From 6a9686673740ea2081e1aec2a2116fcf9c884f44 Mon Sep 17 00:00:00 2001
From: Christopher Haster <geky@geky.net>
Date: Sat, 27 May 2023 14:14:30 -0500
Subject: [PATCH] Added an mtree traversal benchmark

Note that because we amortize the traversal cost over the number of
entries, mtree traversal may have some strange looking results when
compared to mtree lookup.

Though it's interesting to note this is a valid result. In mtree lookups
we need to fetch the mdir for each entry, which is expensive. However
mtree traversal can strictly avoid fetching each mdir more than once.
This does make mdir traversal faster when iterating over all mdirs in
order.

This can be represented in big O notation if we treat the number of
entries (n) and block size (b) as variables:

- mtree traversal via lookup    = O(nb+nlog(b)logb(n))
- mtree traversal via traversal = O(nlog(b)logb(n))
---
 benches/bench_mtree.toml | 66 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/benches/bench_mtree.toml b/benches/bench_mtree.toml
index ab5f274f..2dd81b71 100644
--- a/benches/bench_mtree.toml
+++ b/benches/bench_mtree.toml
@@ -133,3 +133,69 @@ code = '''
 
     lfsr_unmount(&lfs) => 0;
 '''
+
+[cases.bench_mtree_traversal]
+defines.N = [8, 16, 32, 64, 128, 256, 1024]
+# 0 = in-order
+# 1 = reversed-order
+# 2 = random-order
+defines.ORDER = [0, 1, 2]
+defines.SEED = 42
+defines.VALIDATE = [false, true]
+in = 'lfs.c'
+code = '''
+    uint32_t prng = SEED;
+    const char *alphas = "abcdefghijklmnopqrstuvwxyz";
+
+    lfs_t lfs;
+    lfsr_format(&lfs, cfg) => 0;
+    lfsr_mount(&lfs, cfg) => 0;
+
+    // create an mtree with N entries
+    for (lfs_size_t i = 0; i < N; i++) {
+        // choose an mid
+        lfs_ssize_t mid
+                = lfsr_mtree_weight(&lfs) == 0 ? -1
+                : (ORDER == 0) ? (lfs_ssize_t)(lfsr_mtree_weight(&lfs)-1)
+                : (ORDER == 1) ? 0
+                : (lfs_ssize_t)(BENCH_PRNG(&prng) % lfsr_mtree_weight(&lfs));
+        // fetch mdir
+        lfsr_mdir_t mdir;
+        lfsr_mtree_lookup(&lfs, mid, &mdir) => 0;
+
+        // choose rid
+        lfs_ssize_t rid
+                = (ORDER == 0) ? lfsr_mdir_weight(&mdir)
+                : (ORDER == 1) ? 0
+                : BENCH_PRNG(&prng) % (lfsr_mdir_weight(&mdir)+1);
+
+        // create an entry
+        lfsr_mdir_commit(&lfs, &mdir, &rid, LFSR_ATTRS(
+                LFSR_ATTR(rid, MKINLINED, +1, &alphas[i % 26], 1))) => 0;
+    }
+
+    // traverse the mtree
+    BENCH_START();
+    lfsr_mtree_traversal_t traversal = LFSR_MTREE_TRAVERSAL_INIT(
+            VALIDATE ? LFSR_MTREE_TRAVERSAL_VALIDATE : 0);
+
+    for (lfs_block_t i = 0;; i++) {
+        // a bit hacky, but this catches infinite loops
+        assert(i < 2*(1+N));
+
+        lfs_size_t mid_;
+        lfsr_tag_t tag_;
+        lfsr_data_t data_;
+        int err = lfsr_mtree_traversal_next(&lfs, &traversal,
+                &mid_, &tag_, &data_);
+        assert(!err || err == LFS_ERR_NOENT);
+        if (err == LFS_ERR_NOENT) {
+            break;
+        }
+
+        assert(tag_ == LFSR_TAG_BTREE || tag_ == LFSR_TAG_MDIR);
+    }
+    BENCH_STOP();
+
+    lfsr_unmount(&lfs) => 0;
+'''