Hi All,
This is just a heads up: I will be changing employment soon, so my
Akamai email address will cease to operate this week.
My personal email: mich...@flatgalaxy.com. I'll re-subscribe later once
I have come back online to work soon.
Thanks!
- Michael
On 10/23/24 10:34, Michael Galax
On 10/2/24 02:54, Martin Kletzander wrote:
On Sun, Sep 08, 2024 at 08:00:02AM +0200, Martin Kletzander wrote:
On Thu, Aug 15, 2024 at 01:30:38PM -0500, Michael Galaxy wrote:
On 8/7/24 10:10, Michael Galaxy wrote:
On 8/7/24 08:23, Martin Kletzander wrote:
Exactly, we do not want the paths to ch
From: Michael Galaxy
Signed-off-by: Michael Galaxy
---
NEWS.rst | 8
1 file changed, 8 insertions(+)
diff --git a/NEWS.rst b/NEWS.rst
index bbd30ab3b5..c546f0757a 100644
--- a/NEWS.rst
+++ b/NEWS.rst
@@ -25,6 +25,14 @@ v10.7.0 (unreleased)
backed network devices. So, create new n
From: Michael Galaxy
We start by introducing a backwards-compatible, comma-separated
specification that will not break existing installations, such
as in the following example:
$ cat qemu.conf | grep memory_backing_dir
memory_backing_dir = ["/path/to/pmem/0", "/path/to/pmem/1"]
(The old syntax
From: Michael Galaxy
In our environment, we need to convert VMs into a live-update-comptabile
configuration "on-the-fly" (via live migration). More specifically: We
need to convert between anonymous memory-backed VMs and file-backed
memory VMs. So, for this very specific case, this needs to work
From: Michael Galaxy
Signed-off-by: Michael Galaxy
---
docs/kbase/virtiofs.rst | 2 ++
src/qemu/qemu.conf.in | 4
2 files changed, 6 insertions(+)
diff --git a/docs/kbase/virtiofs.rst b/docs/kbase/virtiofs.rst
index 457c15da7f..931ba96104 100644
--- a/docs/kbase/virtiofs.rst
+++ b/docs/
From: Michael Galaxy
CPR-based support for whole-hypervisor kexec-based live updates is
now finally merged into QEMU. In support of this, we need NUMA to be
supported in these kinds of environments. To do this we use a technology
called PMEM (persistent memory) in Linux, which underpins the abili
Hi Martin,
On 8/7/24 10:10, Michael Galaxy wrote:
Hi,
Answers below
On 8/7/24 08:23, Martin Kletzander wrote:
On Tue, Aug 06, 2024 at 03:45:54PM -0500, Michael Galaxy wrote:
Thank you so much for the detailed comments. I'll work on those.
I believe you had a couple questions below on th
Ok, I tested one of your concerns below, and I caught that already.
Just following up..
On 8/6/24 07:35, Martin Kletzander wrote:
On Wed, Jun 05, 2024 at 04:37:35PM -0400, mgal...@akamai.com wrote:
From: Michael Galaxy
+ _("Domain requesting configuration
fo
Hi Martin,
Very good question below.
On 8/9/24 06:10, Martin Kletzander wrote:
On Wed, Aug 07, 2024 at 10:20:49AM -0500, Michael Galaxy wrote:
What we have here so far is the minimal set of changes needed to make it
work.
I'd like to avoid making this set too complicated. How we handle QM
Hi,
Answers below.
On 8/7/24 08:26, Martin Kletzander wrote:
On Tue, Aug 06, 2024 at 03:50:45PM -0500, Michael Galaxy wrote:
Hi,
On 8/6/24 07:38, Martin Kletzander wrote:
On Wed, Jun 05, 2024 at 04:37:36PM -0400, mgal...@akamai.com wrote:
From: Michael Galaxy
if (src->mem.source
Hi,
Answers below
On 8/7/24 08:23, Martin Kletzander wrote:
On Tue, Aug 06, 2024 at 03:45:54PM -0500, Michael Galaxy wrote:
Thank you so much for the detailed comments. I'll work on those.
I believe you had a couple questions below on this one..inlined
.
On 8/6/24 07:35, Martin
From: Michael Galaxy
CPR-based support for whole-hypervisor kexec-based live updates is
now finally merged into QEMU. In support of this, we need NUMA to be
supported in these kinds of environments. To do this we use a technology
called PMEM (persistent memory) in Linux, which underpins the abili
From: Michael Galaxy
We start by introducing a backwards-compatible, comma-separated
specification that will not break existing installations, such
as in the following example:
$ cat qemu.conf | grep memory_backing_dir
memory_backing_dir = ["/path/to/pmem/0", "/path/to/pmem/1"]
(The old syntax
From: Michael Galaxy
Update the documentation and changelog accordingly to reflect
that the syntax of the memory_backing_dir setting has changed.
Signed-off-by: Michael Galaxy
---
NEWS.rst| 7 +++
docs/kbase/virtiofs.rst | 2 ++
src/qemu/qemu.conf.in | 2 ++
3 files chang
From: Michael Galaxy
Update the associated test case.
Signed-off-by: Michael Galaxy
---
tests/testutilsqemu.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tests/testutilsqemu.c b/tests/testutilsqemu.c
index d70850cb5d..dd8db4835e 100644
--- a/tests/testutilsqemu.c
+
From: Michael Galaxy
In our environment, we need to convert VMs into a live-update-comptabile
configuration "on-the-fly" (via live migration). More specifically: We
need to convert between anonymous memory-backed VMs and file-backed
memory VMs. So, for this very specific case, this needs to work
Hi,
Acknowledged all. Thanks again for the instructions/review.
- Michael
On 8/6/24 07:44, Martin Kletzander wrote:
On Wed, Jun 05, 2024 at 04:37:38PM -0400, mgal...@akamai.com wrote:
From: Michael Galaxy
Update the documentation and changelog accordingly to reflect
that the syntax of the m
Hi,
On 8/6/24 07:41, Martin Kletzander wrote:
On Wed, Jun 05, 2024 at 04:37:37PM -0400, mgal...@akamai.com wrote:
From: Michael Galaxy
Update the associated test case.
This definitely needs to be part of the patch that changes this in qemu
driver code as otherwise the compilation would fai
Hi,
On 8/6/24 07:38, Martin Kletzander wrote:
On Wed, Jun 05, 2024 at 04:37:36PM -0400, mgal...@akamai.com wrote:
From: Michael Galaxy
if (src->mem.source != dst->mem.source) {
- virReportError(VIR_ERR_CONFIG_UNSUPPORTED,
- _("Target memoryBacking source '%1$
By the way, it took me a few hours to notice that you reviewed this.
Thanks again.
Please disregard my RESEND. Sorry for the noise!
- Michael
On 8/6/24 07:35, Martin Kletzander wrote:
On Wed, Jun 05, 2024 at 04:37:35PM -0400, mgal...@akamai.com wrote:
From: Michael Galaxy
Hi,
sorry for
Thank you so much for the detailed comments. I'll work on those.
I believe you had a couple questions below on this one..inlined .
On 8/6/24 07:35, Martin Kletzander wrote:
On Wed, Jun 05, 2024 at 04:37:35PM -0400, mgal...@akamai.com wrote:
From: Michael Galaxy
+
I'm so sorry, Martin.
You literally JUST replied (this morning! so funny!) and I totally
missed those emails.
I will reply in the other thread.
Please disregard this resend.
- Michael
On 8/6/24 15:32, mgal...@akamai.com wrote:
From: Michael Galaxy
CPR-based support for whole-hypervisor k
From: Michael Galaxy
Update the documentation and changelog accordingly to reflect
that the syntax of the memory_backing_dir setting has changed.
Signed-off-by: Michael Galaxy
---
NEWS.rst| 7 +++
docs/kbase/virtiofs.rst | 2 ++
src/qemu/qemu.conf.in | 2 ++
3 files chang
From: Michael Galaxy
Update the associated test case.
Signed-off-by: Michael Galaxy
---
tests/testutilsqemu.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/tests/testutilsqemu.c b/tests/testutilsqemu.c
index d70850cb5d..dd8db4835e 100644
--- a/tests/testutilsqemu.c
+
From: Michael Galaxy
In our environment, we need to convert VMs into a live-update-comptabile
configuration "on-the-fly" (via live migration). More specifically: We
need to convert between anonymous memory-backed VMs and file-backed
memory VMs. So, for this very specific case, this needs to work
From: Michael Galaxy
We start by introducing a backwards-compatible, comma-separated
specification that will not break existing installations, such
as in the following example:
$ cat qemu.conf | grep memory_backing_dir
memory_backing_dir = ["/path/to/pmem/0", "/path/to/pmem/1"]
(The old syntax
From: Michael Galaxy
CPR-based support for whole-hypervisor kexec-based live updates is
now finally merged into QEMU. In support of this, we need NUMA to be
supported in these kinds of environments. To do this we use a technology
called PMEM (persistent memory) in Linux, which underpins the abili
These are very compelling results, no?
(40gbps cards, right? Are the cards active/active? or active/standby?)
- Michael
On 5/14/24 10:19, Yu Zhang wrote:
Hello Peter and all,
I did a comparison of the VM live-migration speeds between RDMA and
TCP/IP on our servers
and plotted the results to g
One thing to keep in mind here (despite me not having any hardware to
test) was that one of the original goals here
in the RDMA implementation was not simply raw throughput nor raw
latency, but a lack of CPU utilization in kernel
space due to the offload. While it is entirely possible that newer
Yu Zhang / Jinpu,
Any possibility (at your lesiure, and within the disclosure rules of
your company, IONOS) if you could share any of your performance
information to educate the group?
NICs have indeed changed, but not everybody has 100ge mellanox cards at
their disposal. Some people don't.
Reviewed-by: Michael Galaxy
Thanks Yu Zhang and Peter.
- Michael
On 4/29/24 15:45, Yu Zhang wrote:
Hello Michael and Peter,
We are very glad at your quick and kind reply about our plan to take
over the maintenance of your code. The message is for presenting our
plan and working together.
If
Hi All (and Peter),
My name is Michael Galaxy (formerly Hines). Yes, I changed my last name
(highly irregular for a male) and yes, that's my real last name:
https://www.linkedin.com/in/mrgalaxy/)
I'm the original author of the RDMA implementation. I've been discussing
with Yu Zhang for a lit
33 matches
Mail list logo
