diff options
author | Dan McGee <dan@archlinux.org> | 2011-07-19 11:47:29 +0200 |
---|---|---|
committer | Dan McGee <dan@archlinux.org> | 2011-07-21 22:04:30 +0200 |
commit | bb3dada8711fbb822513cd556167867b537f8986 (patch) | |
tree | 1230de6f94675777e9cdd4150779f4756995efa1 /lib/libalpm/be_local.c | |
parent | 058ee1737182c2d5e900e0feba57f0d6496e735e (diff) | |
download | pacman-bb3dada8711fbb822513cd556167867b537f8986.tar.gz pacman-bb3dada8711fbb822513cd556167867b537f8986.tar.xz |
Convert package filelists to an array instead of linked list
This accomplishes quite a few things with one rather invasive change.
1. Iteration is much more performant, due to a reduction in pointer
chasing and linear item access.
2. Data structures are smaller- we no longer have the overhead of the
linked list as the file struts are now laid out consecutively in
memory.
3. Memory allocation has been massively reworked. Before, we would
allocate three different pieces of memory per file item- the list
struct, the file struct, and the copied filename. What this resulted
in was massive fragmentation of memory when loading filelists since
the memory allocator had to leave holes all over the place. The new
situation here now removes the need for any list item allocation;
allocates the file structs in contiguous memory (and reallocs as
necessary), leaving only the strings as individually allocated. Tests
using valgrind (massif) show some pretty significant memory
reductions on the worst case `pacman -Ql > /dev/null` (366387 files
on my machine):
Before:
Peak heap: 54,416,024 B
Useful heap: 36,840,692 B
Extra heap: 17,575,332 B
After:
Peak heap: 38,004,352 B
Useful heap: 28,101,347 B
Extra heap: 9,903,005 B
Several small helper methods have been introduced, including a list to
array conversion helper as well as a filelist merge sort that works
directly on arrays.
Signed-off-by: Dan McGee <dan@archlinux.org>
Diffstat (limited to 'lib/libalpm/be_local.c')
-rw-r--r-- | lib/libalpm/be_local.c | 41 |
1 files changed, 32 insertions, 9 deletions
diff --git a/lib/libalpm/be_local.c b/lib/libalpm/be_local.c index 70f242d2..261ad871 100644 --- a/lib/libalpm/be_local.c +++ b/lib/libalpm/be_local.c @@ -177,10 +177,10 @@ static alpm_list_t *_cache_get_deltas(alpm_pkg_t UNUSED *pkg) return NULL; } -static alpm_list_t *_cache_get_files(alpm_pkg_t *pkg) +static alpm_filelist_t *_cache_get_files(alpm_pkg_t *pkg) { LAZY_LOAD(INFRQ_FILES, NULL); - return pkg->files; + return &(pkg->files); } static alpm_list_t *_cache_get_backup(alpm_pkg_t *pkg) @@ -631,13 +631,35 @@ static int local_db_read(alpm_pkg_t *info, alpm_dbinfrq_t inforeq) while(fgets(line, sizeof(line), fp)) { _alpm_strtrim(line); if(strcmp(line, "%FILES%") == 0) { + size_t files_count = 0, files_size = 0; + alpm_file_t *files = NULL; + while(fgets(line, sizeof(line), fp) && strlen(_alpm_strtrim(line))) { - alpm_file_t *file; - CALLOC(file, 1, sizeof(alpm_file_t), goto error); - STRDUP(file->name, line, goto error); + if(files_count >= files_size) { + size_t old_size = files_size; + if(files_size == 0) { + files_size = 8; + } else { + files_size *= 2; + } + files = realloc(files, sizeof(alpm_file_t) * files_size); + if(!files) { + ALLOC_FAIL(sizeof(alpm_file_t) * files_size); + goto error; + } + /* ensure all new memory is zeroed out, in both the initial + * allocation and later reallocs */ + memset(files + old_size, 0, + sizeof(alpm_file_t) * (files_size - old_size)); + } + STRDUP(files[files_count].name, line, goto error); /* TODO: lstat file, get mode/size */ - info->files = alpm_list_add(info->files, file); + files_count++; } + /* attempt to hand back any memory we don't need */ + files = realloc(files, sizeof(alpm_file_t) * files_count); + info->files.count = files_count; + info->files.files = files; } else if(strcmp(line, "%BACKUP%") == 0) { while(fgets(line, sizeof(line), fp) && strlen(_alpm_strtrim(line))) { alpm_backup_t *backup; @@ -834,10 +856,11 @@ int _alpm_local_db_write(alpm_db_t *db, alpm_pkg_t *info, alpm_dbinfrq_t inforeq retval = -1; goto cleanup; } - if(info->files) { + if(info->files.count) { + size_t i; fprintf(fp, "%%FILES%%\n"); - for(lp = info->files; lp; lp = lp->next) { - const alpm_file_t *file = lp->data; + for(i = 0; i < info->files.count; i++) { + const alpm_file_t *file = info->files.files + i; fprintf(fp, "%s\n", file->name); } fprintf(fp, "\n"); |