From 92d8ed8ac101d62183d51f280b90efb1de1bda5c Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Wed, 7 Jul 2021 23:10:19 +0000 Subject: 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 Signed-off-by: Junio C Hamano --- t/helper/test-oidtree.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) create mode 100644 t/helper/test-oidtree.c (limited to 't/helper/test-oidtree.c') diff --git a/t/helper/test-oidtree.c b/t/helper/test-oidtree.c new file mode 100644 index 0000000000..180ee28dd9 --- /dev/null +++ b/t/helper/test-oidtree.c @@ -0,0 +1,49 @@ +#include "test-tool.h" +#include "cache.h" +#include "oidtree.h" + +static enum cb_next print_oid(const struct object_id *oid, void *data) +{ + puts(oid_to_hex(oid)); + return CB_CONTINUE; +} + +int cmd__oidtree(int argc, const char **argv) +{ + struct oidtree ot; + struct strbuf line = STRBUF_INIT; + int nongit_ok; + int algo = GIT_HASH_UNKNOWN; + + oidtree_init(&ot); + setup_git_directory_gently(&nongit_ok); + + while (strbuf_getline(&line, stdin) != EOF) { + const char *arg; + struct object_id oid; + + if (skip_prefix(line.buf, "insert ", &arg)) { + if (get_oid_hex_any(arg, &oid) == GIT_HASH_UNKNOWN) + die("insert not a hexadecimal oid: %s", arg); + algo = oid.algo; + oidtree_insert(&ot, &oid); + } else if (skip_prefix(line.buf, "contains ", &arg)) { + if (get_oid_hex(arg, &oid)) + die("contains not a hexadecimal oid: %s", arg); + printf("%d\n", oidtree_contains(&ot, &oid)); + } else if (skip_prefix(line.buf, "each ", &arg)) { + char buf[GIT_MAX_HEXSZ + 1] = { '0' }; + memset(&oid, 0, sizeof(oid)); + memcpy(buf, arg, strlen(arg)); + buf[hash_algos[algo].hexsz] = '\0'; + get_oid_hex_any(buf, &oid); + oid.algo = algo; + oidtree_each(&ot, &oid, strlen(arg), print_oid, NULL); + } else if (!strcmp(line.buf, "clear")) { + oidtree_clear(&ot); + } else { + die("unknown command: %s", line.buf); + } + } + return 0; +} -- cgit v1.2.3