This change adds an optional virtual address parameter
to the `info tlb` monitor command on i386 targets,
only printing a specific entry if found.
Signed-off-by: Josh Junon
---
hmp-commands-info.hx | 5 +
target/i386/monitor.c | 45 +++
2 files
On Fri, Aug 02, 2024 at 04:18:40PM +0200, Markus Armbruster wrote:
> Let's go back to v1's title
>
> qmp: Fix higher half vaddrs for [p]memsave
>
> Josh Junon writes:
>
> > Fixes higher-half address parsing for QMP commands
> > `[p]mem
Fixes higher-half address parsing for QMP commands
`[p]memsave`.
Signed-off-by: Josh Junon
---
qapi/machine.json | 11 +--
system/cpus.c | 10 +-
2 files changed, 14 insertions(+), 7 deletions(-)
diff --git a/qapi/machine.json b/qapi/machine.json
index fcfd249e2d
Fixes higher-half address parsing for QMP commands
`[p]memsave` and `dump-guest-memory`.
Signed-off-by: Josh Junon
---
dump/dump.c | 4 ++--
qapi/dump.json| 2 +-
qapi/machine.json | 11 +--
system/cpus.c | 8
4 files changed, 16 insertions(+), 9 deletions
On Fri, Aug 02, 2024 at 01:39:15PM +0200, Markus Armbruster wrote:
> Josh Junon writes:
>
> > Previously, int64_t's were used when parsing virtual / physical
> > addresses for the [p]memsave commands over QMP (HMP was unaffected).
> > This caused issues when the
Previously, int64_t's were used when parsing virtual / physical
addresses for the [p]memsave commands over QMP (HMP was unaffected).
This caused issues when the virtual addresses were in the higher
half of a 64-bit address space, as various portions of the parsing
code would consider them out of bo
perly handling higher-half virtual addresses correctly,
namely when used over QMP/the monitor. The use and assumption of
signed integers caused issues when parsing otherwise valid
virtual addresses that instead caused signed integer overflow
or ERANGE errors.
Signed-off-by: Josh Junon
---
docs/devel/
Hello all,
I started a thread a thread at
https://lore.kernel.org/linux-newbie/CAFkJGRcg+ThJ-xUve0=WorChW=-6prelhxem8ywtwzwpkht...@mail.gmail.com/T/#m563ab52dd2bfe7ac8d85f838f866a1a9d1a6d0a9
. It is using Qemu, but both Linux and Qemu and rather complex pieces
of software. I was wondering if som
t
> g4mercury so I'm open to votes on naming but hard to be convinced there's
> anything simpler and more straightforward than using machine id which is
> usually also listed everywhere for these.
g4tibook1stgen?
("TiBook" being an affectionate abbreviation for "Titanium PowerBook")
Cheers,
Josh
Signed-off-by: Josh Soref
---
.github/workflows/lockdown.yml | 1 +
1 file changed, 1 insertion(+)
diff --git a/.github/workflows/lockdown.yml b/.github/workflows/lockdown.yml
index 37c6065..b924b25 100644
--- a/.github/workflows/lockdown.yml
+++ b/.github/workflows/lockdown.yml
@@ -12,6 +12,7
Signed-off-by: Josh Soref
---
.github/workflows/lockdown.yml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/.github/workflows/lockdown.yml b/.github/workflows/lockdown.yml
index ad8b8f7..37c6065 100644
--- a/.github/workflows/lockdown.yml
+++ b/.github/workflows/lockdown.yml
The current workflow fails to provide a comment explaining why
it has closed a PR. This is not friendly.
Also, while it's perfectly reasonable to close PRs to the qemu
organization, it's a bit much to close them in forks.
These patches address both of these issues.
Josh Soref
t; On Sun, Aug 16, 2020 at 12:46:10PM -0500, dubo...@gmail.com wrote:
>>>> From: Josh DuBois
>>>>
>>>> Tracing can be enabled at the command line or via the
>>>> monitor. Command-line trace options are recorded during
>>>> trace_opt_par
On Aug 3, 2020, at 4:08 AM, Markus Armbruster wrote:
>
>>
>> - prior to db25d56c014aa1a96319c663e0a60346a223b31e, just like today,
>> QEMU built with simple tracing will always produce a trace- file,
>> regardless of whether the user asks for traces at runtime.
>
> When you send a patch with a
Hi Alex,
Thank you for the reply.
Please see my inline response below.
-Original Message-
From: Alex Bennée
Sent: Friday, July 31, 2020 8:45 AM
To: Pincus, Josh
Cc: linux-ker...@vger.kernel.org; zha...@linux.alibaba.com;
virtio-...@lists.oasis-open.org; qemu-devel@nongnu.org
Subject
If I resubmit, I'll try to test a little more next time. I just wanted
my traces to work. ;)
On 7/29/20 8:05 AM, Stefan Hajnoczi wrote:
On Thu, Jul 23, 2020 at 12:33:59AM -0500, Josh DuBois wrote:
The simple trace backend is enabled / disabled with a call
to st_set_trace_file_enabled(
Hi,
We were looking into a similar enhancement for the Virt I/O MMIO transport and
came across this project.
This enhancement would be perfect for us.
Has there been any progress since Feb, 2020? It looks like the effort might
have stalled?
Thanks,
JP
enabled tracing.)
Fixes: db25d56c014aa1a96319c663e0a60346a223b31e
Signed-off-by: Josh DuBois
---
trace/control.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/trace/control.c b/trace/control.c
index 2ffe000818..6558b5c906 100644
--- a/trace/control.c
+++ b/trace/control.c
@@ -225,6 +225,7
/dcde237b9b0eb1d19306e6f48c0a4e058907619f/include/uapi/linux/if_tun.h#L31
Signed-off-by: Josh Kunz
---
linux-user/ioctls.h | 20
linux-user/syscall.c | 1 +
linux-user/syscall_defs.h | 21 +
3 files changed, 42 insertions(+)
diff --git a/linux
Sorry for the late reply, response inline. Also I noticed a couple
mails ago I seemed to have removed the devel list and maintainers.
I've re-added them to the CC line.
On Wed, Jun 24, 2020 at 3:17 AM Alex Bennée wrote:
>
>
> Josh Kunz writes:
>
> > On Tue, Jun 23, 20
linux-user targets on x86.
[1]:
https://github.com/torvalds/linux/blob/bfe91da29bfad9941d5d703d45e29f0812a20724/net/netlink/af_netlink.c#L683
Signed-off-by: Josh Kunz
---
linux-user/syscall.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/linux-user/syscall.c b/linux-user
usly, since it seems like a pretty heavyweight approach.
Especially compared to the solution included in this series. Do you
think there's a simpler approach that involves using a daemon to do
coordination?
Thanks again for your reviews.
--
Josh Kunz
t be an interesting test of whether we have
> accidental dependencies on the libc internals.
I agree it would be interesting to test against musl. I'm pretty sure it
would work (this patch only relies on POSIX APIs + Platform ABIs for TLS),
but it would be interesting to confirm.
--
Josh Kunz
> +child_tid = atomic_fetch_or(&mgr->managed_tid, 0);
> +/*
> + * Check if the child has already terminated by this point. If not, wait
> + * for the child to exit. As long as the trampoline is not killed by
> + * a signal, the kernel guarantees that the memory at &mgr->managed_
Certain process-level linux features like subreapers, and PDEATHSIG,
depend on the guest's process hierarchy being emulated correctly on the
host. This change adds a test that makes sure PDEATHSIG works for a
guest process created with `clone`.
Signed-off-by: Josh Kunz
---
tests/tcg/mult
a task needs to use a different
FD table.
Signed-off-by: Josh Kunz
---
linux-user/Makefile.objs | 2 +-
linux-user/fd-trans-tbl.c | 13 +++
linux-user/fd-trans-type.h | 17 +
linux-user/fd-trans.c | 3 --
linux-user/fd-trans.h | 75
M.
* CLONE_CHILD_CLEARTID + FUTEX_WAIT: Cannot detect abnormally
terminated children.
* Doing the child clone directly in the TLS manager thread: This saves the
need for the trampoline process, but it causes the child process to be
parented to the wrong kernel task (the TLS thre
atly appreciated.
* execve does not clean up the CPUs of clone'd children, for the same
reasons as `exit_group`.
Josh Kunz (5):
linux-user: Refactor do_fork to use new `qemu_clone`
linux-user: Make fd_trans task-specific.
linux-user: Make sigact_table part of the task state.
when cloning children.
Signed-off-by: Josh Kunz
---
linux-user/qemu.h| 8
linux-user/signal.c | 35 +++
linux-user/syscall.c | 17 +
3 files changed, 52 insertions(+), 8 deletions(-)
diff --git a/linux-user/qemu.h b/linux-user/qemu.h
rk) into a separate file.
Signed-off-by: Josh Kunz
---
linux-user/Makefile.objs | 2 +-
linux-user/clone.c | 152
linux-user/clone.h | 27 +++
linux-user/syscall.c | 376 +++
4 files changed, 365 insertions(+), 192 deletions(-)
c
e is that RT signals are very rarely used, and the only
uses I can find are based off SIGRTMIN. This sounds reasonable to me.
Josh
On Mon, Jan 20, 2020 at 3:36 AM Alex Bennée wrote:
> Ahh the default build target for the BSDs is "check" but as bsd-user
> doesn't have any checks it doesn't end up building. You can force it
> with
>
> make vm-build-netbsd EXTRA_CONFIGURE_OPTS="--disable-system"
> BUILD_TARGET="all"
>
> It wo
Laurent Vivier writes:
> >
> >> Le 17/01/2020 à 20:28, Josh Kunz a écrit :
> >>> Since most calls to `gemu_log` are actually logging unimplemented
> >>> features,
> >>> this change replaces most non-strace calls to `gemu_log` with calls to
> >>>
redirection. bsd-user does not currently implement any
logging redirection options, or log masking options, but this change
brings it more in line with the linux-user tree.
Signed-off-by: Josh Kunz
---
bsd-user/main.c| 29 +
bsd-user/qemu.h| 2 --
bsd-user
Now that all uses have been migrated to `qemu_log' it is no longer
needed.
Reviewed-by: Laurent Vivier
Signed-off-by: Josh Kunz
---
linux-user/main.c | 9 -
linux-user/qemu.h | 1 -
2 files changed, 10 deletions(-)
diff --git a/linux-user/main.c b/linux-user/main.c
index 8f1d0
On Tue, Jan 28, 2020 at 7:07 AM Laurent Vivier wrote:
>
> Le 17/01/2020 à 20:28, Josh Kunz a écrit :
> > This change switches linux-user strace logging to use the newer `qemu_log`
> > logging subsystem rather than the older `gemu_log` (notice the "g")
> > logger.
gging (via the QEMU_LOG environment variable or options).
This change introduces a new log mask: `LOG_STRACE` which is used for
logging of user-mode strace messages.
Reviewed-by: Laurent Vivier
Signed-off-by: Josh Kunz
---
include/qemu/log.h | 2 +
linux-user/main.c| 30 ++-
linux-u
is slightly backwards incompatible, since now these
"unimplemented" log messages will not be logged by default.
Signed-off-by: Josh Kunz
---
linux-user/arm/cpu_loop.c | 5 ++--
linux-user/fd-trans.c | 55 +--
linux-user/syscall.c
logging to stderr.
Tested:
* Built with clang 9 and g++ 8.3
* `make check` run with clang 9 build
* Verified:
* QEMU_STRACE/-strace still works for linux-user
* `make vm-build-netbsd EXTRA_CONFIGURE_OPTS="--disable-system" \
BUILD_TARGET="all"` passed.
Josh
On Sat, Feb 1, 2020 at 4:27 AM Laurent Vivier wrote:
> This has been tested with Go (golang 1.10.1 linux/arm64, bionic) on x86_64
> fedora 31. We can avoid the failure in this case allowing the unsupported
> signals when we don't provide the "act" parameters to sigaction, only the
> "oldact" one.
On Tue, Jan 14, 2020 at 2:56 AM Alex Bennée wrote:
> Could we cut out the middle-man and just qemu_add_log(LOG_STRACE) here
> and drop the enable_strace variable.
This code has been re-factored based on Laurent's comments. In v2
`enable_strace` is still needed to avoid QEMU_LOG/-d overwriting the
On Tue, Jan 14, 2020 at 1:09 AM Laurent Vivier wrote:
> This is really a special case as the flags are all given at the same
> time, could you use directly qemu_set_log() in main()?
Fixed in v2.
> > +/* Remove (subtract) the given log flags from the current log mask. */
> > +static inline void q
On Tue, Jan 14, 2020 at 2:43 AM Alex Bennée wrote:
>
> As Laurent said I think LOG_UNIMP is perfectly fine for stuff we haven't
> done. I don't think any of the cases warrant LOG_GUEST_ERROR.
I've replaced `LOG_USER` with `LOG_UNIMP`. Didn't catch that mask at
first, LOG_UNIMP is indeed a better
redirection. bsd-user does not currently implement any
logging redirection options, or log masking options, but this change
brings it more in line with the linux-user tree.
Signed-off-by: Josh Kunz
---
bsd-user/main.c| 13 ++---
bsd-user/qemu.h| 2 --
bsd-user/strace.c | 32
is slightly backwards incompatible, since now these
"unimplemented" log messages will not be logged by default.
Signed-off-by: Josh Kunz
---
linux-user/arm/cpu_loop.c | 5 ++--
linux-user/fd-trans.c | 55 +--
linux-user/syscall.c
gging (via the QEMU_LOG environment variable or options).
This change introduces a new log mask: `LOG_STRACE` which is used for
logging of user-mode strace messages.
Signed-off-by: Josh Kunz
---
include/qemu/log.h | 2 +
linux-user/main.c| 30 ++-
linux-user/qemu.h| 1 -
linux-use
passed.
Not tested:
* Build/logging with bsd-user. I do not have easy access to a BSD system.
Josh Kunz (4):
linux-user: Use `qemu_log' for non-strace logging
linux-user: Use `qemu_log' for strace
linux-user: remove gemu_log from the linux-user tree
bsd-user: Replace
Now that all uses have been migrated to `qemu_log' it is no longer
needed.
Signed-off-by: Josh Kunz
---
linux-user/main.c | 9 -
linux-user/qemu.h | 1 -
2 files changed, 10 deletions(-)
diff --git a/linux-user/main.c b/linux-user/main.c
index 8f1d07cdd6..22578b1633 100644
--- a/
On Mon, Jan 13, 2020 at 7:06 PM Warner Losh wrote:
> The bsd-user that is in tree doesn't work. I've been trying to catch up to
> qemu head of tree, but I'm only up to 3.2... chances are the bsd-user
> changes will not change the state of things...
>
Ah good to know. Would you all prefer I don't
On Tue, Jan 14, 2020 at 3:02 AM Alex Bennée wrote:
>
> Josh Kunz writes:
>
>
> >
> > Not tested:
> > * Build/logging with bsd-user. I do not have easy access to a BSD
> > system.
>
> If you have the time we have vm-build-netbsd:
>
> make
redirection. bsd-user does not currently implement any
logging redirection options, or log masking options, but this change
brings it more in line with the linux-user tree.
Signed-off-by: Josh Kunz
---
bsd-user/main.c| 13 ++---
bsd-user/qemu.h| 2 --
bsd-user/strace.c | 32
gging (via the QEMU_LOG environment variable or options).
Signed-off-by: Josh Kunz
---
include/qemu/log.h | 13 ++
linux-user/main.c| 17 +-
linux-user/qemu.h| 1 -
linux-user/signal.c | 3 +-
linux-user/strace.c | 479 ++-
linux-user
nd to mask out
these log messages if they desire.
Signed-off-by: Josh Kunz
---
include/qemu/log.h| 2 ++
linux-user/arm/cpu_loop.c | 5 ++--
linux-user/fd-trans.c | 55 +--
linux-user/main.c | 24 +
linux-user
Now that all uses have been migrated to `qemu_log' it is no longer
needed.
Signed-off-by: Josh Kunz
---
linux-user/main.c | 9 -
linux-user/qemu.h | 1 -
2 files changed, 10 deletions(-)
diff --git a/linux-user/main.c b/linux-user/main.c
index 0bf40c4d27..945b6adf3a 100644
--- a/
ied:
* QEMU_STRACE/-strace still works for linux-user
* -no-force-user-mode-logging uses QEMU_LOG + `user_mode` or
`strace` can be set in QEMU_LOG to trigger the appropriate
logging.
Not tested:
* Build/logging with bsd-user. I do not have easy access to a BSD system.
Jo
Thanks for the fixes Laurent, sorry for the delay.
Josh
On Tue, Nov 5, 2019 at 1:25 AM Laurent Vivier wrote:
> Le 29/10/2019 à 23:43, Josh Kunz a écrit :
> > This change includes support for all AF_NETLINK socket options up to
> about
> > kernel version 5.4 (5.4 is not formal
change has been built under gcc 8.3, and clang 9.0, and it passes
`make check`. The netlink options have been tested by emulating some
non-trival software that uses NETLINK socket options, but they have
not been exaustively verified.
Signed-off-by: Josh Kunz
---
linux-user/syscall.c | 98
range, this is unavoidable; but for the SIGRTMIN,
SIGRTMIN+1 case, I’m not sure it’s worth it.
After considering these drawbacks, do the QEMU maintainers still think this
is the right approach for handling these libc reserved signals?
On Fri, Aug 30, 2019 at 6:26 PM Josh Kunz wrote:
> I can t
/gdb/General-Query-Packets.html#General-Query-Packets
On Mon, Aug 26, 2019 at 1:29 AM Laurent Vivier wrote:
> Le 17/08/2019 à 01:34, Josh Kunz via Qemu-devel a écrit :
> > This is needed to support debugging PIE ELF binaries running under QEMU
> > user mode. Currently, `c
I can take over the series. I'll rebase the patch set, and update it to
address the SIGRTMIN - 1 issue. I should have an update sometime next week.
On Wed, Aug 28, 2019 at 10:31 AM Aleksandar Markovic
wrote:
> > From: Laurent Vivier
> > Sent: Wednesday, August 28, 2019 10:5
On Wed, Aug 21, 2019 at 2:28 AM Laurent Vivier wrote:
> Le 19/08/2019 à 23:46, Josh Kunz via Qemu-devel a écrit :
> > Hi all,
> >
> > I have also experienced issues with SIGRTMIN + 1, and am interested in
> > moving this patch forwards. Anything I can do here to help
is a link to the original thread this message is in reply to
in-case my mail-client doesn't set up the reply properly:
https://lists.nongnu.org/archive/html/qemu-devel/2019-07/msg01303.html
Thanks,
Josh Kunz
+cc: riku.voi...@iki.fi, I typoed the email on the first go.
On Fri, Aug 16, 2019 at 4:34 PM Josh Kunz wrote:
> This is needed to support debugging PIE ELF binaries running under QEMU
> user mode. Currently, `code_offset` and `data_offset` remain unset for
> all ELF binaries, so GDB
erved.
Buglink: https://bugs.launchpad.net/qemu/+bug/1528239
Signed-off-by: Josh Kunz
---
linux-user/elfload.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/linux-user/elfload.c b/linux-user/elfload.c
index 3365e192eb..ceac035208 100644
--- a/linux-user/elfload.c
+++ b/linux-user/elfl
On 6/28/19 6:55 AM, jdill...@redhat.com wrote:
From: Jason Dillaman
Remove Josh as per his request since he is no longer the upstream RBD
tech lead. Add myself as the maintainer since I am the current RBD tech
lead.
Signed-off-by: Jason Dillaman
---
MAINTAINERS | 2 +-
1 file changed, 1
Public bug reported:
The SDL interface automatically scales the video output to
match the window size. The GTK3 interface has an off-by-default option
"Zoom To Fit" for that. As far as I can tell, no command-line option
exists to turn that option on. That makes it harder to quickly zoom a
fresh
Public bug reported:
With the GTK3 interface, qemu-system supports pressing Ctrl-Alt-plus
to zoom in and Ctrl-Alt-minus to zoom out. However, unlike many
programs that support similar zoom hotkeys, qemu-system actually
requires using '+', making the hotkey Ctrl-Alt-Shift-= . Most programs
with s
default
Signed-off-by: Alexandre Derumier
Sorry for the delay - this is correct and needed since this option
appeared by default in Ceph hammer.
Reviewed-by: Josh Durgin
---
block/rbd.c | 4
1 file changed, 4 insertions(+)
diff --git a/block/rbd.c b/block/rbd.c
index 0106fea..f3af6c8
Public bug reported:
For full customization of the default set of hardware qemu supports, a
user can pass -nodefaults and then manually specify each device they
want. Many specific options document what they translate to in terms of
the full configuration model; however, the defaults for any give
Public bug reported:
qemu currently provides a default set of sound hardware. The -soundhw
option can change that default set, such as by using "-soundhw pcspkr"
to disable most of it, but no "-soundhw none" option exists to disable
all of it. As far as I can tell, disabling the default sound ha
, 23 insertions(+), 15 deletions(-)
Looks good, thanks!
Reviewed-by: Josh Durgin
diff --git a/block/rbd.c b/block/rbd.c
index 5bc5b32..5226b6f 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -290,7 +290,8 @@ static int qemu_rbd_set_conf(rados_t cluster, const char
*conf,
if
On 05/17/2016 03:03 AM, Sebastian Färber wrote:
Hi Kevin,
A correct reopen implementation must consider all options and flags that
.bdrv_open() looked at.
The options are okay, as both "filename" and "password-secret" aren't
things that we want to allow a reopen to change. However, in the flag
Since this works fine with krbd, it sounds like the bug may be in
librbd. Could you install debug symbols (the librbd1-dbg package) and
when this occurs, attach to the qemu process with gdb and get a
backtrace of all threads (there will be a lot of them) via 'gdb -p $pid'
and in gdb 'thread apply a
ey.b64
$QEMU -object secret,id=secret0,file=poolkey.b64,format=base64 \
-drive driver=rbd,filename=rbd:pool/image:id=myname:\
auth_supported=cephx,passwordid=secret0
Signed-off-by: Daniel P. Berrange
Looks good to me, thanks!
Reviewed-by: Josh Durgin
On 10/19/2015 08:09 AM, Daniel P. Berrange wrote:
Currently RBD passwords must be provided on the command line
via
$QEMU -drive file=rbd:pool/image:id=myname:\
key=QVFDVm41aE82SHpGQWhBQXEwTkN2OGp0SmNJY0UrSE9CbE1RMUE=:\
auth_supported=cephx
This is insecure because the key is visibl
EFAULT_OBJ_ORDER
<https://lxr.missinglinkelectronics.com/qemu+v2.1.0/+code=OBJ_DEFAULT_OBJ_ORDER>,
if someone knows , please tell me. Thanks a lot.
I have CCed the rbd.c maintainer for you:
$ scripts/get_maintainer.pl -f block/rbd.c
Josh Durgin (supporter:RBD)
Thanks for CCing me, I missed it before.
You can s
ould also
take advantage of the ability to directly mmap a file from outside the
VM into the VM's address space.
In any case, we're getting a bit far afield for the original thread. :)
- Josh Triplett
On Thu, Sep 03, 2015 at 07:19:40PM +0200, Laszlo Ersek wrote:
> On 09/03/15 18:41, j...@joshtriplett.org wrote:
> > On Thu, Sep 03, 2015 at 05:53:45PM +0200, Laszlo Ersek wrote:
> >> On 09/03/15 16:50, Josh Triplett wrote:
>
> >>> Do you virtualize those I/O ports
On Thu, Sep 03, 2015 at 05:53:45PM +0200, Laszlo Ersek wrote:
> On 09/03/15 16:50, Josh Triplett wrote:
> > On Thu, Sep 03, 2015 at 11:16:40AM +0200, Laszlo Ersek wrote:
> >> Then this payload is passed to the guest firmware (SeaBIOS or OVMF) over
> >> "fw_
On Thu, Sep 03, 2015 at 07:50:07AM -0700, Josh Triplett wrote:
> On Thu, Sep 03, 2015 at 11:16:40AM +0200, Laszlo Ersek wrote:
> > I'm excited because for virtualization we might have the reverse use
> > case: use BITS to test / debug / develop the ACPI generator of QEMU. :)
On Thu, Sep 03, 2015 at 11:16:40AM +0200, Laszlo Ersek wrote:
> Hi Josh,
>
> I just found the LWN.net article with the title in the subject:
>
> http://lwn.net/SubscriberLink/655992/04701db2bbb7e716/
>
> ("Thank you LWN", of course. :))
>
> This got me
he main culprit here is rbd cache letting itself burst too
large, rather than the bounce buffers.
Andrey, does this still occur with caching off?
Josh
On 08/26/2015 04:47 PM, Andrey Korolyov wrote:
On Thu, Aug 27, 2015 at 2:31 AM, Josh Durgin wrote:
On 08/26/2015 10:10 AM, Andrey Korolyov wrote:
On Thu, May 14, 2015 at 4:42 PM, Andrey Korolyov wrote:
On Wed, Aug 27, 2014 at 9:43 AM, Chris Friesen
wrote:
On 08/25/2014 03:50 PM, Chris
7;re seeing.
In-flight requests do have buffers and structures allocated for them in
librbd, but these should have lower overhead than cow. If these are the
problem, it seems to me a generic limit on in flight ops in qemu would
be a reasonable fix. Other backends have resources tied up by in-flight
ops as well.
Josh
[1] https://github.com/ceph/ceph/pull/3410
On 07/14/2015 07:20 AM, Kevin Wolf wrote:
Am 09.07.2015 um 11:59 hat Stefan Hajnoczi geschrieben:
On Tue, Jun 30, 2015 at 11:28:18AM -0700, Josh Durgin wrote:
Ping
On 06/10/2015 08:28 PM, Josh Durgin wrote:
Patches 1 and 2 are simple cleanups. 3 and 4 fix the precedence of
cache options and
Ping
On 06/10/2015 08:28 PM, Josh Durgin wrote:
Patches 1 and 2 are simple cleanups. 3 and 4 fix the precedence of
cache options and ceph settings. The cache option precedence in
particular is important due to the potential for misconfigurations
(ceph.conf setting rbd_cache=true, qemu setting
The old one still works for now, but will not work indefinitely.
Signed-off-by: Josh Durgin
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index 4ed8215..34eeb88 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1135,7 +1135,7 @@ S
RBDAIOCB.status was only used for cancel, which was removed in
7691e24dbebb46658e89b3f950fda6ec78bbb823.
RBDAIOCB.sector_num was never used.
RADOSCB.done and rcbid were never used.
RBD_FD* are obsolete since the pipe was removed in
e04fb07fd1676e9facd7f3f878c1bbe03bccd26b.
Signed-off-by: Josh
Apply the ceph settings from a config file before any ceph settings
from the command line. Since the ceph config file location may be
specified on the command line, parse it once to read the config file,
and do a second pass to apply the rest of the command line ceph
options.
Signed-off-by: Josh
, although this would just be a performance problem.
Fix this by changing rbd's cache setting to match qemu after all other
ceph settings have been applied.
Signed-off-by: Josh Durgin
---
block/rbd.c | 24
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/
Patches 1 and 2 are simple cleanups. 3 and 4 fix the precedence of
cache options and ceph settings. The cache option precedence in
particular is important due to the potential for misconfigurations
(ceph.conf setting rbd_cache=true, qemu setting cache=none) to
accidentally put data at risk.
Josh
n EINVAL from rbd_aio_{read,write,discard} in rbd_start_aio()
to avoid duplicating the check. An out of bounds i/o is the only way
EINVAL can be returned from these functions in librbd.
Josh
On 12/09/2014 01:49 AM, Stefan Hajnoczi wrote:
On Tue, Dec 9, 2014 at 3:52 AM, Josh Durgin wrote:
On 12/08/2014 05:58 AM, Jun Li wrote:
On Fri, 12/05 18:01, Max Reitz wrote:
On 2014-12-05 at 16:32, Jun Li wrote:
Currently, qemu-img can not create qcow2 image format on rbd server
rbd already supports snapshots, cloning, thin provisioning, and
differential backup natively, so putting qcow2 on top tends to just add
overhead.
Josh
So use "-o preallocation=falloc or -o preallocation=full", it not a good
solution.
Regards,
Jun Li
I can't say a lot about makin
)
+{
+BDRVRBDState *s = bs->opaque;
+int r = rbd_invalidate_cache(s->image);
+if (r < 0) {
+error_setg_errno(errp, -r, "Failed to invalidate the cache");
+}
+return r;
No return needed here. With that fixed:
Reviewed-by: Josh Durgin
+}
+#endif
+
o_release(acb);
return NULL;
}
Reviewed-by: Josh Durgin
FWIW this error path can only happen in certain combinations of odd
circumstances, including specific forms of disk corruption of certain
objects in concert with other factors, so it's quite unlikely to occur
in practice.
imers, or BHs stay registered when
requests have been drained.
Cc: Josh Durgin
Signed-off-by: Stefan Hajnoczi
---
block/rbd.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/block/rbd.c b/block/rbd.c
index dbc79f4..41f7bdc 100644
--- a/block/rbd.c
+++ b/block/
g into its cache before the
destination starts
4) raw format images have no extra metadata that needs invalidation
If librbd populated its cache when the disk was opened, the rbd driver
would need to implement bdrv_invalidate(), but since it does not, it's
unnecessary.
Is this correct K
On 01/15/2014 10:12 PM, ?? wrote:
Hi Josh
# strings /usr/bin/qemu-system-x86_64 | grep rbd_aio
rbd_aio_write
rbd_aio_flush
rbd_aio_read
rbd_aio_create_completion
rbd_aio_release
rbd_aio_discard
rbd_aio_get_return_value
So, librbd's asynchronous flush is being used.
I set log set
On 01/15/2014 01:40 AM, ?? wrote:
Hi Josh
there is some issues
1. use 'none' cache mode in xml, and unset 'rbd cache=true' in
ceph.conf, the network latency issue not show.
2. use 'writethrough' cache mode in xml, and unset 'rbd cache=true' in
ceph.
1 - 100 of 191 matches
Mail list logo
