summaryrefslogtreecommitdiff
path: root/cbtree.h
diff options
context:
space:
mode:
authorEric Wong <e@80x24.org>2021-07-07 23:10:19 (GMT)
committerJunio C Hamano <gitster@pobox.com>2021-07-08 04:28:04 (GMT)
commit92d8ed8ac101d62183d51f280b90efb1de1bda5c (patch)
tree8979963947ae78dcdf979c1fd81a06d0dde1ad28 /cbtree.h
parent90e07f0a342df836a33b92e179eb105243dba88d (diff)
downloadgit-92d8ed8ac101d62183d51f280b90efb1de1bda5c.zip
git-92d8ed8ac101d62183d51f280b90efb1de1bda5c.tar.gz
git-92d8ed8ac101d62183d51f280b90efb1de1bda5c.tar.bz2
oidtree: a crit-bit tree for odb_loose_cache
This saves 8K per `struct object_directory', meaning it saves around 800MB in my case involving 100K alternates (half or more of those alternates are unlikely to hold loose objects). This is implemented in two parts: a generic, allocation-free `cbtree' and the `oidtree' wrapper on top of it. The latter provides allocation using alloc_state as a memory pool to improve locality and reduce free(3) overhead. Unlike oid-array, the crit-bit tree does not require sorting. Performance is bound by the key length, for oidtree that is fixed at sizeof(struct object_id). There's no need to have 256 oidtrees to mitigate the O(n log n) overhead like we did with oid-array. Being a prefix trie, it is natively suited for expanding short object IDs via prefix-limited iteration in `find_short_object_filename'. On my busy workstation, p4205 performance seems to be roughly unchanged (+/-8%). Startup with 100K total alternates with no loose objects seems around 10-20% faster on a hot cache. (800MB in memory savings means more memory for the kernel FS cache). The generic cbtree implementation does impose some extra overhead for oidtree in that it uses memcmp(3) on "struct object_id" so it wastes cycles comparing 12 extra bytes on SHA-1 repositories. I've not yet explored reducing this overhead, but I expect there are many places in our code base where we'd want to investigate this. More information on crit-bit trees: https://cr.yp.to/critbit.html Signed-off-by: Eric Wong <e@80x24.org> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'cbtree.h')
-rw-r--r--cbtree.h56
1 files changed, 56 insertions, 0 deletions
diff --git a/cbtree.h b/cbtree.h
new file mode 100644
index 0000000..fe45870
--- /dev/null
+++ b/cbtree.h
@@ -0,0 +1,56 @@
+/*
+ * crit-bit tree implementation, does no allocations internally
+ * For more information on crit-bit trees: https://cr.yp.to/critbit.html
+ * Based on Adam Langley's adaptation of Dan Bernstein's public domain code
+ * git clone https://github.com/agl/critbit.git
+ *
+ * This is adapted to store arbitrary data (not just NUL-terminated C strings
+ * and allocates no memory internally. The user needs to allocate
+ * "struct cb_node" and fill cb_node.k[] with arbitrary match data
+ * for memcmp.
+ * If "klen" is variable, then it should be embedded into "c_node.k[]"
+ * Recursion is bound by the maximum value of "klen" used.
+ */
+#ifndef CBTREE_H
+#define CBTREE_H
+
+#include "git-compat-util.h"
+
+struct cb_node;
+struct cb_node {
+ struct cb_node *child[2];
+ /*
+ * n.b. uint32_t for `byte' is excessive for OIDs,
+ * we may consider shorter variants if nothing else gets stored.
+ */
+ uint32_t byte;
+ uint8_t otherbits;
+ uint8_t k[FLEX_ARRAY]; /* arbitrary data */
+};
+
+struct cb_tree {
+ struct cb_node *root;
+};
+
+enum cb_next {
+ CB_CONTINUE = 0,
+ CB_BREAK = 1
+};
+
+#define CBTREE_INIT { .root = NULL }
+
+static inline void cb_init(struct cb_tree *t)
+{
+ t->root = NULL;
+}
+
+struct cb_node *cb_lookup(struct cb_tree *, const uint8_t *k, size_t klen);
+struct cb_node *cb_insert(struct cb_tree *, struct cb_node *, size_t klen);
+struct cb_node *cb_unlink(struct cb_tree *t, const uint8_t *k, size_t klen);
+
+typedef enum cb_next (*cb_iter)(struct cb_node *, void *arg);
+
+void cb_each(struct cb_tree *, const uint8_t *kpfx, size_t klen,
+ cb_iter, void *arg);
+
+#endif /* CBTREE_H */