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. 22 1月, 2009 2 次提交
  3. 09 1月, 2009 1 次提交
  5. 03 1月, 2009 1 次提交
  7. 16 12月, 2008 1 次提交
  9. 13 12月, 2008 1 次提交
    • A
      Replace posix-aio with custom thread pool · 3c529d93
      由 aliguori 提交于 
      glibc implements posix-aio as a thread pool and imposes a number of limitations.

1) it limits one request per-file descriptor.  we hack around this by dup()'ing
file descriptors which is hideously ugly

2) it's impossible to add new interfaces and we need a vectored read/write
operation to properly support a zero-copy API.

What has been suggested to me by glibc folks, is to implement whatever new
interfaces we want and then it can eventually be proposed for standardization.
This requires that we implement our own posix-aio implementation though.

This patch implements posix-aio using pthreads.  It immediately eliminates the
need for fd pooling.

It performs at least as well as the current posix-aio code (in some
circumstances, even better).
Signed-off-by: NAnthony Liguori <aliguori@us.ibm.com>



git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5996 c046a42c-6fe2-441c-8c8c-71466251a162
      3c529d93
  11. 11 12月, 2008 1 次提交
  13. 07 12月, 2008 1 次提交
  15. 27 11月, 2008 1 次提交
  17. 23 11月, 2008 1 次提交
  19. 12 11月, 2008 2 次提交
  21. 09 10月, 2008 1 次提交
    • A
      Fix IO performance regression in sparc · 9e472e10
      由 aliguori 提交于 
      Replace signalfd with signal handler/pipe.  There is no way to interrupt
the CPU execution loop when a file descriptor becomes readable.  This
results in a large performance regression in sparc emulation during
bootup.
   
This patch switches us to signal handler/pipe which was originally
suggested by Ian Jackson.  The signal handler lets us interrupt the
CPU emulation loop while the write to a pipe lets us avoid the
select/signal race condition.
Signed-off-by: NAnthony Liguori <aliguori@us.ibm.com>



git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5451 c046a42c-6fe2-441c-8c8c-71466251a162
      9e472e10
  23. 02 10月, 2008 1 次提交
  25. 29 9月, 2008 7 次提交
  27. 24 9月, 2008 1 次提交
  29. 23 9月, 2008 1 次提交
    • A
      Refactor AIO to allow multiple AIO implementations · a76bab49
      由 aliguori 提交于 
      This patch refactors the AIO layer to allow multiple AIO implementations.  It's
only possible because of the recent signalfd() patch.  

Right now, the AIO infrastructure is pretty specific to the block raw backend.
For other block devices to implement AIO, the qemu_aio_wait function must
support registration.  This patch introduces a new function,
qemu_aio_set_fd_handler, which can be used to register a file descriptor to be
called back.  qemu_aio_wait() now polls a set of file descriptors registered
with this function until one becomes readable or writable.

This patch should allow the implementation of alternative AIO backends (via a
thread pool or linux-aio) and AIO backends in non-traditional block devices
(like NBD).
Signed-off-by: NAnthony Liguori <aliguori@us.ibm.com>



git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5297 c046a42c-6fe2-441c-8c8c-71466251a162
      a76bab49
  31. 15 9月, 2008 1 次提交
    • A
      Use common objects for qemu-img and qemu-nbd · 03ff3ca3
      由 aliguori 提交于 
      Right now, we sprinkle #if defined(QEMU_IMG) && defined(QEMU_NBD) all over the
code.  It's ugly and causes us to have to build multiple object files for
linking against qemu and the tools.

This patch introduces a new file, qemu-tool.c which contains enough for
qemu-img, qemu-nbd, and QEMU to all share the same objects.

This also required getting qemu-nbd to be a bit more Windows friendly.  I also
changed the Windows block-raw to use normal IO instead of overlapping IO since
we don't actually do AIO yet on Windows.  I changed the various #if 0's to
 #if WIN32_AIO to make it easier for someone to eventually fix AIO on Windows.

After this patch, there are no longer any #ifdef's related to qemu-img and
qemu-nbd.
Signed-off-by: NAnthony Liguori <aliguori@us.ibm.com>



git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5226 c046a42c-6fe2-441c-8c8c-71466251a162
      03ff3ca3
  33. 12 9月, 2008 1 次提交
  35. 10 9月, 2008 1 次提交
    • A
      Use signalfd() to work around signal/select race · baf35cb9
      由 aliguori 提交于 
      This patch introduces signalfd() to work around the signal/select race in
checking for AIO completions.  For platforms that don't support signalfd(), we
emulate it with threads.

There was a long discussion about this approach.  I don't believe there are any
fundamental problems with this approach and I believe eliminating the use of
signals is a good thing.

I've tested Windows and Linux using Windows and Linux guests.  I've also checked
for disk IO performance regressions.
Signed-off-by: NAnthony Liguori <aliguori@us.ibm.com>



git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5187 c046a42c-6fe2-441c-8c8c-71466251a162
      baf35cb9
  37. 22 8月, 2008 1 次提交
    • A
      Fix windows build · cd01b4a3
      由 aliguori 提交于 
      Right now, the Windows build is broken because of NBD.  Using a mingw32 cross
compiler is also badly broken.

This patch fixes the Windows build by stubbing out NBD support until someone
fixes it for Windows.  It also santizing the mingw32 cross compiler support
by replacing the --enable-mingw32 option with a compiler check to determine
if we're on windows or not.

Also remove the weird SDL pseudo-detection for mingw32 using a cross compiler.
The hardcoded sdl-config name is seemly arbitrary.  If you cross compiler SDL
correctly and modify your PATH variable appropriately, it will Just Work when
cross compiling.

The audio driver detection is also broken for cross compiling so you have to
specify the audio drivers explicitly for now.
Signed-off-by: NAnthony Liguori <aliguori@us.ibm.com>




git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5046 c046a42c-6fe2-441c-8c8c-71466251a162
      cd01b4a3
  39. 02 8月, 2008 1 次提交
  41. 27 7月, 2008 1 次提交
  43. 19 7月, 2008 1 次提交
  45. 18 7月, 2008 1 次提交
  47. 03 7月, 2008 4 次提交
  49. 09 6月, 2008 1 次提交
  51. 29 5月, 2008 1 次提交
  53. 28 5月, 2008 1 次提交
  55. 10 5月, 2008 1 次提交
  57. 24 4月, 2008 1 次提交