osdep: add a qemu_close_all_open_fd() helper
PATCH v3 1/1 osdep: add a qemu_close_all_open_fd() helper
Since commit 03e471c41d8b ("qemu_init: increase NOFILE soft limit on POSIX"), the maximum number of file descriptors that can be opened are raised to nofile.rlim_max. On recent debian distro, this yield a maximum of 1073741816 file descriptors. Now, when forking to start qemu-bridge-helper, this actually calls close() on the full possible file descriptor range (more precisely [3 - sysconf(_SC_OPEN_MAX)]) which takes a considerable amount of time. In order to reduce that time, factorize existing code to close all open files descriptors in a new qemu_close_all_open_fd() function. This function uses various methods to close all the open file descriptors ranging from the most efficient one to the least one. It also accepts an ordered array of file descriptors that should not be closed since this is required by the callers that calls it after forking.
----
v3:
- Use STD*_FILENO defines instead of raw values
- Fix indentation of close_all_fds_after_fork()
- Check for nksip in fallback code
- Check for path starting with a '.' in qemu_close_all_open_fd_proc()
- Use unsigned for cur_skip
- Move ifdefs inside close_fds functions rather than redefining them
- Remove uneeded 'if(nskip)' test
- Add comments to close_range version
- Reduce range of skip fd as we find them in
- v2: https://lore.kernel.org/qemu-devel/[email protected]/
v2:
- Factorize async_teardown.c close_fds implementation as well as tap.c ones
- Apply checkpatch
- v1: https://lore.kernel.org/qemu-devel/[email protected]/
--- include/qemu/osdep.h | 8 +++ net/tap.c | 33 +++++----- system/async-teardown.c | 37 +----------- util/osdep.c | 129 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 157 insertions(+), 50 deletions(-)
include/qemu/osdep.h +8 -0
@@ -757,6 +757,14 @@ static inline void qemu_reset_optind(void)int qemu_fdatasync (int fd); +/** +* Close all open file descriptors except the ones supplied in the @skip array +* +* @skip: ordered array of distinct file descriptors that should not be closed +* @nskip: number of entries in the @skip array. +*/ +void qemu_close_all_open_fd (const int *skip,unsigned int nskip); +/** * Sync changes made to the memory mapped file back to the backing * storage. For POSIX compliant systems this will fallback
net/tap.c +19 -14
@@ -385,6 +385,23 @@ static TAPState *net_tap_fd_init(NetClientState *peer,return s; } +static void close_all_fds_after_fork (int excluded_fd) +{ +const int skip_fd[] = {STDIN_FILENO ,STDOUT_FILENO ,STDERR_FILENO , + excluded_fd}; +unsigned int nskip =ARRAY_SIZE (skip_fd); + +/* +* skip_fd must be an ordered array of distinct fds, exclude +* excluded_fd if already included in the [STDIN_FILENO - STDERR_FILENO] +* range +*/ +if (excluded_fd <=STDERR_FILENO ) { + nskip--; + } +qemu_close_all_open_fd (skip_fd, nskip); +} +static void launch_script (const char *setup_script,const char *ifname,int fd,Error **errp) {
@@ -400,13 +417,7 @@ static void launch_script(const char *setup_script, const char *ifname,return ; }if (pid ==0 ) { -int open_max =sysconf (_SC_OPEN_MAX), i; - -for (i =3 ; i < open_max; i++) { -if (i != fd) { -close (i); - } - } +close_all_fds_after_fork (fd); parg = args; *parg++ = (char *)setup_script; *parg++ = (char *)ifname;
@@ -490,17 +501,11 @@ static int net_bridge_run_helper(const char *helper, const char *bridge,return -1 ; }if (pid ==0 ) { -int open_max =sysconf (_SC_OPEN_MAX), i;char *fd_buf =NULL ;char *br_buf =NULL ;char *helper_cmd =NULL ; -for (i =3 ; i < open_max; i++) { -if (i != sv[1 ]) { -close (i); - } - } - +close_all_fds_after_fork (sv[1 ]); fd_buf =g_strdup_printf ("%s%d" ,"--fd=" , sv[1 ]);if (strrchr (helper,' ' ) ||strrchr (helper,'\t' )) {
system/async-teardown.c +1 -36
@@ -26,40 +26,6 @@static pid_t the_ppid; -/* -* Close all open file descriptors. -*/ -static void close_all_open_fd (void ) -{ -struct dirent *de; -int fd, dfd; -DIR *dir; - -#ifdef CONFIG_CLOSE_RANGE -int r =close_range (0 , ~0U ,0 ); -if (!r) { -/* Success, no need to try other ways. */ -return ; - } -#endif - - dir =opendir ("/proc/self/fd" ); -if (!dir) { -/* If /proc is not mounted, there is nothing that can be done. */ -return ; - } -/* Avoid closing the directory. */ - dfd =dirfd (dir); - -for (de =readdir (dir); de; de =readdir (dir)) { - fd =atoi (de->d_name); -if (fd != dfd) { -close (fd); - } - } -closedir (dir); -} -static void hup_handler (int signal) {/* Check every second if this process has been reparented. */
@@ -85,9 +51,8 @@ static int async_teardown_fn(void *arg)/* * Close all file descriptors that might have been inherited from the * main qemu process when doing clone, needed to make libvirt happy. -* Not using close_range for increased compatibility with older kernels. */ -close_all_open_fd (); +qemu_close_all_open_fd (NULL ,0 );/* Set up a handler for SIGHUP and unblock SIGHUP. */ sigaction (SIGHUP , &sa,NULL );
util/osdep.c +129 -0
132 lines not on this page · raw message
Signature · 1 line
2.45.2
Hi Clément,
Quoted 47 lines · Clément Léger
Since commit
03e471c41d8b("qemu_init: increase NOFILE soft limit on POSIX"), the maximum number of file descriptors that can be opened are raised to nofile.rlim_max. On recent debian distro, this yield a maximum of 1073741816 file descriptors. Now, when forking to start qemu-bridge-helper, this actually callsclose()on the full possible file descriptor range (more precisely [3 -sysconf(_SC_OPEN_MAX)]) which takes a considerable amount of time. In order to reduce that time, factorize existing code to close all open files descriptors in a newqemu_close_all_open_fd()function. This function uses various methods to close all the open file descriptors ranging from the most efficient one to the least one. It also accepts an ordered array of file descriptors that should not be closed since this is required by the callers that calls it after forking.Signed-off-by Clément Léger <[email protected]>----
v3:
- Use STD*_FILENO defines instead of raw values
- Fix indentation ofclose_all_fds_after_fork()
- Check for nksip in fallback code
- Check for path starting with a '.' inqemu_close_all_open_fd_proc()
- Use unsigned forcur_skip
- Move ifdefs insideclose_fdsfunctions rather than redefining them
- Remove uneeded 'if(nskip)' test
- Add comments toclose_rangeversion
- Reduce range of skip fd as we find them in
- v2: https://lore.kernel.org/qemu-devel/[email protected]/v2:
- Factorizeasync_teardown.cclose_fdsimplementation as well astap.cones
- Apply checkpatch
- v1: https://lore.kernel.org/qemu-devel/[email protected]/--- include/qemu/osdep.h | 8 +++ net/tap.c | 33 +++++----- system/async-teardown.c | 37 +----------- util/osdep.c | 129 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 157 insertions(+), 50 deletions(-)include/qemu/osdep.h +0
-0
include/qemu/osdep.h static inline void qemu_reset_optind(void) · line 765
Quoted 9 lines
include/qemu/osdep.h +6
-0@@ -757,6 +757,14 @@ static inline void qemu_reset_optind(void)int qemu_fdatasync (int fd); +/** +* Close all open file descriptors except the ones supplied in the @skip array +* +* @skip: ordered array of distinct file descriptors that should not be closed +* @nskip: number of entries in the @skip array. +*/
Can we mention @skip is optional, and @nskip can be 0?
Also I'd assert(skip != NULL || nskip == 0).
Quoted 65 lines · Philippe Mathieu-Daudé
Hi Clément,
Quoted 51 lines · Clément Léger
Since commit
03e471c41d8b("qemu_init: increase NOFILE soft limit on POSIX"), the maximum number of file descriptors that can be opened are raised to nofile.rlim_max. On recent debian distro, this yield a maximum of 1073741816 file descriptors. Now, when forking to start qemu-bridge-helper, this actually callsclose()on the full possible file descriptor range (more precisely [3 -sysconf(_SC_OPEN_MAX)]) which takes a considerable amount of time. In order to reduce that time, factorize existing code to close all open files descriptors in a newqemu_close_all_open_fd()function. This function uses various methods to close all the open file descriptors ranging from the most efficient one to the least one. It also accepts an ordered array of file descriptors that should not be closed since this is required by the callers that calls it after forking.Signed-off-by Clément Léger <[email protected]>----
v3:
- Use STD*_FILENO defines instead of raw values
- Fix indentation ofclose_all_fds_after_fork()
- Check for nksip in fallback code
- Check for path starting with a '.' inqemu_close_all_open_fd_proc()
- Use unsigned forcur_skip
- Move ifdefs insideclose_fdsfunctions rather than redefining them
- Remove uneeded 'if(nskip)' test
- Add comments toclose_rangeversion
- Reduce range of skip fd as we find them in
- v2:
https://lore.kernel.org/qemu-devel/[email protected]/v2:
- Factorizeasync_teardown.cclose_fdsimplementation as well astap.cones
- Apply checkpatch
- v1:
https://lore.kernel.org/qemu-devel/[email protected]/---
include/qemu/osdep.h | 8 +++
net/tap.c | 33 +++++-----system/async-teardown.c| 37 +-----------
util/osdep.c | 129 ++++++++++++++++++++++++++++++++++++++++4 files changed, 157 insertions(+), 50 deletions(-)include/qemu/osdep.h +0
-0@@ -757,6 +757,14 @@ static inline void qemu_reset_optind(void) int qemu_fdatasync(int fd);Quoted 8 lines
+/**
+ * Close all open file descriptors except the ones supplied in the @skip array
+ *
+ * @skip: ordered array of distinct file descriptors that should not be closed
+ * @nskip: number of entries in the @skip array.
+ */Can we mention @skip is optional, and @nskip can be 0?
Quoted 1 line
Also I'd assert(skip != NULL || nskip == 0).
Yes sure, I'll add that.
Thanks,
Clément
util/osdep.c int qemu_fdatasync(int fd) · line 653
Quoted 5 lines · Clément Léger
util/osdep.c +5
-0+/* Restrict the range as we found fds matching start/end */ +if (i == skip_start) + skip_start++; +else if (i == skip_end) + skip_end--;
Need braces.
Otherwise,
r~
Quoted 9 lines · Richard Henderson
Quoted 6 lines · Clément Léger
+ /* Restrict the range as we found fds matching start/end */
+ if (i ==skip_start)
+ skip_start++;
+ else if (i ==skip_end)
+ skip_end--;Need braces.
Sorry for that, I'll run checkpatch before sending v4.
Thanks,
Clément
Quoted 7 lines
Otherwise,
Reviewed-by Richard Henderson <[email protected]>r~