CMPXCHG latency

By: Linus Torvalds (, April 1, 2008 7:08 am
Room: Moderated Discussions
Michael S ( on 4/1/08 wrote:
>You made a very good points but I somehow have a doubt that
>in cases you mentioned there is a measurable difference
>between Lock CMPXCHG taking 25 clocks or 2 clocks.

Remember: this is more than just locking. It's also the
simple atomic inc/dec for statistics and reference counts.

We definitely have hot paths in the kernel where the locking
and reference count updates are quite a noticeable cost. For
things like pathname lookup, for example, we end up taking
a lock and incrementing (and then decrementing when we're
done) a reference count for each component.

So when you do something like a recursive "stat()" on each
file in a subdirectory (and hey, it's what an SCM will do
to check that files are all up-to-date, or what "make" will
do to check the timestamps of all the dependencies), when
it is all cached, the locking and refcounting is actually a
big part of the kernel costs.

Is it half? No. But we're talking 10+% if everything else
is going well (which it often is - developers make sure
that their working tree are all happily cached in memory
etc). That's a biggish deal.

It's quite visible for things like page faulting too. The
cost of the fault itself is bigger, but once you fault,
if the page is just a read-only page from the cache (which
is not an uncommon case - think demand-loading of an
executable), a noticeable part of the cost is again the
locking and the reference counting. To the point that I
could easily see a single new lock we added a few months
ago in our page fault costs.

(Page faulting is important in traditional UNIX loads since
it's how new programs are loaded - think of shell scripting
and how many hundreds of small programs are loaded for just
something trivial. Yeah, you wouldn't use shell for anything
performance-critical, but all those "not critical" parts end
up adding up ;^)

Of course, it's true that on most loads, the actual kernel
cost itself is already just a very small percentage of the
real application performance. Rather few applications
have more than 10% of their time spent in the kernel, and
if those few locks are then another 10% of some
paths, it's not going to be visible to most people. You'll
see performance improvements that are mostly in the noise.

Me, because I profile kernel code, I see the kernel side,
and there it's one of the bigger single improvements (the
other being memory copying and clearing) I could hope for
from a performance angle.

< Previous Post in ThreadNext Post in Thread >
TopicPosted ByDate
Nehalem Architecture: Improvements Detailed Blut Aus Nord2008/03/17 02:52 PM
  Nehalem Architecture: Improvements Detailed bah2008/03/17 04:45 PM
    Nehalem Architecture: Improvements Detailed Linus Torvalds2008/03/17 06:14 PM
      Nehalem Architecture: Improvements Detailed Gabriele Svelto2008/03/18 01:11 AM
        Nehalem Architecture: Improvements Detailed Henrik S2008/03/18 04:23 AM
        Nehalem Architecture: Improvements Detailed Doug Siebert2008/03/18 09:48 PM
          Nehalem Architecture: Improvements Detailed anon2008/03/18 10:37 PM
            Nehalem Architecture: Improvements Detailed Doug Siebert2008/03/19 05:23 PM
          Nehalem Architecture: Improvements Detailed Ian Ollmann2008/03/19 08:15 AM
            SSE 4.2 Michael S2008/03/19 04:13 PM
              SSE 4.2 Ian Ollmann2008/03/20 09:56 AM
              SSE 4.2 anonymous2008/03/20 12:29 PM
                SSE 4.2 David W. Hess2008/03/21 07:24 AM
                  SSE 4.2 anonymous2008/03/22 07:27 AM
      CMPXCHG latencyDavid Kanter2008/03/28 05:59 PM
        CMPXCHG latencyanonymous coward2008/03/28 10:24 PM
          CMPXCHG latencyDavid Kanter2008/03/28 10:26 PM
            CMPXCHG latencyLinus Torvalds2008/03/29 11:43 AM
              CMPXCHG latencyDavid W. Hess2008/03/29 11:56 AM
              CMPXCHG latencyLinus Torvalds2008/03/29 02:17 PM
                CMPXCHG latencyGabriele Svelto2008/03/31 12:25 AM
                  CMPXCHG latencyMichael S2008/03/31 12:38 AM
                    CMPXCHG latencynick2008/03/31 12:52 AM
                      CMPXCHG latencyMichael S2008/03/31 01:51 AM
                        CMPXCHG latencyGabriele Svelto2008/03/31 02:08 AM
                        CMPXCHG latencynick2008/03/31 07:20 PM
                          CMPXCHG latencyMichael S2008/04/01 01:14 AM
                            CMPXCHG latencynick2008/04/01 02:34 AM
                    CMPXCHG latencyLinus Torvalds2008/03/31 10:16 AM
                      CMPXCHG latencyAaron Spink2008/03/31 07:15 PM
                        CMPXCHG latencynick2008/03/31 07:34 PM
                        CMPXCHG latencyLinus Torvalds2008/04/01 08:25 AM
                          CMPXCHG latencyZan2008/04/01 09:54 PM
                          CMPXCHG latencyZan2008/04/02 12:11 AM
                            CMPXCHG latencyLinus Torvalds2008/04/02 08:04 AM
                              CMPXCHG latencyZan2008/04/02 11:02 AM
                                CMPXCHG latencyLinus Torvalds2008/04/02 12:02 PM
                                  CMPXCHG latencyZan2008/04/02 04:15 PM
                      CMPXCHG latencyMichael S2008/04/01 01:26 AM
                        CMPXCHG latencyLinus Torvalds2008/04/01 07:08 AM
                CMPXCHG latency - Intel sourceWouter Tinus2008/04/02 12:36 PM
                  CMPXCHG latency - Intel sourceLinus Torvalds2008/04/02 02:21 PM
                    CMPXCHG latency - Intel sourceDavid Kanter2008/04/02 02:39 PM
    Nehalem Architecture: Improvements Detailed Philip Honermann2008/03/19 01:11 PM
      Nehalem Architecture: Improvements Detailed Linus Torvalds2008/03/19 01:43 PM
        CMPXCHG - all or nothingMichael S2008/03/19 03:49 PM
          multithreading - all or nothingno@thanks.com2008/03/19 05:17 PM
          CMPXCHG - all or nothingLinus Torvalds2008/03/19 05:21 PM
            CMPXCHG - all or nothingMichael S2008/03/20 06:38 AM
              CMPXCHG - all or nothingLinus Torvalds2008/03/20 08:45 AM
                CMPXCHG - all or nothingMichael S2008/03/21 07:08 AM
                  CMPXCHG - all or nothingLinus Torvalds2008/03/21 08:47 AM
            CMPXCHG - all or nothingHenrik S2008/03/20 10:09 AM
              CMPXCHG - all or nothingLinus Torvalds2008/03/20 10:53 AM
                CMPXCHG - all or nothingHenrik S2008/03/20 12:03 PM
                  CMPXCHG - all or nothingLinus Torvalds2008/03/20 01:12 PM
                    CMPXCHG - all or nothingHenrik S2008/03/21 12:13 AM
                      CMPXCHG - all or nothingGabriele Svelto2008/03/21 01:22 AM
        Nehalem Architecture: Improvements Detailed Philip Honermann2008/03/19 06:28 PM
          Nehalem Architecture: Improvements Detailed Linus Torvalds2008/03/19 07:42 PM
            Nehalem Architecture: Improvements Detailed Philip Honermann2008/03/20 06:03 PM
              Nehalem Architecture: Improvements Detailed Linus Torvalds2008/03/20 06:33 PM
                Nehalem Architecture: Improvements Detailed Philip Honermann2008/03/25 06:37 AM
                  Nehalem Architecture: Improvements Detailed Linus Torvalds2008/03/25 08:52 AM
                    What is DCAS? (NT)David Kanter2008/03/25 10:13 AM
                      Double compare-and-exchangeHenrik S2008/03/25 10:57 AM
                        Double compare-and-exchangeLinus Torvalds2008/03/25 11:38 AM
                          Double compare-and-exchangesavantu2008/03/25 01:54 PM
                            Double compare-and-exchangeLinus Torvalds2008/03/25 04:09 PM
                              Double compare-and-exchangeJamie Lucier2008/03/25 08:55 PM
                                Double compare-and-exchangesavantu2008/03/25 09:15 PM
                                  Double compare-and-exchangeHenrik S2008/03/26 08:40 AM
                                    Double compare-and-exchangeArun Ramakrishnan2008/03/27 02:07 AM
                                      Double compare-and-exchangeHenrik S2008/03/27 04:45 AM
                                  Surely GPL applies ?Richard Cownie2008/03/26 10:05 AM
                                    Surely GPL applies ?anon2008/03/26 02:58 PM
                                    Surely GPL applies ?Paul2008/03/26 05:01 PM
                                Double compare-and-exchangesomeone2008/03/25 09:18 PM
                                  Double compare-and-exchangeArun Ramakrishnan2008/03/27 02:03 AM
                                    Double compare-and-exchangesavantu2008/03/27 03:01 AM
                                      Double compare-and-exchangeArun Ramakrishnan2008/03/30 09:09 AM
                                        Double compare-and-exchangesavantu2008/03/30 09:59 AM
                                Double compare-and-exchangeLinus Torvalds2008/03/26 10:50 AM
                                  Double compare-and-exchangeanon2008/03/26 04:47 PM
                                  Double compare-and-exchangePaul2008/03/26 05:07 PM
                          Double compare-and-exchangeHoward Chu2008/03/25 05:18 PM
  Nehalem Architecture: Improvements Detailed Mr. Camel2008/03/17 08:50 PM
    Nehalem Architecture: Improvements Detailed anonymous2008/03/17 09:20 PM
  TFP will finally come :-)Paul A. Clayton2008/03/18 12:56 PM
  Nehalem Architecture: Improvements Detailed IntelUser20002008/03/27 07:46 PM
    Nehalem Architecture: Improvements Detailed David Kanter2008/03/27 10:21 PM
      Nehalem Architecture: Improvements Detailed nick2008/03/27 11:06 PM
        Nehalem Architecture: Improvements Detailed David Kanter2008/03/28 02:45 PM
          Nehalem Architecture: Improvements Detailed nick2008/03/28 07:52 PM
  L1 I-cachepuzzled2008/04/01 07:53 AM
    L1 I-cacheS. Rao2008/04/01 09:47 AM
    L1 I-cacherwessel2008/04/01 12:23 PM
    L1 I-cacheGabriele Svelto2008/04/03 12:30 AM
Reply to this Topic
Body: No Text
How do you spell tangerine? 🍊