diff options
Diffstat (limited to 'db')
| -rw-r--r-- | db/migrate/20170920024819_status_ids_to_timestamp_ids.rb | 32 | ||||
| -rw-r--r-- | db/migrate/20170920032311_fix_reblogs_in_feeds.rb | 63 | ||||
| -rw-r--r-- | db/schema.rb | 2 |
3 files changed, 96 insertions, 1 deletions
diff --git a/db/migrate/20170920024819_status_ids_to_timestamp_ids.rb b/db/migrate/20170920024819_status_ids_to_timestamp_ids.rb new file mode 100644 index 000000000..5d15817bd --- /dev/null +++ b/db/migrate/20170920024819_status_ids_to_timestamp_ids.rb @@ -0,0 +1,32 @@ +class StatusIdsToTimestampIds < ActiveRecord::Migration[5.1] + def up + # Prepare the function we will use to generate IDs. + Rake::Task['db:define_timestamp_id'].execute + + # Set up the statuses.id column to use our timestamp-based IDs. + ActiveRecord::Base.connection.execute(<<~SQL) + ALTER TABLE statuses + ALTER COLUMN id + SET DEFAULT timestamp_id('statuses') + SQL + + # Make sure we have a sequence to use. + Rake::Task['db:ensure_id_sequences_exist'].execute + end + + def down + # Revert the column to the old method of just using the sequence + # value for new IDs. Set the current ID sequence to the maximum + # existing ID, such that the next sequence will be one higher. + + # We lock the table during this so that the ID won't get clobbered, + # but ID is indexed, so this should be a fast operation. + ActiveRecord::Base.connection.execute(<<~SQL) + LOCK statuses; + SELECT setval('statuses_id_seq', (SELECT MAX(id) FROM statuses)); + ALTER TABLE statuses + ALTER COLUMN id + SET DEFAULT nextval('statuses_id_seq');" + SQL + end +end diff --git a/db/migrate/20170920032311_fix_reblogs_in_feeds.rb b/db/migrate/20170920032311_fix_reblogs_in_feeds.rb new file mode 100644 index 000000000..c813ecd46 --- /dev/null +++ b/db/migrate/20170920032311_fix_reblogs_in_feeds.rb @@ -0,0 +1,63 @@ +class FixReblogsInFeeds < ActiveRecord::Migration[5.1] + def up + redis = Redis.current + fm = FeedManager.instance + + # find_each is batched on the database side. + User.includes(:account).find_each do |user| + account = user.account + + # Old scheme: + # Each user's feed zset had a series of score:value entries, + # where "regular" statuses had the same score and value (their + # ID). Reblogs had a score of the reblogging status' ID, and a + # value of the reblogged status' ID. + + # New scheme: + # The feed contains only entries with the same score and value. + # Reblogs result in the reblogging status being added to the + # feed, with an entry in a reblog tracking zset (where the score + # is once again set to the reblogging status' ID, and the value + # is set to the reblogged status' ID). This is safe for Redis' + # float coersion because in this reblog tracking zset, we only + # need the rebloggging status' ID to be able to stop tracking + # entries after they have gotten too far down the feed, which + # does not require an exact value. + + # So, first, we iterate over the user's feed to find any reblogs. + timeline_key = fm.key(:home, account.id) + reblog_key = fm.key(:home, account.id, 'reblogs') + redis.zrange(timeline_key, 0, -1, with_scores: true).each do |entry| + next if entry[0] == entry[1] + + # The score and value don't match, so this is a reblog. + # (note that we're transitioning from IDs < 53 bits so we + # don't have to worry about the loss of precision) + + reblogged_id, reblogging_id = entry + + # Remove the old entry + redis.zrem(timeline_key, reblogged_id) + + # Add a new one for the reblogging status + redis.zadd(timeline_key, reblogging_id, reblogging_id) + + # Track the fact that this was a reblog + redis.zadd(reblog_key, reblogging_id, reblogged_id) + end + end + end + + def down + # We *deliberately* do nothing here. This means that reverting + # this and the associated changes to the FeedManager code could + # allow one superfluous reblog of any given status, but in the case + # where things have gone wrong and a revert is necessary, this + # appears preferable to requiring a database hit for every status + # in every users' feed simply to revert. + + # Note that this is operating under the assumption that entries + # with >53-bit IDs have already been entered. Otherwise, we could + # just use the data in Redis to reverse this transition. + end +end diff --git a/db/schema.rb b/db/schema.rb index 2cb105553..00cc24bae 100644 --- a/db/schema.rb +++ b/db/schema.rb @@ -321,7 +321,7 @@ ActiveRecord::Schema.define(version: 20170927215609) do t.index ["account_id", "status_id"], name: "index_status_pins_on_account_id_and_status_id", unique: true end - create_table "statuses", force: :cascade do |t| + create_table "statuses", id: :bigint, default: -> { "timestamp_id('statuses'::text)" }, force: :cascade do |t| t.string "uri" t.text "text", default: "", null: false t.datetime "created_at", null: false |