.discourse-cdn.com/v4/letter/i/df788c/32.png) [@Ivan](https://discuss.elastic.co/u/Ivan)\ **Post date:** [February 5, 2014, 7:35pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/18 "2014-02-05T19:35:50Z")
The primary issue with G1 is the Trove library. Elasticsearch no longer uses Trove with versions 0.90.6 and higher, so I would suggest upgrading if you plan on using G1GC. -- Ivan On Wed, Feb 5, 2014 at 11:19 AM, saiprasad mishra \<[saiprasadmishra@gmail.com](mailto:saiprasadmishra@gmail.com) > wrote: > Any update on exact gc params that work with elasticsearch on G1. I am > having the similar issue on ES 0.90.0 with G1 > > Thanks for your time on this > Cheers > Sai > > On Wednesday, July 24, 2013 1:56:41 AM UTC-7, Jörg Prante wrote: > > > I could reproduce the issue, both on JDK 7 and 8. Trying to build a > > reproducible test case. > > > > Jörg > > > > On Wed, Jul 24, 2013 at 1:22 AM, Dan Everton [d...@iocaine.org](mailto:d...@iocaine.org) wrote: > > > > > On Tuesday, July 23, 2013 7:52:49 AM UTC+10, Jörg Prante wrote: > > > > > > > On Maven repo, I found this gnu/trove/Version.class: compiled Java > > > > class data, version 49.0 (Java 1.5) built with 1.6.0\_31-b04-415-11M3646 > > > > (Apple Inc.) > > > > > > > > I have copied over the source for a Java 1.6 (class file format 50) > > > > mavenized build of trove here (using Java 1.7.0\_21): > > > > > > I wouldn't expect recompiling the JAR with Java 7 would make any > > > difference but I'll see if we can get it tested. > > > > > > Switching to mmapfs from niofs helped a little bit with G1GC enabled. > > > The nodes survive for a few minutes instead of dying immediately. There's > > > no load on them during this time so I've no idea what the cause might be. > > > But at this point it looks like G1GC is completely unusable for us. > > > > > > Cheers, > > > Dan > > > > > > -- > > > You received this message because you are subscribed to the Google > > > Groups "elasticsearch" group. > > > To unsubscribe from this group and stop receiving emails from it, send > > > an email to [elasticsearc...@googlegroups.com](mailto:elasticsearc...@googlegroups.com). > > > > > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). > > > > -- > > You received this message because you are subscribed to the Google Groups > > "elasticsearch" group. > > To unsubscribe from this group and stop receiving emails from it, send an > > email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). > > To view this discussion on the web visit > > [https://groups.google.com/d/msgid/elasticsearch/8705c21e-62da-4247-803c-d0a3c8cdcfc4%40googlegroups.com](https://groups.google.com/d/msgid/elasticsearch/8705c21e-62da-4247-803c-d0a3c8cdcfc4%40googlegroups.com) > > . > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). To view this discussion on the web visit [https://groups.google.com/d/msgid/elasticsearch/CALY%3DcQD92eLQTmXnTqr4xURKHn9Vrsv2aRmYHcekELzXAALRKg%40mail.gmail.com](https://groups.google.com/d/msgid/elasticsearch/CALY%3DcQD92eLQTmXnTqr4xURKHn9Vrsv2aRmYHcekELzXAALRKg%40mail.gmail.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![saiprasad\_mishra](https://avatars.discourse-cdn.com/v4/letter/s/da6949/32.png) [@saiprasad\_mishra](https://discuss.elastic.co/u/saiprasad_mishra)\ **Post date:** [February 5, 2014, 8:02pm UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/19 "2014-02-05T20:02:46Z")
Thanks Ivan for very quick help here.... Planning to upgrade , this is one more reason to consider Will keep posted how it goes Cheers Sai On Wednesday, February 5, 2014 11:35:50 AM UTC-8, Ivan Brusic wrote: > The primary issue with G1 is the Trove library. Elasticsearch no longer > uses Trove with versions 0.90.6 and higher, so I would suggest upgrading if > you plan on using G1GC. > > -- > Ivan > > On Wed, Feb 5, 2014 at 11:19 AM, saiprasad mishra \<[saipras...@gmail.com](mailto:saipras...@gmail.com)\ > > > wrote: > > > Any update on exact gc params that work with elasticsearch on G1. I am > > having the similar issue on ES 0.90.0 with G1 > > > > Thanks for your time on this > > Cheers > > Sai > > > > On Wednesday, July 24, 2013 1:56:41 AM UTC-7, Jörg Prante wrote: > > > > > I could reproduce the issue, both on JDK 7 and 8. Trying to build a > > > reproducible test case. > > > > > > Jörg > > > > > > On Wed, Jul 24, 2013 at 1:22 AM, Dan Everton [d...@iocaine.org](mailto:d...@iocaine.org) wrote: > > > > > > > On Tuesday, July 23, 2013 7:52:49 AM UTC+10, Jörg Prante wrote: > > > > > > > > > On Maven repo, I found this gnu/trove/Version.class: compiled Java > > > > > class data, version 49.0 (Java 1.5) built with 1.6.0\_31-b04-415-11M3646 > > > > > (Apple Inc.) > > > > > > > > > > I have copied over the source for a Java 1.6 (class file format 50) > > > > > mavenized build of trove here (using Java 1.7.0\_21): > > > > > > > > I wouldn't expect recompiling the JAR with Java 7 would make any > > > > difference but I'll see if we can get it tested. > > > > > > > > Switching to mmapfs from niofs helped a little bit with G1GC enabled. > > > > The nodes survive for a few minutes instead of dying immediately. There's > > > > no load on them during this time so I've no idea what the cause might be. > > > > But at this point it looks like G1GC is completely unusable for us. > > > > > > > > Cheers, > > > > Dan > > > > > > > > -- > > > > You received this message because you are subscribed to the Google > > > > Groups "elasticsearch" group. > > > > To unsubscribe from this group and stop receiving emails from it, send > > > > an email to [elasticsearc...@googlegroups.com](mailto:elasticsearc...@googlegroups.com). > > > > > > > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). > > > > > > -- > > > You received this message because you are subscribed to the Google Groups > > > "elasticsearch" group. > > > To unsubscribe from this group and stop receiving emails from it, send an > > > email to [elasticsearc...@googlegroups.com](mailto:elasticsearc...@googlegroups.com) \. > > > To view this discussion on the web visit > > > [https://groups.google.com/d/msgid/elasticsearch/8705c21e-62da-4247-803c-d0a3c8cdcfc4%40googlegroups.com](https://groups.google.com/d/msgid/elasticsearch/8705c21e-62da-4247-803c-d0a3c8cdcfc4%40googlegroups.com) > > > . > > > > For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). -- You received this message because you are subscribed to the Google Groups "elasticsearch" group. To unsubscribe from this group and stop receiving emails from it, send an email to [elasticsearch+unsubscribe@googlegroups.com](mailto:elasticsearch+unsubscribe@googlegroups.com). To view this discussion on the web visit [https://groups.google.com/d/msgid/elasticsearch/4ae2c332-ce53-45af-952e-87b8bef9d60e%40googlegroups.com](https://groups.google.com/d/msgid/elasticsearch/4ae2c332-ce53-45af-952e-87b8bef9d60e%40googlegroups.com). For more options, visit [https://groups.google.com/groups/opt\_out](https://groups.google.com/groups/opt_out). ---
**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\ **Post date:** [July 6, 2017, 1:52am UTC](https://discuss.elastic.co/t/elasticsearch-process-dies-when-using-g1gc/12247/20 "2017-07-06T01:52:17Z")