Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
大约 1 年 前同步成功

通知 156
Star 36
Fork 7
cloud-kernel
cloud-kernel

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 08 8月, 2013 26 次提交
  3. 31 7月, 2013 8 次提交
  5. 23 7月, 2013 6 次提交
    • P
      sched: Micro-optimize the smart wake-affine logic · 7d9ffa89
      由 Peter Zijlstra 提交于 
      Smart wake-affine is using node-size as the factor currently, but the overhead
of the mask operation is high.

Thus, this patch introduce the 'sd_llc_size' percpu variable, which will record
the highest cache-share domain size, and make it to be the new factor, in order
to reduce the overhead and make it more reasonable.
Tested-by: NDavidlohr Bueso <davidlohr.bueso@hp.com>
Tested-by: NMichael Wang <wangyun@linux.vnet.ibm.com>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Acked-by: NMichael Wang <wangyun@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Link: http://lkml.kernel.org/r/51D5008E.6030102@linux.vnet.ibm.com
[ Tidied up the changelog. ]
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      7d9ffa89
    • M
      sched: Implement smarter wake-affine logic · 62470419
      由 Michael Wang 提交于 
      The wake-affine scheduler feature is currently always trying to pull
the wakee close to the waker. In theory this should be beneficial if
the waker's CPU caches hot data for the wakee, and it's also beneficial
in the extreme ping-pong high context switch rate case.

Testing shows it can benefit hackbench up to 15%.

However, the feature is somewhat blind, from which some workloads
such as pgbench suffer. It's also time-consuming algorithmically.

Testing shows it can damage pgbench up to 50% - far more than the
benefit it brings in the best case.

So wake-affine should be smarter and it should realize when to
stop its thankless effort at trying to find a suitable CPU to wake on.

This patch introduces 'wakee_flips', which will be increased each
time the task flips (switches) its wakee target.

So a high 'wakee_flips' value means the task has more than one
wakee, and the bigger the number, the higher the wakeup frequency.

Now when making the decision on whether to pull or not, pay attention to
the wakee with a high 'wakee_flips', pulling such a task may benefit
the wakee. Also imply that the waker will face cruel competition later,
it could be very cruel or very fast depends on the story behind
'wakee_flips', waker therefore suffers.

Furthermore, if waker also has a high 'wakee_flips', that implies that
multiple tasks rely on it, then waker's higher latency will damage all
of them, so pulling wakee seems to be a bad deal.

Thus, when 'waker->wakee_flips / wakee->wakee_flips' becomes
higher and higher, the cost of pulling seems to be worse and worse.

The patch therefore helps the wake-affine feature to stop its pulling
work when:

	wakee->wakee_flips > factor &&
	waker->wakee_flips > (factor * wakee->wakee_flips)

The 'factor' here is the number of CPUs in the current CPU's NUMA node,
so a bigger node will lead to more pulling since the trial becomes more
severe.

After applying the patch, pgbench shows up to 40% improvements and no regressions.

Tested with 12 cpu x86 server and tip 3.10.0-rc7.

The percentages in the final column highlight the areas with the biggest wins,
all other areas improved as well:

	pgbench		    base	smart

	| db_size | clients |  tps  |	|  tps  |
	+---------+---------+-------+   +-------+
	| 22 MB   |       1 | 10598 |   | 10796 |
	| 22 MB   |       2 | 21257 |   | 21336 |
	| 22 MB   |       4 | 41386 |   | 41622 |
	| 22 MB   |       8 | 51253 |   | 57932 |
	| 22 MB   |      12 | 48570 |   | 54000 |
	| 22 MB   |      16 | 46748 |   | 55982 | +19.75%
	| 22 MB   |      24 | 44346 |   | 55847 | +25.93%
	| 22 MB   |      32 | 43460 |   | 54614 | +25.66%
	| 7484 MB |       1 |  8951 |   |  9193 |
	| 7484 MB |       2 | 19233 |   | 19240 |
	| 7484 MB |       4 | 37239 |   | 37302 |
	| 7484 MB |       8 | 46087 |   | 50018 |
	| 7484 MB |      12 | 42054 |   | 48763 |
	| 7484 MB |      16 | 40765 |   | 51633 | +26.66%
	| 7484 MB |      24 | 37651 |   | 52377 | +39.11%
	| 7484 MB |      32 | 37056 |   | 51108 | +37.92%
	| 15 GB   |       1 |  8845 |   |  9104 |
	| 15 GB   |       2 | 19094 |   | 19162 |
	| 15 GB   |       4 | 36979 |   | 36983 |
	| 15 GB   |       8 | 46087 |   | 49977 |
	| 15 GB   |      12 | 41901 |   | 48591 |
	| 15 GB   |      16 | 40147 |   | 50651 | +26.16%
	| 15 GB   |      24 | 37250 |   | 52365 | +40.58%
	| 15 GB   |      32 | 36470 |   | 50015 | +37.14%
Signed-off-by: NMichael Wang <wangyun@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: NPeter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/51D50057.9000809@linux.vnet.ibm.com
[ Improved the changelog. ]
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      62470419
    • V
      sched: Move h_load calculation to task_h_load() · 68520796
      由 Vladimir Davydov 提交于 
      The bad thing about update_h_load(), which computes hierarchical load
factor for task groups, is that it is called for each task group in the
system before every load balancer run, and since rebalance can be
triggered very often, this function can eat really a lot of cpu time if
there are many cpu cgroups in the system.

Although the situation was improved significantly by commit a35b6466
('sched, cgroup: Reduce rq->lock hold times for large cgroup
hierarchies'), the problem still can arise under some kinds of loads,
e.g. when cpus are switching from idle to busy and back very frequently.

For instance, when I start 1000 of processes that wake up every
millisecond on my 8 cpus host, 'top' and 'perf top' show:

Cpu(s): 17.8%us, 24.3%sy,  0.0%ni, 57.9%id,  0.0%wa,  0.0%hi,  0.0%si
Events: 243K cycles
  7.57%  [kernel]               [k] __schedule
  7.08%  [kernel]               [k] timerqueue_add
  6.13%  libc-2.12.so           [.] usleep

Then if I create 10000 *idle* cpu cgroups (no processes in them), cpu
usage increases significantly although the 'wakers' are still executing
in the root cpu cgroup:

Cpu(s): 19.1%us, 48.7%sy,  0.0%ni, 31.6%id,  0.0%wa,  0.0%hi,  0.7%si
Events: 230K cycles
 24.56%  [kernel]            [k] tg_load_down
  5.76%  [kernel]            [k] __schedule

This happens because this particular kind of load triggers 'new idle'
rebalance very frequently, which requires calling update_h_load(),
which, in turn, calls tg_load_down() for every *idle* cpu cgroup even
though it is absolutely useless, because idle cpu cgroups have no tasks
to pull.

This patch tries to improve the situation by making h_load calculation
proceed only when h_load is really necessary. To achieve this, it
substitutes update_h_load() with update_cfs_rq_h_load(), which computes
h_load only for a given cfs_rq and all its ascendants, and makes the
load balancer call this function whenever it considers if a task should
be pulled, i.e. it moves h_load calculations directly to task_h_load().
For h_load of the same cfs_rq not to be updated multiple times (in case
several tasks in the same cgroup are considered during the same balance
run), the patch keeps the time of the last h_load update for each cfs_rq
and breaks calculation when it finds h_load to be uptodate.

The benefit of it is that h_load is computed only for those cfs_rq's,
which really need it, in particular all idle task groups are skipped.
Although this, in fact, moves h_load calculation under rq lock, it
should not affect latency much, because the amount of work done under rq
lock while trying to pull tasks is limited by sched_nr_migrate.

After the patch applied with the setup described above (1000 wakers in
the root cgroup and 10000 idle cgroups), I get:

Cpu(s): 16.9%us, 24.8%sy,  0.0%ni, 58.4%id,  0.0%wa,  0.0%hi,  0.0%si
Events: 242K cycles
  7.57%  [kernel]                  [k] __schedule
  6.70%  [kernel]                  [k] timerqueue_add
  5.93%  libc-2.12.so              [.] usleep
Signed-off-by: NVladimir Davydov <vdavydov@parallels.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1373896159-1278-1-git-send-email-vdavydov@parallels.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      68520796
    • A
      perf tools: Add test for converting perf time to/from TSC · 3bd5a5fc
      由 Adrian Hunter 提交于 
      The test uses the newly added cap_usr_time_zero and time_zero of
perf_event_mmap_page.  TSC from rdtsc is compared with the time
from 2 perf events.  The test passes if the calculated times are
all in the correct order.
Signed-off-by: NAdrian Hunter <adrian.hunter@intel.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/1372425741-1676-4-git-send-email-adrian.hunter@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      3bd5a5fc
    • A
      perf/x86: Add ability to calculate TSC from perf sample timestamps · c73deb6a
      由 Adrian Hunter 提交于 
      For modern CPUs, perf clock is directly related to TSC.  TSC
can be calculated from perf clock and vice versa using a simple
calculation.  Two of the three componenets of that calculation
are already exported in struct perf_event_mmap_page.  This patch
exports the third.
Signed-off-by: NAdrian Hunter <adrian.hunter@intel.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1372425741-1676-3-git-send-email-adrian.hunter@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      c73deb6a
    • A
      perf: Fix broken union in 'struct perf_event_mmap_page' · 860f085b
      由 Adrian Hunter 提交于 
      The capabilities bits must not be "union'ed" together.
Put them in a separate struct.
Signed-off-by: NAdrian Hunter <adrian.hunter@intel.com>
Signed-off-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1372425741-1676-2-git-send-email-adrian.hunter@intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      860f085b