[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <fc431a95-789a-6c02-13d0-d0d01916ee99@redhat.com>
Date: Fri, 22 Mar 2019 16:13:52 -0400
From: Carlos O'Donell <codonell@...hat.com>
To: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Carlos O'Donell <carlos@...hat.com>
Cc: Florian Weimer <fweimer@...hat.com>,
Joseph Myers <joseph@...esourcery.com>,
Szabolcs Nagy <szabolcs.nagy@....com>,
libc-alpha@...rceware.org, Thomas Gleixner <tglx@...utronix.de>,
Ben Maurer <bmaurer@...com>,
Peter Zijlstra <peterz@...radead.org>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
Boqun Feng <boqun.feng@...il.com>,
Will Deacon <will.deacon@....com>,
Dave Watson <davejwatson@...com>, Paul Turner <pjt@...gle.com>,
linux-kernel@...r.kernel.org, linux-api@...r.kernel.org
Subject: Re: [PATCH 2/4] glibc: sched_getcpu(): use rseq cpu_id TLS on Linux
On 2/12/19 2:42 PM, Mathieu Desnoyers wrote:
> When available, use the cpu_id field from __rseq_abi on Linux to
> implement sched_getcpu(). Fall-back on the vgetcpu vDSO if unavailable.
>
> Benchmarks:
>
> x86-64: Intel E5-2630 v3@...0GHz, 16-core, hyperthreading
This patch looks good to me for master, but is blocked on patch 1/4
being reworked.
Reviewed-by: Carlos O'Donell <carlos@...hat.com>
> glibc sched_getcpu(): 13.7 ns (baseline)
> glibc sched_getcpu() using rseq: 2.5 ns (speedup: 5.5x)
> inline load cpuid from __rseq_abi TLS: 0.8 ns (speedup: 17.1x)
>
> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
> CC: Carlos O'Donell <carlos@...hat.com>
> CC: Florian Weimer <fweimer@...hat.com>
> CC: Joseph Myers <joseph@...esourcery.com>
> CC: Szabolcs Nagy <szabolcs.nagy@....com>
> CC: Thomas Gleixner <tglx@...utronix.de>
> CC: Ben Maurer <bmaurer@...com>
> CC: Peter Zijlstra <peterz@...radead.org>
> CC: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
> CC: Boqun Feng <boqun.feng@...il.com>
> CC: Will Deacon <will.deacon@....com>
> CC: Dave Watson <davejwatson@...com>
> CC: Paul Turner <pjt@...gle.com>
> CC: libc-alpha@...rceware.org
> CC: linux-kernel@...r.kernel.org
> CC: linux-api@...r.kernel.org
> ---
> sysdeps/unix/sysv/linux/sched_getcpu.c | 25 +++++++++++++++++++++++--
> 1 file changed, 23 insertions(+), 2 deletions(-)
>
> diff --git a/sysdeps/unix/sysv/linux/sched_getcpu.c b/sysdeps/unix/sysv/linux/sched_getcpu.c
> index fb0d317f83..8bfb03778b 100644
> --- a/sysdeps/unix/sysv/linux/sched_getcpu.c
> +++ b/sysdeps/unix/sysv/linux/sched_getcpu.c
> @@ -24,8 +24,8 @@
> #endif
> #include <sysdep-vdso.h>
>
> -int
> -sched_getcpu (void)
> +static int
> +vsyscall_sched_getcpu (void)
OK.
> {
> #ifdef __NR_getcpu
> unsigned int cpu;
> @@ -37,3 +37,24 @@ sched_getcpu (void)
> return -1;
> #endif
> }
> +
> +#ifdef __NR_rseq
> +#include <linux/rseq.h>
> +
> +extern __attribute__ ((tls_model ("initial-exec")))
> +__thread volatile struct rseq __rseq_abi;
OK.
> +
> +int
> +sched_getcpu (void)
> +{
> + int cpu_id = __rseq_abi.cpu_id;
> +
> + return cpu_id >= 0 ? cpu_id : vsyscall_sched_getcpu ();
OK. Impressive :-)
> +}
> +#else
> +int
> +sched_getcpu (void)
> +{
> + return vsyscall_sched_getcpu ();
OK.
> +}
> +#endif
>
--
Cheers,
Carlos.
Powered by blists - more mailing lists