Skip to content

Q
qemu

openeuler / qemu

通知 10
Star 0
Fork 0
Q
qemu
切换分支/标签
  1. 18 12月, 2008 1 次提交
  3. 16 12月, 2008 3 次提交
  5. 15 12月, 2008 2 次提交
  7. 13 12月, 2008 2 次提交
    • A
      Make sure to link librt if we need to. · da93a1fd
      由 aliguori 提交于 
      This is really a stop-gap.  The recent thread pool changes uncovered a 
deeper issue with how we use librt.  We really should be probing for 
timer_create and then conditionally enabling that code.
Signed-off-by: NAnthony Liguori <aliguori@us.ibm.com>



git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5997 c046a42c-6fe2-441c-8c8c-71466251a162
      da93a1fd
    • 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
  9. 10 12月, 2008 1 次提交
  11. 09 12月, 2008 1 次提交
  13. 08 12月, 2008 4 次提交
  15. 07 12月, 2008 2 次提交
  17. 06 12月, 2008 2 次提交
  19. 30 11月, 2008 2 次提交
  21. 27 11月, 2008 1 次提交
  23. 23 11月, 2008 3 次提交
  25. 18 11月, 2008 1 次提交
  27. 06 11月, 2008 3 次提交
  29. 01 11月, 2008 1 次提交
  31. 27 10月, 2008 1 次提交
  33. 24 10月, 2008 1 次提交
  35. 12 10月, 2008 1 次提交
  37. 11 10月, 2008 2 次提交
  39. 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
  41. 08 10月, 2008 2 次提交
  43. 01 10月, 2008 1 次提交
  45. 30 9月, 2008 2 次提交