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>
diff --git a/ipc/shm.c b/ipc/shm.c
index 8828b4c..8fc97be 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -72,14 +72,14 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp);
static int sysvipc_shm_proc_show(struct seq_file *s, void *it);
#endif
-void shm_init_ns(struct ipc_namespace *ns)
+int shm_init_ns(struct ipc_namespace *ns)
{
ns->shm_ctlmax = SHMMAX;
ns->shm_ctlall = SHMALL;
ns->shm_ctlmni = SHMMNI;
ns->shm_rmid_forced = 0;
ns->shm_tot = 0;
- ipc_init_ids(&shm_ids(ns));
+ return ipc_init_ids(&shm_ids(ns));
}
/*
@@ -95,7 +95,7 @@ static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
if (shp->shm_nattch) {
shp->shm_perm.mode |= SHM_DEST;
/* Do not find it any more */
- shp->shm_perm.key = IPC_PRIVATE;
+ ipc_set_key_private(&shm_ids(ns), &shp->shm_perm);
shm_unlock(shp);
} else
shm_destroy(ns, shp);
@@ -106,13 +106,15 @@ void shm_exit_ns(struct ipc_namespace *ns)
{
free_ipcs(ns, &shm_ids(ns), do_shm_rmid);
idr_destroy(&ns->ids[IPC_SHM_IDS].ipcs_idr);
+ rhashtable_destroy(&ns->ids[IPC_SHM_IDS].key_ht);
}
#endif
static int __init ipc_ns_init(void)
{
- shm_init_ns(&init_ipc_ns);
- return 0;
+ const int err = shm_init_ns(&init_ipc_ns);
+ WARN(err, "ipc: sysv shm_init_ns failed: %d\n", err);
+ return err;
}
pure_initcall(ipc_ns_init);