From 0217bedede81b2b3ec0493b3dc4c97ef183e781e Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Tue, 24 Jan 2017 15:12:13 -0500 Subject: [PATCH 1/2] fscache: add key for GIT_TRACE_FSCACHE Signed-off-by: Jeff Hostetler --- compat/win32/fscache.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/compat/win32/fscache.c b/compat/win32/fscache.c index 990d7dc8dd1e7e..87187ac4061862 100644 --- a/compat/win32/fscache.c +++ b/compat/win32/fscache.c @@ -7,6 +7,7 @@ static int initialized; static volatile long enabled; static struct hashmap map; static CRITICAL_SECTION mutex; +static struct trace_key trace_fscache = TRACE_KEY_INIT(FSCACHE); /* * An entry in the file system cache. Used for both entire directory listings @@ -191,6 +192,8 @@ static struct fsentry *fsentry_create_list(const struct fsentry *dir) if (h == INVALID_HANDLE_VALUE) { err = GetLastError(); errno = (err == ERROR_DIRECTORY) ? ENOTDIR : err_win_to_posix(err); + trace_printf_key(&trace_fscache, "fscache: error(%d) '%.*s'\n", + errno, dir->len, dir->name); return NULL; } @@ -392,6 +395,7 @@ int fscache_enable(int enable) fscache_clear(); LeaveCriticalSection(&mutex); } + trace_printf_key(&trace_fscache, "fscache: enable(%d)\n", enable); return result; } From 8544ec3873a7ff7b48d55d4194085243820d3d16 Mon Sep 17 00:00:00 2001 From: Jeff Hostetler Date: Tue, 13 Dec 2016 14:05:32 -0500 Subject: [PATCH 2/2] fscache: remember not-found directories Teach FSCACHE to remember "not found" directories. This is a performance optimization. FSCACHE is a performance optimization available for Windows. It intercepts Posix-style lstat() calls into an in-memory directory using FindFirst/FindNext. It improves performance on Windows by catching the first lstat() call in a directory, using FindFirst/ FindNext to read the list of files (and attribute data) for the entire directory into the cache, and short-cut subsequent lstat() calls in the same directory. This gives a major performance boost on Windows. However, it does not remember "not found" directories. When STATUS runs and there are missing directories, the lstat() interception fails to find the parent directory and simply return ENOENT for the file -- it does not remember that the FindFirst on the directory failed. Thus subsequent lstat() calls in the same directory, each re-attempt the FindFirst. This completely defeats any performance gains. This can be seen by doing a sparse-checkout on a large repo and then doing a read-tree to reset the skip-worktree bits and then running status. This change reduced status times for my very large repo by 60%. Signed-off-by: Jeff Hostetler --- compat/win32/fscache.c | 34 ++++++++++++++++++++++++++++++---- 1 file changed, 30 insertions(+), 4 deletions(-) diff --git a/compat/win32/fscache.c b/compat/win32/fscache.c index 87187ac4061862..18871fa36fd185 100644 --- a/compat/win32/fscache.c +++ b/compat/win32/fscache.c @@ -164,7 +164,8 @@ static struct fsentry *fseentry_create_entry(struct fsentry *list, * Dir should not contain trailing '/'. Use an empty string for the current * directory (not "."!). */ -static struct fsentry *fsentry_create_list(const struct fsentry *dir) +static struct fsentry *fsentry_create_list(const struct fsentry *dir, + int *dir_not_found) { wchar_t pattern[MAX_LONG_PATH + 2]; /* + 2 for "\*" */ WIN32_FIND_DATAW fdata; @@ -173,6 +174,8 @@ static struct fsentry *fsentry_create_list(const struct fsentry *dir) struct fsentry *list, **phead; DWORD err; + *dir_not_found = 0; + /* convert name to UTF-16 and check length */ if ((wlen = xutftowcs_path_ex(pattern, dir->name, MAX_LONG_PATH, dir->len, MAX_PATH - 2, core_long_paths)) < 0) @@ -191,6 +194,7 @@ static struct fsentry *fsentry_create_list(const struct fsentry *dir) h = FindFirstFileW(pattern, &fdata); if (h == INVALID_HANDLE_VALUE) { err = GetLastError(); + *dir_not_found = 1; /* or empty directory */ errno = (err == ERROR_DIRECTORY) ? ENOTDIR : err_win_to_posix(err); trace_printf_key(&trace_fscache, "fscache: error(%d) '%.*s'\n", errno, dir->len, dir->name); @@ -199,6 +203,7 @@ static struct fsentry *fsentry_create_list(const struct fsentry *dir) /* allocate object to hold directory listing */ list = fsentry_alloc(NULL, dir->name, dir->len); + list->st_mode = S_IFDIR; /* walk directory and build linked list of fsentry structures */ phead = &list->next; @@ -299,12 +304,16 @@ static struct fsentry *fscache_get_wait(struct fsentry *key) static struct fsentry *fscache_get(struct fsentry *key) { struct fsentry *fse, *future, *waiter; + int dir_not_found; EnterCriticalSection(&mutex); /* check if entry is in cache */ fse = fscache_get_wait(key); if (fse) { - fsentry_addref(fse); + if (fse->st_mode) + fsentry_addref(fse); + else + fse = NULL; /* non-existing directory */ LeaveCriticalSection(&mutex); return fse; } @@ -313,7 +322,10 @@ static struct fsentry *fscache_get(struct fsentry *key) fse = fscache_get_wait(key->list); if (fse) { LeaveCriticalSection(&mutex); - /* dir entry without file entry -> file doesn't exist */ + /* + * dir entry without file entry, or dir does not + * exist -> file doesn't exist + */ errno = ENOENT; return NULL; } @@ -327,7 +339,7 @@ static struct fsentry *fscache_get(struct fsentry *key) /* create the directory listing (outside mutex!) */ LeaveCriticalSection(&mutex); - fse = fsentry_create_list(future); + fse = fsentry_create_list(future, &dir_not_found); EnterCriticalSection(&mutex); /* remove future entry and signal waiting threads */ @@ -341,6 +353,17 @@ static struct fsentry *fscache_get(struct fsentry *key) /* leave on error (errno set by fsentry_create_list) */ if (!fse) { + if (dir_not_found && key->list) { + /* + * Record that the directory does not exist (or is + * empty, which for all practical matters is the same + * thing as far as fscache is concerned). + */ + fse = fsentry_alloc(key->list->list, + key->list->name, key->list->len); + fse->st_mode = 0; + hashmap_add(&map, fse); + } LeaveCriticalSection(&mutex); return NULL; } @@ -352,6 +375,9 @@ static struct fsentry *fscache_get(struct fsentry *key) if (key->list) fse = hashmap_get(&map, key, NULL); + if (fse && !fse->st_mode) + fse = NULL; /* non-existing directory */ + /* return entry or ENOENT */ if (fse) fsentry_addref(fse);