Scale unique answer tracking

This commit is contained in:
hz
2026-07-13 02:11:54 -05:00
parent 700da4e415
commit f2c59388eb
23 changed files with 1064 additions and 131 deletions
@@ -0,0 +1,251 @@
using MongoDB.Driver;
using QuestionsApi.Models;
using System.Collections.Concurrent;
namespace QuestionsApi.Services;
public sealed class AnswerStatisticsStore
{
private const string StateId = "answer-statistics-v1";
private static readonly TimeSpan CacheDuration = TimeSpan.FromMinutes(5);
private readonly IMongoCollection<QuestionAttemptCounter> _counters;
private readonly IMongoCollection<AnswerStatisticsState> _state;
private readonly QuestionAttemptStore _attempts;
private readonly ConcurrentDictionary<string, CachedPercentages> _cache = new();
private volatile bool _backfillComplete;
public AnswerStatisticsStore(MongoDatabaseProvider mongo, QuestionAttemptStore attempts)
{
_attempts = attempts;
_counters = mongo.Database.GetCollection<QuestionAttemptCounter>("QuestionAttemptCounters");
_state = mongo.Database.GetCollection<AnswerStatisticsState>("SystemState");
var counterIndex = Builders<QuestionAttemptCounter>.IndexKeys
.Ascending(counter => counter.QuestionExternalId)
.Ascending(counter => counter.Bucket)
.Ascending(counter => counter.ChoiceId);
_counters.Indexes.CreateOne(new CreateIndexModel<QuestionAttemptCounter>(
counterIndex,
new CreateIndexOptions { Unique = true }));
}
public async Task IncrementAsync(QuestionAttempt attempt)
{
if (attempt.IsSkip)
return;
var filter = Builders<QuestionAttemptCounter>.Filter.And(
Builders<QuestionAttemptCounter>.Filter.Eq(counter => counter.QuestionExternalId, attempt.QuestionExternalId),
Builders<QuestionAttemptCounter>.Filter.Eq(counter => counter.Bucket, attempt.CounterBucket),
Builders<QuestionAttemptCounter>.Filter.Eq(counter => counter.ChoiceId, attempt.ChoiceId));
var update = Builders<QuestionAttemptCounter>.Update
.Inc(counter => counter.Count, 1)
.Set(counter => counter.UpdatedUtc, DateTime.UtcNow)
.SetOnInsert(counter => counter.QuestionExternalId, attempt.QuestionExternalId)
.SetOnInsert(counter => counter.Bucket, attempt.CounterBucket)
.SetOnInsert(counter => counter.ChoiceId, attempt.ChoiceId);
try
{
await _counters.UpdateOneAsync(filter, update, new UpdateOptions { IsUpsert = true });
}
catch (MongoWriteException exception) when (exception.WriteError.Category == ServerErrorCategory.DuplicateKey)
{
await _counters.UpdateOneAsync(filter, update);
}
_cache.TryRemove(attempt.QuestionExternalId, out _);
}
public async Task<Dictionary<string, int>> GetPercentagesForQuestionAsync(string questionExternalId)
{
var result = await GetPercentagesByQuestionAsync([questionExternalId]);
return result.GetValueOrDefault(questionExternalId, []);
}
public async Task<Dictionary<string, Dictionary<string, int>>> GetPercentagesByQuestionAsync(
IEnumerable<string> questionExternalIds)
{
var ids = questionExternalIds.Where(id => !string.IsNullOrWhiteSpace(id)).Distinct().ToList();
var output = new Dictionary<string, Dictionary<string, int>>();
var missing = new List<string>();
var now = DateTime.UtcNow;
foreach (var id in ids)
{
if (_cache.TryGetValue(id, out var cached) && cached.ExpiresUtc > now)
output[id] = new Dictionary<string, int>(cached.Percentages);
else
missing.Add(id);
}
if (missing.Count == 0)
return output;
var backfillComplete = await IsBackfillCompleteAsync();
if (!backfillComplete)
{
var rawPercentages = await _attempts.GetPercentagesByQuestionAsync(missing);
foreach (var id in missing)
{
var percentages = rawPercentages.GetValueOrDefault(id, []);
output[id] = percentages;
_cache[id] = new CachedPercentages(percentages, now.Add(CacheDuration));
}
return output;
}
var totals = await _counters.Aggregate()
.Match(counter => missing.Contains(counter.QuestionExternalId))
.Group(
counter => new { counter.QuestionExternalId, counter.ChoiceId },
group => new QuestionAttemptCounterTotal
{
Key = new QuestionChoiceCounterKey
{
QuestionExternalId = group.Key.QuestionExternalId,
ChoiceId = group.Key.ChoiceId
},
Count = group.Sum(counter => counter.Count)
})
.ToListAsync();
var grouped = totals.GroupBy(total => total.Key.QuestionExternalId)
.ToDictionary(group => group.Key, group => group.ToList());
foreach (var id in missing)
{
Dictionary<string, int> percentages;
if (grouped.TryGetValue(id, out var questionTotals))
{
var total = questionTotals.Sum(item => item.Count);
percentages = total == 0
? []
: questionTotals.ToDictionary(
item => item.Key.ChoiceId,
item => (int)Math.Round(item.Count * 100.0 / total));
}
else
{
percentages = [];
}
output[id] = percentages;
_cache[id] = new CachedPercentages(percentages, now.Add(CacheDuration));
}
return output;
}
public async Task<bool> TryAcquireBackfillLeaseAsync(string owner, TimeSpan duration)
{
var now = DateTime.UtcNow;
var filter = Builders<AnswerStatisticsState>.Filter.And(
Builders<AnswerStatisticsState>.Filter.Eq(state => state.Id, StateId),
Builders<AnswerStatisticsState>.Filter.Eq(state => state.Completed, false),
Builders<AnswerStatisticsState>.Filter.Or(
Builders<AnswerStatisticsState>.Filter.Lt(state => state.LeaseUntilUtc, now),
Builders<AnswerStatisticsState>.Filter.Eq(state => state.LeaseOwner, owner)));
var update = Builders<AnswerStatisticsState>.Update
.SetOnInsert(state => state.Id, StateId)
.SetOnInsert(state => state.Completed, false)
.Set(state => state.LeaseOwner, owner)
.Set(state => state.LeaseUntilUtc, now.Add(duration))
.Set(state => state.UpdatedUtc, now);
try
{
var leased = await _state.FindOneAndUpdateAsync(
filter,
update,
new FindOneAndUpdateOptions<AnswerStatisticsState>
{
IsUpsert = true,
ReturnDocument = ReturnDocument.After
});
return leased?.LeaseOwner == owner;
}
catch (MongoWriteException exception) when (exception.WriteError.Category == ServerErrorCategory.DuplicateKey)
{
return false;
}
}
public async Task MarkBackfillCompleteAsync(string owner)
{
var update = Builders<AnswerStatisticsState>.Update
.Set(state => state.Completed, true)
.Set(state => state.LeaseOwner, owner)
.Set(state => state.UpdatedUtc, DateTime.UtcNow);
await _state.UpdateOneAsync(state => state.Id == StateId && state.LeaseOwner == owner, update);
_backfillComplete = true;
}
public async Task RebuildAllAsync() => await RebuildAsync(null);
public async Task RebuildQuestionsAsync(IReadOnlyCollection<string> questionExternalIds)
{
if (questionExternalIds.Count > 0)
await RebuildAsync(questionExternalIds);
}
private async Task RebuildAsync(IReadOnlyCollection<string>? questionExternalIds)
{
var aggregate = _attempts.Collection.Aggregate().Match(attempt => !attempt.IsSkip);
if (questionExternalIds is not null)
aggregate = aggregate.Match(attempt => questionExternalIds.Contains(attempt.QuestionExternalId));
var totals = await aggregate
.Group(
attempt => new { attempt.QuestionExternalId, attempt.CounterBucket, attempt.ChoiceId },
group => new QuestionAttemptCounterAggregate
{
Key = new QuestionChoiceBucketKey
{
QuestionExternalId = group.Key.QuestionExternalId,
Bucket = group.Key.CounterBucket,
ChoiceId = group.Key.ChoiceId
},
Count = group.Sum(_ => 1L)
})
.ToListAsync();
if (totals.Count > 0)
{
var now = DateTime.UtcNow;
var replacements = totals.Select(total =>
{
var counter = new QuestionAttemptCounter
{
QuestionExternalId = total.Key.QuestionExternalId,
Bucket = total.Key.Bucket,
ChoiceId = total.Key.ChoiceId,
Count = total.Count,
UpdatedUtc = now
};
var filter = Builders<QuestionAttemptCounter>.Filter.And(
Builders<QuestionAttemptCounter>.Filter.Eq(item => item.QuestionExternalId, counter.QuestionExternalId),
Builders<QuestionAttemptCounter>.Filter.Eq(item => item.Bucket, counter.Bucket),
Builders<QuestionAttemptCounter>.Filter.Eq(item => item.ChoiceId, counter.ChoiceId));
return new ReplaceOneModel<QuestionAttemptCounter>(filter, counter) { IsUpsert = true };
}).ToList();
await _counters.BulkWriteAsync(replacements, new BulkWriteOptions { IsOrdered = false });
}
if (questionExternalIds is null)
_cache.Clear();
else
foreach (var id in questionExternalIds)
_cache.TryRemove(id, out _);
}
private async Task<bool> IsBackfillCompleteAsync()
{
if (_backfillComplete)
return true;
_backfillComplete = (await _state.Find(state => state.Id == StateId).FirstOrDefaultAsync())?.Completed == true;
return _backfillComplete;
}
private sealed record CachedPercentages(Dictionary<string, int> Percentages, DateTime ExpiresUtc);
}