Limit file descriptors used by packs

Rather than using 'errno == EMFILE' after a failed open() call
to indicate the process is out of file descriptors and an LRU
pack window should be closed, place a hard upper limit on the
number of open packs based on the actual rlimit of the process.

By using a hard upper limit that is below the rlimit of the current
process it is not necessary to check for EMFILE on every single
fd-allocating system call.  Instead reserving 25 file descriptors
makes it safe to assume the system call won't fail due to being over
the filedescriptor limit.  Here 25 is chosen as a WAG, but considers
3 for stdin/stdout/stderr, and at least a few for other Git code
to operate on temporary files.  An additional 20 is reserved as it
is not known what the C library needs to perform other services on
Git's behalf, such as nsswitch or name resolution.

This fixes a case where running `git gc --auto` in a repository
with more than 1024 packs (but an rlimit of 1024 open fds) fails
due to the temporary output file not being able to allocate a
file descriptor.  The output file is opened by pack-objects after
object enumeration and delta compression are done, both of which
have already opened all of the packs and fully populated the file
descriptor table.

Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/sha1_file.c b/sha1_file.c
index 27730c334cb433ef749a0efc5353a7f38032559c..c6beed2d6b727a72c94a14e5fc63b217946c75f8 100644 (file)
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -417,6 +417,8 @@ static unsigned int pack_used_ctr;
 static unsigned int pack_mmap_calls;
 static unsigned int peak_pack_open_windows;
 static unsigned int pack_open_windows;
+static unsigned int pack_open_fds;
+static unsigned int pack_max_fds;
 static size_t peak_pack_mapped;
 static size_t pack_mapped;
 struct packed_git *packed_git;
@@ -596,6 +598,7 @@ static int unuse_one_window(struct packed_git *current, int keep_fd)
                        lru_p->windows = lru_w->next;
                        if (!lru_p->windows && lru_p->pack_fd != keep_fd) {
                                close(lru_p->pack_fd);
+                               pack_open_fds--;
                                lru_p->pack_fd = -1;
                        }
                }
@@ -680,8 +683,10 @@ void free_pack_by_name(const char *pack_name)
                if (strcmp(pack_name, p->pack_name) == 0) {
                        clear_delta_base_cache();
                        close_pack_windows(p);
-                       if (p->pack_fd != -1)
+                       if (p->pack_fd != -1) {
                                close(p->pack_fd);
+                               pack_open_fds--;
+                       }
                        close_pack_index(p);
                        free(p->bad_object_sha1);
                        *pp = p->next;
@@ -707,9 +712,29 @@ static int open_packed_git_1(struct packed_git *p)
        if (!p->index_data && open_pack_index(p))
                return error("packfile %s index unavailable", p->pack_name);
 
+       if (!pack_max_fds) {
+               struct rlimit lim;
+               unsigned int max_fds;
+
+               if (getrlimit(RLIMIT_NOFILE, &lim))
+                       die_errno("cannot get RLIMIT_NOFILE");
+
+               max_fds = lim.rlim_cur;
+
+               /* Save 3 for stdin/stdout/stderr, 22 for work */
+               if (25 < max_fds)
+                       pack_max_fds = max_fds - 25;
+               else
+                       pack_max_fds = 1;
+       }
+
+       while (pack_max_fds <= pack_open_fds && unuse_one_window(NULL, -1))
+               ; /* nothing */
+
        p->pack_fd = git_open_noatime(p->pack_name, p);
        if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
                return -1;
+       pack_open_fds++;
 
        /* If we created the struct before we had the pack we lack size. */
        if (!p->pack_size) {
@@ -761,6 +786,7 @@ static int open_packed_git(struct packed_git *p)
                return 0;
        if (p->pack_fd != -1) {
                close(p->pack_fd);
+               pack_open_fds--;
                p->pack_fd = -1;
        }
        return -1;
@@ -918,6 +944,9 @@ struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
 
 void install_packed_git(struct packed_git *pack)
 {
+       if (pack->pack_fd != -1)
+               pack_open_fds++;
+
        pack->next = packed_git;
        packed_git = pack;
 }
@@ -935,8 +964,6 @@ static void prepare_packed_git_one(char *objdir, int local)
        sprintf(path, "%s/pack", objdir);
        len = strlen(path);
        dir = opendir(path);
-       while (!dir && errno == EMFILE && unuse_one_window(NULL, -1))
-               dir = opendir(path);
        if (!dir) {
                if (errno != ENOENT)
                        error("unable to open object pack directory: %s: %s",
@@ -1092,14 +1119,6 @@ static int git_open_noatime(const char *name, struct packed_git *p)
                if (fd >= 0)
                        return fd;
 
-               /* Might the failure be insufficient file descriptors? */
-               if (errno == EMFILE) {
-                       if (unuse_one_window(p, -1))
-                               continue;
-                       else
-                               return -1;
-               }
-
                /* Might the failure be due to O_NOATIME? */
                if (errno != ENOENT && sha1_file_open_flag) {
                        sha1_file_open_flag = 0;
@@ -2359,8 +2378,6 @@ static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
 
        filename = sha1_file_name(sha1);
        fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
-       while (fd < 0 && errno == EMFILE && unuse_one_window(NULL, -1))
-               fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
        if (fd < 0) {
                if (errno == EACCES)
                        return error("insufficient permission for adding an object to repository database %s\n", get_object_directory());