Expand metrics on pg_stat_replication to include lag expressed as time. #115
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,99 @@ | ||
| package collector | ||
|
|
||
| import ( | ||
| "context" | ||
|
|
||
| pgx "github.com/jackc/pgx/v4" | ||
| "github.com/prometheus/client_golang/prometheus" | ||
| ) | ||
|
|
||
| /* When pg_basebackup is running in stream mode, it opens a second connection | ||
| to the server and starts streaming the transaction log in parallel while | ||
| running the backup. In both connections (state=backup and state=streaming) the | ||
| pg_log_location_diff is null and it requires to be excluded */ | ||
|
There was a problem hiding this comment. Where is Even Google has no clue what |
||
| const ( | ||
| // Scrape query | ||
| statWalReceiver = ` | ||
| WITH pg_wal_receiver AS ( | ||
| SELECT status | ||
| , pg_wal_lsn_diff(pg_last_wal_receive_lsn(), pg_last_wal_replay_lsn())::float | ||
| as postgres_wal_receiver_replay_bytes | ||
| , ( | ||
| CASE WHEN pg_last_wal_receive_lsn() = pg_last_wal_replay_lsn() | ||
| THEN 0 | ||
| ELSE EXTRACT (EPOCH FROM now() - pg_last_xact_replay_timestamp()) | ||
| END | ||
| ) as postgres_wal_receiver_replay_lag | ||
| FROM pg_stat_wal_receiver | ||
| ) | ||
| SELECT * FROM pg_wal_receiver WHERE postgres_wal_receiver_replay_lag IS NOT NULL /*postgres_exporter*/` | ||
| ) | ||
|
|
||
| type statWalReceiverScraper struct { | ||
| walReceiverReplayBytes *prometheus.Desc | ||
| walReceiverReplayLag *prometheus.Desc | ||
| } | ||
|
|
||
| // NewStatWalReceiverScraper returns a new Scraper exposing postgres pg_stat_replication | ||
| func NewWalReceiverScraper() Scraper { | ||
| return &statWalReceiverScraper{ | ||
| walReceiverReplayBytes: prometheus.NewDesc( | ||
| "postgres_wal_receiver_replay_lag_bytes", | ||
| "delay in standby wal replay bytes pg_wal_lsn_diff(pg_last_wal_receive_lsn(), pg_last_wal_replay_lsn())::float", | ||
| []string{"status"}, | ||
| nil, | ||
| ), | ||
| walReceiverReplayLag: prometheus.NewDesc( | ||
| "postgres_wal_receiver_replay_lag_seconds", | ||
| "delay in standby wal replay seconds EXTRACT (EPOCH FROM now() - pg_last_xact_replay_timestamp()", | ||
| []string{"status"}, | ||
| nil, | ||
| ), | ||
| } | ||
| } | ||
|
|
||
| func (c *statWalReceiverScraper) Name() string { | ||
| return "StatWalReceiverScraperr" | ||
| } | ||
|
|
||
| func (c *statWalReceiverScraper) Scrape(ctx context.Context, conn *pgx.Conn, version Version, ch chan<- prometheus.Metric) error { | ||
| var rows pgx.Rows | ||
| var err error | ||
|
|
||
| rows, err = conn.Query(ctx, statWalReceiver) | ||
|
|
||
| if err != nil { | ||
| return err | ||
| } | ||
| defer rows.Close() | ||
|
|
||
| var status string | ||
| var pgWalReceiverReplayBytes, pgWalReceiverReplayLag float64 | ||
|
|
||
| for rows.Next() { | ||
|
|
||
| if err := rows.Scan(&status, | ||
| &pgWalReceiverReplayBytes, | ||
| &pgWalReceiverReplayLag); err != nil { | ||
|
|
||
| return err | ||
| } | ||
| // postgres_wal_receiver_replay_lag_bytes | ||
| ch <- prometheus.MustNewConstMetric(c.walReceiverReplayBytes, | ||
| prometheus.GaugeValue, | ||
| pgWalReceiverReplayBytes, | ||
| status) | ||
| // postgres_wal_receiver_replay_lag_seconds | ||
| ch <- prometheus.MustNewConstMetric(c.walReceiverReplayLag, | ||
| prometheus.GaugeValue, | ||
| pgWalReceiverReplayLag, | ||
| status) | ||
| } | ||
|
|
||
| err = rows.Err() | ||
| if err != nil { | ||
| return err | ||
| } | ||
|
|
||
| return nil | ||
| } | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@ahjmorton I didn't have time to go into details here, but could you share more details about these metrics disappearing?
Later you make a conditional have a value to report these metrics. We should avoid that, as metrics that disappear from Prometheus are complex to deal with
https://prometheus.io/docs/practices/instrumentation/#avoid-missing-metrics
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
If the WAL sender process didn't have an activity for some period of time (not sure how long, might need to look at source) then Postgres would null out those "*_lag" fields.
I was trying to avoid reporting metrics for nodes that didn't have a WAL sender process however those would be eliminated by the query as they wouldn't have a row in
pg_stat_replication.Going to change this to default to zero in case of null.