sched domains kernbench improvements

From: Nick Piggin (piggin_at_cyberone.com.au)
Date: 02/28/04

  • Next message: Adrian Bunk: "[2.6 patch] tmscsim: remove kernel kenel 2.2 #ifdef's" 
    Date:	Sat, 28 Feb 2004 20:21:02 +1100
To: Con Kolivas <conman@kolivas.net>, Andrew Morton <akpm@osdl.org>

    Con,
    I was able to reproduce your half-load kernbench problems
    on the non-NUMA stp 8-way.

    I made a pretty simple "lessidle" patch which tweaks some
    sched domain parameters to be more inclined to move tasks,
    especially when idle. That brought performance to nearly
    exactly the same as 2.6.3.

    Context switches are still up, but user and system time
    is down a bit. So indicates it is still less balance-happy
    but is obviously enough to bring the idle time down.

    2.6.3: http://khack.osdl.org/stp/288459/
    2.6.3-mm4-lessidle: http://khack.osdl.org/stp/288995/

    Phew! So it is more a matter of tuning than anything
    fundamental. It may be that the patch now makes balancing
    too aggressive, but it is probably better to err on the
    side that is closer to 2.6 behaviour.

    I haven't tested this on much else.

     linux-2.6-npiggin/include/linux/sched.h | 16 ++++++++--------
     linux-2.6-npiggin/kernel/sched.c | 5 +++++
     2 files changed, 13 insertions(+), 8 deletions(-)

    diff -puN include/linux/sched.h~sched-lessidle include/linux/sched.h
    --- linux-2.6/include/linux/sched.h~sched-lessidle 2004-02-21 10:57:07.000000000 +1100
    +++ linux-2.6-npiggin/include/linux/sched.h 2004-02-21 10:59:46.000000000 +1100
    @@ -598,11 +598,11 @@ struct sched_domain {
             .parent = NULL, \
             .groups = NULL, \
             .min_interval = 1, \
    - .max_interval = 8, \
    - .busy_factor = 32, \
    + .max_interval = 4, \
    + .busy_factor = 64, \
             .imbalance_pct = 125, \
    - .cache_hot_time = (5*1000000), \
    - .cache_nice_tries = 2, \
    + .cache_hot_time = (5*1000000/2), \
    + .cache_nice_tries = 1, \
             .flags = SD_FLAG_FASTMIGRATE | SD_FLAG_NEWIDLE,\
             .last_balance = jiffies, \
             .balance_interval = 1, \
    @@ -615,11 +615,11 @@ struct sched_domain {
             .span = CPU_MASK_NONE, \
             .parent = NULL, \
             .groups = NULL, \
    - .min_interval = 20, \
    - .max_interval = 1000*fls(num_online_cpus()),\
    - .busy_factor = 4, \
    + .min_interval = 8, \
    + .max_interval = 256*fls(num_online_cpus()),\
    + .busy_factor = 8, \
             .imbalance_pct = 125, \
    - .cache_hot_time = (5*1000000), \
    + .cache_hot_time = (10*1000000), \
             .cache_nice_tries = 1, \
             .flags = SD_FLAG_EXEC, \
             .last_balance = jiffies, \
    diff -puN kernel/sched.c~sched-lessidle kernel/sched.c
    --- linux-2.6/kernel/sched.c~sched-lessidle 2004-02-21 10:57:10.000000000 +1100
    +++ linux-2.6-npiggin/kernel/sched.c 2004-02-21 16:15:18.000000000 +1100
    @@ -1493,6 +1493,11 @@ nextgroup:
             return busiest;
     
     out_balanced:
    + if (busiest && idle == NEWLY_IDLE) {
    + *imbalance = 1;
    + return busiest;
    + }
    +
             *imbalance = 0;
             return NULL;
     }

    _

    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  • Next message: Adrian Bunk: "[2.6 patch] tmscsim: remove kernel kenel 2.2 #ifdef's"

    Relevant Pages