LATEST VERSION: 8.2.7 - CHANGELOG
Pivotal GemFire® v8.2

GemFire Statistics List

GemFire Statistics List

This section describes the primary statistics gathered by GemFire when statistics are enabled.

All statistics gathering requires the gemfire.properties statistic-sampling-enabled in gemfire.properties file to be true. Statistics that use time require the gemfire.properties enable-time-statistics to be true.

Performance statistics are collected for each Java application or cache server that connects to a distributed system.
Note: For pure Java applications, operating system statistics are not available for collection. Operating system statistics are categorized as process statistics and system statistics.

Cache Performance (CachePerfStats)

Statistics for the GemFire cache. These can be used to determine the type and number of cache operations being performed and how much time they consume.

Regarding GemFire cache transactions, transaction-related statistics are compiled and stored as properties in the CachePerfStats statistic resource. Because the transaction’s data scope is the cache, these statistics are collected on a per-cache basis.

The primary statistics are:

Statistic Description
cacheListenerCallsCompleted Total number of times a cache listener call has completed.
cacheListenerCallsInProgress Current number of threads doing a cache listener call.
cacheListenerCallTime Total time spent doing cache listener calls.
cacheWriterCallsCompleted Total number of times a cache writer call has completed.
cacheWriterCallsInProgress Current number of threads doing a cache writer call.
cacheWriterCallTime Total time spent doing cache writer calls.
compressions Total number of compression operations.
compressTime Total time, in nanoseconds, spent compressing data.
conflatedEvents The number of events that were conflated, and not delivered to event listeners or gateway senders on this member. Events are typically conflated because a later event was already applied to the cache, or because a concurrent event was ignored to ensure cache consistency. Note that some members may discard an update while other members apply the update, depending on the order in which each member receives the update. For this reason, the conflatedEvents statistic will differ for each GemFire member. See How Consistency Checking Works for Replicated Regions.
creates The total number of times an entry is added to this cache.
decompressions Total number of decompression operations.
decompressTime Total time, in nanoseconds, spent decompressing data.
destroys The total number of times a cache object entry has been destroyed in this cache.
eventQueueSize The number of cache events waiting to be processed.
eventQueueThrottleCount The total number of times a thread was delayed in adding an event to the event queue.
eventQueueThrottleTime The total amount of time, in nanoseconds, spent delayed by the event queue throttle.
eventThreads The number of threads currently processing events.
getInitialImageKeysReceived Total number of keys received while doing getInitialImage operations.
getInitialImagesCompleted Total number of times getInitialImages initiated by this cache have completed.
getInitialImagesInProgressDesc Current number of getInitialImage operations currently in progress.
getInitialImageTime Total time spent doing getInitialImages for region creation.
getsDesc The total number of times a successful get has been done on this cache.
getTime Total time spent doing get operations from this cache (including netsearch and netload).
invalidates The total number of times an existing cache object entry value in this cache has been invalidated.
loadsCompleted Total number of times a load on this cache has completed as a result of either a local get() or a remote netload.
loadsInProgress Current number of threads in this cache doing a cache load.
loadTime Total time spent invoking loaders on this cache.
misses Total number of times a get on the cache did not find a value already in local memory. The number of hits (that is, gets that did not miss) can be calculated by subtracting misses from gets.
netloadsCompleted Total number of times a network load initiated on this cache has completed.
netloadsInProgress Current number of threads doing a network load initiated by a get() in this cache.
netloadTime Total time spent doing network loads on this cache.
netsearchesCompleted Total number of times network searches initiated by this cache have completed.
netsearchesInProgress Current number of threads doing a network search initiated by a get() in this cache.
netsearchTimeDesc Total time spent doing network searches for cache values.
nonReplicatedTombstonesSize The approximate number of bytes that are currently consumed by tombstones in non-replicated regions. See How Destroy and Clear Operations Are Resolved.
partitionedRegions The current number of partitioned regions in the cache.
postCompressedBytes Total number of bytes after compressing.
preCompressedBytes Total number of bytes before compressing.
putAlls The total number of times a map is added or replaced in this cache as a result of a local operation. Note, this only counts putAlls done explicitly on this cache; it does not count updates pushed from other caches.
putallTime Total time spent replacing a map in this cache as a result of a local operation. This includes synchronizing on the map, invoking cache callbacks, sending messages to other caches and waiting for responses (if required).
puts The total number of times an entry is added or replaced in this cache as a result of a local operation (put(), create(), or get() which results in load, netsearch, or netloading a value). Note, this only counts puts done explicitly on this cache; it does not count updates pushed from other caches.
putTime Total time spent adding or replacing an entry in this cache as a result of a local operation. This includes synchronizing on the map, invoking cache callbacks, sending messages to other caches, and waiting for responses (if required).
queryExecutions Total number of times some query has been executed.
queryExecutionTime Total time spent executing queries.
regions The current number of regions in the cache.
reliableQueuedOps Current number of cache operations queued for distribution to required roles.
reliableQueueMax Maximum size in megabytes allotted for disk usage to queue for distribution to required roles.
reliableQueueSize Current size in megabytes of disk used to queue for distribution to required roles.
reliableRegions Current number of regions configured for reliability.
reliableRegionsMissing Current number regions configured for reliability that are missing required roles.
reliableRegionsMissingFullAccess Current number of regions configured for reliability that are missing require roles with full access.
reliableRegionsMissingLimitedAccess Current number of regions configured for reliability that are missing required roles with limited access.
reliableRegionsMissingNoAccess Current number of regions configured for reliability that are missing required roles with no access.
reliableRegionsQueuing Current number regions configured for reliability that are queuing for required roles.
replicatedTombstonesSize The approximate number of bytes that are currently consumed by tombstones in replicated or partitioned regions. See How Destroy and Clear Operations Are Resolved.
tombstoneCount The total number of tombstone entries created for performing concurrency checks. See How Destroy and Clear Operations Are Resolved.
tombstoneGCCount The total number of tombstone garbage collection cycles that a member has performed. See How Destroy and Clear Operations Are Resolved.
txCommitChanges Total number of changes made by committed transactions.
txCommits Total number of times a transaction commit has succeeded.
txCommitTime The total amount of time, in nanoseconds, spent doing successful transaction commits.
txConflictCheckTime The total amount of time, in nanoseconds, spent doing conflict checks during transaction commit.
txFailedLifeTime The total amount of time, in nanoseconds, spent in a transaction before a failed commit. The time measured starts at transaction begin and ends when commit is called.
txFailureChanges Total number of changes lost by failed transactions.
txFailures Total number of times a transaction commit has failed.
txFailureTime The total amount of time, in nanoseconds, spent doing failed transaction commits.
txRollbackChanges Total number of changes lost by explicit transaction rollbacks.
txRollbackLifeTime The total amount of time, in nanoseconds, spent in a transaction before an explicit rollback. The time measured starts at transaction begin and ends when rollback is called.
txRollbacks Total number of times a transaction has been explicitly rolled back.
txRollbackTime The total amount of time, in nanoseconds, spent doing explicit transaction rollbacks.
txSuccessLifeTime The total amount of time, in nanoseconds, spent in a transaction before a successful commit. The time measured starts at transaction begin and ends when commit is called.
updates The total number of updates originating remotely that have been applied to this cache.
updateTime Total time spent performing an update.

Cache Server (CacheServerStats)

Statistics used for cache servers and for gateway receivers are recorded in CacheServerStats in a cache server. The primary statistics are:

Statistic Description
abandonedReadRequests Number of read operations (requests) abandoned by clients.
abandonedWriteRequests Number of write operations (requests) abandoned by clients.
acceptsInProgress Current number of server accepts that are attempting to do the initial handshake with the client.
acceptThreadStarts Total number of threads created (starts) to deal with an accepted socket. Note, this is not the current number of threads.
batchSize The size (in bytes) of the batches received.
clearRegionRequests Number of cache client operations clearRegion requests.
clearRegionResponses Number of clearRegion responses written to the cache client.
clientNotificationRequests Number of cache client operations notification requests.
clientReadyRequests Number of cache client ready requests.
clientReadyResponses Number of client ready responses written to the cache client.
closeConnectionRequests Number of cache client close connection operations requests.
connectionLoad The load from client to server connections as reported by the load probe installed in this server.
connectionsTimedOut Total number of connections that have been timed out by the server because of client inactivity.
connectionThreads Current number of threads dealing with a client connection.
connectionThreadStarts Total number of threads created (starts) to deal with a client connection. Note, this is not the current number of threads.
containsKeyRequests Number of cache client operations containsKey requests.
containsKeyResponses Number of containsKey responses written to the cache client.
currentClientConnections Number of sockets accepted.
currentClients Number of client virtual machines (clients) connected.
destroyRegionRequests Number of cache client operations destroyRegion requests.
destroyRegionResponses Number of destroyRegion responses written to the cache client.
destroyRequests Number of cache client operations destroy requests.
destroyResponses Number of destroy responses written to the cache client.
failedConnectionAttempts Number of failed connection attempts.
getRequests Number of cache client operations get requests.
getResponses Number of getResponses written to the cache client.
loadPerConnection The estimate of how much load i.s added for each new connection as reported by the load probe installed in this server.
loadPerQueue The estimate of how much load would be added for each new subscription connection as reported by the load probe installed in this server.
messageBytesBeingReceived Current number of bytes consumed by messages being received or processed.
messagesBeingReceived Current number of messages being received off the network or being processed after reception.
outOfOrderGatewayBatchIds Number of Out of Order batch IDs (batches).
processBatchRequests Number of cache client operations processBatch requests.
processBatchResponses Number of processBatch responses written to the cache client.
processBatchTime Total time, in nanoseconds, spent in processing a cache client processBatch request.
processClearRegionTime Total time, in nanoseconds, spent in processing a cache client clearRegion request, including the time to clear the region from the cache.
processClientNotificationTime Total time, in nanoseconds, spent in processing a cache client notification request.
processClientReadyTime Total time, in nanoseconds, spent in processing a cache client ready request, including the time to destroy an object from the cache.
processCloseConnectionTime Total time, in nanoseconds, spent in processing a cache client close connection request.
processContainsKeyTime Total time spent, in nanoseconds, processing a containsKey request.
processDestroyRegionTime Total time, in nanoseconds, spent in processing a cache client destroyRegion request, including the time to destroy the region from the cache.
processDestroyTime Total time, in nanoseconds, spent in processing a cache client destroy request, including the time to destroy an object from the cache.
processGetTime Total time, in nanoseconds, spent in processing a cache client get request, including the time to get an object from the cache.
processPutAllTime Total time, in nanoseconds, spent in processing a cache client putAll request, including the time to put all objects into the cache.
processPutTime Total time, in nanoseconds, spent in processing a cache client put request, including the time to put an object into the cache.
processQueryTime Total time, in nanoseconds, spent in processing a cache client query request, including the time to destroy an object from the cache.
processUpdateClientNotificationTime Total time, in nanoseconds, spent in processing a client notification update request.
putAllRequests Number of cache client operations putAll requests.
putAllResponses Number of putAllResponses written to the cache client.
putRequests Number of cache client operations put requests.
putResponses Number of putResponses written to the cache client.
queryRequests Number of cache client operations query requests.
queryResponses Number of query responses written to the cache client.
queueLoad The load from subscription queues as reported by the load probe installed in this server
readClearRegionRequestTime Total time, in nanoseconds, spent in reading clearRegion requests.
readClientNotificationRequestTime Total time, in nanoseconds, spent in reading client notification requests.
readClientReadyRequestTime Total time, in nanoseconds, spent in reading cache client ready requests.
readCloseConnectionRequestTime Total time, in nanoseconds, spent in reading close connection requests.
readContainsKeyRequestTime Total time, in nanoseconds, spent reading containsKey requests.
readDestroyRegionRequestTime Total time, in nanoseconds, spent in reading destroyRegion requests.
readDestroyRequestTime Total time, in nanoseconds, spent in reading destroy requests.
readGetRequestTime Total time, in nanoseconds, spent in reading get requests.
readProcessBatchRequestTime Total time, in nanoseconds, spent in reading processBatch requests.
readPutAllRequestTime Total time, in nanoseconds, spent in reading putAll requests.
readPutRequestTime Total time, in nanoseconds, spent in reading put requests.
readQueryRequestTime Total time, in nanoseconds, spent in reading query requests.
readUpdateClientNotificationRequestTime Total time, in nanoseconds, spent in reading client notification update requests.
receivedBytes Total number of bytes received from clients.
sentBytes Total number of bytes sent to clients.
threadQueueSize Current number of connections waiting for a thread to start processing their message.
updateClientNotificationRequests Number of cache client notification update requests.
writeClearRegionResponseTime Total time, in nanoseconds, spent in writing clearRegion responses.
writeClientReadyResponseTime Total time, in nanoseconds, spent in writing client ready responses.
writeContainsKeyResponseTime Total time, in nanoseconds, spent writing containsKey responses.
writeDestroyRegionResponseTime Total time, in nanoseconds, spent in writing destroyRegion responses.
writeDestroyResponseTime Total time, in nanoseconds, spent in writing destroy responses.
writeGetResponseTime Total time, in nanoseconds, spent in writing get responses.
writeProcessBatchResponseTime Total time, in nanoseconds, spent in writing processBatch responses.
writePutAllResponseTime Total time, in nanoseconds, spent in writing putAll responses.
writePutResponseTime Total time, in nanoseconds, spent in writing put responses.
writeQueryResponseTime Total time, in nanoseconds, spent in writing query responses.

Client-Side Notifications (CacheClientUpdaterStats)

Statistics in a client that pertain to server-to-client data pushed from the server over a queue to the client (they are the client side of the server’s CacheClientNotifierStatistics) :

Statistic Description
receivedBytes Total number of bytes received from the server.
messagesBeingReceived Current number of message being received off the network or being processed after reception.
messageBytesBeingReceived Current number of bytes consumed by messages being received or processed.

Client-to-Server Messaging Performance (ClientStats)

These statistics are in a client and they describe all the messages sent from the client to a specific server. The primary statistics are:

Statistic Description
clearFailures Total number of clear attempts that have failed.
clears Total number of clears completed successfully.
clearSendFailures Total number of clearSends that have failed.
clearSends Total number of clearSends that have completed successfully.
clearSendsInProgress Current number of clearSends being executed.
clearSendTime Total amount of time, in nanoseconds, spent doing clearSends.
clearsInProgress Current number of clears being executed.
clearTime Total amount of time, in nanoseconds, spent doing clears.
clearTimeouts Total number of clear attempts that have timed out.
closeConFailures Total number of closeCon attempts that have failed.
closeCons Total number of closeCons that have completed successfully.
closeConSendFailures Total number of closeConSends that have failed.
closeConSends Total number of closeConSends that have completed successfully.
closeConSendsInProgress Current number of closeConSends being executed.
closeConSendTime Total amount of time, in nanoseconds, spent doing closeConSends.
closeConsInProgress Current number of closeCons being executed.
closeConTime Total amount of time, in nanoseconds, spent doing closeCons.
closeConTimeouts Total number of closeCon attempts that have timed out.
connections Current number of connections.
connects Total number of times a connection has been created.
containsKeyFailures Total number of containsKey attempts that have failed.
containsKeys Total number of containsKeys that completed successfully.
containsKeySendFailures Total number of containsKeySends that have failed.
containsKeySends Total number of containsKeySends that have completed successfully.
containsKeySendsInProgress Current number of containsKeySends being executed.
containsKeySendTime Total amount of time, in nanoseconds, spent doing containsKeyends.
containsKeysInProgress Current number of containsKeys being executed.
containsKeyTime Total amount of time, in nanoseconds, spent doing containsKeys.
containsKeyTimeouts Total number of containsKey attempts that have timed out.
destroyFailures Total number of destroy attempts that have failed.
destroyRegionFailures Total number of destroyRegion attempts that have failed.
destroyRegions Total number of destroyRegions that have completed successfully.
destroyRegionSendFailures Total number of destroyRegionSends that have failed.
destroyRegionSends Total number of destroyRegionSends that have completed successfully.
destroyRegionSendsInProgress Current number of destroyRegionSends being executed.
destroyRegionSendTime Total amount of time, in nanoseconds, spent doing destroyRegionSends.
destroyRegionsInProgress Current number of destroyRegions being executed.
destroyRegionTime Total amount of time, in nanoseconds, spent doing destroyRegions.
destroyRegionTimeouts Total number of destroyRegion attempts that have timed out.
destroys Total number of destroys that have completed successfully.
destroySendFailures Total number of destroySends that have failed.
destroySends Total number of destroySends that have completed successfully.
destroySendsInProgress Current number of destroySends being executed.
destroySendTime Total amount of time, in nanoseconds, spent doing destroySends.
destroysInProgress Current number of destroys being executed.
destroyTime Total amount of time, in nanoseconds, spent doing destroys.
destroyTimeouts Total number of destroy attempts that have timed out.
disconnects Total number of times a connection has been destroyed.
gatewayBatchFailures Total number of gatewayBatch attempts that have failed.
gatewayBatchs Total number of gatewayBatchs completed successfully.
gatewayBatchSendFailures Total number of gatewayBatchSends that have failed.
gatewayBatchSends Total number of gatewayBatchSends that have completed successfully.
gatewayBatchSendsInProgress Current number of gatewayBatchSends being executed.
gatewayBatchSendTime Total amount of time, in nanoseconds, spent doing gatewayBatchSends.
gatewayBatchsInProgress Current number of gatewayBatchs being executed.
gatewayBatchTime Total amount of time, in nanoseconds, spent doing gatewayBatchs.
gatewayBatchTimeouts Total number of gatewayBatch attempts that have timed out.
getAllFailures Total number of getAll attempts that have failed.
getAlls Total number of getAlls that have completed successfully.
getAllSendFailures Total number of getAllSends that have failed.
getAllSends Total number of getAllSends that have completed successfully.
getAllSendsInProgress Current number of getAllSends being executed.
getAllSendTime Total amount of time, in nanoseconds, spent doing getAllSends.
getAllsInProgress Current number of getAlls being executed.
getAllTime Total amount of time, in nanoseconds, spent doing getAlls.
getAllTimeouts Total number of getAll attempts that have timed out.
getFailures Total number of get attempts that have failed.
gets Total number of gets that have completed successfully.
getSendFailures Total number of getSends that have failed.
getSends Total number of getSends that have completed successfully.
getSendsInProgress Current number of getSends being executed.
getSendTime Total amount of time, in nanoseconds, spent doing getSends.
getsInProgress Current number of gets being executed.
getTime Total amount of time, in nanoseconds, spent doing gets.
getTimeouts Total number of get attempts that have timed out.
keySetFailures Total number of keySet attempts that have failed.
keySets Total number of keySets that have completed successfully.
keySetSendFailures Total number of keySetSends that have failed.
keySetSends Total number of keySetSends that have completed successfully.
keySetSendsInProgress Current number of keySetSends being executed.
keySetSendTime Total amount of time, in nanoseconds, spent doing keySetSends.
keySetsInProgress Current number of keySets being executed.
keySetTime Total amount of time, in nanoseconds, spent doing keySets.
keySetTimeouts Total number of keySet attempts that have timed out.
makePrimaryFailures Total number of makePrimary attempts that have failed.
makePrimarys Total number of makePrimarys that have completed successfully.
makePrimarySendFailures Total number of makePrimarySends that have failed.
makePrimarySends Total number of makePrimarySends that have completed successfully.
makePrimarySendsInProgress Current number of makePrimarySends being executed.
makePrimarySendTime Total amount of time, in nanoseconds, spent doing makePrimarySends.
makePrimarysInProgress Current number of makePrimarys being executed.
makePrimaryTime Total amount of time, in nanoseconds, spent doing makePrimarys.
makePrimaryTimeouts Total number of makePrimary attempts that have timed out.
messageBytesBeingReceived Current number of bytes consumed by messages being received or processed.
messagesBeingReceived Current number of messages being received off the network or being processed after reception.
opFailures Total number of op attempts that have failed.
ops Total number of ops that have completed successfully.
opSendFailures Total number of opSends that have failed.
opSends Total number of opSends that have completed successfully.
opSendsInProgress Current number of opSends being executed.
opSendTime Total amount of time, in nanoseconds, spent doing opSends.
opsInProgress Current number of ops being executed.
opTime Total amount of time, in nanoseconds, spent doing ops.
opTimeouts Total number of op attempts that have timed out.
pingFailures Total number of ping attempts that have failed.
pings Total number of pings that have completed successfully.
pingSendFailures Total number of pingSends that have failed.
pingSends Total number of pingSends that have completed successfully.
pingSendsInProgress Current number of pingSends being executed.
pingSendTime Total amount of time, in nanoseconds, spent doing pingSends.
pingsInProgress Current number of pings being executed.
pingTime Total amount of time, in nanoseconds, spent doing pings.
pingTimeouts Total number of ping attempts that have timed out.
primaryAckFailures Total number of primaryAck attempts that have failed.
primaryAcks Total number of primaryAcks that have completed successfully.
primaryAckSendFailures Total number of primaryAckSends that have failed.
primaryAckSends Total number of primaryAckSends that have completed successfully.
primaryAckSendTime Total amount of time, in nanoseconds, spent doing primaryAckSends.
primaryAcksInProgress Current number of primaryAcks being executed.
primaryAckTime Total amount of time, in nanoseconds, spent doing primaryAcks.
primaryAckTimeouts Total number of primaryAck attempts that have timed out.
putAllFailures Total number of putAll attempts that have failed.
putAlls Total number of putAlls that have completed successfully.
putAllSendFailures Total number of putAllSends that have failed.
putAllSends Total number of putAllSends that have completed successfully.
putAllSendsInProgress Current number of putAllSends being executed.
putAllSendTime Total amount of time, in nanoseconds, spent doing putAllSends.
putAllsInProgress Current number of putAlls being executed.
putAllTime Total amount of time, in nanoseconds, spent doing putAlls.
putAllTimeouts Total number of putAll attempts that have timed out.
putFailures Total number of put attempts that have failed.
puts Total number of puts that have completed successfully.
putSendFailures Total number of putSends that have failed.
putSends Total number of putSends that have completed successfully.
putSendsInProgress Current number of putSends being executed.
putSendTime Total amount of time, in nanoseconds, spent doing putSends.
putsInProgress Current number of puts being executed.
putTime Total amount of time, in nanoseconds, spent doing puts.
putTimeouts Total number of put attempts that have timed out.
queryFailures Total number of query attempts that have failed.
querys Total number of querys completed successfully.
querySendFailures Total number of querySends that have failed.
querySends Total number of querySends that have completed successfully.
querySendsInProgress Current number of querySends being executed.
querySendTime Total amount of time, in nanoseconds, spent doing querySends.
querysInProgress Current number of querys being executed.
queryTime Total amount of time, in nanoseconds. spent doing querys.
queryTimeouts Total number of query attempts that have timed out.
readyForEvents Total number of readyForEventss that have completed successfully.
readyForEventsFailures Total number of readyForEvents attempts that have failed.
readyForEventsInProgress Current number of readyForEventss being executed
readyForEventsSendFailures Total number of readyForEventsSends that have failed.
readyForEventsSends Total number of readyForEventsSends that have completed successfully.
readyForEventsSendsInProgress Current number of readyForEventsSends being executed.
readyForEventsSendTime Total amount of time, in nanoseconds, spent doing readyForEventsSends.
readyForEventsTime Total amount of time, in nanoseconds, spent doing readyForEvents.
readyForEventsTimeouts Total number of readyForEvents attempts that have timed out.
receivedBytes Total number of bytes received from the server.
registerInstantiators Total number of registerInstantiators completed successfully
registerInstantiatorsFailures Total number of registerInstantiators attempts that have failed.
registerInstantiatorsSendFailures Total number of registerInstantiators sends that have failed
registerInstantiatorsSends Total number of registerInstantiators sends that have completed successfully
registerInstantiatorsSendsInProgress Current number of registerInstantiators sends being executed
registerInstantiatorsSendTime Total amount of time, in nanoseconds, spent doing registerInstantiatorsSends.
registerInstantiatorssInProgress Current number of registerInstantiators being executed
registerInstantiatorsTime Total amount of time, in nanoseconds, spent doing registerInstantiators.
registerInstantiatorsTimeouts Total number of registerInstantiators attempts that have timed out.
registerInterestFailures Total number of registerInterest attempts that have failed.
registerInterests Total number of registerInterests that have completed successfully.
registerInterestSendFailures Total number of registerInterestSends that have failed.
registerInterestSends Total number of registerInterestSends that have completed successfully.
registerInterestSendsInProgress Current number of registerInterestSends being executed.
registerInterestSendTime Total amount of time, in nanoseconds, spent doing registerInterestSends.
registerInterestsInProgress Current number of registerInterests being executed.
registerInterestTime Total amount of time, in nanoseconds, spent doing registerInterests.
registerInterestTimeouts Total number of registerInterest attempts that have timed out.
sentBytes Total number of bytes sent to the server.
unregisterInterestFailures Total number of unregisterInterest attempts that have failed.
unregisterInterests Total number of unregisterInterests that have completed successfully
unregisterInterestSendFailures Total number of unregisterInterestSends that have failed.
unregisterInterestSends Total number of unregisterInterestSends that have completed successfully.
unregisterInterestSendsInProgress Current number of unregisterInterestSends being executed.
unregisterInterestSendTime Total amount of time, in nanoseconds, spent doing unregisterInterestSends.
unregisterInterestsInProgress Current number of unregisterInterests being executed.
unregisterInterestTime Total amount of time, in nanoseconds, spent doing unregisterInterests.
unregisterInterestTimeouts Total number of unregisterInterest attempts that have timed out.

Client Connection Pool (PoolStats)

These statistics are in a client and they describe one of the client’s connection pools. The primary statistics are:

Statistic Description
connections Current number of connections.
connectionWaits Total number of times a thread completed waiting for a connection (either by timing out or by getting a connection).
connectionWaitsInProgress Current number of threads waiting for a connection.
connectionWaitTime Total time, in nanoseconds, spent waiting for a connection.
connects Total number of times a connection has been created.
disconnects Total number of times a connection has been destroyed.
ENDPOINTS_KNOWN Current number of servers discovered.
idleChecks Total number of checks done for idle expiration.
idleDisconnects Total number of disconnects done due to idle expiration.
INITIAL_CONTACTS Number of contacts initially made the user.
KNOWN_LOCATORS Current number of locators discovered.
lifetimeChecks Total number of checks done for lifetime expiration.
lifetimeConnects Total number of connects done due to lifetime expiration.
lifetimeDisconnects Total number of disconnects done due to lifetime expiration.
lifetimeExtensions Total number of times a connection's lifetime has been extended because the servers are still balanced.
minPoolSizeConnects Total number of connects done to maintain minimum pool size.
QUEUE_SERVERS Number of servers hosting this client.s subscription queue.
REQUESTS_TO_LOCATOR Number of requests from this connection pool to a locator.
RESPONSES_FROM_LOCATOR Number of responses from the locator to this connection pool.

Delta Propagation (DeltaPropagationStatistics)

These statistics are for delta propagation between members. The primary statistics are:

Statistic Description
deltaFullValuePuts Total number of full value puts processed successfully in response to failed delta puts.
deltaFullValueRequests Number of full value requests received from a client after failing to apply delta and processed successfully by this server.
deltaMessageFailures The number of distribution messages containing delta that could not be processed at receiving side.
deltaMessageFailures Current number of delta messages received but could not be processed after reception.
deltaPutFailures Number of failures encountered while processing delta received from a client on this server.
deltaPuts Total number of puts containing delta.
deltaPutsTime Total amount of time, in nanoseconds, spent constructing delta part of puts.
fullDeltaMessages Current number of full value delta messages received off network and processed after reception.
fullDeltaRequests Number of full value requests made by this server to the sender client after failing to apply delta.
fullValueDeltaMessagesRequested The number of distribution messages containing full value requested by this GemFire system after failing to apply received delta.
fullValueDeltaMessagesSent The number of distribution messages sent in response to full value requests by a remote GemFire System as a result of failure in applying delta.
partitionMessagesWithDeltaFailures Number of failures while processing PartitionMessages containing delta.
partitionMessagesWithDeltaProcessed Number of PartitionMessages containing delta processed.
partitionMessagesWithDeltaProcessedTime Total time spent applying deltas.
partitionMessagesWithDeltaSent Number of PartitionMessages containing delta sent.
partitionMessagesWithDeltaSentTime Total time spent extractng deltas.
partitionMessagesWithFullValueDeltaRequested Number of requests for PartitionMessages containing full delta value as a result of failure in applying delta.
partitionMessagesWithFullValueDeltaSent Number of PartitionMessages containing full delta value sent.
preparedDeltaMessages The number of distribution messages containing delta that this GemFire system has prepared for distribution.
preparedDeltaMessages Number of client messages being prepared for dispatch, which have delta part in them.
preparedDeltaMessagesTime The total amount of time this distribution manager has spent preparing delta parts of messages.
processedDeltaMessages The number of distribution messages containing delta that this GemFire system has processed.
processedDeltaMessages Current number of delta messages received off network and processed after reception.
processedDeltaMessagesTime The amount of time this distribution manager has spent in applying delta on its existing value.
processedDeltaMessagesTime Total time spent applying received delta parts on existing messages at clients.
processedDeltaPuts Number of cache client put requests containing delta received from a client and processed successfuly.
processedDeltaPutsTime Total time spent in applying delta received from a client on existing value in this server's region.

Disk Space Usage (DiskDirStatistics)

These statistics pertain to the disk usage for a region’s disk directory. The primary statistics are:

Statistic Description
diskSpace The total number of bytes currently being used on disk in this directory for oplog files.
maximumSpace The configured maximum number of bytes allowed in this directory for oplog files. Note that some product configurations allow this maximum to be exceeded.
volumeFreeSpace The total free space in bytes on the disk volume.
volumeFreeSpaceChecks The total number of disk space checks.
volumeFreeSpaceTime The total time, in nanseconds, spent checking disk usage.
volumeSize The total size in bytes of the disk volume.

Disk Usage and Performance (DiskRegionStatistics)

Statistics regarding operations performed on a disk region for persistence/overflow. The primary statistics are:

Statistic Description
bufferSize Current number of bytes buffered to be written to the disk.
commits Total number of commits.
commitTime Total amount of time, in nanoseconds, spent doing commits.
entriesInVM Current number of entries whose value resides in the member. The value may also have been written to the disk.
entriesOnDisk Current number of entries whose value is on the disk and is not in memory. This is true of overflowed entries. It is also true of recovered entries that have not yet been faulted in.
flushedBytes Total number of bytes flushed out of the async write buffer to the disk.
flushes Total number of times the async write buffer has been flushed.
flushTime Total amount of time, in nanoseconds, spent doing a buffer flush.
readBytes Total number of bytes that have been read from the disk.
reads Total number of region entries that have been read from the disk.
readTime Total amount of time, in nanoseconds, spent reading from the disk.
recoveredBytes Total number of bytes that have been read from disk during a recovery.
recoveryTime Total amount of time, in nanoseconds, spent doing a recovery.
removes Total number of region entries that have been removed from the disk.
removeTime Total amount of time, in nanoseconds, spent removing from the disk.
writes Total number of region entries that have been written to disk. A write is done every time an entry is created on disk or every time its value is modified on the disk.
writeTime Total amount of time, in nanoseconds, spent writing to the disk.
writtenBytes Total number of bytes that have been written to the disk.

Distributed System Messaging (DistributionStats)

Statistics on the GemFire distribution layer. These statistcs can be used to tell how much message traffic exists between this member and other distributed system members.

The primary statistics are:
Statistic Description
asyncConflatedMsgsDesc The total number of queued conflated messages used for asynchronous queues.
asyncDequeuedMsgsDesc The total number of queued messages that have been removed from the queue and successfully sent.
asyncDistributionTimeoutExceededDesc Total number of times the async-distribution-timeout has been exceeded during a socket write.
asyncQueueAddTime Total amount of time, in nanoseconds, spent in adding messages to async queue.
asyncQueuedMsgsDesc The total number of queued messages used for asynchronous queues.
asyncQueueFlushesCompletedDesc Total number of asynchronous queue flushes completed.
asyncQueueFlushesInProgressDesc Current number of asynchronous queues being flushed.
asyncQueueFlushTimeDesc Total time spent flushing asynchronous queues.
asyncQueueRemoveTime Total amount of time, in nanoseconds, spent in removing messages from async queue.
asyncQueuesDesc Current number of queues for asynchronous messaging.
asyncQueueSizeDesc Current size in bytes used for asynchronous queues.
asyncQueueSizeExceededDesc Total number of asynchronous queues that have exceeded the maximum size.
asyncQueueTimeoutExceededDesc Total number of asynchronous queues that have timed out by being blocked for more than async-queue-timeout milliseconds.
asyncSocketWriteBytes Total number of bytes sent out on non-blocking sockets.
asyncSocketWriteRetries Total number of retries needed to write a single block of data using non-blocking socket write calls.
asyncSocketWrites Total number of non-blocking socket write calls completed.
asyncSocketWritesInProgress Current number of non-blocking socket write calls in progress.
asyncSocketWriteTime Total amount of time, in nanoseconds, spent in non-blocking socket write calls.
asyncThreadCompletedDesc Total number of iterations of work performed by asynchronous message queue threads.
asyncThreadInProgressDesc Current iterations of work performed by asynchronous message queue threads.
asyncThreadsDesc Total number of asynchronous message queue threads.
asyncThreadTimeDesc Total time spent by asynchronous message queue threads performing iterations.
batchCopyTime Total amount of time, in nanoseconds, spent copying messages for batched transmission.
batchFlushTime Total amount of time, in nanoseconds, spent flushing batched messages to the network.
batchSendTime Total amount of time, in nanoseconds, spent queueing and flushing message batches.
batchWaitTime Reserved for future use
broadcastMessagesDesc The number of distribution messages that the GemFire system has broadcast. A broadcast message is one sent to every other manager in the group.
broadcastMessagesTimeDesc The total amount of time this distribution manager has spent broadcasting messages. A broadcast message is one sent to every other manager in the group.
bufferAcquires Total number of times a buffer has been acquired.
bufferAcquiresInProgress Current number of threads waiting to acquire a buffer.
bufferAcquireTime Total amount of time, in nanoseconds, spent acquiring a socket.
commitWaitsDesc The number of transaction commits that had to wait for a response before they could complete.
deserializations Total number of object deserialization calls.
deserializationTime Total amount of time, in nanoseconds, spent deserializing objects.
deserializedBytes Total number of bytes consumed by object deserialization.
failedAcceptsDesc Total number of times an accept (receiver creation) of a connect from some other member has failed.
failedConnectsDesc Total number of times a connect (sender creation) to some other member has failed.
final String distributeMessageTimeDesc = The amount of time it takes to prepare a message and send it on the network. This includes sentMessagesTime.
flowControlRequests Total number of flow control credit requests sent to other processes.
flowControlResponses Total number of flow control credit responses sent to a requestor.
flowControlThrottleWaitsInProgress Number of threads blocked waiting due to flow-control throttle requests from other members.
flowControlWaitsInProgress Number of threads blocked waiting for flow-control recharges from other processes.
flowControlWaitTime Total amount of time, in nanoseconds, spent waiting for other processes to recharge the flow of the control meter.
highPriorityQueueSizeDesc The number of high priority distribution messages currently waiting to be processed.
highPriorityQueueThrottleCounDesc The total number of times a thread was delayed in adding a normal message to the high priority queue.
highPriorityQueueThrottleTimeDesc The total amount of time, in nanoseconds, spent delayed by the high priority queue throttle.
highPriorityThreadJobsDesc The number of messages currently being processed by high priority processor threads.
highPriorityThreadsDesc The number of threads currently processing high priority messages.
highPriorityThreadStarts Total number of times a thread has been created for the pool handling high priority messages.
jChannelUpTime Up Time spent in JChannel including jgroup stack.
jgDirAckdownTime Time, in nanoseconds, spent in JGroups DirAck processing down events.
jgDirAcksReceived Number of DirAck acks received.
jgDirAckupTime Time, in nanoseconds, spent in JGroups DirAck processing up events.
jgDISCOVERYdownTime Time, in nanoseconds, spent in JGroups DISCOVERY processing down events.
jgDISCOVERYupTime Time, in nanoseconds, spent in JGroups DISCOVERY processing up events.
jgDownTime Down Time spent in JGroups stacks.
jgFCautoRequests Number of times JGroups FC automatically sent replenishment requests.
jgFCdownTime Time, in nanoseconds, spent in JGroups FC processing down events.
jgFCreplenish Number of times JGroups FC received replenishments messages from receivers.
jgFCresumes Number of times JGroups FC resumed sends events due to backpressure.
jgFCsendBlocks Number of times JGroups FC halted send events due to backpressure.
jgFCsentCredits Number of times JGroups FC sent credits events to a sender.
jgFCsentThrottleRequests Number of times JGroups FC sent throttle events requests to a sender.
jgFCupTime Time, in nanoseconds, spent in JGroups FC processing up events.
jgFDdownTime Time, in nanoseconds, spent in JGroups FD processing down events.
jgFDupTime Time, in nanoseconds, spent in JGroups FD processing up events.
jgFRAG2downTime Time, in nanoseconds, spent in JGroups FRAG2 processing down events.
jgFRAG2upTime Time, in nanoseconds, spent in JGroups FRAG2 processing up events.
jgFragmentationsPerformed Number of message fragmentation operations performed.
jgFragmentsCreated Number of message fragments created.
jgGMSdownTime Time, in nanoseconds, spent in JGroups GMS processing down events.
jgGMSupTime Time, in nanoseconds, spent in JGroups GMS processing up events.
jgNAKACKdownTime Time, in nanoseconds, spent in JGroups NAKACK processing down events.
jgNAKACKreceivedMessages Number of received messages awaiting stability in NAKACK.
jgNAKACKsentMessages Number of sent messages awaiting stability in NAKACK.
jgNAKACKupTime Time, in nanoseconds, spent in JGroups NAKACK processing up events.
jgSTABILITYmessages Number of STABILITY messages received by JGroups.
jgSTABLEdownTime Time, in nanoseconds, spent in JGroups STABLE processing down events.
jgSTABLEmessages Number of STABLE messages received by JGroups.
jgSTABLEmessagesSent Number of STABLE messages sent by JGroups.
jgSTABLEsuspendTime Amount of time JGroups STABLE is suspended.
jgSTABLEupTime Time, in nanoseconds, spent in JGroups STABLE processing up events.
jgTCPGOSSIPdownTime Time, in nanoseconds, spent in JGroups TCPGOSSIP processing down events.
jgTCPGOSSIPupTime Time, in nanoseconds, spent in JGroups TCPGOSSIP processing up events.
jgUDPdownTime Time, in nanoseconds, spent in JGroups UDP processing down events.
jgUDPupTime Time, in nanosecnds, spent in JGroups UDP processing up events.
jgUNICASTdataReceivedTime Amount of time spent in JGroups UNICAST send.
jgUNICASTdownTime Time, in nanoseconds, spent in JGroups UNICAST processing down events.
jgUNICASTreceivedMessages Number of received messages awaiting receipt of prior messages.
jgUNICASTsentHighPriorityMessages Number of un-acked high priority messages
jgUNICASTsentMessages Number of un-acked normal priority messages.
jgUNICASTupTime Time, in nanoseconds, spent in JGroups UNICAST processing up events.
jgUpTime Up Time spent in JGroups stacks.
jgVIEWSYNCdownTime Time, in nanoseconds, spent in JGroups VIEWSYNC processing down events.
jgVIEWSYNCupTime Time, in nanoseconds, spent in JGroups VIEWSYNC processing up events.
lostConnectionLeaseDesc Total number of times an unshared sender socket has remained idle long enough that its lease expired.
mcastReadBytes Total number of bytes received in multicast datagrams.
mcastReads Total number of multicast datagrams received.
mcastRetransmitRequests Total number of multicast datagram socket retransmission requests sent to other processes.
mcastRetransmits Total number of multicast datagram socket retransmissions.
mcastWriteBytes Total number of bytes sent out on multicast datagram sockets.
mcastWrites Total number of multicast datagram socket write calls.
mcastWriteTime Total amount of time, in nanoseconds, spent in multicast datagram socket write calls.
messageBytesBeingReceived Current number of bytes consumed by messages being received or processed.
messageChannelTimeDesc The total amount of time received messages spent in the distribution channel.
messageProcessingScheduleTimeDesc The amount of time this distribution manager has spent dispatching a message to processor threads.
messagesBeingReceived Current number of messages being received off the network or being processed after reception.
msgDeserializationTime Total amount of time, in nanoseconds, spent deserializing messages.
msgSerializationTime Total amount of time, in nanoseconds, spent serializing messages.
nodesDesc The current number of members in this distributed system.
overflowQueueSizeDesc The number of normal distribution messages currently waiting to be processed.
overflowQueueThrottleCountDesc The total number of times a thread was delayed in adding a normal message to the overflow queue.
overflowQueueThrottleTimeDesc The total amount of time, in nanoseconds, spent delayed by the overflow queue throttle.
partitionedRegionThreadJobsDesc The number of messages currently being processed by partitioned region threads.
partitionedRegionThreadsDesc The number of threads currently processing partitioned region messages.
partitionedRegionThreadStarts Total number of times a thread has been created for the pool handling partitioned region messages.
pdxDeserializations Total number of PDX deserializations.
pdxDeserializedBytes Total number of bytes read by PDX deserialization.
pdxInstanceCreations Total number of times a PdxInstance has been created by deserialization.
pdxInstanceDeserializations Total number of times getObject has been called on a PdxInstance.
pdxInstanceDeserializationTime Total amount of time, in nanoseconds, spent deserializing PdxInstances by calling getObject.
pdxSerializations Total number of PDX serializations.
pdxSerializedBytes Total number of bytes produced by PDX serialization.
processedMessagesDesc The number of distribution messages that the GemFire system has processed.
processedMessagesTimeDesc The amount of time this distribution manager has spent in message.process().
processingThreadJobsDesc The number of messages currently being processed by pooled message processor threads.
processingThreadsDesc The number of threads currently processing normal messages.
processingThreadStarts Total number of times a thread has been created for the pool processing normal messages.
receivedBytesDesc The number of distribution message bytes that the GemFire system has received.
receivedMessagesDesc The number of distribution messages that the GemFire system has received.
receiverConnectionsDesc Current number of sockets dedicated to receiving messages.
receiverDirectBufferSizeDesc Current number of bytes allocated from direct memory as buffers for incoming messages.
receiverHeapBufferSizeDesc Current number of bytes allocated from Java heap memory as buffers for incoming messages.S
reconnectAttemptsDesc Total number of times an established connection was lost and a reconnect was attempted.
replyHandoffTimeDesc Total number of seconds to switch thread contexts from processing thread to application thread.
replyMessageTimeDesc The amount of time spent processing reply messages;
replyTimeoutsDesc Total number of message replies that have timed out.
replyWaitMaxTimeDesc Maximum time spent transmitting and then waiting for a reply to a message. See sentMessagesMaxTime for related information.
replyWaitsCompletedDesc Total number of times waits for a reply have completed.
replyWaitsInProgressDesc Current number of threads waiting for a reply.
replyWaitTimeDesc Total time spent waiting for a reply to a message.
senderDirectBufferSizeDesc Current number of bytes allocated from direct memory as buffers for outgoing messages.
senderHeapBufferSizeDesc Current number of bytes allocated from Java heap memory as buffers for outgoing messages.
sentBytesDesc The number of distribution message bytes that the GemFire system has sent.
sentCommitMessagesDesc The number of transaction commit messages that the GemFire system has created to be sent. Note, it is possible for a commit to only create one message even though it will end up being sent to multiple recipients.
sentMessagesDesc The number of distribution messages that the GemFire system has sent, which includes broadcastMessages.
sentMessagesMaxTimeDesc The highest amount of time this distribution manager has spent distributing a single message to the network.
sentMessagesTimeDesc The total amount of time this distribution manager has spent sending messages, which includes broadcastMessagesTime.
serializations Total number of object serialization calls.
serializationTime Total amount of time, in nanoseconds, spent serializing objects.
serializedBytes Total number of bytes produced by object serialization.
serialPooledThreadDesc The number of threads created in the SerialQueuedExecutorPool.
serialPooledThreadJobsDesc The number of messages currently being processed by pooled serial processor threads.
serialPooledThreadStarts Total number of times a thread has been created for the serial pool(s).
serialQueueBytesDesc The approximate number of bytes consumed by serial distribution messages currently waiting to be processed.
serialQueueSizeDesc The number of serial distribution messages currently waiting to be processed.
serialQueueThrottleCountDesc The total number of times a thread was delayed in adding a ordered message to the serial queue.
serialQueueThrottleTimeDesc The total amount of time, in nanoseconds, spent delayed by the serial queue throttle.
serialThreadJobsDesc The number of messages currently being processed by serial threads.
serialThreadsDesc The number of threads currently processing serial/ordered messages.
serialThreadStarts Total number of times a thread has been created for the serial message executor.
sharedOrderedSenderConnectionsDesc Current number of shared sockets dedicated to sending ordered messages.
sharedUnorderedSenderConnectionsDesc Current number of shared sockets dedicated to sending unordered messages.
socketLocks Total number of times a socket has been locked.
socketLockTime Total amount of time, in nanoseconds, spent locking a socket.
syncSocketWriteBytes Total number of bytes sent out in synchronous/blocking mode on sockets.
syncSocketWrites Total number of completed synchronous/blocking socket write calls.
syncSocketWritesInProgress Current number of synchronous/blocking socket write calls in progress.
syncSocketWriteTime Total amount of time, in nanoseconds, spent in synchronous/blocking socket write calls.
threadOrderedSenderConnectionsDesc Current number of thread sockets dedicated to sending ordered messages.
threadUnorderedSenderConnectionsDesc Current number of thread sockets dedicated to sending unordered messages.
TOSentMsgs Total number of messages sent on thread owned senders.
ucastFlushes Total number of flushes of the unicast datagram protocol, prior to sending a multicast message.
ucastFlushTime Total amount of time, in nanoseconds, spent waiting for acknowledgements for outstanding unicast datagram messages.
ucastReadBytes Total number of bytes received in unicast datagrams.
ucastReads Total number of unicast datagrams received.
ucastRetransmits Total number of unicast datagram socket retransmissions.
ucastWriteBytes Total number of bytes sent out on unicast datagram sockets.
ucastWrites Total number of unicast datagram socket write calls.
ucastWriteTime Total amount of time, in nanoseconds, spent in unicast datagram socket write calls.
viewThreadJobsDesc The number of messages currently being processed by view threads.
viewThreadsDesc The number of threads currently processing view messages.
viewThreadStarts Total number of times a thread has been created for the view message executor.
waitingQueueSizeDesc The number of distribution messages currently waiting for some other resource before they can be processed.
waitingThreadJobsDesc The number of messages currently being processed by waiting pooly processor threads.
waitingThreadsDesc The number of threads currently processing messages that had to wait for a resource.
waitingThreadStarts Total number of times a thread has been created for the waiting pool.

Distribution Statistics Related to Slow Receivers

The distribution statistics provide statistics pertaining to slow receivers. The primary statistics are:

Statistic Description
asyncDistributionTimeoutExceeded Incremented every time an asyncSocketWrite has exceeded async-distribution-timeout and an async queue has been created.
asyncQueue* Provide information about queues the producer is managing for its consumers. There are no statistics maintained for individual consumers. The following are the primary statistics of this type.
asyncQueues Indicates the number of queues currently in the producer.
asyncQueueSizeExceeded Incremented every time a queue has exceeded async-max-queue-size and the receiver has been sent a disconnect message.
asyncQueueTimeoutExceeded Incremented every time a queue flushing has exceeded async-queue-timeout and the receiver has been sent a disconnect message.
asyncSocketWrite* Used anytime a producer is distributing to one or more consumers with a non-zero distribution timeout. These statistics also reflect the writes done by the threads that service asynchronous queues.

Distributed Lock Services (DLockStats)

These statistics are for distributed lock services. The primary statistics are:

Statistic Description
becomeGrantorRequestsDesc Total number of times this member has explicitly requested to become lock grantor.
createGrantorsCompletedDesc Total number of initial grantors created in this process.
createGrantorsInProgressDesc Current number of initial grantors being created in this process.
destroyReadsDesc The current number of DLockService destroy read locks held by this process.
destroyReadWaitFailedTimeDesc Total time spent waiting for a DLockService destroy read lock that was not obtained.
destroyReadWaitsCompletedDesc Total number of times a DLockService destroy read lock wait has completed successfully.
destroyReadWaitsFailedDesc Total number of times a DLockService destroy read lock wait has completed unsuccessfully.
destroyReadWaitsInProgressDesc Current number of threads waiting for a DLockService destroy read lock.
destroyReadWaitTimeDesc Total time spent waiting for a DLockService destroy read lock that was obtained.
destroyWritesDesc The current number of DLockService destroy write locks held by this process.
destroyWriteWaitFailedTimeDesc Total time spent waiting for a DLockService destroy write lock that was not obtained.
destroyWriteWaitsCompletedDesc Total number of times a DLockService destroy write lock wait has completed successfully.
destroyWriteWaitsFailedDesc Total number of times a DLockService destroy write lock wait has completed unsuccessfully.
destroyWriteWaitsInProgressDesc Current number of writes waiting for a DLockService destroy write lock.
destroyWriteWaitTimeDesc Total time spent waiting for a DLockService destroy write lock that was obtained.
grantorsDesc The current number of lock grantors hosted by this system member.
grantorThreadExpireAndGrantLocksTimeDesc Total time spent by grantor thread(s) performing expireAndGrantLocks tasks.
grantorThreadHandleRequestTimeoutsTimeDesc Total time spent by grantor thread(s) performing handleRequestTimeouts tasks.";
grantorThreadRemoveUnusedTokensTimeDesc Total time spent by grantor thread(s) performing removeUnusedTokens tasks.
grantorThreadsCompletedDesc Total number of iterations of work performed by grantor thread(s).
grantorThreadsInProgressDesc Current iterations of work performed by grantor thread.
grantorThreadTimeDesc Total time spent by grantor thread(s) performing all grantor tasks.
grantorWaitFailedTimeDesc Total time spent waiting for the grantor latch which resulted in failure.
grantorWaitsCompletedDesc Total number of times waiting threads completed waiting for the grantor latch to open.
grantorWaitsFailedDesc Total number of times waiting threads failed to finish waiting for the grantor latch to open.
grantorWaitsInProgressDesc Current number of threads waiting for grantor latch to open.
grantorWaitTimeDesc Total time spent waiting for the grantor latch which resulted in success.
grantWaitDestroyedTimeDesc Total time spent granting of lock requests that failed because lock service was destroyed.
grantWaitFailedTimeDesc Total time spent granting of lock requests that failed because try locks failed.
grantWaitNotGrantorTimeDesc Total time spent granting of lock requests that failed because not grantor.
grantWaitNotHolderTimeDesc Total time spent granting of lock requests that failed because reentrant was not holder.
grantWaitsCompletedDesc Total number of times granting of a lock request has completed by successfully granting the lock.
grantWaitsDestroyedDesc Total number of times granting of lock request failed because lock service was destroyed.
grantWaitsFailedDesc Total number of times granting of lock request failed because try locks failed.
grantWaitsInProgressDesc Current number of distributed lock requests being granted.
grantWaitsNotGrantorDesc Total number of times granting of lock request failed because not grantor.
grantWaitsNotHolderDesc Total number of times granting of lock request failed because reentrant was not holder.
grantWaitsSuspendedDesc Total number of times granting of lock request failed because lock service was suspended.
grantWaitsTimeoutDesc Total number of times granting of lock request failed because of a timeout.
grantWaitSuspendedTimeDesc Total time spent granting of lock requests that failed because lock service was suspended.
grantWaitTimeDesc Total time spent attempting to grant a distributed lock.
grantWaitTimeoutTimeDesc Total time spent granting of lock requests that failed because of a timeout.
lockReleasesCompletedDesc Total number of times distributed lock release has completed.
lockReleasesInProgressDesc Current number of threads releasing a distributed lock.
lockReleaseTimeDesc Total time spent releasing a distributed lock.
lockWaitFailedTimeDesc Total number of times distributed lock wait has completed by failing to obtain the lock.
lockWaitsCompletedDesc Total number of times distributed lock wait has completed by successfully obtaining the lock.
lockWaitsFailedDesc Total time spent waiting for a distributed lock that failed to be obtained.
lockWaitsInProgressDesc Current number of threads waiting for a distributed lock.
lockWaitTimeDesc Total time spent waiting for a distributed lock that was obtained.
pendingRequestsDesc The current number of pending lock requests queued by grantors in this process.
requestQueuesDesc The current number of lock request queues used by this system member.
serialQueueSizeDesc The number of serial distribution messages currently waiting to be processed.
serialThreadsDesc The number of threads currently processing serial/ordered messages.
serviceCreateLatchTimeDesc Total time spent creating lock services before releasing create latches.
serviceCreatesCompletedDesc Total number of lock services created in this process.
serviceCreatesInProgressDesc Current number of lock services being created in this process.
serviceInitLatchTimeDesc Total time spent creating lock services before releasing init latches.
servicesDesc The current number of lock services used by this system member.
String createGrantorTimeDesc Total time spent waiting create the initial grantor for lock services.
tokensDesc The current number of lock tokens used by this system member.
waitingQueueSizeDesc The number of distribution messages currently waiting for some other resource before they can be processed.
waitingThreadsDesc The number of threads currently processing messages that had to wait for a resource.

Function Execution (FunctionServiceStatistics)

These are the statistics for each execution of the function. The primary statistics are:

Statistic Description
functionExecutionCalls Total number of FunctionService.execute() calls for given function.
functionExecutionsCompleted Total number of completed function.execute() calls for given function.
functionExecutionsCompletedProcessingTime Total time consumed for all completed invocations of the given function.
functionExecutionsExceptions Total number of Exceptions Occurred while executing function.
functionExecutionsHasResultCompletedProcessingTime Total time consumed for all completed given function.execute() calls where hasResult() returns true.
functionExecutionsHasResultRunning A gauge indicating the number of currently active execute() calls for functions where hasResult() returns true.
functionExecutionsRunning number of currently running invocations of the given function.
resultsReceived Total number of results received and passed to the ResultCollector.
resultsSentToResultCollector Total number of results sent to the ResultCollector.

Indexes (IndexStats)

Query-Independent Statistics on Indexes

Statistic Description
numKeys Number of keys currently stored in the Index.
numUpdates Number of updates applied and completed on the Index while inserting, modifying , or deleting corresponding data in GemFire.
numValues Number of values currently stored in the Index.
updatesInProgress Current number of updates in progress on the Index. Concurrent updates on an index are allowed.
updateTime Total time taken in applying and completing updates on the Index.

Query-Dependent Statistics on Indexes

Statistic Description
numUses Number of times the Index has been used for querying.
usesInProgress Current number of uses of the index in progress or current number of concurrent threads accessing the index for querying. Concurrent use of an index is allowed for different queries.
useTime Total time during the use of the Index for querying.

JVM Performance

GemFire JVM Resource Manager (ResourceManagerStats)

Statistics related to the GemFire's resource manager. Use these to help analyze and tune your JVM memory settings and the GemFire resource manager settings. The primary statistics are:

Statistic Description
criticalThreshold The cache resource-manager setting critical-heap-percentage.
evictionStartEvents Number of times eviction activities were started due to the heap use going over the eviction threshold.
evictionStopEvents Number of times eviction activities were stopped due to the heap use going below the eviction threshold.
evictionThreshold The cache resource-manager setting eviction-heap-percentage..
heapCriticalEvents Number of times incoming cache activities were blocked due to heap use going over the critical threshold.
heapSafeEvents Number of times incoming cache activities were unblocked due to heap use going under the critical threshold.
tenuredHeapUsed Percentage of tenured heap currently in use.

JVM Java Runtime (VMStats)

Show the JVM’s Java usage and can be used to detect possible problems with memory consumption. These statistics are recorded from java.lang.Runtime under VMStats. The primary statistics are:

Statistic Description
cpus Number of CPUs available to the member on its machine.
daemonThreads Current number of live daemon threads in this JVM.
fdLimit Maximum number of file descriptors.
fdsOpen Current number of open file descriptors.
freeMemory An approximation for the total amount of memory, measured in bytes, currently available for future allocated objects.
loadedClasses Total number of classes loaded since the JVM started.
maxMemory The maximum amount of memory, measured in bytes, that the JVM will attempt to use.
peakThreads High water mark of live threads in this JVM.
pendingFinalization Number of objects that are pending finalization in the JVM.
processCpuTime CPU time, measured in nanoseconds, used by the process.
threads Current number of live threads (both daemon and non-daemon) in this JVM.
threadStarts Total number of times a thread has been started since this JVM started.
totalMemory The total amount of memory, measure in bytes, currently available for current and future objects.
unloadedClasses Total number of classes unloaded since the JVM started.

JVM Garbage Collection (VMGCStats)

These statistics show how much time used by different JVM garbage collection and are available on JDK 1.5 and later JVMs. The primary statistics are:

Statistic Description
collections Total number of collections this garbage collector has done.
collectionTime Approximate elapsed time spent doing collections by this garbage collector.

JVM Garbage Collector Memory Pools (VMMemoryPoolStats)

These statistics describe memory usage in different garbage collector memory pools. The primary statistics are:

Statistic Description
collectionUsageExceeded Total number of times the garbage collector detected that memory usage in this pool exceeded the collectionUsageThreshold.
collectionUsageThreshold The collection usage threshold, measured in bytes, for this pool.
collectionUsedMemory The estimated amount of used memory, measured in bytes, after that last garbage collection of this pool.
currentCommittedMemory The amount of committed memory, measured in bytes, for this pool.
currentInitMemory Initial memory the JVM requested from the operating system for this pool.
currentMaxMemory The maximum amount of memory, measured in bytes, this pool can have.
currentUsedMemory The estimated amount of used memory, measured in bytes, currently in use for this pool.
usageExceeded Total number of times that memory usage in this pool exceeded the usageThreshold.
usageThreshold The usage threshold, measured in bytes, for this pool.

JVM Heap Memory Usage (VMMemoryUsageStats)

Show details on how the Java heap memory is being used. This statistic is available on JDK 1.5 and later JVMs. The primary statistics are:

Statistic Description
committedMemory The amount of committed memory, measured in bytes, for this area.
initMemory Initial memory the JVM requested from the operating system for this area.
maxMemory The maximum amount of memory, measured in bytes, this area can have.
usedMemory The amount of used memory, measured in bytes, for this area.

Locator (LocatorStatistics)

These statistics are on the GemFire locator. The primary statistics are:

Statistic Description
ENDPOINTS_KNOWN Number of servers this locator knows about.
KNOWN_LOCATORS Number of locators known to this locator.
REQUEST_TIME Time, measured in nanoseconds, spent processing server location requests.
REQUESTS_IN_PROGRESS The number of location requests currently being processed by the thread pool.
REQUESTS_TO_LOCATOR Number of requests this locator has received from clients.
RESPONSE_TIME Time, measured in nanoseconds, spent sending location responses to clients.
RESPONSES_FROM_LOCATOR Number of responses this locator has sent to clients.
SERVER_LOAD_UPDATES Total number of times a server load update has been received.

Partitioned Regions (PartitionedRegion<partitioned_region_name>Statistics)

Partitioned Region Statistics on Region Operations

These statistics track the standard region operations executed in the member. Operations can originate locally or in a request from a remote member.
Note: Unsuccessful operations are not counted in these statistics.
The primary statistics are:
Statistic Description
containsKeyCompleted Number of successful containsKey operations in this member.
containsKeyOpsRetried Number of containsKey or containsValueForKey operations retried due to failures. This stat counts each retried operation only once, even if it requires multiple retries.
containsKeyRetries Total number of times containsKey or containsValueForKey operations were retried. If multiple retries are required on a single operation, this stat counts them all.
containsKeyTime Total time, in nanoseconds, the member spent doing containsKey operations in this member.
containsValueForKeyCompleted Number of successful containsValueForKey operations in this member.
containsValueForKeyTime Total time, in nanoseconds, the member spent doing containsValueForKey operations in this member.
createOpsRetried Number of create operations retried due to failures. This stat counts each retried operation only once, even if it requires multiple retries.
createRetries Total number of times create operations were retried. If multiple retries are required on a single operation, this stat counts them all.
createsCompleted Number of successful create operations in this member.
createTime Total time, in nanoseconds, the member spent doing create operations in this member.
destroyOpsRetried Number of destroy operations retried due to failures. This stat counts each retried operation only once, even if it requires multiple retries.
destroyRetries Total number of times destroy operations were retried. If multiple retries are required on a single operation, this stat counts them all.
destroysCompleted Number of successful destroy operations in this member.
destroyTime Total time, in nanoseconds, the member spent doing destroy operations in this member.
getEntriesCompleted Number of get entry operations completed.
getEntriesTime Total time, in nanoseconds, spent performing get entry operations.
getOpsRetried Number of get operations retried due to failures. This stat counts each retried operation only once, even if it requires multiple retries.
getRetries Total number of times get operations were retried. If multiple retries are required on a single operation, this stat counts them all.
getsCompleted Number of successful get operations in this member.
getTime Total time, in nanoseconds, the member spent doing get operations in this member.
invalidateOpsRetried Number of invalidate operations retried due to failures. This stat counts each retried operation only once, even if it requires multiple retries.
invalidateRetries Total number of times invalidate operations were retried. If multiple retries are required on a single operation, this stat counts them all.
invalidatesCompleted Number of successful invalidate operations in this member.
invalidateTime Total time, in nanoseconds, the member spent doing invalidate operations in this member.
putOpsRetried Number of put operations retried due to failures. This stat counts each retried operation only once, even if it requires multiple retries.
putRetries Total number of times put operations were retried. If multiple retries are required on a single operation, this stat counts them all.
putsCompleted Number of successful put operations in this member.
putTime Total time, in nanoseconds, the member spent doing put operations in this member.
replyWaitMaxTime Longest amount of time, in milliseconds, taken to write a message and receive a reply before a forced disconnect occurs. This stat is always active regardless of the setting of the enable-time-statistics gemfire.properties setting.
sentMessageMaxTime Longest amount of time, in milliseconds, taken to write a message to the network before a forced disconnect occurs. This stat is always active regardless of the setting of the enable-time-statistics gemfire.properties setting.

Partitioned Region Statistics on Partition Messages

Note: Unsuccessful operations and local operations—those that originated in this member—are not counted in these statistics.
The primary statistics are:
Statistic Description
partitionMessagesProcessed Number of region operations executed in this member at the request of other data stores for the region.
partitionMessagesProcessingTime Total time, in nanoseconds, the member spent executing region operations in this member at the request of remote members.
partitionMessagesReceived Number of remote requests this member received for any region operation in this member.
partitionMessagesSent Number of requests this member sent for any region operation on a remote member.
prMetaDataSentCount Number of times meta data refresh sent on client's request. Used with pr-single-hop functionality.

Partitioned Region Statistics on Data Entry Caching

These statistics track the pattern of data entry distribution among the buckets in this member. The primary statistics are:

Statistic Description
avgBucketSize Average number of entries for each of the primary buckets in this member.
bucketCount Total number of buckets in this member.
bucketCreationsCompleted Number of logical bucket creation operations requests completed after which the bucket was created.
bucketCreationsDiscoveryCompleted Number of bucket creation operations requests completed after which it was discovered that the bucket was created by another member.
bucketCreationsDiscoveryTime Total time, in nanoseconds, spent waiting for bucket creation requests to complete after which it was discovered that the bucket was created by another member.
bucketCreationsTime Total time, in nanoseconds, spent waiting for bucket creation requests to complete after which the bucket was created.
dataStoreBytesInUse The number of bytes stored in this cache for the named partitioned region.
dataStoreEntryCount Total number of entries in all the buckets in this member.
maxBucketSize Largest number of entries in the primary buckets in this member.
minBucketSize Smallest number of entries in the primary buckets in this member.
totalBucketSize Total number of entries in the primary buckets.

Partitioned Region Statistics on Redundancy

These statistics track status on partitioned region data copies. The primary statistics are:

Statistic Description
actualRedundantCopies The least current redundant number of copies for any data in this partitioned region (there may be some data that is fully redundant, but some data will have only this number of copies). This value may drop when a data store is lost or rise when a data store is added. This value may drop temporarily during partitioned region creation or destruction and then rise again.
Note: If this value remains low, then partitioned region data is at risk and may be lost if another data store is lost.
A healthy partitioned region will maintain a value equal to configuredRedundantCopies. The user should add one or more data stores if the value remains low. High-availability may result in a brief fluctuation, but it should return to a value equal to configuredRedundantCopies if there are sufficient data stores present (that is, killing one data store will cause its data to fail over to another data store).
configuredRedundantCopies This is equivalent to the PartitionAttributes.getRedundantCopies configuration that was used to create this partitioned region. This value remains unchanged for a given partitioned region.
lowRedundancyBucketCount The number of buckets in this partitioned region that currently have fewer copies than the configuredRedundantCopies. This value may rise above zero when a data store is lost and return to zero when one or more data stores are added. This value may rise temporarily during partitioned region creation or destruction and then return to zero.
Note: If this value remains above zero, then partitioned region data is at risk and may be lost if another data store is lost.
This value will be above zero whenever actualRedundantCopies is less than configuredRedundantCopies. A healthy partitioned region will maintain a value of zero. The user should add one or more datstores if this value remains above zero. High-availability may result in a brief fluctuation, but it should return to zero if there are sufficient data stores present (that is, killing one data store will cause its data to fail over to another data store).

Operating System Statistics - Linux

Linux Process Performance (LinuxProcessStats)

Operating system statistics on the member’s process. These can be used to determine the member’s CPU, memory, and disk usage. Operating system statistics are not available in pure Java mode, where GemFire runs without the use of the GemFire native library. These are the equivalent of SolarisProcessStats when we're running on Linux. The primary statistics are:

Statistic Description
imageSize Size, in megabytes, of the process's image.
rssSize Size, in megabytes, of the process's resident size.

Linux Operating System (LinuxSystemStats)

Operating system statistics on the member’s machine. These can be used to determine total cpu, memory, and disk usage on the machine. Operating system statistics are not available in pure Java mode. These are the equivalent of SolarisSystemStats when running on Linux. The primary statistics are:

Statistic Description
allocatedSwap Number of megabytes of swap space that have actually been written to. Swap space must be reserved before it can be allocated.
bufferMemory Number of megabytes of memory allocated to buffers.
contextSwitches Total number of context switches from one thread to another on the computer. Thread switches can occur either inside of a single process or across processes. A thread switch may be caused either by one thread asking another for information, or by a thread being preempted by another, higher priority thread becoming ready to run.
cpuActive Percentage of the total available time that has been used in a non-idle state.
cpuIdle Percentage of the total available time that has been spent sleeping.
cpuNice Percentage of the total available time that has been used to execute user code in processes with low priority.
cpus Number of online CPUs (items) on the local machine.
cpuSystem Percentage of the total available time that has been used to execute system (that is, kernel) code.
cpuUser Percentage of the total available time that has been used to execute user code.
freeMemory Number of megabytes of unused memory on the machine.
loadAverage1 Average number of threads in the run queue or waiting for disk I/O over the last minute.
loadAverage15 Average number of threads in the run queue or waiting for disk I/O over the last fifteen minutes.
loadAverage5 Average number of threads in the run queue or waiting for disk I/O over the last five minutes.
loopbackBytes Number of network bytes sent (or received) on the loopback interface.
loopbackPackets Number of network packets sent (or received) on the loopback interface.
pagesPagedIn Total number of pages that have been brought into memory from disk by the operating system's memory manager.
pagesPagedOut Total number of pages that have been flushed from memory to disk by the operating system's memory manager.
pagesSwappedIn Total number of swap pages that have been read in from disk by the operating system's memory manager.
pagesSwappedOut Total number of swap pages that have been written out to disk by the operating system's memory manager.
physicalMemory Actual amount of total physical memory on the machine.
processCreates The total number of times a process (operation) has been created.
processes Number of processes in the computer at the time of data collection. Notice that this is an instantaneous count, not an average over the time interval. Each process represents the running of a program.
recvBytes Total number of network bytes received (excluding loopback).
recvDrops Total number network receives (packets) dropped.
recvErrors Total number of network receive errors.
recvPackets Total number of network packets received (excluding loopback).
sharedMemory Number of megabytes of shared memory on the machine.
unallocatedSwap Number of megabytes of swap space that have not been allocated.
xmitBytes Total number of network bytes transmitted (excluding loopback).
xmitCollisions Total number of network transmit collisions.
xmitDrops Total number of network transmits (packets) dropped.
xmitErrors Total number of network transmit errors.
xmitPackets Total number of network packets transmitted (excluding loopback.

Operating System Statistics - Solaris

Solaris Process Statistics (SolarisProcessStats)

Operating system statistics on the member process. These can be used to determine the member’s CPU, memory, and disk usage. Operating system statistics are not available in pure Java mode, where GemFire runs without the use of the GemFire native library. For the Solaris operating system, when not using pure-java mode, these statistics are gathered for every process. The primary statistics are:

Statistic Description
activeTime The amount of time, in milliseconds, the process has been using the CPU to execute user or system code.
allOtherSleepTime The number of milliseconds the process has been sleeping for some reason not tracked by any other stat. Note, all lightweight processes (lwps) contribute to this stat's value, so check lwpCurCount to understand large values.
characterIo The number of characters read and written.
cpuUsed The percentage of recent CPU time used by the process.
dataFaultSleepTime The number of milliseconds the process has been faulting in data pages.
heapSize The size, in megabytes, of the process's heap.
imageSize The size, in megabytes, of the process's image.
involContextSwitches The number of times the process operation was forced to do a context switch.
kernelFaultSleepTime The number of milliseconds the process has been faulting in kernel pages.
lockWaitSleepTime The number of milliseconds the process has been waiting for a user lock. Note, all lwp's contribute to this stat's value, so check lwpCurCount to understand large values.
lwpCurCount The current number of lightweight process threads that exist in the process.
lwpTotalCount The total number of lightweight process threads that have ever contributed to the process's statistics.
majorFaults The number of times the process operation has had a page fault that needed disk access.
memoryUsed The percentage of real memory used by the process.
messagesRecv The number of messages received by the process.
messagesSent The number of messages sent by the process.
minorFaults The number of times the process operation has had a page fault that did not need disk access.
rssSize The size, in megabytes of the process's resident set size.
signalsReceived The total number of operating system signals this process has received.
stackSize The size, in megabytes, of the process's stack.
stoppedTime The amount of time, in milliseconds, the process has been stopped.
systemCalls The total number system call operations done by this process.
systemTime The amount it time, in milliseconds, the process has been using the CPU to execute system calls.
textFaultSleepTime The amount of time, in milliseconds, the process has been faulting in text pages.
trapTime The amount of time, in milliseconds, the process has been in system traps.
userTime The amount of time, in milliseconds, the process has been using the CPU to execute user code.
volContextSwitches The number of voluntary context switch operations done by the process.
waitCpuTime The amount of time, in milliseconds, the process has been waiting for a CPU due to latency.

Solaris System (SolarisSystemStats)

Operating system statistics on the member’s machine. These can be used to determine total cpu, memory, and disk usage on the machine. Operating system statistics are not available in pure Java mode. These statistics are recorded for the machine on which the program is running when not using pure Java and running on Solaris. The primary statistics are:

Statistic Description
allocatedSwap The number of megabytes of swap space that have actually been written to. Swap space must be reserved before it can be allocated.
anonymousPagesFreed The total number pages that contain heap, stack, or other changeable data that have been removed from memory and added to the free list.
anonymousPagesPagedIn The total number pages that contain heap, stack, or other changeable data that have been allocated in memory and possibly copied from disk.
anonymousPagesPagedOut The total number pages that contain heap, stack, or other changeable data that have been removed from memory and copied to disk.
broadcastInputPackets Broadcast packets received.
broadcastOutputPackets Broadcast packets requested to be sent.
collisions Solaris collisions.
contextSwitches The total number of context switches from one thread to another on the computer. Thread switches can occur either inside of a single process or across processes. A thread switch may be caused either by one thread asking another for information, or by a thread being preempted by another, higher priority thread becoming ready to run.
cpuActive The percentage of the total available time that has been used to execute user or system code.
cpuIdle The percentage of the total available time that has been spent sleeping.
cpuIoWait The percentage of the total available time that has been spent waiting for disk IO to complete.
cpus The number of online CPUs on the local machine.
cpuSwapWait The percentage of the total available time that has been spent waiting for paging and swapping to complete.
cpuSystem The percentage of the total available time that has been used to execute system (that is, kernel) code.
cpuUser The percentage of the total available time that has been used to execute user code.
cpuWaiting The percentage of the total available time that has been spent waiting for IO, paging, or swapping.
execPagesFreed The total number read only pages that contain code or data that have been removed from memory and returned to the free list.
execPagesPagedIn The total number read only pages that contain code or data that have been copied from disk to memory.
execPagesPagedOut The total number read only pages that contain code or data that have been removed from memory and will need to be paged in when used again.
failedMutexEnters The total number of times a thread entering a mutex had to wait for the mutex to be unlocked.
failedReaderLocks The total number of times readers failed to obtain a readers/writer locks on their first try. When this happens the reader must wait for the current writer to release the lock.
failedWriterLocks The total number of times writers failed to obtain a readers/writer locks on their first try. When this happens the writer must wait for all the current readers or the single writer to release the lock.
fileSystemPagesFreed The total number of pages, that contained the contents of a file due to the file being read from a file system, that have been removed from memory and put on the free list.
fileSystemPagesPagedIn The total number of pages that contain the contents of a file due to the file being read from a file system.
fileSystemPagesPagedOut The total number of pages, that contained the contents of a file due to the file being read from a file system, that have been removed from memory and copied to disk.
freeMemory The number of megabytes of unused memory on the machine.
hatMinorFaults The total number of hat faults. You only get these on systems with software memory management units.
inputBytes Octets received.
inputErrors Input errors.
inputPackets Packets received.
inputPacketsDiscarded Number of received packets discarded.
interrupts The total number of interrupts that have occurred on the computer.
involContextSwitches The total number of times a thread was forced to give up the CPU even though it was still ready to run.
loadAverage1 The average number of threads ready to run over the last minute.
loadAverage15 The average number of threads ready to run over the last 15 minutes.
loadAverage5 The average number of threads ready to run over the last five minute.
loopbackInputPackets The total number of input packets received over the loopback network adaptor.
loopbackOutputPackets The total number of output packets sent over the loopback network adaptor.
majorPageFaults The total number of times a page fault required disk IO to get the page.
messageCount The total number of msgrcv and msgsnd system calls.
multicastInputPackets Multicast packets received.
multicastOutputPackets Multicast packets requested to be sent.
outputBytes Octats transmitted.
outputErrors Output errors.
outputPackets Solaris out packets.
outputPacketsDiscarded Packets that could not be sent up because the queue was flow controlled.
pageDaemonCycles The total number of revolutions of the page daemon's scan "clock hand".
pageIns The total number of times pages have been brought into memory from disk by the operating system's memory manager.
pageOuts The total number of times pages have been flushed from memory to disk by the operating system's memory manager.
pagerRuns The total number of times the pager daemon has been scheduled to run.
pagesPagedIn The total number of pages that have been brought into memory from disk by the operating system's memory manager.
pagesPagedOut The total number of pages that have been flushed from memory to disk by the operating system's memory manager.
pagesScanned The total number pages examined by the pageout daemon. When the amount of free memory gets below a certain size, the daemon starts to look for inactive memory pages to steal from processes. A high scan rate is a good indication of needing more memory.
physicalMemory The actual amount of total physical memory on the machine.
processes The number of processes in the computer at the time of data collection. Notice, this is an instantaneous count, not an average over the time interval. Each process represents the running of a program
procsInIoWait The number of processes waiting for block I/O at this instant in time.
protectionFaults The total number of times memory has been accessed in a way that was not allowed. This results in a segmentation violation and in most cases a core dump.
reservedSwap The number of megabytes of swap space reserved for allocation by a particular process.
schedulerRunCount The total number of times the system scheduler has put a thread in its run queue.
schedulerSwapCount The total number of times the system scheduler has swapped out an idle process.
schedulerWaitCount The total number of times the system scheduler has removed a thread from the run queue because it was waiting for a resource.
semphoreOps The total number of semaphore operations.
softwareLockFaults The total number of fault operations caused by software locks held on memory pages.
systemCalls The total number of fault operations caused by software locks held on memory pages.
systemMinorFaults The total number of minor page fault operations in kernel code. Minor page faults do not require disk access.
threadCreates The total number of times a thread operation has been created.
traps The total number of trap operations that have occurred on the computer.
unallocatedSwap The number of megabytes of swap space that have not been allocated.
unreservedSwap The number of megabytes of swap space that are free. If this value goes to zero new processes can no longer be created.
userMinorFaults The total number of minor page fault operations in non-kernel code. Minor page faults do not require disk access.

Operating System Statistics - Windows

Windows Process Stats (WindowsProcessStats)

Operating system statistics on the member process. These can be used to determine the member’s CPU, memory, and disk usage. Operating system statistics are not available in pure Java mode, where GemFire runs without the use of the GemFire native library. These are the equivalent of SolarisProcessStats when running on Windows. The primary statistics are:

Statistic Description
activeTime The elapsed time, in milliseconds, that all of the threads of this process used the processor to execute instructions. An instruction is the basic unit of execution in a computer, a thread is the object that executes instructions, and a process is the object created when a program is run. Code executed to handle some hardware interrupts and trap conditions are included in this count.
handles The total number of handle items currently open by this process. This number is the sum of the handles currently open by each thread in this process.
pageFaults The total number of page fault operations by the threads executing in this process. A page fault occurs when a thread refers to a virtual memory page that is not in its working set in main memory. This will not cause the page to be fetched from disk if it is on the standby list and hence already in main memory, or if it is in use by another process with whom the page is shared.
pageFileSize The current number of bytes this process has used in the paging file(s). Paging files are used to store pages of memory used by the process that are not contained in other files. Paging files are shared by all processes, and lack of space in paging files can prevent other processes from allocating memory.
pageFileSizePeak The maximum number of bytes this process has used in the paging file(s). Paging files are used to store pages of memory used by the process that are not contained in other files. Paging files are shared by all processes, and lack of space in paging files can prevent other processes from allocating memory.
priorityBase The current base priority of the process. Threads within a process can raise and lower their own base priority relative to the process's base priority.
privateSize The current number of bytes this process has allocated that cannot be shared with other processes.
systemTime The elapsed time, in milliseconds, that the threads of the process have spent executing code in privileged mode. When a Windows system service is called, the service will often run in Privileged Mode to gain access to system-private data. Such data is protected from access by threads executing in user mode. Calls to the system can be explicit or implicit, such as page faults or interrupts. Unlike some early operating systems, Windows uses process boundaries for subsystem protection in addition to the traditional protection of user and privileged modes. These subsystem processes provide additional protection. Therefore, some work done by Windows on behalf of your application might appear in other subsystem processes in addition to the privileged time in your process.
threads Number of threads currently active in this process. An instruction is the basic unit of execution in a processor, and a thread is the object that executes instructions. Every running process has at least one thread.
userTime The elapsed time, in milliseconds, that this process's threads have spent executing code in user mode. Applications, environment subsystems, and integral subsystems execute in user mode. Code executing in User Mode cannot damage the integrity of the Windows Executive, Kernel, and device drivers. Unlike some early operating systems, Windows uses process boundaries for subsystem protection in addition to the traditional protection of user and privileged modes. These subsystem processes provide additional protection. Therefore, some work done by Windows on behalf of your application might appear in other subsystem processes in addition to the privileged time in your process.
virtualSize Virtual Bytes is the current size in bytes of the virtual address space the process is using. Use of virtual address space does not necessarily imply corresponding use of either disk or main memory pages. Virtual space is finite, and by using too much, the process can limit its ability to load libraries.
virtualSizePeak The maximum number of bytes of virtual address space the process has used at any one time. Use of virtual address space does not necessarily imply corresponding use of either disk or main memory pages. Virtual space is however finite, and by using too much, the process might limit its ability to load libraries.
workingSetSize The current number of bytes in the Working Set of this process. The Working Set is the set of memory pages touched recently by the threads in the process. If free memory in the computer is above a threshold, pages are left in the Working Set of a process even if they are not in use. When free memory falls below a threshold, pages are trimmed from Working Sets. If they are needed they will then be soft-faulted back into the Working Set before they are paged out to disk.
workingSetSizePeak The maximum number of bytes in the Working Set of this process at any point in time. The Working Set is the set of memory pages touched recently by the threads in the process. If free memory in the computer is above a threshold, pages are left in the Working Set of a process even if they are not in use. When free memory falls below a threshold, pages are trimmed from Working Sets. If they are needed they will then be soft-faulted back into the Working Set before they leave main memory.

Region Entry Eviction – Count-Based (LRUStatistics)

The entry-count least recently used (LRU) eviction mechanism records these LRUStatistics. The primary statistics are:

Statistic Description
entriesAllowed Number of entries allowed in this region.
entryCount Number of entries in this region.
lruDestroys Number of entry destroys triggered by an LRU.
lruDestroysLimit Maximum number of entry destroys triggered by an LRU before a scan occurs.
lruEvaluations Number of entries evaluated during LRU operations
lruEvictions Number of total entry evictions triggered by an LRU.
lruGreedyReturns Number of non-LRU entries evicted during LRU operations.

Region Entry Eviction – Size-based (LRUStatistics)

The least recently used (LRU) mechanism that keeps the size of a region under a given set point records these MemLRUStatistics. The primary statistics are:

Statistic Description
byteCount Number of bytes in region
bytesAllowed Total number of bytes allowed in this region.
lruDestroys Number of entry destroys triggered by LRU.
lruDestroysLimit Maximum number of entry destroys triggered by LRU before a scan occurs.
lruEvaluations Number of entries evaluated during LRU operations.
lruEvictions Total number of entry evictions triggered by LRU.
lruGreedyReturns Number of non-LRU entries evicted during LRU operations.

Server Notifications for All Clients (CacheClientNotifierStatistics)

Statistics regarding cache server operations sent to all clients.

Statistic Description
clientHealthMonitorRegister Number of clients that register.
clientHealthMonitorUnRegister Number of clients that unregister.
clientRegistrations Number of clients (operations) that have registered for updates.
clientRegistrationTime Total time, in nanoseconds, spent doing client registrations.
durableReconnectionCount Number of times the same durable client connects to the server.
eventProcessingTime Total time, in nanoseconds, spent by the cache client notifier processing events.
events Number of events (operations) processed by the cache client notifier.
eventsEnqueuedWhileClientAwayCount Number of events enqueued for a durable client.
queueDroppedCount Number of times the client subscription queue for a particular durable client is dropped.

Server Notifications for Single Client (CacheClientProxyStatistics)

Statistics regarding cache server operations and cache server client notifications sent to a single client.

Statistic Description
messageProcessingTime Total time, in nanoseconds, spent sending messages to clients.
messageQueueSize Size of the operations subscription queue.
messagesFailedQueued Number of client operations messages attempted but failed to be added to the subscription queue.
messagesNotQueuedConflated Number of client operations messages received but not added to the subscription queue because the queue already contains a message with the message's key.
messagesNotQueuedNotInterested Number of client operations messages received but not added to the subscription queue because the client represented by the receiving proxy was not interested in the message's key.
messagesNotQueuedOriginator Number of client operations messages received but not added to the subscription queue, because the receiving proxy represents the client originating the message.
messagesProcessed Number of client operations messages removed from the subscription queue and sent.
messagesQueued Number of client operations messages added to the subscription queue.
messagesReceived Number of client operations messages received.

Server-to-Client Messaging Performance (ClientSubscriptionStats)

Collected in the server, these statistics track event messages queued on the server to be sent to the client. The statistics are gathered for each client subscription queue and are incremental for the lifetime of the queue. The event messages are referred to as events in these statistics. The primary statistics are:

Statistic Description
eventsConflated Number of events conflated. If this is high, the server's dispatcher may be running slowly. This could be caused by one or more slow client.s causing blocking in their subscription queues.
eventsExpired Number of events that have expired while in the subscription queue. If this is high on a secondary server, it might be that the MessageSyncInterval on the primary is set too high, causing the secondary to fall behind in event cleanup.
eventsQueued Number of events placed in the subscription queue.
eventsRemoved Number of events removed from the subscription queue.
eventsRemovedByQrm Number of events removed based on a message sent from the primary. Only incremented while the subscription queue is in a secondary server.
eventsTaken Number of events taken from the subscription queue.
numSequenceViolated Number of events that had sequence ID less than or equal to the last sequence ID. The system assumes these events are duplicates and does not add them to the subscription queue. A non-zero value may indicate message loss.
numVoidRemovals Number of events which were supposed to be destroyed from the subscription queue through remove but were removed by some other operation like conflation or expiration.
threadIdentifiers Number of ThreadIdentifier objects (units) in the subscription queue.

Statistics Collection (StatSampler)

These statistics show how much time is spent collecting statistics. The primary statistics are:

Statistic Description
sampleCount Total number of samples taken by this sampler.
sampleTime Total amount of time spent taking samples.