1
0
mirror of https://github.com/git/git.git synced 2024-11-19 00:44:22 +01:00
git/unpack-trees.h

47 lines
1.1 KiB
C
Raw Normal View History

#ifndef UNPACK_TREES_H
#define UNPACK_TREES_H
#define MAX_UNPACK_TREES 8
struct unpack_trees_options;
typedef int (*merge_fn_t)(struct cache_entry **src,
struct unpack_trees_options *options);
struct unpack_trees_options {
int reset;
int merge;
int update;
int index_only;
int nontrivial_merge;
int trivial_merges_only;
int verbose_update;
int aggressive;
int skip_unmerged;
int gently;
const char *prefix;
int pos;
struct dir_struct *dir;
merge_fn_t fn;
int head_idx;
int merge_size;
struct cache_entry *df_conflict_entry;
Make run_diff_index() use unpack_trees(), not read_tree() A plain "git commit" would still run lstat() a lot more than necessary, because wt_status_print() would cause the index to be repeatedly flushed and re-read by wt_read_cache(), and that would cause the CE_UPTODATE bit to be lost, resulting in the files in the index being lstat'ed three times each. The reason why wt-status.c ended up invalidating and re-reading the cache multiple times was that it uses "run_diff_index()", which in turn uses "read_tree()" to populate the index with *both* the old index and the tree we want to compare against. So this patch re-writes run_diff_index() to not use read_tree(), but instead use "unpack_trees()" to diff the index to a tree. That, in turn, means that we don't need to modify the index itself, which then means that we don't need to invalidate it and re-read it! This, together with the lstat() optimizations, means that "git commit" on the kernel tree really only needs to lstat() the index entries once. That noticeably cuts down on the cached timings. Best time before: [torvalds@woody linux]$ time git commit > /dev/null real 0m0.399s user 0m0.232s sys 0m0.164s Best time after: [torvalds@woody linux]$ time git commit > /dev/null real 0m0.254s user 0m0.140s sys 0m0.112s so it's a noticeable improvement in addition to being a nice conceptual cleanup (it's really not that pretty that "run_diff_index()" dirties the index!) Doing an "strace -c" on it also shows that as it cuts the number of lstat() calls by two thirds, it goes from being lstat()-limited to being limited by getdents() (which is the readdir system call): Before: % time seconds usecs/call calls errors syscall ------ ----------- ----------- --------- --------- ---------------- 60.69 0.000704 0 69230 31 lstat 23.62 0.000274 0 5522 getdents 8.36 0.000097 0 5508 2638 open 2.59 0.000030 0 2869 close 2.50 0.000029 0 274 write 1.47 0.000017 0 2844 fstat After: % time seconds usecs/call calls errors syscall ------ ----------- ----------- --------- --------- ---------------- 45.17 0.000276 0 5522 getdents 26.51 0.000162 0 23112 31 lstat 19.80 0.000121 0 5503 2638 open 4.91 0.000030 0 2864 close 1.48 0.000020 0 274 write 1.34 0.000018 0 2844 fstat ... It passes the test-suite for me, but this is another of one of those really core functions, and certainly pretty subtle, so.. NOTE! The Linux lstat() system call is really quite cheap when everything is cached, so the fact that this is quite noticeable on Linux is likely to mean that it is *much* more noticeable on other operating systems. I bet you'll see a much bigger performance improvement from this on Windows in particular. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-01-20 02:27:12 +01:00
void *unpack_data;
struct index_state *dst_index;
const struct index_state *src_index;
struct index_state result;
};
extern int unpack_trees(unsigned n, struct tree_desc *t,
struct unpack_trees_options *options);
int threeway_merge(struct cache_entry **stages, struct unpack_trees_options *o);
int twoway_merge(struct cache_entry **src, struct unpack_trees_options *o);
int bind_merge(struct cache_entry **src, struct unpack_trees_options *o);
int oneway_merge(struct cache_entry **src, struct unpack_trees_options *o);
#endif