diff --git a/etc/metrics_metadata.json b/etc/metrics_metadata.json index e830aa28..1d2d2608 100644 --- a/etc/metrics_metadata.json +++ b/etc/metrics_metadata.json @@ -1,20 +1,20 @@ { "xdcr_add_docs_cas_changed": { "type": "counter", - "help": "Number of add failed because target cas changed", + "help": "Number of Add operations that failed because the CAS on the Target changed", "added": "7.0.0", "stability": "internal" }, "xdcr_add_docs_written": { "type": "counter", - "help": "Number of adds successfully written to target", + "help": "Number of Add operations successfully written to the Target", "added": "7.0.0", - "notes": "This means that the target did not have the source document by name prior to this operation", + "notes": "This means that the Target did not have the Source Document by name prior to this operation", "stability": "internal" }, "xdcr_add_failed_cr_target": { "type": "counter", - "help": "Number of ADD failed conflict resolution at target cluster", + "help": "Number of Add operations failed Conflict Resolution at Target Cluster", "added": "7.1.0", "labels": [ { @@ -40,10 +40,10 @@ }, "xdcr_changes_left": { "type": "gauge", - "help": "Given the VBs of this node, the number of seqnos that need to be processed (either replicated or handled) before catching up to the high sequence numbers for the VBs", + "help": "Given the vBuckets of this node, the number of sequence numbers that need to be processed (either replicated or handled) before catching up to the high sequence numbers for the vBuckets", "added": "7.0.0", "uiName": "xdcr_changes_left_total", - "notes": "This metric is calculated as (totalChanges - docsProcessed).TotalChanges is calculated as: SumForEachVB(HighSeqno) that this node owns.The term 'changes' is more of a misnomer as it is still defined as each mutation or event that gets stamped with a sequence number. Since 7.0, system events also get stamped as a seqno per VB and thus the changes_left term no longer accurately represents actual mutations that needs to be replicated.Regardless, this number represents the concept of how much work is to be done before a replication is considered caught up.", + "notes": "This metric is calculated as (totalChanges - docsProcessed). TotalChanges is calculated as: SumForEachVB(HighSeqno) that this node owns.The term 'changes' is more of a misnomer as it is still defined as each mutation or event that gets stamped with a sequence number. Since 7.0, system events also get stamped as a seqno per VB and thus the changes_left term no longer accurately represents actual mutations that needs to be replicated.Regardless, this number represents the concept of how much work is to be done before a replication is considered caught up.", "stability": "committed" }, "xdcr_data_merge_failed": { @@ -92,7 +92,7 @@ }, "xdcr_dcp_datach_length": { "type": "gauge", - "help": "The number of items sent by KV DCP waiting for XDCR DCP nozzle to ingest and process", + "help": "The number of items sent by the Data Service waiting for the XDCR Source Nozzle to ingest and process", "added": "7.0.0", "labels": [ { @@ -110,7 +110,7 @@ }, "xdcr_dcp_dispatch_time": { "type": "gauge", - "help": "The rolling average amount of time it takes for a document to be received by XDCR from DCP, to the time it is queued up in the out nozzle ready to be sent", + "help": "The rolling average amount of time it takes for a document to be received by XDCR from the Data Service, to the time it is queued up in the Target Nozzle ready to be sent", "added": "7.0.0", "unit": "seconds", "labels": [ @@ -124,26 +124,26 @@ }, "xdcr_deletion_cloned": { "type": "counter", - "help": "The number of times a source deletion or expiration is cloned to be written to multiple target namespaces", + "help": "The number of times a Source Deletion or Expiration is cloned to be written to multiple Target Namespaces", "added": "7.2.1", - "notes": "This usually happens in collection migration using explicit rule-based mapping where deletions and expirations will pass all rules.", + "notes": "This usually happens in collection migration using explicit rule-based mapping where Deletions and Expirations will pass all rules.", "stability": "committed" }, "xdcr_deletion_docs_cas_changed": { "type": "counter", - "help": "Number of deletion failed because target cas changed", + "help": "Number of Deletions failed because Target CAS changed", "added": "7.0.0", "stability": "internal" }, "xdcr_deletion_docs_written": { "type": "counter", - "help": "Number of deletion written to target", + "help": "Number of Deletions written to Target", "added": "7.0.0", "stability": "committed" }, "xdcr_deletion_failed_cr_source": { "type": "counter", - "help": "Subset of the number of documents that failed source-side conflict resolution that were delete operations", + "help": "Number of Deletions that failed Source-side Conflict Resolution", "added": "7.0.0", "labels": [ { @@ -156,7 +156,7 @@ }, "xdcr_deletion_failed_cr_target": { "type": "counter", - "help": "Number of DELETE failed conflict resolution at target cluster", + "help": "Number of Deletions that failed Conflict Resolution at the Target", "added": "7.1.0", "labels": [ { @@ -169,7 +169,7 @@ }, "xdcr_deletion_filtered": { "type": "counter", - "help": "Number of documents filtered that was of a DCP deletion", + "help": "Number of Deletions that were filtered Source-side", "added": "6.5.0", "labels": [ { @@ -182,7 +182,7 @@ }, "xdcr_deletion_received_from_dcp": { "type": "counter", - "help": "The subset of documents received from DCP that is a Delete action", + "help": "Number of Deletions received from the Data Service", "added": "7.0.0", "stability": "committed" }, @@ -194,7 +194,7 @@ }, "xdcr_docs_checked": { "type": "gauge", - "help": "Across VBs for this node, the sum of all seqnos that have been considered to be checkpointed", + "help": "Across vBuckets for this node, the sum of all sequence numbers that have been considered to be checkpointed", "added": "7.0.0", "uiName": "xdcr_docs_checked_total", "notes": "This metric is often used in conjunction with docs_processed. The wider the difference means the more duplicate replication would take place if a replication pipeline were to restart, as it means less information is checkpointed", @@ -202,7 +202,7 @@ }, "xdcr_docs_cloned": { "type": "counter", - "help": "The number of times a source mutation is cloned to be written to different target namespace", + "help": "Number of Source Document Mutation cloned to be written to different Target Namespaces", "added": "7.0.0", "labels": [ { @@ -260,7 +260,7 @@ }, "xdcr_docs_merge_cas_changed": { "type": "counter", - "help": "Number of merges failed because source cas changed", + "help": "Number of expiry merges failed because source CAS changed", "added": "7.0.0", "stability": "internal" }, @@ -285,22 +285,22 @@ }, "xdcr_docs_opt_repd": { "type": "counter", - "help": "Number of documents optimistically replicated to the target", + "help": "Number of Documents Optimistically Replicated to the Target Cluster", "added": "7.0.0", "uiName": "xdcr_docs_opt_repd_total", - "notes": "Optimistic replication takes one less RTT, but could potential cause more network usage if the documents are decent sized", + "notes": "Optimistic Replication takes one less round trip on the network, but could potentially cause more network usage if the documents are reasonably sized", "stability": "committed" }, "xdcr_docs_processed": { "type": "gauge", - "help": "Number of docs processed for a replication", + "help": "Number of Documents processed for a Replication", "added": "7.0.0", - "notes": "Each document is considered to be a single mutation or event tagged with a sequence number. It is considered processed when a mutation is either replicated to the target, or not replicated due to a decision made, such as a document being filtered, or if it loses source conflict resolution. Another example can be a system event such as a collection creation that gets its own sequence number, but is not actually something that can be replicated. These are also counted as a doc being processed.", + "notes": "Each Document is considered to be a single Mutation or event tagged with a Ssequence Number. It is considered processed when a Mutation is either Replicated to the Target Cluster, or not replicated due to a decision made, such as a document being filtered, or if it loses Source Conflict Resolution. Another example can be a system event such as a Collection creation that gets its own Sequence Number, but is not actually something that can be replicated. These are also counted as a doc being processed.", "stability": "committed" }, "xdcr_docs_received_from_dcp": { "type": "counter", - "help": "The number of set operations received from DCP", + "help": "Number of Document Mutations received from the Data Service", "added": "7.0.0", "uiName": "xdcr_docs_received_from_dcp_total", "stability": "committed" @@ -357,7 +357,7 @@ }, "xdcr_expiry_failed_cr_source": { "type": "counter", - "help": "Subset of the number of documents that failed source-side conflict resolution that specifically had expiry flag set", + "help": "Number of Expirations that failed Source-side Conflict Resolution", "added": "7.0.0", "labels": [ { @@ -370,7 +370,7 @@ }, "xdcr_expiry_failed_cr_target": { "type": "counter", - "help": "Number of EXPIRE failed conflict resolution at target cluster", + "help": "Number of Expirations that failed Conflict Resolution at the Target", "added": "7.1.0", "labels": [ { @@ -383,7 +383,7 @@ }, "xdcr_expiry_filtered": { "type": "counter", - "help": "Number of documents filtered that had expiry flag set", + "help": "Number of Expirations filtered Source-side", "added": "6.5.0", "labels": [ { @@ -396,13 +396,13 @@ }, "xdcr_expiry_merge_cas_changed": { "type": "counter", - "help": "Number of expiry merges failed because source cas changed", + "help": "Number of expiry merges failed because source CAS changed", "added": "7.0.0", "stability": "internal" }, "xdcr_expiry_received_from_dcp": { "type": "counter", - "help": "The subset of documents received from DCP that either 1.) Is a DCP expiration or 2) Is a document that contains an expiration time", + "help": "Number of Expirations received from the Data Service", "added": "7.0.0", "stability": "committed" }, @@ -500,19 +500,19 @@ }, "xdcr_set_docs_cas_changed": { "type": "counter", - "help": "Number of set failed because target cas changed", + "help": "Number of Set operations that failed because the CAS on the Target changed", "added": "7.0.0", "stability": "internal" }, "xdcr_set_docs_written": { "type": "counter", - "help": "Number of SET_WITH_META written to target", + "help": "Number of Set operations successfully written to the Target", "added": "7.0.0", "stability": "committed" }, "xdcr_set_failed_cr_source": { "type": "counter", - "help": "Subset of the number of documents that failed source-side conflict resolution that were set operations", + "help": "Number of Set operations that failed Source-side Conflict Resolution", "added": "7.0.0", "labels": [ { @@ -525,7 +525,7 @@ }, "xdcr_set_failed_cr_target": { "type": "counter", - "help": "Number of SET_WITH_META failed conflict resolution at target cluster", + "help": "Number of Set operations that failed Conflict Resolution at the Target", "added": "7.1.0", "labels": [ { @@ -551,7 +551,7 @@ }, "xdcr_set_received_from_dcp": { "type": "counter", - "help": "The subset of documents received from DCP that is a mutation (set action)", + "help": "Number of Sets received from the Data Service", "added": "7.0.0", "stability": "committed" }, @@ -563,10 +563,10 @@ }, "xdcr_size_rep_queue": { "type": "gauge", - "help": "Amount of data being queued to be sent in an out nozzle", + "help": "Amount of data being queued to be sent to a Target Nozzle", "added": "7.0.0", "unit": "bytes", - "notes": "The larger the amount of data being buffered to be sent will cause the goxdcr process to take up more memory.If too much memory is being used, consider decreasing the number of nozzles or tune such that less data will be buffered", + "notes": "The larger the amount of data being buffered to be sent will cause the goxdcr process to take up more memory. If too much memory is being used, consider decreasing the number of Nozzles or tune such that less data will be buffered", "stability": "committed" }, "xdcr_target_docs_skipped": { @@ -630,7 +630,7 @@ }, "xdcr_wtavg_docs_latency": { "type": "gauge", - "help": "The rolling average amount of time it takes for the source cluster to receive the acknowledgement of a SET_WITH_META response after the Memcached request has been composed to be processed by the XDCR outnozzle", + "help": "The rolling average amount of time it takes for the source cluster to receive the acknowledgement of a SET_WITH_META response after the Memcached request has been composed to be processed by the XDCR Target Nozzle", "added": "7.0.0", "uiName": "xdcr_wtavg_docs_latency_seconds", "unit": "seconds", @@ -646,7 +646,7 @@ "added": "7.0.0" } ], - "notes": "This metric indicates the lag time of both the network as well as the target KV set latency. The latency tracks the followings: 1. The time it takes to issue a SET_WITH_META from the source to the target. 2. The time it takes for KV to handle the SET_WITH_META request. 3. The time it takes for KV to send a response back to XDCR indicating that a SET_WITH_META has been handled. When combined with traditional network diagnostic tools, one can use this number to differentiate between the network latency as well as target KV latency.", + "notes": "This metric indicates the lag time of both the network as well as the target Key-Value set latency. The latency tracks the followings: 1. The time it takes to issue a SET_WITH_META from the source to the target. 2. The time it takes for KV to handle the SET_WITH_META request. 3. The time it takes for KV to send a response back to XDCR indicating that a SET_WITH_META has been handled. When combined with traditional network diagnostic tools, one can use this number to differentiate between the network latency as well as target KV latency.", "stability": "committed" }, "xdcr_wtavg_get_doc_latency": {