linux-brain/include/linux/ipc_namespace.h
Guillaume Knispel 0cfb6aee70 ipc: optimize semget/shmget/msgget for lots of keys
ipc_findkey() used to scan all objects to look for the wanted key.  This
is slow when using a high number of keys.  This change adds an rhashtable
of kern_ipc_perm objects in ipc_ids, so that one lookup cease to be O(n).

This change gives a 865% improvement of benchmark reaim.jobs_per_min on a
56 threads Intel(R) Xeon(R) CPU E5-2695 v3 @ 2.30GHz with 256G memory [1]

Other (more micro) benchmark results, by the author: On an i5 laptop, the
following loop executed right after a reboot took, without and with this
change:

    for (int i = 0, k=0x424242; i < KEYS; ++i)
        semget(k++, 1, IPC_CREAT | 0600);

                 total       total          max single  max single
   KEYS        without        with        call without   call with

      1            3.5         4.9   µs            3.5         4.9
     10            7.6         8.6   µs            3.7         4.7
     32           16.2        15.9   µs            4.3         5.3
    100           72.9        41.8   µs            3.7         4.7
   1000        5,630.0       502.0   µs             *           *
  10000    1,340,000.0     7,240.0   µs             *           *
  31900   17,600,000.0    22,200.0   µs             *           *

 *: unreliable measure: high variance

The duration for a lookup-only usage was obtained by the same loop once
the keys are present:

                 total       total          max single  max single
   KEYS        without        with        call without   call with

      1            2.1         2.5   µs            2.1         2.5
     10            4.5         4.8   µs            2.2         2.3
     32           13.0        10.8   µs            2.3         2.8
    100           82.9        25.1   µs             *          2.3
   1000        5,780.0       217.0   µs             *           *
  10000    1,470,000.0     2,520.0   µs             *           *
  31900   17,400,000.0     7,810.0   µs             *           *

Finally, executing each semget() in a new process gave, when still
summing only the durations of these syscalls:

creation:
                 total       total
   KEYS        without        with

      1            3.7         5.0   µs
     10           32.9        36.7   µs
     32          125.0       109.0   µs
    100          523.0       353.0   µs
   1000       20,300.0     3,280.0   µs
  10000    2,470,000.0    46,700.0   µs
  31900   27,800,000.0   219,000.0   µs

lookup-only:
                 total       total
   KEYS        without        with

      1            2.5         2.7   µs
     10           25.4        24.4   µs
     32          106.0        72.6   µs
    100          591.0       352.0   µs
   1000       22,400.0     2,250.0   µs
  10000    2,510,000.0    25,700.0   µs
  31900   28,200,000.0   115,000.0   µs

[1] http://lkml.kernel.org/r/20170814060507.GE23258@yexl-desktop

Link: http://lkml.kernel.org/r/20170815194954.ck32ta2z35yuzpwp@debix
Signed-off-by: Guillaume Knispel <guillaume.knispel@supersonicimagine.com>
Reviewed-by: Marc Pardo <marc.pardo@supersonicimagine.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Serge Hallyn <serge@hallyn.com>
Cc: Andrey Vagin <avagin@openvz.org>
Cc: Guillaume Knispel <guillaume.knispel@supersonicimagine.com>
Cc: Marc Pardo <marc.pardo@supersonicimagine.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 18:26:51 -07:00

164 lines
4.5 KiB
C

#ifndef __IPC_NAMESPACE_H__
#define __IPC_NAMESPACE_H__
#include <linux/err.h>
#include <linux/idr.h>
#include <linux/rwsem.h>
#include <linux/notifier.h>
#include <linux/nsproxy.h>
#include <linux/ns_common.h>
#include <linux/refcount.h>
#include <linux/rhashtable.h>
struct user_namespace;
struct ipc_ids {
int in_use;
unsigned short seq;
bool tables_initialized;
struct rw_semaphore rwsem;
struct idr ipcs_idr;
int next_id;
struct rhashtable key_ht;
};
struct ipc_namespace {
refcount_t count;
struct ipc_ids ids[3];
int sem_ctls[4];
int used_sems;
unsigned int msg_ctlmax;
unsigned int msg_ctlmnb;
unsigned int msg_ctlmni;
atomic_t msg_bytes;
atomic_t msg_hdrs;
size_t shm_ctlmax;
size_t shm_ctlall;
unsigned long shm_tot;
int shm_ctlmni;
/*
* Defines whether IPC_RMID is forced for _all_ shm segments regardless
* of shmctl()
*/
int shm_rmid_forced;
struct notifier_block ipcns_nb;
/* The kern_mount of the mqueuefs sb. We take a ref on it */
struct vfsmount *mq_mnt;
/* # queues in this ns, protected by mq_lock */
unsigned int mq_queues_count;
/* next fields are set through sysctl */
unsigned int mq_queues_max; /* initialized to DFLT_QUEUESMAX */
unsigned int mq_msg_max; /* initialized to DFLT_MSGMAX */
unsigned int mq_msgsize_max; /* initialized to DFLT_MSGSIZEMAX */
unsigned int mq_msg_default;
unsigned int mq_msgsize_default;
/* user_ns which owns the ipc ns */
struct user_namespace *user_ns;
struct ucounts *ucounts;
struct ns_common ns;
} __randomize_layout;
extern struct ipc_namespace init_ipc_ns;
extern spinlock_t mq_lock;
#ifdef CONFIG_SYSVIPC
extern void shm_destroy_orphaned(struct ipc_namespace *ns);
#else /* CONFIG_SYSVIPC */
static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {}
#endif /* CONFIG_SYSVIPC */
#ifdef CONFIG_POSIX_MQUEUE
extern int mq_init_ns(struct ipc_namespace *ns);
/*
* POSIX Message Queue default values:
*
* MIN_*: Lowest value an admin can set the maximum unprivileged limit to
* DFLT_*MAX: Default values for the maximum unprivileged limits
* DFLT_{MSG,MSGSIZE}: Default values used when the user doesn't supply
* an attribute to the open call and the queue must be created
* HARD_*: Highest value the maximums can be set to. These are enforced
* on CAP_SYS_RESOURCE apps as well making them inviolate (so make them
* suitably high)
*
* POSIX Requirements:
* Per app minimum openable message queues - 8. This does not map well
* to the fact that we limit the number of queues on a per namespace
* basis instead of a per app basis. So, make the default high enough
* that no given app should have a hard time opening 8 queues.
* Minimum maximum for HARD_MSGMAX - 32767. I bumped this to 65536.
* Minimum maximum for HARD_MSGSIZEMAX - POSIX is silent on this. However,
* we have run into a situation where running applications in the wild
* require this to be at least 5MB, and preferably 10MB, so I set the
* value to 16MB in hopes that this user is the worst of the bunch and
* the new maximum will handle anyone else. I may have to revisit this
* in the future.
*/
#define DFLT_QUEUESMAX 256
#define MIN_MSGMAX 1
#define DFLT_MSG 10U
#define DFLT_MSGMAX 10
#define HARD_MSGMAX 65536
#define MIN_MSGSIZEMAX 128
#define DFLT_MSGSIZE 8192U
#define DFLT_MSGSIZEMAX 8192
#define HARD_MSGSIZEMAX (16*1024*1024)
#else
static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; }
#endif
#if defined(CONFIG_IPC_NS)
extern struct ipc_namespace *copy_ipcs(unsigned long flags,
struct user_namespace *user_ns, struct ipc_namespace *ns);
static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
{
if (ns)
refcount_inc(&ns->count);
return ns;
}
extern void put_ipc_ns(struct ipc_namespace *ns);
#else
static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
struct user_namespace *user_ns, struct ipc_namespace *ns)
{
if (flags & CLONE_NEWIPC)
return ERR_PTR(-EINVAL);
return ns;
}
static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
{
return ns;
}
static inline void put_ipc_ns(struct ipc_namespace *ns)
{
}
#endif
#ifdef CONFIG_POSIX_MQUEUE_SYSCTL
struct ctl_table_header;
extern struct ctl_table_header *mq_register_sysctl_table(void);
#else /* CONFIG_POSIX_MQUEUE_SYSCTL */
static inline struct ctl_table_header *mq_register_sysctl_table(void)
{
return NULL;
}
#endif /* CONFIG_POSIX_MQUEUE_SYSCTL */
#endif