Skip to content

Q
qemu

openeuler / qemu

通知 10
Star 0
Fork 0
Q
qemu

体验新版 GitCode，发现更多精彩内容 >>

切换分支/标签
  1. 10 9月, 2016 2 次提交
    • L
      target-i386: present virtual L3 cache info for vcpus · 14c985cf
      由 Longpeng(Mike) 提交于 
      Some software algorithms are based on the hardware's cache info, for example,
for x86 linux kernel, when cpu1 want to wakeup a task on cpu2, cpu1 will trigger
a resched IPI and told cpu2 to do the wakeup if they don't share low level
cache. Oppositely, cpu1 will access cpu2's runqueue directly if they share llc.
The relevant linux-kernel code as bellow:

	static void ttwu_queue(struct task_struct *p, int cpu)
	{
		struct rq *rq = cpu_rq(cpu);
		......
		if (... && !cpus_share_cache(smp_processor_id(), cpu)) {
			......
			ttwu_queue_remote(p, cpu); /* will trigger RES IPI */
			return;
		}
		......
		ttwu_do_activate(rq, p, 0); /* access target's rq directly */
		......
	}

In real hardware, the cpus on the same socket share L3 cache, so one won't
trigger a resched IPIs when wakeup a task on others. But QEMU doesn't present a
virtual L3 cache info for VM, then the linux guest will trigger lots of RES IPIs
under some workloads even if the virtual cpus belongs to the same virtual socket.

For KVM, there will be lots of vmexit due to guest send IPIs.
The workload is a SAP HANA's testsuite, we run it one round(about 40 minuates)
and observe the (Suse11sp3)Guest's amounts of RES IPIs which triggering during
the period:
        No-L3           With-L3(applied this patch)
cpu0:	363890		44582
cpu1:	373405		43109
cpu2:	340783		43797
cpu3:	333854		43409
cpu4:	327170		40038
cpu5:	325491		39922
cpu6:	319129		42391
cpu7:	306480		41035
cpu8:	161139		32188
cpu9:	164649		31024
cpu10:	149823		30398
cpu11:	149823		32455
cpu12:	164830		35143
cpu13:	172269		35805
cpu14:	179979		33898
cpu15:	194505		32754
avg:	268963.6	40129.8

The VM's topology is "1*socket 8*cores 2*threads".
After present virtual L3 cache info for VM, the amounts of RES IPIs in guest
reduce 85%.

For KVM, vcpus send IPIs will cause vmexit which is expensive, so it can cause
severe performance degradation. We had tested the overall system performance if
vcpus actually run on sparate physical socket. With L3 cache, the performance
improves 7.2%~33.1%(avg:15.7%).
Signed-off-by: NLongpeng(Mike) <longpeng2@huawei.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
      14c985cf
    • L
      pc: Add 2.8 machine · a4d3c834
      由 Longpeng(Mike) 提交于 
      This will used by the next patch.
Signed-off-by: NLongpeng(Mike) <longpeng2@huawei.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
      a4d3c834
  3. 08 9月, 2016 6 次提交
  5. 07 9月, 2016 4 次提交
  7. 06 9月, 2016 16 次提交
  9. 05 9月, 2016 3 次提交
  11. 19 8月, 2016 1 次提交
  13. 18 8月, 2016 1 次提交
    • E
      block: fix deadlock in bdrv_co_flush · ce83ee57
      由 Evgeny Yakovlev 提交于 
      The following commit
    commit 3ff2f67a
    Author: Evgeny Yakovlev <eyakovlev@virtuozzo.com>
    Date:   Mon Jul 18 22:39:52 2016 +0300
    block: ignore flush requests when storage is clean
has introduced a regression.

There is a problem that it is still possible for 2 requests to execute
in non sequential fashion and sometimes this results in a deadlock
when bdrv_drain_one/all are called for BDS with such stalled requests.

1. Current flushed_gen and flush_started_gen is 1.
2. Request 1 enters bdrv_co_flush to with write_gen 1 (i.e. the same
   as flushed_gen). It gets past flushed_gen != flush_started_gen and
   sets flush_started_gen to 1 (again, the same it was before).
3. Request 1 yields somewhere before exiting bdrv_co_flush
4. Request 2 enters bdrv_co_flush with write_gen 2. It gets past
   flushed_gen != flush_started_gen and sets flush_started_gen to 2.
5. Request 2 runs to completion and sets flushed_gen to 2
6. Request 1 is resumed, runs to completion and sets flushed_gen to 1.
   However flush_started_gen is now 2.

From here on out flushed_gen is always != to flush_started_gen and all
further requests will wait on flush_queue. This change replaces
flush_started_gen with an explicitly tracked active flush request.
Signed-off-by: NEvgeny Yakovlev <eyakovlev@virtuozzo.com>
Signed-off-by: NDenis V. Lunev <den@openvz.org>
Message-id: 1471457214-3994-2-git-send-email-den@openvz.org
CC: Stefan Hajnoczi <stefanha@redhat.com>
CC: Fam Zheng <famz@redhat.com>
CC: Kevin Wolf <kwolf@redhat.com>
CC: Max Reitz <mreitz@redhat.com>
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>
      ce83ee57
  15. 16 8月, 2016 1 次提交
    • D
      virtio-gpu: fix missing log.h include file · 8afc224f
      由 Daniel P. Berrange 提交于 
      The virtio-gpu.h file defines a macro VIRTIO_GPU_FILL_CMD
which includes a call to qemu_log_mask, but does not
include qemu/log.h. In a default configure, it is lucky
and gets qemu/log.h indirectly due to the 'log' trace
backend being enabled. If that trace backend is disabled
though, eg

 ./configure --enable-trace-backends=nop

Then the build will fail:

In file included from /home/berrange/src/virt/qemu/hw/display/virtio-gpu-3d.c:19:0:
/home/berrange/src/virt/qemu/hw/display/virtio-gpu-3d.c: In function ‘virgl_cmd_create_resource_2d’:
/home/berrange/src/virt/qemu/include/hw/virtio/virtio-gpu.h:138:13: error: implicit declaration of function ‘qemu_log_mask’ [-Werror=implicit-function-declaration]
             qemu_log_mask(LOG_GUEST_ERROR,                              \
             ^
/home/berrange/src/virt/qemu/hw/display/virtio-gpu-3d.c:34:5: note: in expansion of macro ‘VIRTIO_GPU_FILL_CMD’
     VIRTIO_GPU_FILL_CMD(c2d);
     ^~~~~~~~~~~~~~~~~~~
/home/berrange/src/virt/qemu/hw/display/virtio-gpu-3d.c:34:5: error: nested extern declaration of ‘qemu_log_mask’ [-Werror=nested-externs]
In file included from /home/berrange/src/virt/qemu/hw/display/virtio-gpu-3d.c:19:0:
/home/berrange/src/virt/qemu/include/hw/virtio/virtio-gpu.h:138:27: error: ‘LOG_GUEST_ERROR’ undeclared (first use in this function)
             qemu_log_mask(LOG_GUEST_ERROR,                              \

[snip many more errors]
Signed-off-by: NDaniel P. Berrange <berrange@redhat.com>
Message-id: 1470648700-3474-1-git-send-email-berrange@redhat.com
Reviewed-by: NPeter Maydell <peter.maydell@linaro.org>
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>
      8afc224f
  17. 15 8月, 2016 1 次提交
  19. 13 8月, 2016 2 次提交
  21. 11 8月, 2016 1 次提交
  23. 10 8月, 2016 2 次提交
    • P
      clang: Fix warning reg. expansion to 'defined' · 2368635d
      由 Pranith Kumar 提交于 
      Clang produces the following warning. The warning is detailed here:
https://reviews.llvm.org/D15866. Fix the warning.

/home/pranith/devops/code/qemu/hw/display/qxl.c:507:5: warning: macro expansion producing 'defined' has undefined behavior [-Wexpansion-to-defined]
    ^
/home/pranith/devops/code/qemu/include/ui/qemu-spice.h:46:5: note: expanded from macro 'SPICE_NEEDS_SET_MM_TIME'
  (!defined(SPICE_SERVER_VERSION) || (SPICE_SERVER_VERSION < 0xc06))
    ^
/home/pranith/devops/code/qemu/hw/display/qxl.c:1074:5: warning: macro expansion producing 'defined' has undefined behavior [-Wexpansion-to-defined]
    ^
/home/pranith/devops/code/qemu/include/ui/qemu-spice.h:46:5: note: expanded from macro 'SPICE_NEEDS_SET_MM_TIME'
  (!defined(SPICE_SERVER_VERSION) || (SPICE_SERVER_VERSION < 0xc06))
Suggested-by: NPeter Maydell <peter.maydell@linaro.org>
Signed-off-by: NPranith Kumar <bobby.prani@gmail.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
      2368635d
    • P
      atomic: strip "const" from variables declared with typeof · 5927ed84
      由 Paolo Bonzini 提交于 
      With the latest clang, we have the following warning:

    /home/pranith/devops/code/qemu/include/qemu/seqlock.h:62:21: warning: passing 'typeof (*&sl->sequence) *' (aka 'const unsigned int *') to parameter of type 'unsigned int *' discards qualifiers [-Wincompatible-pointer-types-discards-qualifiers]
        return unlikely(atomic_read(&sl->sequence) != start);
                        ^~~~~~~~~~~~~~~~~~~~~~~~~~
    /home/pranith/devops/code/qemu/include/qemu/atomic.h:58:25: note: expanded from macro 'atomic_read'
        __atomic_load(ptr, &_val, __ATOMIC_RELAXED);     \
                           ^~~~~

Stripping const is a bit tricky due to promotions, but it is doable
with either C11 _Generic or GCC extensions.  Use the latter.
Reported-by: NPranith Kumar <bobby.prani@gmail.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
[pranith: Add conversion for bool type]
Signed-off-by: NPranith Kumar <bobby.prani@gmail.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
      5927ed84