48 lines
1.5 KiB
Go
48 lines
1.5 KiB
Go
package main
|
|
|
|
import (
|
|
"context"
|
|
"time"
|
|
|
|
"github.com/jackc/pgx/v5/pgxpool"
|
|
)
|
|
|
|
type HostRow struct {
|
|
ID int64
|
|
Hostname string
|
|
Protocol string
|
|
HtmlTitle string
|
|
IframeAllowed bool
|
|
BestIconHash string
|
|
RandomOrder float64
|
|
IconDownloadedAt *time.Time
|
|
}
|
|
|
|
// fetchHostsPage gets a page of hosts with titles, ordered by icon_downloaded_at for disk locality.
|
|
// Icons written to disk at similar times are physically adjacent — reading in write order
|
|
// maximizes OS readahead cache hits. Hosts without icons come last (no disk reads needed).
|
|
// random_order is included for bundle bucket assignment (randomized bundles).
|
|
func fetchHostsPage(ctx context.Context, pool *pgxpool.Pool, lastDownloaded *time.Time, lastID int64, limit int) ([]HostRow, error) {
|
|
rows, err := pool.Query(ctx, `
|
|
SELECT id, hostname, protocol, html_title, COALESCE(iframe_allowed, true), COALESCE(best_icon_hash, ''), random_order, icon_downloaded_at
|
|
FROM hosts
|
|
WHERE html_title IS NOT NULL
|
|
AND (icon_downloaded_at, id) > ($1, $2)
|
|
ORDER BY icon_downloaded_at NULLS LAST, id
|
|
LIMIT $3
|
|
`, lastDownloaded, lastID, limit)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer rows.Close()
|
|
|
|
var hosts []HostRow
|
|
for rows.Next() {
|
|
var h HostRow
|
|
if err := rows.Scan(&h.ID, &h.Hostname, &h.Protocol, &h.HtmlTitle, &h.IframeAllowed, &h.BestIconHash, &h.RandomOrder, &h.IconDownloadedAt); err != nil {
|
|
return nil, err
|
|
}
|
|
hosts = append(hosts, h)
|
|
}
|
|
return hosts, rows.Err()
|
|
}
|