mirror of
https://github.com/gravitl/netmaker.git
synced 2026-04-23 00:17:10 +08:00
292af315dd
* feat(go): add user schema; * feat(go): migrate to user schema; * feat(go): add audit fields; * feat(go): remove unused fields from the network model; * feat(go): add network schema; * feat(go): migrate to network schema; * refactor(go): add comment to clarify migration logic; * fix(go): test failures; * fix(go): test failures; * feat(go): change membership table to store memberships at all scopes; * feat(go): add schema for access grants; * feat(go): remove nameservers from new networks table; ensure db passed for schema functions; * feat(go): set max conns for sqlite to 1; * fix(go): issues updating user account status; * NM-236: streamline operations in HA mode * NM-236: only master pod should subscribe to updates from clients * refactor(go): remove converters and access grants; * refactor(go): add json tags in schema models; * refactor(go): rename file to migrate_v1_6_0.go; * refactor(go): add user groups and user roles tables; use schema tables; * refactor(go): inline get and list from schema package; * refactor(go): inline get network and list users from schema package; * fix(go): staticcheck issues; * fix(go): remove test not in use; fix test case; * fix(go): validate network; * fix(go): resolve static checks; * fix(go): new models errors; * fix(go): test errors; * fix(go): handle no records; * fix(go): add validations for user object; * fix(go): set correct extclient status; * fix(go): test error; * feat(go): make schema the base package; * feat(go): add host schema; * feat(go): use schema host everywhere; * feat(go): inline get host, list hosts and delete host; * feat(go): use non-ptr value; * feat(go): use save to upsert all fields; * feat(go): use save to upsert all fields; * feat(go): save turn endpoint as string; * feat(go): check for gorm error record not found; * fix(go): test failures; * fix(go): update all network fields; * fix(go): update all network fields; * feat(go): add paginated list networks api; * feat(go): add paginated list users api; * feat(go): add paginated list hosts api; * feat(go): add pagination to list groups api; * fix(go): comment; * fix(go): implement marshal and unmarshal text for custom types; * fix(go): implement marshal and unmarshal json for custom types; * fix(go): just use the old model for unmarshalling; * fix(go): implement marshal and unmarshal json for custom types; * NM-271:Import swap: compress/gzip replaced with github.com/klauspost/compress/gzip (2-4x faster, wire-compatible output). Added sync import. Two sync.Pool variables (gzipWriterPool, bufferPool): reuse gzip.Writer and bytes.Buffer across calls instead of allocating fresh ones per publish. compressPayload rewritten: pulls writer + buffer from pools, resets them, compresses at gzip.BestSpeed (level 1), copies the result out of the pooled buffer, and returns both objects to the pools. * feat(go): remove paginated list networks api; * feat(go): use custom paginated response object; * NM-271: Improve server scalability under high host count - Replace stdlib compress/gzip with klauspost/compress at BestSpeed and pool gzip writers and buffers via sync.Pool to eliminate compression as the dominant CPU hotspot. - Debounce peer update broadcasts with a 500ms resettable window capped at 3s max-wait, coalescing rapid-fire PublishPeerUpdate calls into a single broadcast cycle. - Cache HostPeerInfo (batch-refreshed by debounce worker) and HostPeerUpdate (stored as side-effect of each publish) so the pull API and peer_info API serve from pre-computed maps instead of triggering expensive per-host computations under thundering herd conditions. - Warm both caches synchronously at startup before the first publish cycle so early pull requests are served instantly. - Bound concurrent MQTT publishes to 5 via semaphore to prevent broker TCP buffer overflows that caused broken pipe disconnects. - Remove manual Disconnect+SetupMQTT from ConnectionLostHandler and rely on the paho client's built-in AutoReconnect; add a 5s retry wait in publish() to ride out brief reconnection windows. * NM-271: Reduce server CPU contention under high concurrent load - Cache ServerSettings with atomic.Value to eliminate repeated DB reads on every pull request (was 32+ goroutines blocked on read lock) - Batch UpdateNodeCheckin writes in memory, flush every 30s to reduce per-checkin write lock contention (was 88+ goroutines blocked) - Enable SQLite WAL mode + busy_timeout and remove global dbMutex; let SQLite handle concurrency natively (reads no longer block writes) - Move ResetFailedOverPeer/ResetAutoRelayedPeer to async in pull() handler since results don't affect the cached response - Skip no-op UpsertNode writes in failover/relay reset functions (early return when node has no failover/relay state) - Remove CheckHostPorts from hostUpdateFallback hot path - Switch to pure-Go SQLite driver (glebarez/sqlite), set CGO_ENABLED=0 * fix(go): ensure default values for page and per_page are used when not passed; * fix(go): rename v1.6.0 to v1.5.1; * fix(go): check for gorm.ErrRecordNotFound instead of database.IsEmptyRecord; * fix(go): use host id, not pending host id; * NM-271: Revert pure-Go SQLite and FIPS disable to verify impact Revert to CGO-based mattn/go-sqlite3 driver and re-enable FIPS to isolate whether these changes are still needed now that the global dbMutex has been removed and WAL mode is enabled. Keep WAL mode pragma with mattn-compatible DSN format. * feat(go): add filters to paginated apis; * feat(go): add filters to paginated apis; * feat(go): remove check for max username length; * feat(go): add filters to count as well; * feat(go): use library to check email address validity; * feat(go): ignore pagination if params not passed; * fix(go): pagination issues; * fix(go): check exists before using; * fix(go): remove debug log; * NM-271: rm debug logs * NM-271: check if caching is enabled * NM-271: add server sync mq topic for HA mode * NM-271: fix build * NM-271: push metrics in batch to exproter over api * NM-271: use basic auth for exporter metrics api * fix(go): use gorm err record not found; * NM-271: Add monitoring stack on demand * NM-271: -m arg for install script should only add monitoring stack * fix(go): use gorm err record not found; * NM-271: update docker compose file for prometheus * NM-271: update docker compose file for prometheus * fix(go): use user principal name when creating pending user; * fix(go): use schema package for consts; * NM-236: rm duplicate network hook * NM-271: add server topic to reset idp hooks on master node * fix(go): prevent disabling superadmin user; Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * fix(go): swap is admin and is superadmin; Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * fix(go): remove dead code block; https://github.com/gravitl/netmaker/pull/3910#discussion_r2928837937 * fix(go): incorrect message when trying to disable self; https://github.com/gravitl/netmaker/pull/3910#discussion_r2928837934 * NM-271: fix stale peers on reset_failovered pull and add HTTP timeout to metrics exporter Run the failover/relay reset synchronously in the pull handler so the response reflects post-reset topology instead of serving stale cached peers. Add a 30s timeout to the metrics exporter HTTP client to prevent PushAllMetricsToExporter from blocking the Keepalive loop. * NM-271: fix gzip pool corruption, MQTT topic mismatch, stale settings cache, and reduce redundant DB fetches - Only return gzip.Writer to pool after successful Close to prevent silently malformed MQTT payloads from a previously errored writer. - Fix serversync subscription to exact topic match since syncType is now in the message payload, not the topic path. - Prevent zero-value ServerSettings from being cached indefinitely when the DB record is missing or unmarshal fails on startup. - Return fetched hosts/nodes from RefreshHostPeerInfoCache so warmPeerCaches reuses them instead of querying the DB twice. - Compute fresh HostPeerUpdate on reset_failovered pull instead of serving stale cache, and store result back for subsequent requests. * NM-271: fix gzip writer pool leak, log checkin flush errors, and fix master pod ordinal parsing - Reset gzip.Writer to io.Discard before returning to pool so errored writers are never leaked or silently reused with corrupt state. - Track and log failed DB inserts in FlushNodeCheckins so operators have visibility when check-in timestamps are lost. - Parse StatefulSet pod ordinal as integer instead of using HasSuffix to prevent netmaker-10 from being misidentified as master pod. * NM-271: simplify masterpod logic * fix(go): use correct header; Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * fix(go): return after error response; Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * fix(go): use correct order of params; https://github.com/gravitl/netmaker/pull/3910#discussion_r2929593036 * fix(go): set default values for page and page size; use v2 instead of /list; * NM-271: use host name * Update mq/serversync.go Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * NM-271: fix duplicate serversynce case * NM-271: streamline gw updates * Update logic/auth.go Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * Update schema/user_roles.go Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * fix(go): syntax error; * fix(go): set default values when page and per_page are not passed or 0; * fix(go): use uuid.parse instead of uuid.must parse; * fix(go): review errors; * fix(go): review errors; * Update controllers/user.go Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * Update controllers/user.go Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * NM-163: fix errors: * Update db/types/options.go Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * fix(go): persist return user in event; * Update db/types/options.go Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com> * NM-271: signal pull on ip changes * NM-163: duplicate lines of code * NM-163: fix(go): fix missing return and filter parsing in user controller - Add missing return after error response in updateUserAccountStatus to prevent double-response and spurious ext-client side-effects - Use switch statements in listUsers to skip unrecognized account_status and mfa_status filter values * NM-271: signal pull req on node ip change * fix(go): check for both min and max page size; * NM-271: refresh node object before update * fix(go): enclose transfer superadmin in transaction; * fix(go): review errors; * fix(go): remove free tier checks; * fix(go): review fixes; * NM-271: streamline ip pool ops * NM-271: fix tests, set max idle conns * NM-271: fix(go): fix data races in settings cache and peer update worker - Use pointer type in atomic.Value for serverSettingsCache to avoid replacing the variable non-atomically in InvalidateServerSettingsCache - Swap peerUpdateReplace flag before draining the channel to prevent a concurrent replacePeers=true from being consumed by the wrong cycle --------- Co-authored-by: VishalDalwadi <dalwadivishal26@gmail.com> Co-authored-by: Vishal Dalwadi <51291657+VishalDalwadi@users.noreply.github.com> Co-authored-by: tenki-reviewer[bot] <262613592+tenki-reviewer[bot]@users.noreply.github.com>
84 lines
3.1 KiB
YAML
84 lines
3.1 KiB
YAML
services:
|
|
|
|
prometheus:
|
|
container_name: prometheus
|
|
image: prom/prometheus:latest
|
|
environment:
|
|
- METRICS_USERNAME=${METRICS_USERNAME:-netmaker}
|
|
- METRICS_SECRET=${METRICS_SECRET}
|
|
- NETMAKER_METRICS_TARGET=${NETMAKER_METRICS_TARGET:-http://netmaker-exporter:8085}
|
|
- PROMETHEUS_RETENTION_TIME=${PROMETHEUS_RETENTION_TIME:-15d}
|
|
- PROMETHEUS_RETENTION_SIZE=${PROMETHEUS_RETENTION_SIZE:-0}
|
|
volumes:
|
|
- ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml.tmpl:ro
|
|
- prometheus_data:/prometheus
|
|
entrypoint: /bin/sh
|
|
command:
|
|
- -c
|
|
- |
|
|
cp /etc/prometheus/prometheus.yml.tmpl /etc/prometheus/prometheus.rendered.yml
|
|
url="$${NETMAKER_METRICS_TARGET}"
|
|
if echo "$${url}" | grep -q '://'; then
|
|
scheme="$${url%%://*}"; target="$${url#*://}"
|
|
else
|
|
scheme="https"; target="$${url}"
|
|
fi
|
|
sed -i "s~NETMAKER_METRICS_TARGET~$${target}~g" /etc/prometheus/prometheus.rendered.yml
|
|
sed -i "s~__SCHEME__~$${scheme}~g" /etc/prometheus/prometheus.rendered.yml
|
|
sed -i "s~METRICS_USERNAME~$${METRICS_USERNAME}~g" /etc/prometheus/prometheus.rendered.yml
|
|
sed -i "s~METRICS_SECRET~$${METRICS_SECRET}~g" /etc/prometheus/prometheus.rendered.yml
|
|
exec /bin/prometheus \
|
|
--config.file=/etc/prometheus/prometheus.rendered.yml \
|
|
--storage.tsdb.path=/prometheus \
|
|
--storage.tsdb.retention.time=$${PROMETHEUS_RETENTION_TIME:-15d} \
|
|
--storage.tsdb.retention.size=$${PROMETHEUS_RETENTION_SIZE:-0}
|
|
restart: unless-stopped
|
|
|
|
grafana:
|
|
container_name: grafana
|
|
image: grafana/grafana:latest
|
|
environment:
|
|
- PROMETHEUS_HOST=${PROMETHEUS_HOST:-http://prometheus:9090}
|
|
volumes:
|
|
- ./grafana/grafana.ini:/etc/grafana/grafana.ini:ro
|
|
- ./grafana/datasource.yaml:/etc/grafana/provisioning/datasources/datasource.yaml:ro
|
|
- ./grafana/dashboard-config.yaml:/etc/grafana/provisioning/dashboards/dashboard-config.yaml:ro
|
|
- ./grafana/dashboard.json:/var/lib/grafana/dashboards/dashboard.json:ro
|
|
- grafana_data:/var/lib/grafana
|
|
restart: unless-stopped
|
|
|
|
|
|
netmaker-exporter:
|
|
container_name: netmaker-exporter
|
|
image: gravitl/netmaker-exporter:latest
|
|
env_file: ./netmaker.env
|
|
environment:
|
|
- PROMETHEUS_HOST=${PROMETHEUS_HOST:-http://prometheus:9090}
|
|
# The domain/host IP indicating the mq broker address
|
|
- BROKER_ENDPOINT=ws://mq:1883 #wss://broker.${NM_DOMAIN}
|
|
- API_PORT=${EXPORTER_API_PORT}
|
|
- SERVER_NAME=${NM_DOMAIN}
|
|
restart: always
|
|
depends_on:
|
|
- netmaker
|
|
# - clickhouse
|
|
#
|
|
# clickhouse:
|
|
# container_name: clickhouse
|
|
# image: clickhouse/clickhouse-server:latest
|
|
# env_file: ./netmaker.env
|
|
# restart: always
|
|
# environment:
|
|
# - CLICKHOUSE_DB=${CLICKHOUSE_DB}
|
|
# - CLICKHOUSE_USER=${CLICKHOUSE_USER}
|
|
# - CLICKHOUSE_PASSWORD=${CLICKHOUSE_PASS}
|
|
# volumes:
|
|
# - clickhouse_data:/var/lib/clickhouse
|
|
# - clickhouse_logs:/var/log/clickhouse-server
|
|
|
|
volumes:
|
|
prometheus_data: { }
|
|
grafana_data: { }
|
|
# clickhouse_data: { }
|
|
# clickhouse_logs: { }
|