Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1343336

Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread

From Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Newsgroups linux.kernel
Subject Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread
Date 2016-02-25 18:20 +0100
Message-ID <r67K2-71c-15@gated-at.bofh.it> (permalink)
References <r5uyZ-4cb-5@gated-at.bofh.it> <r5uz0-4cb-19@gated-at.bofh.it> <r60Sg-1Sg-47@gated-at.bofh.it> <r67qH-6DX-25@gated-at.bofh.it> <r67An-6XN-31@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

----- On Feb 25, 2016, at 12:04 PM, Peter Zijlstra peterz@infradead.org wrote:

> On Thu, Feb 25, 2016 at 04:55:26PM +0000, Mathieu Desnoyers wrote:
>> ----- On Feb 25, 2016, at 4:56 AM, Peter Zijlstra peterz@infradead.org wrote:
>> The restartable sequences are intrinsically designed to work
>> on per-cpu data, so they need to fetch the current CPU number
>> within the rseq critical section. This is where the getcpu_cache
>> system call becomes very useful when combined with rseq:
>> getcpu_cache allows reading the current CPU number in a
>> fraction of cycle.
> 
> Yes yes, I know how restartable sequences work.
> 
> But what I worry about is that they want a cpu number and a sequence
> number, and for performance it would be very good if those live in the
> same cacheline.
> 
> That means either getcpu needs to grow a seq number, or restartable
> sequences need to _also_ provide the cpu number.

If we plan things well, we could have both the cpu number and the
seqnum in the same cache line, registered by two different system
calls. It's up to user-space to organize those two variables
to fit within the same cache-line.

getcpu_cache GETCPU_CACHE_SET operation takes the address where
the CPU number should live as input.

rseq system call could do the same for the seqnum address.

The question becomes: how do we introduce this to user-space,
considering that only a single address per thread is allowed
for each of getcpu_cache and rseq ?

If both CPU number and seqnum are centralized in a TLS within
e.g. glibc, that would be OK, but if we intend to allow libraries
or applications to directly register their own getcpu_cache
address and/or rseq, we may end up in situations where we have
to fallback on using two different cache-lines. But how much
should we care about performance in cases where non-generic
libraries directly use those system calls ?

Thoughts ?

Thanks,

Mathieu

-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-24 00:30 +0100
  Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Thomas Gleixner <tglx@linutronix.de> - 2016-02-24 12:20 +0100
    Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-24 18:20 +0100
    Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread Rasmus Villemoes <linux@rasmusvillemoes.dk> - 2016-02-26 00:40 +0100
      Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-26 18:50 +0100
  Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-02-25 11:00 +0100
    Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-25 18:00 +0100
      Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-02-25 18:10 +0100
        Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-25 18:20 +0100
          Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-02-26 12:40 +0100
            Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Thomas Gleixner <tglx@linutronix.de> - 2016-02-26 17:40 +0100
              Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-26 18:30 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Thomas Gleixner <tglx@linutronix.de> - 2016-02-26 19:10 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-26 21:30 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread "H. Peter Anvin" <hpa@zytor.com> - 2016-02-27 00:10 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-27 01:50 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread "H. Peter Anvin" <hpa@zytor.com> - 2016-02-27 07:30 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-27 15:20 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-02-27 16:00 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Linus Torvalds <torvalds@linux-foundation.org> - 2016-02-27 19:40 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread "H. Peter Anvin" <hpa@zytor.com> - 2016-02-27 20:10 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-28 01:00 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Linus Torvalds <torvalds@linux-foundation.org> - 2016-02-28 02:00 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-28 15:40 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-02-29 11:40 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-03-01 21:30 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-03-01 22:40 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-03-01 22:40 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread "H. Peter Anvin" <hpa@zytor.com> - 2016-03-01 23:00 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-03-02 11:40 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-02-29 11:40 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread Arnd Bergmann <arnd@arndb.de> - 2016-02-29 11:50 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-02-29 13:50 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread Arnd Bergmann <arnd@arndb.de> - 2016-02-29 14:20 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread "H. Peter Anvin" <hpa@zytor.com> - 2016-02-29 19:30 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Geert Uytterhoeven <geert@linux-m68k.org> - 2016-03-02 11:50 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread "H. Peter Anvin" <hpa@zytor.com> - 2016-03-01 19:30 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Mathieu Desnoyers <mathieu.desnoyers@efficios.com> - 2016-03-01 19:50 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Geert Uytterhoeven <geert@linux-m68k.org> - 2016-02-28 14:10 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Linus Torvalds <torvalds@linux-foundation.org> - 2016-02-28 17:30 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of  running thread Peter Zijlstra <peterz@infradead.org> - 2016-02-29 11:10 +0100
                Re: [PATCH v4 1/5] getcpu_cache system call: cache CPU number of running thread "H. Peter Anvin" <hpa@zytor.com> - 2016-02-27 16:10 +0100

csiph-web