시장 데이터 타임스탬프: SIP와 거래소 시각 비교

WITH venues AS
(
    SELECT
        toUInt32(id)                             AS exchange_id,
        any(coalesce(nullIf(acronym, ''), name)) AS venue_name
    FROM global_markets.stocks_exchanges
    WHERE asset_class = 'stocks'
    GROUP BY exchange_id
)
SELECT
    if(v.venue_name = '', concat('Venue ', toString(t.exchange)), v.venue_name) AS venue,
    count()                                                                     AS print_count,
    round(quantileDeterministic(0.5)(
        toFloat64(toUnixTimestamp64Nano(t.sip_timestamp)
                - toUnixTimestamp64Nano(t.participant_timestamp)) / 1000,
        toUInt64(t.sequence_number)), 1)                                        AS median_lag_us,
    round(quantileDeterministic(0.99)(
        toFloat64(toUnixTimestamp64Nano(t.sip_timestamp)
                - toUnixTimestamp64Nano(t.participant_timestamp)) / 1000,
        toUInt64(t.sequence_number)), 1)                                        AS p99_lag_us
FROM global_markets.stocks_trades AS t
LEFT JOIN venues AS v ON v.exchange_id = toUInt32(t.exchange)
WHERE t.ticker = 'AAPL'
  AND t.sip_timestamp >= '2026-06-10 14:30:00'
  AND t.sip_timestamp <  '2026-06-10 15:00:00'
  AND ifNull(toUnixTimestamp64Nano(t.trf_timestamp), 0) = 0
GROUP BY venue
HAVING count() >= 200
ORDER BY median_lag_us DESC
LIMIT 15

WITH
    burst AS
    (
        SELECT intDiv(toUnixTimestamp64Nano(participant_timestamp), 10000000) AS slice_10ms
        FROM global_markets.stocks_trades
        WHERE ticker = 'AAPL'
          AND sip_timestamp >= '2026-06-10 14:30:00'
          AND sip_timestamp <  '2026-06-10 15:00:00'
          AND ifNull(toUnixTimestamp64Nano(trf_timestamp), 0) = 0
        GROUP BY slice_10ms
        ORDER BY count() DESC, slice_10ms ASC
        LIMIT 1
    ),
    sample AS
    (
        SELECT
            participant_timestamp,
            sip_timestamp,
            toUInt64(sequence_number) AS seq,
            toUnixTimestamp64Nano(sip_timestamp)
              - toUnixTimestamp64Nano(participant_timestamp) AS lag_ns
        FROM global_markets.stocks_trades
        WHERE ticker = 'AAPL'
          AND sip_timestamp >= '2026-06-10 14:30:00'
          AND sip_timestamp <  '2026-06-10 15:00:00'
          AND ifNull(toUnixTimestamp64Nano(trf_timestamp), 0) = 0
          AND intDiv(toUnixTimestamp64Nano(participant_timestamp), 10000000)
              IN (SELECT slice_10ms FROM burst)
        ORDER BY participant_timestamp ASC, seq ASC
        LIMIT 12
    ),
    ranked AS
    (
        SELECT
            participant_timestamp,
            sip_timestamp,
            lag_ns,
            row_number() OVER (ORDER BY participant_timestamp ASC, seq ASC) AS participant_rank,
            row_number() OVER (ORDER BY sip_timestamp ASC, seq ASC)         AS sip_rank
        FROM sample
    )
SELECT
    concat('P', leftPad(toString(participant_rank), 2, '0')) AS print_label,
    concat(formatDateTime(toTimeZone(participant_timestamp, 'America/New_York'), '%H:%i:%S'), '.',
           leftPad(toString(intDiv(toUnixTimestamp64Nano(participant_timestamp) % 1000000000, 1000)), 6, '0')) AS venue_clock_et,
    concat(formatDateTime(toTimeZone(sip_timestamp, 'America/New_York'), '%H:%i:%S'), '.',
           leftPad(toString(intDiv(toUnixTimestamp64Nano(sip_timestamp) % 1000000000, 1000)), 6, '0'))         AS tape_clock_et,
    participant_rank,
    sip_rank,
    abs(toInt32(sip_rank) - toInt32(participant_rank)) AS places_moved,
    round(lag_ns / 1000, 1)                            AS sip_lag_delta_us
FROM ranked
ORDER BY places_moved DESC, participant_rank ASC

WITH off_exchange AS
(
    SELECT
        (toUnixTimestamp64Nano(sip_timestamp)
       - toUnixTimestamp64Nano(participant_timestamp)) / 1000000.0 AS delay_ms
    FROM global_markets.stocks_trades
    WHERE ticker = 'AAPL'
      AND sip_timestamp >= '2026-06-10 14:30:00'
      AND sip_timestamp <  '2026-06-10 15:00:00'
      AND ifNull(toUnixTimestamp64Nano(trf_timestamp), 0) > 0
)
SELECT
    multiIf(delay_ms <     1, 'under 1 ms',
            delay_ms <    10, '1 to 10 ms',
            delay_ms <   100, '10 to 100 ms',
            delay_ms <  1000, '100 ms to 1 s',
            delay_ms < 10000, '1 s to 10 s',
                              'over 10 s')                       AS reporting_delay,
    count()                                                      AS print_count,
    round(100 * count() / (SELECT count() FROM off_exchange), 2) AS share_pct
FROM off_exchange
GROUP BY reporting_delay
ORDER BY min(delay_ms) ASC

WITH
    prints AS
    (
        SELECT
            toUnixTimestamp64Nano(participant_timestamp) AS venue_ns,
            toUnixTimestamp64Nano(sip_timestamp)         AS tape_ns
        FROM global_markets.stocks_trades
        WHERE ticker = 'AAPL'
          AND sip_timestamp >= '2026-06-10 14:30:00'
          AND sip_timestamp <  '2026-06-10 15:00:00'
    ),
    grids AS
    (
        SELECT arrayJoin([1, 10, 60, 300]) AS bar_seconds
    )
SELECT
    multiIf(bar_seconds =  1, '1 second',
            bar_seconds = 10, '10 seconds',
            bar_seconds = 60, '1 minute',
                              '5 minutes') AS bar_length,
    countIf(intDiv(venue_ns, toInt64(bar_seconds) * 1000000000)
         != intDiv(tape_ns,  toInt64(bar_seconds) * 1000000000)) AS moved_print_count,
    round(100 * countIf(intDiv(venue_ns, toInt64(bar_seconds) * 1000000000)
                     != intDiv(tape_ns,  toInt64(bar_seconds) * 1000000000)) / count(), 3) AS moved_pct
FROM prints
CROSS JOIN grids
GROUP BY bar_seconds
ORDER BY bar_seconds ASC