Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2620559975 | ||
|
|
ed19f51a52 | ||
|
|
e85db73dbc | ||
|
|
d38bbc52ec | ||
|
|
fe761e119e |
+127
-1
@@ -14,7 +14,9 @@
|
|||||||
# ARG/ENV (APP_VERSION / GIT_SHA / BUILD_DATE) and as OCI labels, so a running
|
# ARG/ENV (APP_VERSION / GIT_SHA / BUILD_DATE) and as OCI labels, so a running
|
||||||
# container can report exactly what is deployed.
|
# container can report exactly what is deployed.
|
||||||
#
|
#
|
||||||
# Release flow: git tag v1.2.0 && git push origin v1.2.0 -> versioned images.
|
# Release flow: git tag v1.2.0 && git push origin v1.2.0 -> versioned images
|
||||||
|
# -> deploy-galactus.yml is dispatched automatically (see the
|
||||||
|
# `deploy` job at the bottom).
|
||||||
|
|
||||||
name: Build and Push Images
|
name: Build and Push Images
|
||||||
|
|
||||||
@@ -99,3 +101,127 @@ jobs:
|
|||||||
APP_VERSION=${{ steps.meta.outputs.version }}
|
APP_VERSION=${{ steps.meta.outputs.version }}
|
||||||
GIT_SHA=${{ github.sha }}
|
GIT_SHA=${{ github.sha }}
|
||||||
BUILD_DATE=${{ fromJSON(steps.meta.outputs.json).labels['org.opencontainers.image.created'] }}
|
BUILD_DATE=${{ fromJSON(steps.meta.outputs.json).labels['org.opencontainers.image.created'] }}
|
||||||
|
|
||||||
|
# Chain the PROD deploy onto a green tag build.
|
||||||
|
#
|
||||||
|
# `needs: build` waits for BOTH matrix legs, so api and web at this tag are
|
||||||
|
# both in the registry before anything is deployed — deploy-galactus.yml does
|
||||||
|
# not build, it only pulls, and a half-pushed pair is exactly the state that
|
||||||
|
# leaves prod running one new image and one old one.
|
||||||
|
#
|
||||||
|
# Why a dispatch and not a `workflow_run:` trigger, which Gitea does support
|
||||||
|
# as of 1.24: deploy-galactus.yml reads `github.event.inputs.*` in ten places
|
||||||
|
# (tag, scope, bootstrap, skip_migrate). Under workflow_run every one of them
|
||||||
|
# is the empty string, so the deploy would silently run with no tag and
|
||||||
|
# scope != 'full'. A dispatch keeps that workflow's contract intact and keeps
|
||||||
|
# it hand-runnable for rollbacks, which is the whole point of it.
|
||||||
|
#
|
||||||
|
# Kill switch: set the repo variable AUTO_DEPLOY_GALACTUS to `false` to cut
|
||||||
|
# the chain and go back to dispatching the deploy by hand. Anything else
|
||||||
|
# (including unset) deploys.
|
||||||
|
deploy:
|
||||||
|
name: Deploy to galactus
|
||||||
|
needs: build
|
||||||
|
if: startsWith(github.ref, 'refs/tags/v')
|
||||||
|
runs-on: docker
|
||||||
|
container:
|
||||||
|
image: node:20-alpine
|
||||||
|
steps:
|
||||||
|
- name: Preflight — RELEASE_TOKEN
|
||||||
|
env:
|
||||||
|
RELEASE_TOKEN: ${{ secrets.RELEASE_TOKEN }}
|
||||||
|
run: |
|
||||||
|
set -eu
|
||||||
|
if [ -z "${RELEASE_TOKEN:-}" ]; then
|
||||||
|
echo "::error::Secret RELEASE_TOKEN is not set, so this build cannot"
|
||||||
|
echo "::error::dispatch the deploy. The images ARE published — run"
|
||||||
|
V=${GITHUB_REF#refs/tags/}
|
||||||
|
echo "::error::'Deploy to galactus' by hand with tag=${V#v}."
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
- name: Dispatch deploy-galactus.yml
|
||||||
|
env:
|
||||||
|
RELEASE_TOKEN: ${{ secrets.RELEASE_TOKEN }}
|
||||||
|
AUTO_DEPLOY: ${{ vars.AUTO_DEPLOY_GALACTUS }}
|
||||||
|
TAG_REF: ${{ github.ref }}
|
||||||
|
run: |
|
||||||
|
node -e '
|
||||||
|
const base = `${process.env.GITHUB_SERVER_URL}/api/v1/repos/${process.env.GITHUB_REPOSITORY}`;
|
||||||
|
const headers = { Authorization: `token ${process.env.RELEASE_TOKEN}` };
|
||||||
|
// refs/tags/v1.2.3 — derived from github.ref rather than ref_name so
|
||||||
|
// it does not depend on how Gitea populates GITHUB_REF_NAME.
|
||||||
|
const tagRef = process.env.TAG_REF;
|
||||||
|
// The git tag carries the leading v; the image tag does not.
|
||||||
|
const version = tagRef.replace(/^refs\/tags\/v?/, "");
|
||||||
|
const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
|
||||||
|
|
||||||
|
// Every deploy-galactus run id visible right now. A dispatch is
|
||||||
|
// only confirmed by an id that is NOT in here — a plain "is there a
|
||||||
|
// deploy run" check is satisfied by the previous release run, and
|
||||||
|
// would report success for a dispatch that never took.
|
||||||
|
const deployRunIds = async () => {
|
||||||
|
const r = await fetch(`${base}/actions/runs?limit=50`, { headers });
|
||||||
|
if (!r.ok) throw new Error(`runs query failed: HTTP ${r.status}`);
|
||||||
|
const body = await r.json();
|
||||||
|
return new Set(
|
||||||
|
(body.workflow_runs || [])
|
||||||
|
.filter((run) => String(run.path || "").includes("deploy-galactus.yml"))
|
||||||
|
.map((run) => run.id),
|
||||||
|
);
|
||||||
|
};
|
||||||
|
|
||||||
|
(async () => {
|
||||||
|
if (process.env.AUTO_DEPLOY === "false") {
|
||||||
|
console.log("AUTO_DEPLOY_GALACTUS=false — not deploying.");
|
||||||
|
console.log(`Deploy by hand with tag=${version} when ready.`);
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
const before = await deployRunIds();
|
||||||
|
|
||||||
|
// Dispatch against the TAG, not master: the deploy applies the
|
||||||
|
// compose files under deploy/galactus/ from whatever ref it runs
|
||||||
|
// on, and those must be the ones this release was cut with.
|
||||||
|
const res = await fetch(
|
||||||
|
`${base}/actions/workflows/deploy-galactus.yml/dispatches`,
|
||||||
|
{
|
||||||
|
method: "POST",
|
||||||
|
headers: { ...headers, "Content-Type": "application/json" },
|
||||||
|
body: JSON.stringify({
|
||||||
|
ref: tagRef,
|
||||||
|
inputs: {
|
||||||
|
tag: version,
|
||||||
|
scope: "app",
|
||||||
|
bootstrap: "false",
|
||||||
|
skip_migrate: "false",
|
||||||
|
},
|
||||||
|
}),
|
||||||
|
},
|
||||||
|
);
|
||||||
|
if (!res.ok) {
|
||||||
|
console.log(`::error::Dispatch returned HTTP ${res.status}: ${await res.text()}`);
|
||||||
|
console.log(`::error::Images for ${version} are published. Run`);
|
||||||
|
console.log(`::error::"Deploy to galactus" by hand with tag=${version}.`);
|
||||||
|
process.exit(1);
|
||||||
|
}
|
||||||
|
|
||||||
|
// A 204 only means Gitea accepted the request. Confirm a NEW run
|
||||||
|
// exists, the same way release.yml confirms this build started —
|
||||||
|
// an accepted call that creates no run is the failure mode that
|
||||||
|
// cost v1.0.3 its images.
|
||||||
|
for (let i = 0; i < 3; i++) {
|
||||||
|
await sleep(5_000);
|
||||||
|
const now = await deployRunIds();
|
||||||
|
const fresh = [...now].filter((id) => !before.has(id));
|
||||||
|
if (fresh.length) {
|
||||||
|
console.log(`Deploy of ${version} to galactus is running (run ${fresh[0]}).`);
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
console.log(`::error::Dispatch was accepted but no deploy run appeared.`);
|
||||||
|
console.log(`::error::Run "Deploy to galactus" by hand with tag=${version}.`);
|
||||||
|
process.exit(1);
|
||||||
|
})();
|
||||||
|
'
|
||||||
|
|||||||
@@ -1,11 +1,15 @@
|
|||||||
# Cut a release: stamp the version across every package.json, commit, tag, push.
|
# Cut a release: stamp the version across every package.json, commit, tag, push.
|
||||||
#
|
#
|
||||||
# This does NOT build and does NOT deploy. Pushing the `vX.Y.Z` tag is what
|
# This does NOT build and does NOT deploy itself. Pushing the `vX.Y.Z` tag is
|
||||||
# triggers build.yml, which publishes `X.Y.Z`, `X.Y`, `sha-<short>` and `latest`
|
# what triggers build.yml, which publishes `X.Y.Z`, `X.Y`, `sha-<short>` and
|
||||||
# image tags. Deploying stays a separate, deliberate act: once the build is
|
# `latest` image tags — and then, on a green tag build only, dispatches
|
||||||
# green, dispatch deploy-galactus.yml with `tag=X.Y.Z` (no leading v — the tag
|
# deploy-galactus.yml with `tag=X.Y.Z scope=app` (no leading v — the git tag
|
||||||
# carries the `v`, the image tag does not).
|
# carries the `v`, the image tag does not).
|
||||||
#
|
#
|
||||||
|
# So cutting a release DOES reach prod. To cut a version without deploying it,
|
||||||
|
# set the repo variable AUTO_DEPLOY_GALACTUS=false first; build.yml's `deploy`
|
||||||
|
# job then prints the manual command instead of running it.
|
||||||
|
#
|
||||||
# Why a workflow instead of three local commands: the release commit is the one
|
# Why a workflow instead of three local commands: the release commit is the one
|
||||||
# thing that must be identical every time, and cutting it from a laptop is how
|
# thing that must be identical every time, and cutting it from a laptop is how
|
||||||
# a manifest bump gets forgotten or a tag lands on an unpushed commit. Here the
|
# a manifest bump gets forgotten or a tag lands on an unpushed commit. Here the
|
||||||
@@ -266,5 +270,9 @@ jobs:
|
|||||||
echo "Released v${VERSION}."
|
echo "Released v${VERSION}."
|
||||||
echo ""
|
echo ""
|
||||||
echo "build.yml is now building git.mancinas.io/rmancinas/jorgecuadros-{api,web}:${VERSION}."
|
echo "build.yml is now building git.mancinas.io/rmancinas/jorgecuadros-{api,web}:${VERSION}."
|
||||||
echo "When it is green, dispatch 'Deploy to galactus' with:"
|
echo "When both images are pushed, build.yml dispatches 'Deploy to galactus'"
|
||||||
echo " tag=${VERSION} scope=app bootstrap=false skip_migrate=false"
|
echo "automatically with tag=${VERSION} scope=app bootstrap=false skip_migrate=false."
|
||||||
|
echo ""
|
||||||
|
echo "Watch that run. If it did not start (or AUTO_DEPLOY_GALACTUS=false),"
|
||||||
|
echo "dispatch 'Deploy to galactus' by hand with the same inputs."
|
||||||
|
echo "Rollback = re-dispatch it with an older tag."
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"name": "@jorgecuadros/api",
|
"name": "@jorgecuadros/api",
|
||||||
"version": "1.0.11",
|
"version": "1.0.13",
|
||||||
"private": true,
|
"private": true,
|
||||||
"scripts": {
|
"scripts": {
|
||||||
"build": "nest build",
|
"build": "nest build",
|
||||||
|
|||||||
@@ -400,7 +400,12 @@ export class OpsService implements OnModuleInit {
|
|||||||
`${PIPEFAIL}echo '== Respaldo de seguridad previo ==' && ` +
|
`${PIPEFAIL}echo '== Respaldo de seguridad previo ==' && ` +
|
||||||
`${this.dumpCommand(flags, db, out)} && ` +
|
`${this.dumpCommand(flags, db, out)} && ` +
|
||||||
`echo '== Sincronización aditiva desde carpeta de ingesta ==' && ` +
|
`echo '== Sincronización aditiva desde carpeta de ingesta ==' && ` +
|
||||||
`${shq(py)} ${runAll} --env ${shq(this.migrationEnv)} --sync`;
|
// --stage is not optional here. The staged Parquet lives in the image
|
||||||
|
// at migration/output, NOT on a volume, so every redeploy wipes it and
|
||||||
|
// a sync without --stage dies on a missing stg_*/*.parquet. Re-staging
|
||||||
|
// is also the only thing that makes "desde carpeta de ingesta" true:
|
||||||
|
// stale Parquet would sync the previous upload, not the current one.
|
||||||
|
`${shq(py)} ${runAll} --env ${shq(this.migrationEnv)} --stage --sync`;
|
||||||
return { cmd, resolvedParams: { safetyBackup: file } };
|
return { cmd, resolvedParams: { safetyBackup: file } };
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -4,6 +4,45 @@ import { promisify } from "node:util";
|
|||||||
|
|
||||||
const exec = promisify(execFile);
|
const exec = promisify(execFile);
|
||||||
|
|
||||||
|
/**
|
||||||
|
* How far the SQL thread is behind the I/O thread, in source binlog bytes.
|
||||||
|
*
|
||||||
|
* This is a different question from `secondsBehind`, and it answers the case
|
||||||
|
* that lag hides: while the SQL thread grinds through one huge transaction,
|
||||||
|
* `Seconds_Behind_Source` can sit still or even read 0, but the relay backlog
|
||||||
|
* is plainly shrinking (or not). It costs nothing extra — every field here
|
||||||
|
* comes out of the same `SHOW REPLICA STATUS` the panel already runs.
|
||||||
|
*
|
||||||
|
* Both positions are coordinates in the SOURCE's binlog, so they are only
|
||||||
|
* comparable while both threads are working on the SAME source file. When they
|
||||||
|
* are not, the replica is whole files behind and the byte delta is meaningless
|
||||||
|
* (positions restart at ~4 in each new file), so `backlogBytes` and `percent`
|
||||||
|
* are null and `sameFile` says why.
|
||||||
|
*/
|
||||||
|
export interface ApplyProgress {
|
||||||
|
/** Source binlog file the I/O thread is currently reading. */
|
||||||
|
sourceLogFile: string | null;
|
||||||
|
/** Position in `sourceLogFile` that the I/O thread has fetched up to. */
|
||||||
|
readPos: number;
|
||||||
|
/** Source binlog file the SQL thread is currently applying. */
|
||||||
|
relayLogFile: string | null;
|
||||||
|
/** Position in `relayLogFile` that the SQL thread has applied up to. */
|
||||||
|
execPos: number;
|
||||||
|
/** True while both threads are on the same source file. */
|
||||||
|
sameFile: boolean;
|
||||||
|
/** Fetched-but-not-yet-applied bytes. Null when the files differ. */
|
||||||
|
backlogBytes: number | null;
|
||||||
|
/**
|
||||||
|
* `execPos / readPos` as a percentage, null when the files differ.
|
||||||
|
*
|
||||||
|
* Deliberately never rounded up to 100 while any backlog remains: binlog
|
||||||
|
* positions are large, so a real backlog of a few KB is 99.99% of the file
|
||||||
|
* and would render as "caught up" when it is not. Read `backlogBytes === 0`
|
||||||
|
* for actually caught up.
|
||||||
|
*/
|
||||||
|
percent: number | null;
|
||||||
|
}
|
||||||
|
|
||||||
export interface ReplicationStatus {
|
export interface ReplicationStatus {
|
||||||
/** false when the replica is not configured for this environment at all. */
|
/** false when the replica is not configured for this environment at all. */
|
||||||
configured: boolean;
|
configured: boolean;
|
||||||
@@ -17,6 +56,8 @@ export interface ReplicationStatus {
|
|||||||
lastIoError: string | null;
|
lastIoError: string | null;
|
||||||
lastSqlError: string | null;
|
lastSqlError: string | null;
|
||||||
sourceHost: string | null;
|
sourceHost: string | null;
|
||||||
|
/** Relay-log apply progress. Null when the status output has no positions. */
|
||||||
|
apply: ApplyProgress | null;
|
||||||
/** Human-readable reason when healthy is false. */
|
/** Human-readable reason when healthy is false. */
|
||||||
problem: string | null;
|
problem: string | null;
|
||||||
checkedAt: string;
|
checkedAt: string;
|
||||||
@@ -57,6 +98,7 @@ export class ReplicationService {
|
|||||||
lastIoError: null,
|
lastIoError: null,
|
||||||
lastSqlError: null,
|
lastSqlError: null,
|
||||||
sourceHost: null,
|
sourceHost: null,
|
||||||
|
apply: null,
|
||||||
problem: null,
|
problem: null,
|
||||||
checkedAt: now,
|
checkedAt: now,
|
||||||
};
|
};
|
||||||
@@ -142,12 +184,60 @@ export class ReplicationService {
|
|||||||
lastIoError,
|
lastIoError,
|
||||||
lastSqlError,
|
lastSqlError,
|
||||||
sourceHost: field("Source_Host"),
|
sourceHost: field("Source_Host"),
|
||||||
|
// Reported, never folded into `healthy`: a non-zero backlog is the normal
|
||||||
|
// state of a working replica for the instant between fetch and apply, so
|
||||||
|
// alarming on it would cry wolf. It is here to answer "is it moving?"
|
||||||
|
// when the lag counter is stuck.
|
||||||
|
apply: applyProgress(raw),
|
||||||
problem,
|
problem,
|
||||||
checkedAt: now,
|
checkedAt: now,
|
||||||
};
|
};
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Derive relay-apply progress from `SHOW REPLICA STATUS\G` output.
|
||||||
|
*
|
||||||
|
* Exported for testing. Free in query terms — it re-reads four more fields from
|
||||||
|
* the output the caller already has, with no second round trip to the replica
|
||||||
|
* and no connection to the source.
|
||||||
|
*
|
||||||
|
* @returns null when either position is missing or unparseable, which is what
|
||||||
|
* happens on a server that is not a replica at all.
|
||||||
|
*/
|
||||||
|
export function applyProgress(raw: string): ApplyProgress | null {
|
||||||
|
const num = (name: string): number | null => {
|
||||||
|
const v = replicaField(raw, name);
|
||||||
|
if (v === null || v === "NULL") return null;
|
||||||
|
const n = Number(v);
|
||||||
|
return Number.isFinite(n) ? n : null;
|
||||||
|
};
|
||||||
|
|
||||||
|
const readPos = num("Read_Source_Log_Pos");
|
||||||
|
const execPos = num("Exec_Source_Log_Pos");
|
||||||
|
if (readPos === null || execPos === null) return null;
|
||||||
|
|
||||||
|
const sourceLogFile = replicaField(raw, "Source_Log_File");
|
||||||
|
const relayLogFile = replicaField(raw, "Relay_Source_Log_File");
|
||||||
|
const sameFile =
|
||||||
|
sourceLogFile !== null && relayLogFile !== null && sourceLogFile === relayLogFile;
|
||||||
|
|
||||||
|
// Clamped at 0: the SQL thread cannot be ahead of the I/O thread, but the two
|
||||||
|
// fields are sampled independently, so a rotation racing this read can print
|
||||||
|
// a momentarily negative delta. Zero is the honest floor, not a bug.
|
||||||
|
const backlogBytes = sameFile ? Math.max(0, readPos - execPos) : null;
|
||||||
|
|
||||||
|
let percent: number | null = null;
|
||||||
|
if (backlogBytes !== null && readPos > 0) {
|
||||||
|
// Truncate rather than round, and hold short of 100 while bytes remain —
|
||||||
|
// see the doc on ApplyProgress.percent.
|
||||||
|
const p = Math.floor((execPos / readPos) * 10_000) / 100;
|
||||||
|
percent = backlogBytes === 0 ? 100 : Math.min(p, 99.99);
|
||||||
|
}
|
||||||
|
|
||||||
|
return { sourceLogFile, readPos, relayLogFile, execPos, sameFile, backlogBytes, percent };
|
||||||
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Read one field out of `SHOW REPLICA STATUS\G` output.
|
* Read one field out of `SHOW REPLICA STATUS\G` output.
|
||||||
*
|
*
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
import { replicaField } from "./replication.service";
|
import { applyProgress, replicaField } from "./replication.service";
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Verbatim shape of `SHOW REPLICA STATUS\G` from the live replica, trimmed to
|
* Verbatim shape of `SHOW REPLICA STATUS\G` from the live replica, trimmed to
|
||||||
@@ -13,6 +13,10 @@ const HEALTHY = [
|
|||||||
" Replica_IO_State: Waiting for source to send event",
|
" Replica_IO_State: Waiting for source to send event",
|
||||||
" Source_Host: 100.103.77.46",
|
" Source_Host: 100.103.77.46",
|
||||||
" Source_User: repl",
|
" Source_User: repl",
|
||||||
|
" Source_Log_File: binlog.000042",
|
||||||
|
" Read_Source_Log_Pos: 194884231",
|
||||||
|
" Relay_Source_Log_File: binlog.000042",
|
||||||
|
" Exec_Source_Log_Pos: 194884231",
|
||||||
" Replica_IO_Running: Yes",
|
" Replica_IO_Running: Yes",
|
||||||
" Replica_SQL_Running: Yes",
|
" Replica_SQL_Running: Yes",
|
||||||
" Replicate_Do_DB: ",
|
" Replicate_Do_DB: ",
|
||||||
@@ -85,3 +89,92 @@ describe("replicaField", () => {
|
|||||||
expect(replicaField(raw, "Last_SQL_Error")).toBe("boom");
|
expect(replicaField(raw, "Last_SQL_Error")).toBe("boom");
|
||||||
});
|
});
|
||||||
});
|
});
|
||||||
|
|
||||||
|
/** Builds the four position fields the apply-progress reader cares about. */
|
||||||
|
function positions(
|
||||||
|
sourceFile: string,
|
||||||
|
readPos: number | string,
|
||||||
|
relayFile: string,
|
||||||
|
execPos: number | string,
|
||||||
|
): string {
|
||||||
|
return [
|
||||||
|
` Source_Log_File: ${sourceFile}`,
|
||||||
|
` Read_Source_Log_Pos: ${readPos}`,
|
||||||
|
` Relay_Source_Log_File: ${relayFile}`,
|
||||||
|
` Exec_Source_Log_Pos: ${execPos}`,
|
||||||
|
].join("\n");
|
||||||
|
}
|
||||||
|
|
||||||
|
describe("applyProgress", () => {
|
||||||
|
it("reports zero backlog and 100% when both positions match", () => {
|
||||||
|
const p = applyProgress(HEALTHY)!;
|
||||||
|
expect(p.sameFile).toBe(true);
|
||||||
|
expect(p.sourceLogFile).toBe("binlog.000042");
|
||||||
|
expect(p.readPos).toBe(194884231);
|
||||||
|
expect(p.execPos).toBe(194884231);
|
||||||
|
expect(p.backlogBytes).toBe(0);
|
||||||
|
expect(p.percent).toBe(100);
|
||||||
|
});
|
||||||
|
|
||||||
|
it("reports the byte delta when the SQL thread trails inside one file", () => {
|
||||||
|
const p = applyProgress(positions("binlog.000042", 2_000_000, "binlog.000042", 1_500_000))!;
|
||||||
|
expect(p.backlogBytes).toBe(500_000);
|
||||||
|
expect(p.percent).toBe(75);
|
||||||
|
});
|
||||||
|
|
||||||
|
/**
|
||||||
|
* The reason the byte delta exists at all. `Seconds_Behind_Source` holds at 0
|
||||||
|
* while the SQL thread is mid-transaction, so the backlog is the only field
|
||||||
|
* that moves — and the only one that says the replica is not caught up.
|
||||||
|
*/
|
||||||
|
it("shows a backlog even when the lag counter reads zero", () => {
|
||||||
|
const raw = [
|
||||||
|
" Seconds_Behind_Source: 0",
|
||||||
|
positions("binlog.000042", 900, "binlog.000042", 400),
|
||||||
|
].join("\n");
|
||||||
|
expect(replicaField(raw, "Seconds_Behind_Source")).toBe("0");
|
||||||
|
expect(applyProgress(raw)!.backlogBytes).toBe(500);
|
||||||
|
});
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Positions restart near 4 in every new binlog file, so subtracting across
|
||||||
|
* files produces a number that is not a backlog — here it would be a large
|
||||||
|
* NEGATIVE one, which would render as "ahead of the source".
|
||||||
|
*/
|
||||||
|
it("refuses to compare positions across different binlog files", () => {
|
||||||
|
const p = applyProgress(positions("binlog.000043", 500, "binlog.000042", 194_000_000))!;
|
||||||
|
expect(p.sameFile).toBe(false);
|
||||||
|
expect(p.backlogBytes).toBeNull();
|
||||||
|
expect(p.percent).toBeNull();
|
||||||
|
expect(p.sourceLogFile).toBe("binlog.000043");
|
||||||
|
expect(p.relayLogFile).toBe("binlog.000042");
|
||||||
|
});
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Percent must not round up to 100 while bytes remain: binlog positions are
|
||||||
|
* large, so a genuine backlog is a rounding error away from the whole file
|
||||||
|
* and would otherwise render as "caught up" on a replica that is not.
|
||||||
|
*/
|
||||||
|
it("stops short of 100% while any backlog remains", () => {
|
||||||
|
const p = applyProgress(positions("binlog.000042", 194_884_231, "binlog.000042", 194_884_230))!;
|
||||||
|
expect(p.backlogBytes).toBe(1);
|
||||||
|
expect(p.percent).toBe(99.99);
|
||||||
|
});
|
||||||
|
|
||||||
|
/** Sampled independently, so a rotation racing the read can invert them. */
|
||||||
|
it("clamps a momentarily negative delta to zero", () => {
|
||||||
|
const p = applyProgress(positions("binlog.000042", 400, "binlog.000042", 500))!;
|
||||||
|
expect(p.backlogBytes).toBe(0);
|
||||||
|
expect(p.percent).toBe(100);
|
||||||
|
});
|
||||||
|
|
||||||
|
it("returns null when the server is not a replica and prints no positions", () => {
|
||||||
|
expect(applyProgress("")).toBeNull();
|
||||||
|
expect(applyProgress(BROKEN)).toBeNull();
|
||||||
|
});
|
||||||
|
|
||||||
|
/** A stopped thread makes MySQL print NULL, which is not a position. */
|
||||||
|
it("returns null when a position is NULL", () => {
|
||||||
|
expect(applyProgress(positions("binlog.000042", "NULL", "binlog.000042", 400))).toBeNull();
|
||||||
|
});
|
||||||
|
});
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"name": "@jorgecuadros/web",
|
"name": "@jorgecuadros/web",
|
||||||
"version": "1.0.11",
|
"version": "1.0.13",
|
||||||
"private": true,
|
"private": true,
|
||||||
"scripts": {
|
"scripts": {
|
||||||
"dev": "next dev -p 4500",
|
"dev": "next dev -p 4500",
|
||||||
|
|||||||
@@ -23,6 +23,7 @@ import {
|
|||||||
} from "@/lib/api";
|
} from "@/lib/api";
|
||||||
import type { UploadProgress } from "@/lib/api";
|
import type { UploadProgress } from "@/lib/api";
|
||||||
import type {
|
import type {
|
||||||
|
ApplyProgress,
|
||||||
BackupFile,
|
BackupFile,
|
||||||
IngestFile,
|
IngestFile,
|
||||||
OpsJob,
|
OpsJob,
|
||||||
@@ -685,8 +686,58 @@ function ReplicationCard() {
|
|||||||
label="Retraso"
|
label="Retraso"
|
||||||
value={status.secondsBehind === null ? "sin dato" : `${status.secondsBehind} s`}
|
value={status.secondsBehind === null ? "sin dato" : `${status.secondsBehind} s`}
|
||||||
/>
|
/>
|
||||||
|
<KV label="Pendiente de aplicar" value={backlogLabel(status.apply)} />
|
||||||
<KV label="Consultado" value={formatDateTime(status.checkedAt)} />
|
<KV label="Consultado" value={formatDateTime(status.checkedAt)} />
|
||||||
</div>
|
</div>
|
||||||
|
|
||||||
|
<ApplyProgressBar apply={status.apply} />
|
||||||
|
</div>
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Bytes the replica has fetched but not yet applied.
|
||||||
|
*
|
||||||
|
* Kept separate from the lag figure because it answers a question the lag
|
||||||
|
* cannot: while the SQL thread chews through one big transaction, the seconds
|
||||||
|
* counter can hold still, but this number visibly falls.
|
||||||
|
*/
|
||||||
|
function backlogLabel(apply: ApplyProgress | null): string {
|
||||||
|
if (!apply) return "sin dato";
|
||||||
|
// Different source binlog files means the replica is whole files behind and
|
||||||
|
// the byte delta is not a delta at all — positions restart in each new file.
|
||||||
|
if (!apply.sameFile) return "más de un archivo de binlog";
|
||||||
|
if (apply.backlogBytes === 0) return "al día";
|
||||||
|
return formatBytes(apply.backlogBytes);
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Applied-vs-fetched bar. Rendered only when both threads are on the same
|
||||||
|
* source binlog file, because that is the only case where the percentage is
|
||||||
|
* arithmetic rather than a guess.
|
||||||
|
*/
|
||||||
|
function ApplyProgressBar({ apply }: { apply: ApplyProgress | null }) {
|
||||||
|
if (!apply || !apply.sameFile || apply.percent === null) return null;
|
||||||
|
|
||||||
|
return (
|
||||||
|
<div className="upload-progress" style={{ marginTop: 12 }}>
|
||||||
|
<div
|
||||||
|
className="progress-track"
|
||||||
|
role="progressbar"
|
||||||
|
aria-valuenow={apply.percent}
|
||||||
|
aria-valuemin={0}
|
||||||
|
aria-valuemax={100}
|
||||||
|
aria-label="Eventos aplicados de los recibidos"
|
||||||
|
>
|
||||||
|
<div className="progress-fill" style={{ width: `${apply.percent}%` }} />
|
||||||
|
</div>
|
||||||
|
<div className="upload-progress-stats mono">
|
||||||
|
<span>{apply.percent}% aplicado</span>
|
||||||
|
<span>
|
||||||
|
{apply.sourceLogFile} · {apply.execPos.toLocaleString("es-MX")} /{" "}
|
||||||
|
{apply.readPos.toLocaleString("es-MX")}
|
||||||
|
</span>
|
||||||
|
</div>
|
||||||
</div>
|
</div>
|
||||||
);
|
);
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -99,10 +99,32 @@ export interface ReplicationStatus {
|
|||||||
lastIoError: string | null;
|
lastIoError: string | null;
|
||||||
lastSqlError: string | null;
|
lastSqlError: string | null;
|
||||||
sourceHost: string | null;
|
sourceHost: string | null;
|
||||||
|
apply: ApplyProgress | null;
|
||||||
problem: string | null;
|
problem: string | null;
|
||||||
checkedAt: string;
|
checkedAt: string;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Relay-log apply progress, in source binlog bytes.
|
||||||
|
*
|
||||||
|
* Answers "is it moving?" when `secondsBehind` cannot: the lag counter sits
|
||||||
|
* still while the SQL thread works through one large transaction, but the
|
||||||
|
* backlog visibly shrinks. `backlogBytes === 0` is the only reading that means
|
||||||
|
* caught up — `percent` deliberately stops at 99.99 while bytes remain.
|
||||||
|
*
|
||||||
|
* Null fields when the two threads are on different source binlog files
|
||||||
|
* (`sameFile === false`), because the positions are then not comparable.
|
||||||
|
*/
|
||||||
|
export interface ApplyProgress {
|
||||||
|
sourceLogFile: string | null;
|
||||||
|
readPos: number;
|
||||||
|
relayLogFile: string | null;
|
||||||
|
execPos: number;
|
||||||
|
sameFile: boolean;
|
||||||
|
backlogBytes: number | null;
|
||||||
|
percent: number | null;
|
||||||
|
}
|
||||||
|
|
||||||
/** One of the four legacy Access files expected in the ingest folder. */
|
/** One of the four legacy Access files expected in the ingest folder. */
|
||||||
export interface IngestFile {
|
export interface IngestFile {
|
||||||
name: string;
|
name: string;
|
||||||
|
|||||||
+17
-5
@@ -15,6 +15,11 @@ Then:
|
|||||||
./.venv/bin/python run_all.py --env dev # data only (staging already present)
|
./.venv/bin/python run_all.py --env dev # data only (staging already present)
|
||||||
./.venv/bin/python run_all.py --env prod --stage # re-extract from Access first, then load
|
./.venv/bin/python run_all.py --env prod --stage # re-extract from Access first, then load
|
||||||
|
|
||||||
|
--sync swaps the truncate+rebuild steps for the additive upsert ones. It reads
|
||||||
|
the same staged Parquet, so it needs --stage too unless a previous run left
|
||||||
|
migration/output populated on this machine — which is never true in a
|
||||||
|
container, where that directory is part of the image and dies with it.
|
||||||
|
|
||||||
Reproducing dev -> prod is exactly `--env prod` (plus --stage if the staged
|
Reproducing dev -> prod is exactly `--env prod` (plus --stage if the staged
|
||||||
Parquet isn't present on the machine running it).
|
Parquet isn't present on the machine running it).
|
||||||
|
|
||||||
@@ -100,15 +105,22 @@ def main() -> None:
|
|||||||
help="upsert legacy rows and archive removed legacy rows; preserve manual rows")
|
help="upsert legacy rows and archive removed legacy rows; preserve manual rows")
|
||||||
args = ap.parse_args()
|
args = ap.parse_args()
|
||||||
|
|
||||||
if args.stage:
|
|
||||||
run([PY, str(HERE / "load_staging.py"), "--output-dir", str(HERE / "output")])
|
|
||||||
|
|
||||||
steps = SYNC_STEPS if args.sync else STEPS
|
steps = SYNC_STEPS if args.sync else STEPS
|
||||||
for i, step in enumerate(steps, start=1):
|
# Staging counts as a step when it runs: it is the slowest part of the pass
|
||||||
|
# (mdbtools re-reads every Access file), so leaving it outside the numbering
|
||||||
|
# would park the Operaciones progress bar at "nothing yet" for minutes.
|
||||||
|
total = len(steps) + (1 if args.stage else 0)
|
||||||
|
offset = 1 if args.stage else 0
|
||||||
|
|
||||||
|
if args.stage:
|
||||||
|
run([PY, str(HERE / "load_staging.py"), "--output-dir", str(HERE / "output")],
|
||||||
|
step=1, total=total)
|
||||||
|
|
||||||
|
for i, step in enumerate(steps, start=1 + offset):
|
||||||
cmd = [PY, str(HERE / step), "--env", args.env]
|
cmd = [PY, str(HERE / step), "--env", args.env]
|
||||||
if args.sync:
|
if args.sync:
|
||||||
cmd.append("--sync")
|
cmd.append("--sync")
|
||||||
run(cmd, step=i, total=len(steps))
|
run(cmd, step=i, total=total)
|
||||||
|
|
||||||
print(f"\n✓ migration complete for env={args.env}")
|
print(f"\n✓ migration complete for env={args.env}")
|
||||||
|
|
||||||
|
|||||||
+1
-1
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"name": "jorgecuadros-platform",
|
"name": "jorgecuadros-platform",
|
||||||
"version": "1.0.11",
|
"version": "1.0.13",
|
||||||
"private": true,
|
"private": true,
|
||||||
"workspaces": [
|
"workspaces": [
|
||||||
"apps/*",
|
"apps/*",
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"name": "@jorgecuadros/database",
|
"name": "@jorgecuadros/database",
|
||||||
"version": "1.0.11",
|
"version": "1.0.13",
|
||||||
"private": true,
|
"private": true,
|
||||||
"main": "generated/client/index.js",
|
"main": "generated/client/index.js",
|
||||||
"types": "generated/client/index.d.ts",
|
"types": "generated/client/index.d.ts",
|
||||||
|
|||||||
Reference in New Issue
Block a user