the first backtrace.
The fix is obvious: use temporary queue and do not touch coroutine after
first qemu_coroutine_enter() is invoked.
The issue is quite rare and happens every ~12 hours on very high IO
and CPU load (building linux kernel with -j512 inside guest) when IO
throttling is enabled. With t
CAJrWOzD6Xq==b-zYCDdFLgSRMPM-NkNuTSDFEtX=7mret45...@mail.gmail.com
[2] Message id:
5d120f358612d73fc909f5bfa47e7bd082db0af0.1429841474.git.l...@kernel.org
Signed-off-by: Roman Pen
Signed-off-by: Mikhail Sennikovskii
Cc: Paolo Bonzini
Cc: Rddadim Krčmář
Cc: Michael Chapman
Cc: qemu-devel@nongnu.
the first backtrace.
The fix is obvious: use temporary queue and do not touch coroutine after
first qemu_coroutine_enter() is invoked.
The issue is quite rare and happens every ~12 hours on very high IO
and CPU load (building linux kernel with -j512 inside guest) when IO
throttling is enabled. With t
m the first backtrace.
The fix is obvious: use temporal queue and do not touch coroutine after
first qemu_coroutine_enter() is invoked.
The issue is quite rare and happens every ~12 hours on very high IO load
(building linux kernel with -j512 inside guest) when IO throttling is
enabled. With the f
to modify registers (that is
only possible for live process, not for a corefile). This problem
is solved in the next patch for a gdb project itself.
Signed-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: qemu-devel@nongnu.org
---
scripts/qemugdb/coroutine.py | 29 ++---
1 fi
-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: Paolo Bonzini
Cc: qemu-devel@nongnu.org
---
block/linux-aio.c | 125 ++
1 file changed, 99 insertions(+), 26 deletions(-)
diff --git a/block/linux-aio.c b/block/linux-aio.c
index 78f4524..3e29f1d 100644
90160, per=12.49%, avg=245746.04,
stdev=11606.75
Throughput increased from 1822MB/s to 1921MB/s, average completion latencies
decreased from 1051us to 988us.
Signed-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: Paolo Bonzini
Cc: qemu-devel@nongnu.org
---
block/linux-aio.c | 24 ++
Prepare processing events function to be called from ioq_submit(),
thus split function on two parts: the first harvests completed IO
requests, the second submits pending requests.
Signed-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: Paolo Bonzini
Cc: qemu-devel@nongnu.org
---
block/linux-aio.c
latencies
decreased from 1051us to 988us.
Roman Pen (3):
linux-aio: consume events in userspace instead of calling io_getevents
linux-aio: split processing events function
linux-aio: process completions from ioq_submit()
block/linux-aio.c | 178 ++-
90160, per=12.49%, avg=245746.04,
stdev=11606.75
Throughput increased from 1822MB/s to 1921MB/s, average completion latencies
decreased from 1051us to 988us.
Signed-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: Paolo Bonzini
Cc: qemu-devel@nongnu.org
---
block/linux-aio.c | 17 +++--
1 fi
Prepare processing events function to be called from ioq_submit(),
thus split function on two parts: the first harvests completed IO
requests, the second submits pending requests.
Signed-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: Paolo Bonzini
Cc: qemu-devel@nongnu.org
---
block/linux-aio.c
-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: Paolo Bonzini
Cc: qemu-devel@nongnu.org
---
block/linux-aio.c | 125 ++
1 file changed, 99 insertions(+), 26 deletions(-)
diff --git a/block/linux-aio.c b/block/linux-aio.c
index 78f4524..3e29f1d 100644
04,
stdev=11606.75
Throughput increased from 1822MB/s to 1921MB/s, average completion latencies
decreased from 1051us to 988us.
Roman Pen (3):
linux-aio: consume events in userspace instead of calling io_getevents
linux-aio: split processing events function
linux-aio: process comple
or reiteration of io_getevents() call this patch
restricts the number of in-flights, which is now limited to MAX_EVENTS.
Signed-off-by: Roman Pen
Reviewed-by: Fam Zheng
Reviewed-by: Paolo Bonzini
Cc: Stefan Hajnoczi
Cc: qemu-devel@nongnu.org
---
v3:
o comment tweaks.
v2:
o comment tweaks.
o
ore or hang will happen. */
To prevent the hang or reiteration of io_getevents() call this patch
restricts the number of in-flights, which is now limited to MAX_EVENTS.
Signed-off-by: Roman Pen
Reviewed-by: Fam Zheng
Cc: Stefan Hajnoczi
Cc: Paolo Bonzini
Cc: qemu-devel@nongnu.org
---
block/li
or reiteration of io_getevents() call this patch
restricts the number of in-flights, which is limited to MAX_EVENTS.
Signed-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: Paolo Bonzini
Cc: qemu-devel@nongnu.org
---
block/linux-aio.c | 25 +++--
1 file changed, 15 insertions(+),
.
Signed-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: Paolo Bonzini
Cc: qemu-devel@nongnu.org
---
block/linux-aio.c | 86 ---
1 file changed, 70 insertions(+), 16 deletions(-)
diff --git a/block/linux-aio.c b/block/linux-aio.c
index fe7cece
part in reasonable time. Of course, my qemu block
layer experience is rather shallow and I do not see obvious ways how
to make this IO path thread-safe without changing everything all over
the place.
--
Roman
Signed-off-by: Roman Pen
Cc: Stefan Hajnoczi
Cc: qemu-devel@nongnu.o
untime=30
[job]
filename=/dev/vda
VM configuration:
-
-object iothread,id=t0 \
-drive
if=none,id=d0,file=/dev/nullb0,format=raw,snapshot=off,cache=none,aio=native \
-device
virtio-blk-pci,drive=d0,iothread=t0,num-queues=4,disable-modern=off,disable-legacy=on
\
Signed-off-by: Roman
ockBackend
device in order to access one BlockBackend from many iothreads, but I
failed to finish this part in reasonable time. Of course, my qemu block
layer experience is rather shallow and I do not see obvious ways how
to make this IO path thread-safe without changing everything all over
the place.
20 matches
Mail list logo
