How to improve PostgreSQL performance on INSERT?

I wrote a Node.js application that writes many records to a PostgreSQL 9.6 database. Unfortunately, this is rather slow. To verify that I created a short but complete program that plays the script:

'use strict';

const async = require('async'),
      pg = require('pg'),
      uuid = require('uuidv4');

const pool = new pg.Pool({
  protocol: 'pg',
  user: 'golo',
  host: 'localhost',
  port: 5432,
  database: 'golo'
});

const records = [];

for (let i = 0; i < 10000; i++) {
  records.push({ id: uuid(), revision: i, data: { foo: 'bar', bar: 'baz' }, flag: true });
}

pool.connect((err, database, close) => {
  if (err) {
    /* eslint-disable no-console */
    return console.log(err);
    /* eslint-enable no-console */
  }

  database.query(`
    CREATE TABLE IF NOT EXISTS "foo" (
      "position" bigserial NOT NULL,
      "id" uuid NOT NULL,
      "revision" integer NOT NULL,
      "data" jsonb NOT NULL,
      "flag" boolean NOT NULL,

      CONSTRAINT "foo_pk" PRIMARY KEY("position"),
      CONSTRAINT "foo_index_id_revision" UNIQUE ("id", "revision")
    );
  `, errQuery => {
    if (errQuery) {
      /* eslint-disable no-console */
      return console.log(errQuery);
      /* eslint-enable no-console */
    }

    async.series({
      beginTransaction (done) {
        /* eslint-disable no-console */
        console.time('foo');
        /* eslint-enable no-console */
        database.query('BEGIN', done);
      },
      saveRecords (done) {
        async.eachSeries(records, (record, doneEach) => {
          database.query({
            name: 'save',
            text: `
              INSERT INTO "foo"
                ("id", "revision", "data", "flag")
              VALUES
                ($1, $2, $3, $4) RETURNING position;
            `,
            values: [ record.id, record.revision, record.data, record.flag ]
          }, (errQuery2, result) => {
            if (errQuery2) {
              return doneEach(errQuery2);
            }

            record.position = Number(result.rows[0].position);
            doneEach(null);
          });
        }, done);
      },
      commitTransaction (done) {
        database.query('COMMIT', done);
      }
    }, errSeries => {
      /* eslint-disable no-console */
      console.timeEnd('foo');
      /* eslint-enable no-console */
      if (errSeries) {
        return database.query('ROLLBACK', errRollback => {
          close();

          if (errRollback) {
            /* eslint-disable no-console */
            return console.log(errRollback);
            /* eslint-enable no-console */
          }
          /* eslint-disable no-console */
          console.log(errSeries);
          /* eslint-enable no-console */
        });
      }

      close();
      /* eslint-disable no-console */
      console.log('Done!');
      /* eslint-enable no-console */
    });
  });
});

The performance that I get to insert 10,000 rows is 2.5 seconds. This is not bad, but not very. What can I do to increase speed?

Some thoughts that I have had so far:

  • Use prepared statements. As you can see, I did this, it accelerated things by ~ 30%.
  • INSERT. , , , , , .
  • COPY INSERT: , , .
  • text jsonb: .
  • json jsonb: .

, :

  • revision . .
  • flag true, true false.
  • , data .

, :

  • INSERT?
+4
1

INSERT. , , , , , .

, -.

1000 - 10 000 .

.

. . : .

10 000 50 .

: pg-.

+3

Source: https://habr.com/ru/post/1663394/


All Articles