summaryrefslogtreecommitdiff
path: root/internal/regex/bench_test.go
diff options
context:
space:
mode:
authorPaul Buetow <paul@buetow.org>2026-07-22 23:51:18 +0300
committerPaul Buetow <paul@buetow.org>2026-07-22 23:51:18 +0300
commit849951be1d1a7ee9f9302006ccb187bf5b4e36f3 (patch)
tree496c924a03a9ea6212e29bb4699e268066ebad81 /internal/regex/bench_test.go
parentbf78b3abffee6d49c08ca2980156afc455994969 (diff)
feat: DTail fork — server/client feature development
Squashed development of the snonux/dtail fork's product code (internal/, cmd/) since diverging from mimecast/dtail. Major areas: - Read/output path: the former "turbo" channel-less path is now the single, default server-side read/output path for cat/grep/tail and MapReduce; the old channel-based path and its config/env toggles were removed. - MapReduce: single aggregate implementation (server + serverless) fed directly by a processor pipeline, with input-exhausted finalization via the shutdown coordinator; high-concurrency and data-race fixes. - Journal source reads (journal:unit.service) via journalctl, Linux-gated behind a journal-v1 capability. - Auth-key fast reconnect: in-memory per-user public-key cache with TTL/max-keys, registered over an authenticated session (AUTHKEY), checked before authorized_keys. - Interactive query reload (--interactive-query) with SESSION START/UPDATE generation boundaries and capability negotiation. - Client-side deadlines: --timeout / --shutdownAfter as context deadlines; follow shutdown handling. - Client logging: diagnostics-only daily log by default, opt-in payload tee via --log-payload. - Numerous correctness fixes (buffer-pool double-recycle races, EOF-sentinel leaks, glob-expansion cap, TOCTOU in CSV parsing) with accompanying unit tests. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Diffstat (limited to 'internal/regex/bench_test.go')
-rw-r--r--internal/regex/bench_test.go111
1 files changed, 111 insertions, 0 deletions
diff --git a/internal/regex/bench_test.go b/internal/regex/bench_test.go
new file mode 100644
index 0000000..16fd98e
--- /dev/null
+++ b/internal/regex/bench_test.go
@@ -0,0 +1,111 @@
+package regex
+
+import (
+ "bytes"
+ "testing"
+)
+
+func BenchmarkLiteralVsRegex(b *testing.B) {
+ // Test data - typical log lines
+ testLines := [][]byte{
+ []byte("2024-01-01 10:00:00 INFO Starting application"),
+ []byte("2024-01-01 10:00:01 DEBUG Loading configuration"),
+ []byte("2024-01-01 10:00:02 ERROR Failed to connect to database"),
+ []byte("2024-01-01 10:00:03 WARN Retrying connection"),
+ []byte("2024-01-01 10:00:04 INFO Connection established"),
+ []byte("2024-01-01 10:00:05 ERROR Timeout while processing request"),
+ []byte("2024-01-01 10:00:06 DEBUG Processing request ID: 12345"),
+ []byte("2024-01-01 10:00:07 INFO Request processed successfully"),
+ []byte("2024-01-01 10:00:08 ERROR Invalid input parameters"),
+ []byte("2024-01-01 10:00:09 WARN High memory usage detected"),
+ }
+
+ // Benchmark literal pattern matching (our optimization)
+ b.Run("Literal_ERROR", func(b *testing.B) {
+ r, _ := New("ERROR", Default)
+ if !r.isLiteral {
+ b.Fatal("Pattern should be detected as literal")
+ }
+
+ b.ResetTimer()
+ matches := 0
+ for i := 0; i < b.N; i++ {
+ for _, line := range testLines {
+ if r.Match(line) {
+ matches++
+ }
+ }
+ }
+ _ = matches
+ })
+
+ // Force regex pattern matching for comparison
+ b.Run("Regex_ERROR", func(b *testing.B) {
+ // Add a harmless regex operator to force regex compilation
+ r, _ := New("(?:ERROR)", Default)
+ if r.isLiteral {
+ b.Fatal("Pattern should not be detected as literal")
+ }
+
+ b.ResetTimer()
+ matches := 0
+ for i := 0; i < b.N; i++ {
+ for _, line := range testLines {
+ if r.Match(line) {
+ matches++
+ }
+ }
+ }
+ _ = matches
+ })
+
+ // Direct bytes.Contains for reference
+ b.Run("BytesContains_ERROR", func(b *testing.B) {
+ pattern := []byte("ERROR")
+
+ b.ResetTimer()
+ matches := 0
+ for i := 0; i < b.N; i++ {
+ for _, line := range testLines {
+ if bytes.Contains(line, pattern) {
+ matches++
+ }
+ }
+ }
+ _ = matches
+ })
+}
+
+func BenchmarkComplexPatterns(b *testing.B) {
+ testLine := []byte("2024-01-01 10:00:00 ERROR Failed to connect to database server at 192.168.1.100:5432")
+
+ patterns := []struct {
+ name string
+ pattern string
+ }{
+ {"Simple_ERROR", "ERROR"},
+ {"Simple_database", "database"},
+ {"Regex_ERROR.*database", "ERROR.*database"},
+ {"Regex_\\d+\\.\\d+\\.\\d+\\.\\d+", `\d+\.\d+\.\d+\.\d+`}, // IP address pattern
+ {"Regex_^2024", "^2024"},
+ {"Regex_5432$", "5432$"},
+ }
+
+ for _, p := range patterns {
+ b.Run(p.name, func(b *testing.B) {
+ r, err := New(p.pattern, Default)
+ if err != nil {
+ b.Fatal(err)
+ }
+
+ b.ResetTimer()
+ matches := 0
+ for i := 0; i < b.N; i++ {
+ if r.Match(testLine) {
+ matches++
+ }
+ }
+ _ = matches
+ })
+ }
+} \ No newline at end of file