In the benchmarking page "https://docs.vespa.ai/en/performance/vespa-benchmarking.html" it is given that we need to restart the services after we increase the persearch thread using the commands vespa-stop-services and vespa-start-services. Could you tell us if we need to do this on all the content nodes or just the config nodes?
When deploying a change that requires a restart, the deploy command will list the actions you need to take. For example when changing the global per search thread setting changing from 2 to 5 in the below example:
curl --header Content-Type:application/zip --data-binary @target/application.zip localhost:19071/application/v2/tenant/default/prepareandactivate |jq .
{
"log": [
{
"time": 1645036778830,
"level": "WARNING",
"message": "Change(s) between active and new application that require restart:\nIn cluster 'mycluster' of type 'search':\n Restart services of type 'searchnode' because:\n 1) # Number of threads used per search\nproton.numthreadspersearch has changed from 2 to 5\n"
}
],
"tenant": "default",
"url": "http://localhost:19071/application/v2/tenant/default/application/default/environment/prod/region/default/instance/default",
"message": "Session 8 for tenant 'default' prepared and activated.",
"configChangeActions": {
"restart": [
{
"clusterName": "mycluster",
"clusterType": "search",
"serviceType": "searchnode",
"messages": [
"# Number of threads used per search\nproton.numthreadspersearch has changed from 2 to 5"
],
"services": [
{
"serviceName": "searchnode",
"serviceType": "searchnode",
"configId": "mycluster/search/cluster.mycluster/0",
"hostName": "vespa-container"
}
]
}
],
"refeed": [],
"reindex": []
}
}