Re: High memory usage during nodetool repair

2021-08-09 Thread Elliott Sims
Shouldn't cause GCs. You can usually think of heap memory separately from the rest. It's already allocated as far as the OS is concerned, and it doesn't know anything about GC going on inside of that allocation. You can set "-XX:+AlwaysPreTouch" to make sure it's physically allocated on

Re: High memory usage during nodetool repair

2021-08-03 Thread Amandeep Srivastava
Thanks. I guess some earlier thread got truncated. I already applied Erick's recommendations and that seem to have worked in reducing the ram consumption by around 50%. Regarding cheap memory and hardware, we are already running 96GB boxes and getting multiple larger ones might be a little

Re: High memory usage during nodetool repair

2021-08-03 Thread Jim Shaw
I think Erick posted https://community.datastax.com/questions/6947/. explained very clearly. We hit same issue only on a huge table when upgrade, and we changed back after done. My understanding, Which option to chose, shall depend on your user case. If chasing high performance on a big table,

Re: High memory usage during nodetool repair

2021-08-02 Thread manish khandelwal
Missed the heap part, not sure why is that happening On Tue, Aug 3, 2021 at 8:59 AM manish khandelwal < manishkhandelwa...@gmail.com> wrote: > mmap is used for faster reads and as you guessed right you might see read > performance degradation. If you are seeing high memory usage after repairs >

Re: High memory usage during nodetool repair

2021-08-02 Thread manish khandelwal
mmap is used for faster reads and as you guessed right you might see read performance degradation. If you are seeing high memory usage after repairs due to mmaped files, the only way to reduce the memory usage is to trigger some other process which requires memory. *mmapped* files use buffer/cache

Re: High memory usage during nodetool repair

2021-08-02 Thread Amandeep Srivastava
Can anyone please help with the above questions? To summarise: 1) What is the impact of using mmap only for indices besides a degradation in read performance? 2) Why does the off heap consumed during Cassandra full repair remains occupied 12+ hours after the repair completion and is there a

Re: High memory usage during nodetool repair

2021-07-29 Thread Amandeep Srivastava
Hi Erick, Limiting mmap to index only seems to have resolved the issue. The max ram usage remained at 60% this time. Could you please point me to the limitations for setting this param? - For starters, I can see read performance getting reduced up to 30% (CASSANDRA-8464

Re: High memory usage during nodetool repair

2021-07-29 Thread Amandeep Srivastava
Thanks, Bowen, don't think that's an issue - but yes I can try upgrading to 3.11.5 and limit the merkle tree size to bring down the memory utilization. Thanks, Erick, let me try that. Can someone please share documentation relating to internal functioning of full repairs - if there exists one?

Re: High memory usage during nodetool repair

2021-07-28 Thread Erick Ramirez
Based on the symptoms you described, it's most likely caused by SSTables being mmap()ed as part of the repairs. Set `disk_access_mode: mmap_index_only` so only index files get mapped and not the data files. I've explained it in a bit more detail in this article --

Re: High memory usage during nodetool repair

2021-07-28 Thread Bowen Song
Could it be related to https://issues.apache.org/jira/browse/CASSANDRA-14096 ? On 28/07/2021 13:55, Amandeep Srivastava wrote: Hi team, My Cluster configs: DC1 - 9 nodes, DC2 - 4 nodes Node configs: 12 core x 96GB ram x 1 TB HDD Repair params: -full -pr -local Cassandra version: 3.11.4 I'm

High memory usage during nodetool repair

2021-07-28 Thread Amandeep Srivastava
Hi team, My Cluster configs: DC1 - 9 nodes, DC2 - 4 nodes Node configs: 12 core x 96GB ram x 1 TB HDD Repair params: -full -pr -local Cassandra version: 3.11.4 I'm running a full repair on DC2 nodes - one node and one keyspace at a time. During the repair, ram usage on all 4 nodes spike up to