update-initramfs

[Marc Auslander]

I'm on Buster.

In /boot I keep a copy of the current working linux named by appending
-knowngood to the four files. My idea is that if an update fails, I
have a recent working linux. This is different from vmlinuz.old which
is the previous kernel version. The updates in question are not to the
kernel but to initrd.image of course.

Suddenly, update-initramfs insists in trying to first update
initrd.....-knowngood which of course fails because there are no
underling file with that name. This never happened in the past, AFAIK.
Once it fails it gives up.

There seems no way to force update-initramfs to update the right kernel.

Ideas?

[David Wright]

Perhaps check that "all" hasn't been accidentally inserted:

$ grep update /etc/initramfs-tools/update-initramfs.conf
# Configuration file for update-initramfs(8)
# update_initramfs [ yes | all | no ]
# If set to all update-initramfs will update all initramfs
# If set to no disables any update to initramfs beside kernel upgrade
update_initramfs=yes
$

A workaround: change the sort order of the backup initrd files
by adding an appropriate prefix, like backup-knowngood-…
so the "real" ones get updated first.

Cheers,
David.

[zithro]

On 11 Apr 2023 02:17, Marc Auslander wrote:
> I'm on Buster.
>
> In /boot I keep a copy of the current working linux named by appending
> -knowngood to the four files.  My idea is that if an update fails, I
> have a recent working linux.  This is different from vmlinuz.old which
> is the previous kernel version.  The updates in question are not to the
> kernel but to initrd.image of course.

In addition to what David wrote, why are you not using the backup
facility of initramfs instead of doing it manually ?

$ cat /etc/initramfs-tools/update-initramfs.conf
[...]
#
# backup_initramfs [ yes | no ]
#
# Default is no
# If set to no leaves no .bak backup files.

backup_initramfs=yes
[...]

>
> Suddenly, update-initramfs insists in trying to first update
> initrd.....-knowngood  which of course fails because there are no
> underling file with that name.  This never happened in the past, AFAIK.
> Once it fails it gives up.
>
> There seems no way to force update-initramfs to update the right kernel.
>
> Ideas?
>

RTFM ? :)

The solution is in "man update-initramfs" :
update-initramfs -c -k $KERNEL_VERSION

-c creates a new initramfs
-k specifies the version of the kernel

[Marc Auslander]

This breaks when package update tries to update-initramfs. My copies
have the kernel version in their names - with -knowngood appended.

[Marc Auslander]

thanks but that's the first thing I checked - it's yes, not all. But my
backup names contain the current version string.

I'm not sure about the sort order hack. My goal is to have update-grub
see the knowngood as a bootable linux and include it in the boot menu.
That's also why .bak of initrd isn't good enough - I need a complete copy.

[zithro]

Breaks how ?

In Bullseye you have to remove old kernels/initrd manually
(with for example apt autoremove)
I just checked some logs and it also worked like this in Buster
You can keep as many versions as you want.

Also, I found this old post on this very ML:

On Thu, Dec 13, 2007 at 09:54:49PM -0500, Marc Auslander wrote:
> The problem is operator (that's me) stupidity.
>
> I have an overloaded find so I can say find foo and have it mean
> find . -name foo -print
>
> mkinitramfs uses find . | cpio to build the initrd.img
>

[davidson]

Caveat: I don't know WTH I'm doing. Also, I used a bullseye system for
experiments below, not buster.

I read update-initramfs(8) and did a couple experiments, one to
replicate your observations on my bullseye system, and then a variant
of David's version-naming hack.

Results are summarised below, in case you find them interesting.

EXPERIMENT #1

The first experiment simply tried to replicate your observations (as I
understood them). Basically, I added "-kg" suffix to all the files in
/boot corresponding to latest installed kernel, so that I had
unsuffixed copies and "*-kg" ("knowngood") copies, and then tried

# update-initramfs -u

which, as you report, targeted the "*-kg" files (and turned a 28M
initrd.img-*-kg into a 6M file... no longer warranting the suffix
"-kg").

Also (after making fresh "*-kg" copies), I tried

# update-initramfs -u -k all

which went first for the "*-kg" files, trashed the initrd.img-*-kg as
before, but then continued on to update all the other versions.

EXPERIMENT #2

The second experiment is similar to david's suggestion, but alters the
end of the name instead. (I didn't think of using a prefix.)

The manual implies that...

update-initramfs -u

...by default tries to update the "latest" kernel version. The
following result suggests that it determines which files correspond to
that "latest" version by just looking at their filenames.

So basically instead of only adding "-kg" to the files in /boot, I
decremented the last character of uname -r and *then* added "-kg", so
that it wouldn't look like a later version.

# knowngood=( /boot/*-$(uname -r) )
# for ((i=0 ; i<${#knowngood[@]}; i+=1)) ; do cp -a "${knowngood[i]}" "${knowngood[i]/%4/3-kg}" ; done
# ls -l
total 105464
-rw-r--r-- 1 root root 206413 20 déc. 17:56 config-4.19.0-23-amd64
-rw-r--r-- 1 root root 236452 21 janv. 09:35 config-5.10.0-21-amd63-kg
-rw-r--r-- 1 root root 236452 21 janv. 09:35 config-5.10.0-21-amd64
drwxr-xr-x 5 root root 4096 11 avril 01:28 grub
-rw-r--r-- 1 root root 26109076 10 avril 21:59 initrd.img-4.19.0-23-amd64
-rw-r--r-- 1 root root 29199065 10 avril 21:58 initrd.img-5.10.0-21-amd63-kg
-rw-r--r-- 1 root root 29199065 10 avril 21:58 initrd.img-5.10.0-21-amd64
-rw-r--r-- 1 root root 3418327 20 déc. 17:56 System.map-4.19.0-23-amd64
-rw-r--r-- 1 root root 83 21 janv. 09:35 System.map-5.10.0-21-amd63-kg
-rw-r--r-- 1 root root 83 21 janv. 09:35 System.map-5.10.0-21-amd64
-rw-r--r-- 1 root root 5303616 20 déc. 17:56 vmlinuz-4.19.0-23-amd64
-rw-r--r-- 1 root root 7019136 21 janv. 09:35 vmlinuz-5.10.0-21-amd63-kg
-rw-r--r-- 1 root root 7019136 21 janv. 09:35 vmlinuz-5.10.0-21-amd64

# update-initramfs -u
# update-initramfs: Generating /boot/initrd.img-5.10.0-21-amd64

# update-grub
Generating grub configuration file ...
Found linux image: /boot/vmlinuz-5.10.0-21-amd63-kg
Found initrd image: /boot/initrd.img-5.10.0-21-amd63-kg
Found linux image: /boot/vmlinuz-5.10.0-21-amd64
Found initrd image: /boot/initrd.img-5.10.0-21-amd64
Found linux image: /boot/vmlinuz-4.19.0-23-amd64
Found initrd image: /boot/initrd.img-4.19.0-23-amd64
Warning: os-prober will be executed to detect other bootable partitions.
Its output will be used to detect bootable binaries on them and create new boot entries.
done

So update-grub didn't seem to complain.

I haven't tried booting yet with my "5.10.0-21-amd63-kg" initrd,
though. I'll leave that to you, if you want to try.

--
Hackers are free people. They are like artists. If they are in a good
mood, they get up in the morning and begin painting their pictures.
-- Vladimir Putin

[Michel Verdier]

Le 11 avril 2023 davidson a écrit :

> The first experiment simply tried to replicate your observations (as I
> understood them). Basically, I added "-kg" suffix to all the files in
> /boot corresponding to latest installed kernel, so that I had
> unsuffixed copies and "*-kg" ("knowngood") copies, and then tried
>
> # update-initramfs -u

I don't understand a point. On my system I compiled kernel and thus build
a linux-image-...deb with a specific tag. I install package so I have
kernel and initram in /boot with the tag. Same as your system I think ?
And when I update-initramfs it generate right files with right names. And
never break anything on further updates. So why change only filenames and
not rebuild a package with a different tag ?

[davidson]

On Tue, 11 Apr 2023 Michel Verdier wrote:
> Le 11 avril 2023 davidson a écrit :
>
>> The first experiment simply tried to replicate your observations (as I
>> understood them). Basically, I added "-kg" suffix to all the files in
>> /boot corresponding to latest installed kernel, so that I had
>> unsuffixed copies and "*-kg" ("knowngood") copies, and then tried
>>
>> # update-initramfs -u
>
> I don't understand a point.

Hi Michel.

To be clear, I am not the OP.

> On my system I compiled kernel and thus build a linux-image-...deb
> with a specific tag.

That is much more work than I did. I compiled no custom kernel. I just
made copies of the files in /boot installed from package
linux-image-5.10.0-21-amd64, and the corresponding initrd.

Here is a run of my Experiment #1, in full:

# knowngood=( /boot/*-$(uname -r) )

# for ((i=0; i<${#knowngood[@]}; i+=1)) ; do cp -a "${knowngood[i]}" "${knowngood[i]/%/-kg}" ; done
# ls -l "${knowngood[@]}"
-rw-r--r-- 1 root root 236452 21 janv. 09:35 /boot/config-5.10.0-21-amd64
-rw-r--r-- 1 root root 29199065 10 avril 21:58 /boot/initrd.img-5.10.0-21-amd64
-rw-r--r-- 1 root root 83 21 janv. 09:35 /boot/System.map-5.10.0-21-amd64
-rw-r--r-- 1 root root 7019136 21 janv. 09:35 /boot/vmlinuz-5.10.0-21-amd64
# ls -l "${knowngood[@]/%/-kg}"
-rw-r--r-- 1 root root 236452 21 janv. 09:35 /boot/config-5.10.0-21-amd64-kg
-rw-r--r-- 1 root root 29199065 10 avril 21:58 /boot/initrd.img-5.10.0-21-amd64-kg
-rw-r--r-- 1 root root 83 21 janv. 09:35 /boot/System.map-5.10.0-21-amd64-kg
-rw-r--r-- 1 root root 7019136 21 janv. 09:35 /boot/vmlinuz-5.10.0-21-amd64-kg

# update-initramfs -u
# update-initramfs: Generating /boot/initrd.img-5.10.0-21-amd64-kg
W: missing /lib/modules/5.10.0-21-amd64-kg
W: Ensure all necessary drivers are built into the linux image!
depmod: ERROR: could not open directory /lib/modules/5.10.0-21-amd64-kg: No such file or directory
depmod: FATAL: could not search modules: No such file or directory
cat: /var/tmp/mkinitramfs_9UHxvD/lib/modules/5.10.0-21-amd64-kg/modules.builtin: Aucun fichier ou dossier de ce type
find: ‘/var/tmp/mkinitramfs_9UHxvD/lib/modules/5.10.0-21-amd64-kg/kernel’: Aucun fichier ou dossier de ce type
W: Can't find modules.builtin.modinfo (for locating built-in drivers' firmware, supported in Linux >=5.2)
depmod: WARNING: could not open modules.order at /var/tmp/mkinitramfs_9UHxvD/lib/modules/5.10.0-21-amd64-kg: No such file or directory
depmod: WARNING: could not open modules.builtin at /var/tmp/mkinitramfs_9UHxvD/lib/modules/5.10.0-21-amd64-kg: No such file or directory
# ls -l "${knowngood[@]}"
-rw-r--r-- 1 root root 236452 21 janv. 09:35 /boot/config-5.10.0-21-amd64
-rw-r--r-- 1 root root 29199065 10 avril 21:58 /boot/initrd.img-5.10.0-21-amd64
^^^^^^^^
-rw-r--r-- 1 root root 83 21 janv. 09:35 /boot/System.map-5.10.0-21-amd64
-rw-r--r-- 1 root root 7019136 21 janv. 09:35 /boot/vmlinuz-5.10.0-21-amd64
# ls -l "${knowngood[@]/%/-kg}"
-rw-r--r-- 1 root root 236452 21 janv. 09:35 /boot/config-5.10.0-21-amd64-kg
-rw-r--r-- 1 root root 5924752 10 avril 22:07 /boot/initrd.img-5.10.0-21-amd64-kg
^^^^^^^
-rw-r--r-- 1 root root 83 21 janv. 09:35 /boot/System.map-5.10.0-21-amd64-kg
-rw-r--r-- 1 root root 7019136 21 janv. 09:35 /boot/vmlinuz-5.10.0-21-amd64-kg

> I install package so I have kernel and initram in /boot with the
> tag. Same as your system I think ?

You didn't make backup copies of your most recent kernel, *give them
funny names*, and keep them in /boot. That is the distinction here, I
think.

> And when I update-initramfs it generate right files with right
> names. And never break anything on further updates.

That makes sense, of course.

> So why change only filenames and not rebuild a package with a
> different tag ?

I believe the OP just wants an extra entry in his grub menu that will
boot a redundant copy of his latest working kernel. (But that is only
my understanding, which might be wrong. OP can speak for himself on
this point.)

It seems to me that building and packaging like you suggest is more
work than warranted, just to make a backup copy. According to OP's
report, that simple practice used to work for him.

Myself, I was only curious to do

Experiment #1: replicate the OP's observations

and

Experiment #2: see if I could tweak OP's practice enough so that
update-grub would not care.

[davi...@freevolt.org]

...and so that "update-initramfs -u" would not notice.

--
Sometimes it pays to have squirrels in your head running around making
you question everything. -- Clive Robinson

[David Wright]

On Tue 11 Apr 2023 at 10:51:19 (-0400), Marc Auslander wrote:
> On 4/10/2023 11:00 PM, David Wright wrote:
> > On Mon 10 Apr 2023 at 20:17:11 (-0400), Marc Auslander wrote:
> > > I'm on Buster.
> > >
> > > In /boot I keep a copy of the current working linux named by appending
> > > -knowngood to the four files. My idea is that if an update fails, I
> > > have a recent working linux. This is different from vmlinuz.old which
> > > is the previous kernel version. The updates in question are not to
> > > the kernel but to initrd.image of course.
> > >
> > > Suddenly, update-initramfs insists in trying to first update
> > > initrd.....-knowngood which of course fails because there are no
> > > underling file with that name. This never happened in the past,
> > > AFAIK. Once it fails it gives up.
> > >
> > > There seems no way to force update-initramfs to update the right kernel.

[ … ]

> thanks but that's the first thing I checked - it's yes, not all. But
> my backup names contain the current version string.
>
> I'm not sure about the sort order hack. My goal is to have
> update-grub see the knowngood as a bootable linux and include it in
> the boot menu. That's also why .bak of initrd isn't good enough - I
> need a complete copy.

Oh, so it's update-grub calling update-initramfs, which could
complicate things.

Quite honestly, I don't see why you want to make what are essentially
backup files into part of the working set for both Grub and initramfs,
meaning they have to process duplicate files.

Any time you have a set of files that you're happy with, why not just
copy them to another directory, like /boot/backups/, adding suitable
suffixes. With Grub's flexibility, it's very easy to boot from those
copies instead. Press e at the blue screen, and tweak the filenames.
If you forget where they are or what they're called, press c instead
and go hunting with ls.

Cheers,
David.

[zithro]

I thought :

- you can install as many kernel packages as you want, whether built or
downloaded
- updates don't automatically remove old kernels/initrd by default

So I wonder, why handling it manually ?
What is the advantage, except for adding -confusion- ?

[David Wright]

There is one case where a kernel is silently removed, and that is when
they tweak it without changing the minor number (or whatever that
number is now called). IIRC it hasn't happened for quite some time;
perhaps the last was in June 2020, when 4.19.118-2+deb10u1 replaced
4.19.118-2 for linux-image-4.19.0-9-amd64.

Found in APT's history log with /linux-image.*\(([-0-9\.]+), \1

Cheers,
David.

[Michel Verdier]

Le 11 avril 2023 davidson a écrit :

> # update-initramfs -u
> # update-initramfs: Generating /boot/initrd.img-5.10.0-21-amd64-kg
> W: missing /lib/modules/5.10.0-21-amd64-kg

Of course : /lib/modules/<kernel version> is installed via package. You
have to do it manually to get rid of this error. And without it you can't
achieve a bootable kernel.

> You didn't make backup copies of your most recent kernel, *give them
> funny names*, and keep them in /boot. That is the distinction here, I
> think.

I don't have to do it *manually* I give funny names during build so the
.deb include all is needed. And I only need backup of the package, not
the /boot files. Obviously /boot is for operational files not for backup
ones.

> I believe the OP just wants an extra entry in his grub menu that will
> boot a redundant copy of his latest working kernel. (But that is only
> my understanding, which might be wrong. OP can speak for himself on
> this point.)

Ok to cover grub menu you just have to had it in /etc/grub.d.
You simply copy a block menuentry from /boot/grub/grub.cfg and put it in
something like /etc/grub.d/40_custom. In the copy you can change kernel
params, etc. update-grub will include it in generated grub.cfg.

> It seems to me that building and packaging like you suggest is more
> work than warranted, just to make a backup copy. According to OP's
> report, that simple practice used to work for him.

Building a kernel is much less work than believed. And much much less
complicated too. It requires apt install kernel sources, apt install deps
for build, then do the build. I build with my custom make commands but I
heard there is a dedicated debian stance to even more simplify this
point. Overall it is much less work than manually following updates on a
breaked /boot.

[davi...@freevolt.org]

On Wed, 12 Apr 2023 davidson wrote:

> On Tue, 11 Apr 2023 davidson wrote:
>> I haven't tried booting yet with my "5.10.0-21-amd63-kg" initrd,
>> though. I'll leave that to you, if you want to try.
>

> Boot went fine, but it is worth mentioning that grub-update

*update-grub

> decided that the "5.10.0-21-amd63-kg" copy of the 5.10.0-21-amd64
> kernel should be the default grub entry.

[davidson]

On Tue, 11 Apr 2023 davidson wrote:
> On Tue, 11 Apr 2023 Marc Auslander wrote:
>> On 4/10/2023 11:00 PM, David Wright wrote:
>>> On Mon 10 Apr 2023 at 20:17:11 (-0400), Marc Auslander wrote:
>>>> I'm on Buster.
>>>>
>>>> In /boot I keep a copy of the current working linux named by appending
>>>> -knowngood to the four files. My idea is that if an update fails, I
>>>> have a recent working linux. This is different from vmlinuz.old which
>>>> is the previous kernel version. The updates in question are not to
>>>> the kernel but to initrd.image of course.
>>>>
>>>> Suddenly, update-initramfs insists in trying to first update
>>>> initrd.....-knowngood which of course fails because there are no
>>>> underling file with that name. This never happened in the past,
>>>> AFAIK. Once it fails it gives up.
>>>>
>>>> There seems no way to force update-initramfs to update the right kernel.
>>>

[trim]

>
> # update-initramfs -u
> # update-initramfs: Generating /boot/initrd.img-5.10.0-21-amd64
>
> # update-grub
> Generating grub configuration file ...
> Found linux image: /boot/vmlinuz-5.10.0-21-amd63-kg
> Found initrd image: /boot/initrd.img-5.10.0-21-amd63-kg
> Found linux image: /boot/vmlinuz-5.10.0-21-amd64
> Found initrd image: /boot/initrd.img-5.10.0-21-amd64
> Found linux image: /boot/vmlinuz-4.19.0-23-amd64
> Found initrd image: /boot/initrd.img-4.19.0-23-amd64
> Warning: os-prober will be executed to detect other bootable partitions.
> Its output will be used to detect bootable binaries on them and create new
> boot entries.
> done
>
> So update-grub didn't seem to complain.
>
> I haven't tried booting yet with my "5.10.0-21-amd63-kg" initrd,
> though. I'll leave that to you, if you want to try.

Boot went fine, but it is worth mentioning that grub-update decided

that the "5.10.0-21-amd63-kg" copy of the 5.10.0-21-amd64 kernel
should be the default grub entry.

[The Wanderer]

On 2023-04-11 at 22:30, Michel Verdier wrote:

> Le 11 avril 2023 davidson a écrit :

>> I believe the OP just wants an extra entry in his grub menu that
>> will boot a redundant copy of his latest working kernel. (But that
>> is only my understanding, which might be wrong. OP can speak for
>> himself on this point.)
>
> Ok to cover grub menu you just have to had it in /etc/grub.d. You
> simply copy a block menuentry from /boot/grub/grub.cfg and put it in
> something like /etc/grub.d/40_custom. In the copy you can change
> kernel params, etc. update-grub will include it in generated
> grub.cfg.

Without anything more, wouldn't that just result in an extra GRUB-menu
entry pointing to the same copy of the kernel/etc.?

As I think I understand matters, the goal is to have a duplicate copy of
the kernel/etc. *and* a separate GRUB menu entry pointing to it, so that
if something blows away or otherwise messes up the original the
duplicate is still around to serve as a fallback.

--
The Wanderer

The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself. Therefore all
progress depends on the unreasonable man. -- George Bernard Shaw

[Michel Verdier]

Le 12 avril 2023 The Wanderer a écrit :

> Without anything more, wouldn't that just result in an extra GRUB-menu
> entry pointing to the same copy of the kernel/etc.?

Of course he can change menuentry to point to another kernel/initram

> As I think I understand matters, the goal is to have a duplicate copy of
> the kernel/etc. *and* a separate GRUB menu entry pointing to it, so that
> if something blows away or otherwise messes up the original the
> duplicate is still around to serve as a fallback.

Yes if he points menuentry to the backup he got this fallback.

[The Wanderer]

On 2023-04-12 at 07:44, Michel Verdier wrote:

> Le 12 avril 2023 The Wanderer a écrit :
>
>> Without anything more, wouldn't that just result in an extra
>> GRUB-menu entry pointing to the same copy of the kernel/etc.?
>
> Of course he can change menuentry to point to another kernel/initram

From what I understand matters, the problem is that after he creates the
copy of the initrd, update-initramfs (as run by update-grub) fails,
because the underlying files which it thinks would be needed by an
initrd with the filename that the copy has don't exist.

>> As I think I understand matters, the goal is to have a duplicate
>> copy of the kernel/etc. *and* a separate GRUB menu entry pointing
>> to it, so that if something blows away or otherwise messes up the
>> original the duplicate is still around to serve as a fallback.
>
> Yes if he points menuentry to the backup he got this fallback.

The question would therefore be how to have the backup copy without
resulting in this update-initramfs failure happening.

About the only possibility I can think of would be to *also* copy the
respective underlying files, so that they are available under the name
update-initramfs expects to see. That would probably make the backup -
and the process of creating it - noticeably more unwieldy, however.

And it's entirely possible that there's some aspect of the process I'm
not seeing which would mean that that wouldn't work.

[David Wright]

On Wed 12 Apr 2023 at 07:50:33 (-0400), The Wanderer wrote:
> On 2023-04-12 at 07:44, Michel Verdier wrote:
> > Le 12 avril 2023 The Wanderer a écrit :
> >
> >> Without anything more, wouldn't that just result in an extra
> >> GRUB-menu entry pointing to the same copy of the kernel/etc.?
> >
> > Of course he can change menuentry to point to another kernel/initram
>
> From what I understand matters, the problem is that after he creates the
> copy of the initrd, update-initramfs (as run by update-grub) fails,
> because the underlying files which it thinks would be needed by an
> initrd with the filename that the copy has don't exist.
>
> >> As I think I understand matters, the goal is to have a duplicate
> >> copy of the kernel/etc. *and* a separate GRUB menu entry pointing
> >> to it, so that if something blows away or otherwise messes up the
> >> original the duplicate is still around to serve as a fallback.
> >
> > Yes if he points menuentry to the backup he got this fallback.

By my reckoning, the "fallbacks" in this context are old kernel
versions, kept in case the newer version of the kernel doesn't work.

> The question would therefore be how to have the backup copy without
> resulting in this update-initramfs failure happening.

But in what other situation would you make backups, and then store
them all mixed in with the active versions?

> About the only possibility I can think of would be to *also* copy the
> respective underlying files, so that they are available under the name
> update-initramfs expects to see. That would probably make the backup -
> and the process of creating it - noticeably more unwieldy, however.

But why ever /process/ backup copies? Surely you just repeat backing
up the latest updates whenever you've ascertained that they're good.
If you place the backups under a different, non-active directory, then
they won't get accidentally seen by update-initramfs and tampered with.

> And it's entirely possible that there's some aspect of the process I'm
> not seeing which would mean that that wouldn't work.

The only minor difference I see from a typical backup scenario is
that you probably want this set of backups to be quickly available
for the Grub menu to read. Whether that means being included /in
the menu/ is moot. I would maintain that this failure mode is rare
enough for a reasonable penalty of having to type a few characters
editing the Grub menu.

The last time I booted a kernel that was on a different partition
from my installed Grub, it took no more than typing 23 characters
and a load of rubouts. (That was after installing bookworm RC1.)

Cheers,
David.

[Michel Verdier]

Le 12 avril 2023 David Wright a écrit :

> the menu/ is moot. I would maintain that this failure mode is rare
> enough for a reasonable penalty of having to type a few characters
> editing the Grub menu.
>
> The last time I booted a kernel that was on a different partition
> from my installed Grub, it took no more than typing 23 characters
> and a load of rubouts. (That was after installing bookworm RC1.)

I agree with all you said. But on this point I don't follow you. Yes the
need is extremely rare. And so I was never able to remember this few
chars stance and each time rely on rescue boot to do this. So I
understand that a simple grub menu could be useful.

[David Wright]

When I tried installing bookworm RC1, which I reported in:

https://lists.debian.org/debian-user/2023/04/msg00405.html

I was left with a system whose Grub menu only contained entries for
the new system, because os-prober no longer scours all the other
partitions for OSes any more.¹ To get back to booting bullseye by
default, the easiest way was to boot bullseye the once, and then run
install-grub /dev/sda.

So I rebooted, pressed e at the blue Grub screen to edit the first
menuitem, and mangled just these lines:

set root='hd0,gpt4'
if [ x$feature_platform_search_hint = xy ]; then
search --no-floppy --fs-uuid --set=root --hint-bios=hd0,gpt4 --hint-efi=hd0,gpt4 --hint-baremetal=ahci0,gpt4 21c64c1c-2c0c-4376-922e-40ff9d46d08a
else
search --no-floppy --fs-uuid --set=root 21c64c1c-2c0c-4376-922e-40ff9d46d08a
fi
echo 'Loading Linux 6.1.0-7-amd64 ...'
linux /boot/vmlinuz-6.1.0-7-amd64 root=UUID=21c64c1c-2c0c-4376-922e-40ff9d46d08a ro quiet
echo 'Loading initial ramdisk ...'
initrd /boot/initrd.img-6.1.0-7-amd64

to:

set root='hd0,gpt5'
search --no-floppy --label --set=root ezra05
linux /vmlinuz root=LABEL=ezra05 ro quiet
initrd /initrd.img

which sufficed to boot the default kernel on my bullseye root
partition (via the symlinks, which saves having to know the version).

23 new characters: 5labelezra05LABELezra05, and lots of deletions.

Running install-grub then rewrites the BIOS boot partition (/dev/sda1)
with bullseye's Grub, overwriting bookworm's. (The MBR gets rewritten
too, but it's unchanged.)

¹ I also tested uncommenting GRUB_DISABLE_OS_PROBER=false
in /target/etc/default/grub at the point when the d-i first asks:

┌────────────┤ [!] Install the GRUB boot loader ├─────────────┐

This makes os-prober behave as it has done, up until bullseye.

Cheers,
David.

[Charles Curley]

On Thu, 13 Apr 2023 13:57:04 -0500
David Wright <deb...@lionunicorn.co.uk> wrote:

> https://lists.debian.org/debian-user/2023/04/msg00405.html
>
> I was left with a system whose Grub menu only contained entries for
> the new system, because os-prober no longer scours all the other
> partitions for OSes any more.¹ To get back to booting bullseye by
> default, the easiest way was to boot bullseye the once, and then run
> install-grub /dev/sda.

I believe the preferred way to get back to including other OSs in
grub's menu is to enable the OS prober by adding the following (if
necessary) to /etc/default/grub, un-commenting the last line, and
running update-grub.

# Uncomment this to run os-prober to search for and add other OS
# installations to the grub boot menu
#GRUB_DISABLE_OS_PROBER=false

See:

From: Cyril Brulebois <ki...@debian.org>
To: debian-dev...@lists.debian.org
Cc: debia...@lists.debian.org
Subject: Debian Installer Bookworm Alpha 2 release


--
Does anybody read signatures any more?

https://charlescurley.com
https://charlescurley.com/blog/

[Michael Stone]

On Thu, Apr 13, 2023 at 01:57:04PM -0500, David Wright wrote:
>os-prober no longer scours all the other

>partitions for OSes any more.น

Which is wonderful--that was one of the most annoying misfeatures to
have ever been enabled.

[David]

On Fri, 2023-04-14 at 14:40 +0000, Schwibinger Michael wrote:
> Good afternoon.
> The new printer is not  working.
> EPSON is saying
> You cant use EPSON with Linux.

It depends on which printer you are using?
It sounds like the person you are talking to at Epson doesn't know what
he/she's talking about.
Epson supply many Linux drivers for their printers on their site.
I have a WF-C5290 which works just fine that way.
Cheers!

[Brian]

On Fri 14 Apr 2023 at 14:40:33 +0000, Schwibinger Michael wrote:

> Good afternoon.
> The new printer is not working.
> EPSON is saying
> You cant use EPSON with Linux.
>

> Is this true?

You could consider:

* Stating the Debain OS being used.
* Giving the printer make and model.
* Specifying the connection method. USB. Network.
* Giving the exact error message and where it came from.

--
Brian.

[The Wanderer]

On 2023-04-14 at 18:10, Brian wrote:

> On Fri 14 Apr 2023 at 14:40:33 +0000, Schwibinger Michael wrote:
>
>> Good afternoon.
>> The new printer is not working.
>> EPSON is saying
>> You cant use EPSON with Linux.
>>
>> Is this true?
>
> You could consider:
>
> * Stating the Debain OS being used.
> * Giving the printer make and model.

The make *was* stated: Epson.

The model may also have been stated, albeig only in the Subject line: ET
M1120. From a bit of Googling, the "ET" appears to stand for "EcoTank".

> * Specifying the connection method. USB. Network.
> * Giving the exact error message and where it came from.

Also:

* Starting a new thread to discuss the matter, rather than replying to
an existing message deep in an existing thread, deleting the body, and
changing the Subject line before sending.

(This question, and its replies, are appearing as responses to a mail
from Michael Stone in the 'update-initramfs' thread.)

[Jeremy Ardley]

On 15/4/23 06:22, The Wanderer wrote:

The make *was* stated: Epson.

The model may also have been stated, albeig only in the Subject line: ET
M1120. From a bit of Googling, the "ET" appears to stand for "EcoTank".

If you look hard enough you find epson does support it.

https://download.ebz.epson.net/dsc/search/01/search/searchModule

and search for M1120

you find

ET-M1120 Series M1120 Series

Printer Driver

Linux

1.7.26

ESC/P-R Driver (generic driver)

All language

04-10-2023

and that links to the standard esc/p-r driver

-- 
Jeremy
(Lists)

[Stefan Monnier]

>> The new printer is not working.
>> EPSON is saying
>> You cant use EPSON with Linux.
>>
>> Is this true?
>
> You could consider:
>
> * Stating the Debain OS being used.
> * Giving the printer make and model.

"Subject:" says "EPSON ET M 1120"
AFAICT it's a monochrome printer from 2019 with some kind of ink tank.
Given the timescale, it probably supports driverless printing.


Stefan

[David Wright]

On Thu 13 Apr 2023 at 14:39:18 (-0600), Charles Curley wrote:
> On Thu, 13 Apr 2023 13:57:04 -0500
> David Wright <deb...@lionunicorn.co.uk> wrote:
>
> > https://lists.debian.org/debian-user/2023/04/msg00405.html
> >
> > I was left with a system whose Grub menu only contained entries for
> > the new system, because os-prober no longer scours all the other
> > partitions for OSes any more.¹ To get back to booting bullseye by
> > default, the easiest way was to boot bullseye the once, and then run
> > install-grub /dev/sda.

Don't let me leave you with the impression that this was unexpected,
or of concern to me. And the way I dealt with it was offered here to
illustrate why the OP does not +need+ their kernel/initramfs backups
to be mixed up with the originals in /boot/grub, or for Grub's menu
to include them as a separate menuentry.

Also bear in mind that the post cited, on bookworm RC1 installation,
was to replicate the one made by the OP of that thread (right down to
using a BIOS/GPT system), and elicit a response with more information
(not forthcoming) on their "bug".

> I believe the preferred way to get back to including other OSs in
> grub's menu is to enable the OS prober by adding the following (if
> necessary) to /etc/default/grub, un-commenting the last line, and
> running update-grub.

Yes, and in my footnote, I showed that you can, if you want, get the
other OSes back /before/ the first reboot, remembering that that file
is mounted on /target while the OS is being built by the debian-installer.

> # Uncomment this to run os-prober to search for and add other OS
> # installations to the grub boot menu
> #GRUB_DISABLE_OS_PROBER=false

All present and correct in RC1.

Cheers,
David.

[Brian]

On Fri 14 Apr 2023 at 18:22:09 -0400, The Wanderer wrote:

> On 2023-04-14 at 18:10, Brian wrote:
>
> > On Fri 14 Apr 2023 at 14:40:33 +0000, Schwibinger Michael wrote:
> >
> >> Good afternoon.
> >> The new printer is not working.
> >> EPSON is saying
> >> You cant use EPSON with Linux.
> >>
> >> Is this true?
> >
> > You could consider:
> >
> > * Stating the Debain OS being used.
> > * Giving the printer make and model.
>
> The make *was* stated: Epson.
>
> The model may also have been stated, albeig only in the Subject line: ET
> M1120. From a bit of Googling, the "ET" appears to stand for "EcoTank".

The EPSON ET M 1120 doesn't exist. Do we have to guess its correct name as well
as any other relevant information?

> > * Specifying the connection method. USB. Network.
> > * Giving the exact error message and where it came from.
>
> Also:
>
> * Starting a new thread to discuss the matter, rather than replying to
> an existing message deep in an existing thread, deleting the body, and
> changing the Subject line before sending.
>
> (This question, and its replies, are appearing as responses to a mail
> from Michael Stone in the 'update-initramfs' thread.)

I haven't a clue what you are going on about here. Shift-L in mutt was used at
this end.

--
Brian.

[Charles Curley]

On Sat, 15 Apr 2023 06:36:53 +0800
Jeremy Ardley <jer...@ardley.org> wrote:

> On 15/4/23 06:22, The Wanderer wrote:

> [...]

> If you look hard enough you find epson does support it.
>
> https://download.ebz.epson.net/dsc/search/01/search/searchModule
>
> and search for M1120
>
> you find
>
> ET-M1120 Series
> M1120 Series
> Printer Driver Linux
> 1.7.26 ESC/P-R Driver (generic driver) All
> language 04-10-2023
>
>
> and that links to the standard esc/p-r driver
>

And that driver is even available in Debian.

apt show printer-driver-escpr

[Jeremy Ardley]

On 15/4/23 06:52, Brian wrote:
> The EPSON ET M 1120 doesn't exist. Do we have to guess its correct
> name as well

I asked ChatGPT3.5 about that text string. At least ChatGPT could figure
it out

>>>>>>>>>> My Question

Linux printer driver and printer command protocol for epson ET M 1120 ?

>>>>>>>>>> ChatGPT response

The Epson ET-M1120 printer supports the Epson ESC/P-R printer language,
which is a command protocol used by Epson printers.

To install the printer driver for Linux, you can follow these steps:

Connect the printer to your computer and make sure it is turned on.
Open your Linux terminal and run the following command to update your
system package list:

sudo apt-get update

Install the printer driver by running the following command:

sudo apt-get install printer-driver-escpr

Follow the on-screen instructions to complete the installation.

Once the driver is installed, you can use the printer with any
application that supports printing.



--
Jeremy
(Lists)

[The Wanderer]

On 2023-04-14 at 18:52, Brian wrote:

> On Fri 14 Apr 2023 at 18:22:09 -0400, The Wanderer wrote:
>
>> On 2023-04-14 at 18:10, Brian wrote:

>> > You could consider:
>> >
>> > * Stating the Debain OS being used.
>> > * Giving the printer make and model.
>>
>> The make *was* stated: Epson.
>>
>> The model may also have been stated, albeig only in the Subject line: ET
>> M1120. From a bit of Googling, the "ET" appears to stand for "EcoTank".
>
> The EPSON ET M 1120 doesn't exist. Do we have to guess its correct name as well
> as any other relevant information?

When I searched for

Epson ET M 1120

I got a suggestion that I may have meant "M1120" instead of the last two
search terms, and hits for the "Epson EcoTank ET M1120" and/or "Epson
EcoTank M1120", which look to be different names for the same model and
to be a fairly clear match.

While, yes, specifying the exact name clearly would be preferable, this
is far from unreasonably difficult to figure out.

>> > * Specifying the connection method. USB. Network.
>> > * Giving the exact error message and where it came from.
>>
>> Also:
>>
>> * Starting a new thread to discuss the matter, rather than replying
>> to an existing message deep in an existing thread, deleting the
>> body, and changing the Subject line before sending.
>>
>> (This question, and its replies, are appearing as responses to a
>> mail from Michael Stone in the 'update-initramfs' thread.)
>
> I haven't a clue what you are going on about here. Shift-L in mutt
> was used at this end.

Your replies to the OP have been fine, AFAIK. The OP's message was
itself a reply, as can be seen by looking at its headers (In-Reply-To:
and References:), but was otherwise presented as if it had been the
start of a new thread; that is not fine, because it hides the "new
thread" inside of the existing one, at least for anyone using a threaded
view of the list of messages.

[Brian]

On Sat 15 Apr 2023 at 07:00:18 +0800, Jeremy Ardley wrote:

>
> On 15/4/23 06:52, Brian wrote:
> > The EPSON ET M 1120 doesn't exist. Do we have to guess its correct name
> > as well
>
>
> I asked ChatGPT3.5 about that text string. At least ChatGPT could figure it
> out
>
> >>>>>>>>>> My Question
>
> Linux printer driver and printer command protocol for epson ET M 1120 ?
>
> >>>>>>>>>> ChatGPT response
>
> The Epson ET-M1120 printer supports the Epson ESC/P-R printer language,
> which is a command protocol used by Epson printers.

It is the OP who needs help, not me. She couls at least provide correct and full date.

--
Brian.

[Brian]

On Fri 14 Apr 2023 at 19:06:08 -0400, The Wanderer wrote:

> On 2023-04-14 at 18:52, Brian wrote:
>
> > On Fri 14 Apr 2023 at 18:22:09 -0400, The Wanderer wrote:
> >
> >> On 2023-04-14 at 18:10, Brian wrote:
>
> >> > You could consider:
> >> >
> >> > * Stating the Debain OS being used.
> >> > * Giving the printer make and model.
> >>
> >> The make *was* stated: Epson.
> >>
> >> The model may also have been stated, albeig only in the Subject line: ET
> >> M1120. From a bit of Googling, the "ET" appears to stand for "EcoTank".
> >
> > The EPSON ET M 1120 doesn't exist. Do we have to guess its correct name as well
> > as any other relevant information?
>
> When I searched for
>
> Epson ET M 1120
>
> I got a suggestion that I may have meant "M1120" instead of the last two
> search terms, and hits for the "Epson EcoTank ET M1120" and/or "Epson
> EcoTank M1120", which look to be different names for the same model and
> to be a fairly clear match.
>
> While, yes, specifying the exact name clearly would be preferable, this
> is far from unreasonably difficult to figure out.

I decided to take your signature as a template for my original response :).

> >> > * Specifying the connection method. USB. Network.
> >> > * Giving the exact error message and where it came from.
> >>
> >> Also:
> >>
> >> * Starting a new thread to discuss the matter, rather than replying
> >> to an existing message deep in an existing thread, deleting the
> >> body, and changing the Subject line before sending.
> >>
> >> (This question, and its replies, are appearing as responses to a
> >> mail from Michael Stone in the 'update-initramfs' thread.)
> >
> > I haven't a clue what you are going on about here. Shift-L in mutt
> > was used at this end.
>
> Your replies to the OP have been fine, AFAIK. The OP's message was
> itself a reply, as can be seen by looking at its headers (In-Reply-To:
> and References:), but was otherwise presented as if it had been the
> start of a new thread; that is not fine, because it hides the "new
> thread" inside of the existing one, at least for anyone using a threaded
> view of the list of messages.

That's an issue for the OP, not me.

--
Brian.

[David]

On Fri, 2023-04-14 at 23:52 +0100, Brian wrote:
> On Fri 14 Apr 2023 at 18:22:09 -0400, The Wanderer wrote:
>
> > On 2023-04-14 at 18:10, Brian wrote:
> >
> > > On Fri 14 Apr 2023 at 14:40:33 +0000, Schwibinger Michael wrote:
> > >
> > > > Good afternoon.
> > > > The new printer is not  working.
> > > > EPSON is saying
> > > > You cant use EPSON with Linux.
> > > >
> > > > Is this true?
> > >
> > > You could consider:
> > >
> > >   * Stating the Debain OS being used.
> > >   * Giving the printer make and model.
> >
> > The make *was* stated: Epson.
> >
> > The model may also have been stated, albeig only in the Subject
> > line: ET
> > M1120. From a bit of Googling, the "ET" appears to stand for
> > "EcoTank".
>
> The EPSON ET M 1120 doesn't exist.

Yes, it does.
It doesn't take a quantum leap in realisation to identify it as ET-
M1120.

[The Wanderer]

On 2023-04-14 at 19:17, Brian wrote:

> On Fri 14 Apr 2023 at 19:06:08 -0400, The Wanderer wrote:
>
>> On 2023-04-14 at 18:52, Brian wrote:

>>> The EPSON ET M 1120 doesn't exist. Do we have to guess its
>>> correct name as well as any other relevant information?
>>
>> When I searched for
>>
>> Epson ET M 1120
>>
>> I got a suggestion that I may have meant "M1120" instead of the
>> last two search terms, and hits for the "Epson EcoTank ET M1120"
>> and/or "Epson EcoTank M1120", which look to be different names for
>> the same model and to be a fairly clear match.
>>
>> While, yes, specifying the exact name clearly would be preferable,
>> this is far from unreasonably difficult to figure out.
>
> I decided to take your signature as a template for my original
> response :).

I can respect that!

>>> I haven't a clue what you are going on about here. Shift-L in
>>> mutt was used at this end.
>>
>> Your replies to the OP have been fine, AFAIK. The OP's message was
>> itself a reply, as can be seen by looking at its headers
>> (In-Reply-To: and References:), but was otherwise presented as if
>> it had been the start of a new thread; that is not fine, because it
>> hides the "new thread" inside of the existing one, at least for
>> anyone using a threaded view of the list of messages.
>
> That's an issue for the OP, not me.

Certainly. I was meaning that bullet-point item as an addendum to the
list you provided (which I understand to have been aimed at the OP), not
as something directed at you.

[Bret Busby]

Why not just everyone attack each other?

This looks like an uncontrolled pillow fight.

..
Bret Busby
Armadale
West Australia
(UTC+0800)
..............

[David]

Agreed!
Specifically geared to somebody not coming back, or just going back to
using Windows.
Tone and manner are more than disorienting to a new user, and far from
helpful.
Cheers!

[Andrew M.A. Cater]

On Sat, Apr 15, 2023 at 07:17:23AM +0800, Bret Busby wrote:
> Why not just everyone attack each other?
>
> This looks like an uncontrolled pillow fight.
>
> ..
> Bret Busby
> Armadale
> West Australia
> (UTC+0800)
> ..............
>

Agreed: in this instance, however, we've had a series of emails from this
person in the past. Most of them don't reset a subject so go on a long time
on various subjects in the same thread.

That said: people - please remember that this list is subject to the Code
of Conduct. Part of that involves being constructive and helpful: sniping
doesn't really help at all.

We are all human and can get annoyed when someone just doesn't *get it*
but it's useful to remember that email is hard because you can't see
the circumstances of the person on the other end. That's also one of
the reasons why these threads keep asking for technical details / accuracy:
whenever these sorts of questions get asked, we're using guesswork because
we can't see over your shoulder.

With every good wish, as ever,

Andy Cater
[amac...@debian.org]

[to...@tuxteam.de]

On Sat, Apr 15, 2023 at 10:04:46AM +0000, Andrew M.A. Cater wrote:
> On Sat, Apr 15, 2023 at 07:17:23AM +0800, Bret Busby wrote:
> > Why not just everyone attack each other?
> >
> > This looks like an uncontrolled pillow fight.

It does, indeed.

[...]

> Agreed: in this instance, however, we've had a series of emails from this
> person in the past. Most of them don't reset a subject so go on a long time
> on various subjects in the same thread.

Seconded. For whatever reason, the OP can't do better. (S)he is known
to eventually come back on help proposals. Communication is sometimes
difficult. If that rubs you the wrong way, please just abstain.

Pouring vitriol on people should be saved for very specific cases. This
doesn't seem an appropriate one.

> That said: people - please remember that this list is subject to the Code
> of Conduct. Part of that involves being constructive and helpful: sniping
> doesn't really help at all.

Thanks. Fully agreed.

Cheers
--
t

[Thomas Schmitt]

Hi,

Bret Busby wrote:
> > Why not just everyone attack each other?
> > This looks like an uncontrolled pillow fight.

We should rather invest our time in a discussion whether CP/M was better
than DOS.

Andrew M.A. Cater wrote:
> in this instance, however, we've had a series of emails from this

> person in the past. [...]
> sniping doesn't really help at all. [...]

> We are all human and can get annoyed when someone just doesn't *get it*

But this particular poster is quite special.
About a year ago i too tried to help Sophie / Michael Schwibinger with
a question about "CD"
https://lists.debian.org/debian-user/2022/04/msg00742.html
but her/his replies in the thread caused me to ask for an explanation
why "Sophie" uses the mail address of a german amateur clown and IT
engineer, especially whether "Michael Schwibinger" is aware of this usage:
https://lists.debian.org/debian-user/2022/04/msg00964.html
No reply was received.

Given the time pattern of posts and the lack of any learning progress
in respect to proper asking Debian GNU/Linux questions i suspect that
the mails from hb...@hotmail.com are not sent with sincere intentions.
They rather look like somebody is bored from time to time and throws a
pebble into the pond just to watch the ripples.
Just look at the photo on
https://hbss.tripod.com/

I may be wrong. But it would be easy for Sophie / Michael Schwibinger
to explain the circumstances, which she/he did not do up to now.
So i think it is currently not worth to quarrel over these mails.


Have a nice day :)

Thomas

[Brian]

On Fri 14 Apr 2023 at 19:28:19 -0400, The Wanderer wrote:

> On 2023-04-14 at 19:17, Brian wrote:

[...]

> > That's an issue for the OP, not me.
>
> Certainly. I was meaning that bullet-point item as an addendum to the
> list you provided (which I understand to have been aimed at the OP), not
> as something directed at you.

Apologies. I should have taken more notice of the structure of your mail.

--
Brian.

[Brian]

On Sat 15 Apr 2023 at 07:17:23 +0800, Bret Busby wrote:

> On 15/4/23 07:11, Brian wrote:
> > On Sat 15 Apr 2023 at 07:00:18 +0800, Jeremy Ardley wrote:
> >
> > >
> > > On 15/4/23 06:52, Brian wrote:
> > > > The EPSON ET M 1120 doesn't exist. Do we have to guess its correct name
> > > > as well
> > >
> > >
> > > I asked ChatGPT3.5 about that text string. At least ChatGPT could figure it
> > > out
> > >
> > > > > > > > > > > > > My Question
> > >
> > > Linux printer driver and printer command protocol for epson ET M 1120 ?
> > >
> > > > > > > > > > > > > ChatGPT response
> > >
> > > The Epson ET-M1120 printer supports the Epson ESC/P-R printer language,
> > > which is a command protocol used by Epson printers.
> >
> > It is the OP who needs help, not me. She couls at least provide correct and full date.
> >
> Why not just everyone attack each other?

There have not been any attacks whatsoever on any users.

> This looks like an uncontrolled pillow fight.

It only looks that way. In fact, everything is under control.

--
Brian.

[Brian]

The EPSON ET M1120 does not come with enough intelligence to be certified
as AirPrintint-capable. Therefore, it may or may not be be a driverless
device. The printer would need to be queried and its attributes examined
to make a decision.

--
Brian.

[to...@tuxteam.de]

On Sat, Apr 15, 2023 at 12:50:16PM +0200, Thomas Schmitt wrote:

[...]

> Given the time pattern of posts and the lack of any learning progress
> in respect to proper asking Debian GNU/Linux questions i suspect that
> the mails from hb...@hotmail.com are not sent with sincere intentions.

This is a pretty strong assessment. Coming from you, I hesitate to
dismiss it right away, but I'd still prefer to apply a healthy dose
of Hanlon's razor.

Cheers
--
t

[Brian]

On Sat 15 Apr 2023 at 15:32:30 +0200, to...@tuxteam.de wrote:

> On Sat, Apr 15, 2023 at 12:50:16PM +0200, Thomas Schmitt wrote:
>
> [...]
>
> > Given the time pattern of posts and the lack of any learning progress
> > in respect to proper asking Debian GNU/Linux questions i suspect that
> > the mails from hb...@hotmail.com are not sent with sincere intentions.
>
> This is a pretty strong assessment. Coming from you, I hesitate to
> dismiss it right away,

Tongue. Boots. Lick.

> but I'd still prefer to apply a healthy dose
> of Hanlon's razor.

Designating a user as stupid is a no-no in my book.

--
Brian.

[Bret Busby]

On 15/4/23 19:41, Brian wrote:

<snip>

>> Why not just everyone attack each other?
>
> There have not been any attacks whatsoever on any users.
>
>> This looks like an uncontrolled pillow fight.
>
> It only looks that way. In fact, everything is under control.
>

Perhaps you should try to convince the others who have also seen the
sandpit fight.

[Bret Busby]

And, a clear lack of respect has been shown, by the antagonists, for
every other subscriber to the list.

[Jeffrey Walton]

On Sat, Apr 15, 2023 at 4:26 PM Bret Busby <br...@busby.net> wrote:
>
> On 16/4/23 03:57, Bret Busby wrote:
> > On 15/4/23 19:41, Brian wrote:
> >
> > <snip>
> >
> >>> Why not just everyone attack each other?
> >>
> >> There have not been any attacks whatsoever on any users.
> >>
> >>> This looks like an uncontrolled pillow fight.
> >>
> >> It only looks that way. In fact, everything is under control.
> >
> > Perhaps you should try to convince the others who have also seen the
> > sandpit fight.

It's nothing a Plonk won't fix :)

https://duckduckgo.com/?q=usenet+plonk+killfile

Jeff

[Bret Busby]

Or, I suppose, a bottle of plonk (providing the drinker is away from,
and not thinking about, the aggression, when consuming the plonk) .

:)

(Disclaimer - I am not encouraging the drinking of plonk - I am a
teetotaller)

[to...@tuxteam.de]

On Sat, Apr 15, 2023 at 08:44:20PM +0100, Brian wrote:

[...]

> Tongue. Boots. Lick.

You must be a pretty unhappy person. Pity you.

Cheers
--
t

[davidson]

On Sun, 16 Apr 2023 to...@tuxteam.de wrote:
> On Sat, Apr 15, 2023 at 08:44:20PM +0100, Brian wrote:
>
> [...]
>
>> Tongue. Boots. Lick.

This was banter. And you trimmed away the truly funny bit.

> You must be a pretty unhappy person. Pity you.

This was pain.

Pity us all. Humor is the favorite child of pain and misery.

None of us are as happy as we'd like, and even humor takes some
practice.

On both ends.

--
Hackers are free people. They are like artists. If they are in a good
mood, they get up in the morning and begin painting their pictures.
-- Vladimir Putin

[Jeremy Ardley]

On 19/4/23 17:14, Schwibinger Michael wrote:

Good morning

Thank You.

What did I do wrong.

On the printer there is written

ET M 1120.

If this is wrong

what is the right name?

The Epson ET-M1120 printer supports the Epson ESC/P-R printer language, which is a command protocol used by Epson printers.

To install the printer driver for Linux, you can follow these steps:

Connect the printer to your computer and make sure it is turned on.
Open your Linux terminal and run the following command to update your system package list:

sudo apt-get update

Install the printer driver by running the following command:

sudo apt-get install printer-driver-escpr

Follow the on-screen instructions to complete the installation.

-- 
Jeremy
(Lists)

[Jeremy Ardley]

On 19/4/23 17:14, Schwibinger Michael wrote:
>
> Good morning
>
> Thank You.
>
> What did I do wrong.
>
> On the printer there is written
>
> ET M 1120.
>
> If this is wrong
> what is the right name?
>

> Its made by EPSON
>
> Regards
> Sophie
>

I think your problem is you have to change the driver your system
already has to the new standard Epson driver.

You should ask how to do this on the Debian German list
debian-us...@lists.debian.org

--
Jeremy
(Lists)

[Curt]

On 2023-04-15, Brian <ad...@cityscape.co.uk> wrote:
>> >
>> > It is the OP who needs help, not me. She couls at least provide correct and full date.
>> >
>> Why not just everyone attack each other?
>
> There have not been any attacks whatsoever on any users.
>
>> This looks like an uncontrolled pillow fight.
>
> It only looks that way. In fact, everything is under control.
>

When you're Under Down, everything looks like a pillow fight.

[chris]

Another runaway thread that never ends lol

[to...@tuxteam.de]

On Sun, Apr 23, 2023 at 09:08:52AM +0000, Schwibinger Michael wrote:
> Good morning
>
> Thank You
> What is the problem with mutt?

Mutt has no problems.

> Is there a DEBIAN URL
> where I can find drivers for printers?

Start here: https://wiki.debian.org/Printing

--
t

[to...@tuxteam.de]

Good morning, Mr. or Mrs. Schwibinger

your mail provider (hotmail.com) doesn't like my mails.

Please complain to them, as I am not able to help you
with your problems.

Regards
--
tomás

[gene heskett]

On 4/24/23 09:36, Schwibinger Michael wrote:
>
>
> Good afternoon
>
> Thank You
> Was it a good idea to buy EPSON?
>
> Regards
> Sophie
>

In a short answer no. Epson worked very well but that way back, 20 years
ago.

For high quality output, Brother is hard to beat, and has drivers for
linux that Just Work. I have 2 Brothers, an HLL2320 laser for fast
duplex output in B&W, about 20 pages a minute, and a now several years
old MFC-J6920DW, an ink-jet that can handle up to tabloid paper in its
printer and in its scanner, and the scanner can do duplex with letter or
A4 material as it has an ADF feeder. This printer is both huge and gives
very high quality photo outputs with every option it has being usable
with the Debian bullseye I'm running here.

Accessible from USB or from a cat5 connection you can set for your own
home network. Their installer is a script you can run, telling it what
printer you have, it then goes to their site, downloads the proper
driver and installs it in the cups menu's. The USB connection is faster
though.

Brother's ink-jet's will use a wee bit more ink than some because if
powered up full time, will do a quiet nozzle clean at least daily, and
my MFC-J6920-DW has never had a clogged nozzle in 7 or 8 years now.

Something I can't say for my own history with several Epson's years ago.
Aftermarket, lower priced ink has been 100% usable but their inks give
truer color. An ink-jet that Just Works has been a breath of fresh air
here for quite a while now.

An no, I don't work for or own any Brother stock. I'm just a 21 year
retired television station chief engineer. I think that makes me an old
coot. Take care and stay well Sophie

[...]

Cheers, Gene Heskett.
--
"There are four boxes to be used in defense of liberty:
soap, ballot, jury, and ammo. Please use in that order."
-Ed Howdershelt (Author, 1940)
If we desire respect for the law, we must first make the law respectable.
- Louis D. Brandeis
Genes Web page <http://geneslinuxbox.net:6309/>

[Curt]

On 2023-04-24, gene heskett <ghes...@shentel.net> wrote:
> On 4/24/23 09:36, Schwibinger Michael wrote:
>>
>>
>> Good afternoon
>>
>> Thank You
>> Was it a good idea to buy EPSON?
>>
>> Regards
>> Sophie
>>
>
> In a short answer no. Epson worked very well but that way back, 20 years
> ago.
>
> For high quality output, Brother is hard to beat, and has drivers for
> linux that Just Work. I have 2 Brothers, an HLL2320 laser for fast
> duplex output in B&W, about 20 pages a minute, and a now several years
> old MFC-J6920DW, an ink-jet that can handle up to tabloid paper in its
> printer and in its scanner, and the scanner can do duplex with letter or
> A4 material as it has an ADF feeder. This printer is both huge and gives
> very high quality photo outputs with every option it has being usable
> with the Debian bullseye I'm running here.
>

I bought a HL-L2350DW not too long ago after my HL-2030 experienced a paper jam
that wouldn't go away even though there was no longer any visible paper
stuck anywhere and in my infinite patience I kind of ripped the thing
apart and tossed the now definitively broken hunk of machinery into the
trash. And this after many years of loyal service. Never turn on me,
bro!

The new one's quicker and nicer and wireless and does duplex and works with my phone.
Easy set-up on a hybrid, Windows-Linux LAN.

[Jeffrey Walton]

On Mon, Apr 24, 2023 at 1:44 PM Curt <cu...@free.fr> wrote:
> [ ...]

>
> I bought a HL-L2350DW not too long ago after my HL-2030 experienced a paper jam
> that wouldn't go away even though there was no longer any visible paper
> stuck anywhere and in my infinite patience I kind of ripped the thing
> apart and tossed the now definitively broken hunk of machinery into the
> trash. And this after many years of loyal service. Never turn on me,
> bro!

https://www.youtube.com/watch?v=fjsSr3z5nVk

[Curt]

That's it!

[Jeffrey Walton]

On Fri, Apr 14, 2023 at 5:16 PM Schwibinger Michael <hb...@hotmail.com> wrote:
>
> Good afternoon.

> The new printer is not working.
> EPSON is saying
> You cant use EPSON with Linux.
>
> Is this true?

Plonk!

[Greg Wooledge]

On Mon, May 01, 2023 at 08:31:11AM +0000, Schwibinger Michael wrote:
> Good morning

> Thank You for email.
>
>
> Plonk!
>
> Wat is a plonk?
> A bug?

http://www.catb.org/jargon/html/P/plonk.html

It means that person has put you on their ignore list, or killfile, or
whatever it's called in their mail reader. They have chosen never to
see anything you write, ever again.

If you still have issues with your printer, I strongly advise you to ask
on the German mailing list, or whichever mailing list speaks your primary
language. I don't think anyone on this list is interested in continuing
to offer help to you.

[Thomas Hochstein]

Greg Wooledge wrote:

> If you still have issues with your printer, I strongly advise you to ask
> on the German mailing list, or whichever mailing list speaks your primary
> language. I don't think anyone on this list is interested in continuing
> to offer help to you.

They started on the German mailing list, about a year ago ...

[gene heskett]

> .
The last epson I had that worked with linux was a 4 color C82, well over
a decade ago. Then it looks as if they started making windows only
printers because all the normal printer stuff was moved from the driver
in the printer and put into the windows driver, leaving only the ability
to put a drop of the chosen color at the chosen xy spot on the paper in
the printer. That and the constant battle to keep the nozzle unclogged
got tiresome and limited the last printer I bought to about 2 months
life. So that was replaced by a Brother color laser, which worked well
for around 4 years, then slowly lost its corona wire voltage, an easy
enough to diagnose problem for me as I am a CET, but brother refused to
sell me a board despite the fact that I am a CET, fully capable of
handling that high voltage item. So I brought home their biggest inkjet.
That was about 8 years ago, and it is still pumping out full color
images on paper up to tabloid size. A huge device, its also a scanner
for 11x17 tabloid. I also have a much faster HLL2320dw a B&W laser that
does duplex on copy paper at 19 pages a minute. And running on linux,
using the drivers they supply, both run to their full capabilities.

Obviously I am now a Brother fan and I believe in supporting the makers
who support us. Glaringly obvious in my previous post. But apparently
this person doesn't want to admit a mistake was made, and the only way
to solve it is to run an all windows house at much more cost than buying
another printer that is supported would be. Brother's consumables cost
less per page than epson so you get the difference back over time and
reams of paper.

This may be a duplicate of what wallmart had for sale at $31.95 3 or 4
years ago, and which I saw the epson label and drove the cart right on by.

[Thomas Schmitt]

Hi,

Greg Wooledge wrote:
> > > If you still have issues with your printer, I strongly advise you to ask
> > > on the German mailing list,

Thomas Hochstein wrote:
> > They started on the German mailing list, about a year ago ...

Schwibinger Michael / Sophie wrote:
> The Germans did send You to this list.

No. The Germans did send You to this list.

(I could not resist biting the obvious comedy bait and did not even
check whether there was really the advise to mail to debian-user.)


> Was this wrong?

Maybe they wanted to let the world participate in the experience of a
"Hurz!" performance.

Regrettably there is no english version of
https://de.wikipedia.org/wiki/Hurz!
So i try to translate the first sentences:

Hurz! is a tv prank by Hape Kerkeling and Achim Hagemann, which belongs
to the best known works of Kerkeling. [...] aired in 1991 [...]
Kerkeling and Hagemann pretend to be polish musicians who [...] present
the unaware audience an alleged excerpt from an opera by a fictive
contemporary classic composer. Although the text is comprised of short
nonsense passages which get multiple times interrupted by the outcry
"Hoorts!", parts of the audience try hard to find a sincere
interpretation during the subsequent discussion.


About half of the audience of the thread "Debian bootet nicht / Screenshot"
at
https://lists.debian.org/debian-user-german/2022/10/threads.html
makes mocking comments about the overall Sophie show. The other half is
quarreling over the question whether Hanlon's Razor cuts correctly in this
case.
In
https://lists.debian.org/debian-user-german/2023/03/msg00123.html
i see 100% non-Hanlon opinions including a "sudo rm -R /" assassination
attempt.


Have a nice day :)

Thomas

[to...@tuxteam.de]

On Tue, May 02, 2023 at 11:32:13AM +0200, Thomas Schmitt wrote:

[...]

> In
> https://lists.debian.org/debian-user-german/2023/03/msg00123.html
> i see 100% non-Hanlon opinions including a "sudo rm -R /" assassination
> attempt.

Murder by a Hanlon razor. Now that would be... something.

I used to be on Hanlon's side; slowly, that one is decaying.
It seems that you were right, after all.

Perhaps this is just a dark tentacle of ChatGPT, probing the
more fringe aspects of human psychology. It's coming from
a Microsoft domain, after all.

Cheers
--
t

[Thomas Schmitt]

Hi,

i wrote:
> > i see 100% non-Hanlon opinions including a "sudo rm -R /" assassination
> > attempt.

to...@tuxteam.de wrote:
> Murder by a Hanlon razor. Now that would be... something.

It would only be deadly if the assassination target is indeed stupid and
not just pretending.

> Perhaps this is just a dark tentacle of ChatGPT, probing the
> more fringe aspects of human psychology.

Some german list members speculated about a psychology or sociology
experiment going on. Nevertheless i think to have observed Sophie before
ChatGPT (but after ELIZA).

> It's coming from a Microsoft domain, after all.

What is our position on Microsoft Inc. and Hanlon's Razor ?

[to...@tuxteam.de]

On Tue, May 02, 2023 at 01:39:28PM +0200, Thomas Schmitt wrote:
> Hi,
>
> i wrote:
> > > i see 100% non-Hanlon opinions including a "sudo rm -R /" assassination
> > > attempt.
>
> to...@tuxteam.de wrote:
> > Murder by a Hanlon razor. Now that would be... something.
>
> It would only be deadly if the assassination target is indeed stupid and
> not just pretending.
>
>
> > Perhaps this is just a dark tentacle of ChatGPT, probing the
> > more fringe aspects of human psychology.
>
> Some german list members speculated about a psychology or sociology
> experiment going on. Nevertheless i think to have observed Sophie before
> ChatGPT (but after ELIZA).

So that would be pre-release training?

> > It's coming from a Microsoft domain, after all.
>
> What is our position on Microsoft Inc. and Hanlon's Razor ?

...follow the money. Microsoft has dumped such an outrageous amount
of that into OpenAI as to be relevant. Besides, they're now feeling
all smug for having (at least ostensibly) out-maneuvred Google, for
once.

Besides... history. They already released one AI (on twitter?) which
ended up misbehaving.

> Have a nice day :)

Likewise :)
--
t

[Charlie Gibbs]

On Tue, 02 May 2023 13:40:01 +0200 "Thomas Schmitt" <scdb...@gmx.net>

wrote:

> Hi,
>
> i wrote:
>
>>> i see 100% non-Hanlon opinions including a "sudo rm -R /"
>>> assassination attempt.
>
> to...@tuxteam.de wrote:
>
>> Murder by a Hanlon razor. Now that would be... something.
>
> It would only be deadly if the assassination target is indeed stupid
> and not just pretending.
>
>> Perhaps this is just a dark tentacle of ChatGPT, probing the
>> more fringe aspects of human psychology.
>
> Some german list members speculated about a psychology or sociology
> experiment going on. Nevertheless i think to have observed Sophie
> before ChatGPT (but after ELIZA).
>

>> It's coming from a Microsoft domain, after all.
>
> What is our position on Microsoft Inc. and Hanlon's Razor ?

I don't know about your position, but I find myself repeating
Hanlon's Razor a lot: "Never ascribe to malice that which can
adequately be explained by stupidity." But then, in the back
of my mind, a little voice replies: "But Microsoft isn't stupid!"

--
/~\ Charlie Gibbs | Microsoft is a dictatorship.
\ / <cgi...@kltpzyxm.invalid> | Apple is a cult.
X I'm really at ac.dekanfrus | Linux is anarchy.
/ \ if you read it the right way. | Pick your poison.

[to...@tuxteam.de]

On Tue, May 02, 2023 at 09:31:39PM -0700, Charlie Gibbs wrote:

[...]

> I don't know about your position, but I find myself repeating
> Hanlon's Razor a lot: "Never ascribe to malice that which can
> adequately be explained by stupidity." But then, in the back
> of my mind, a little voice replies: "But Microsoft isn't stupid!"

My preferred tool in this case is Clarke's Third Razor:

"any sufficiently advanced form of malice is indistinguishable
from stupidity"

With apologies to Arthur C. Clarke and whoever Hanlon actually is.

Cheers
--
t

[to...@tuxteam.de]

On Fri, May 05, 2023 at 09:02:20AM +0000, Schwibinger Michael wrote:
>
>
> Good morning
>

> The Germans like to do jokes.

1. I am not a German
2. This is not a joke
3. At least one of 1, 2, or 3 is false

Cheers
--
t

[Thomas Schmitt]

Hi,

to...@tuxteam.de wrote:
> 1. I am not a German
> 2. This is not a joke
> 3. At least one of 1, 2, or 3 is false

So the most humorous guess would be that you are a german philosopher.

Have a nice day :)

Thomas

[David]

On Sun, 2023-05-07 at 09:26 +0000, Schwibinger Michael wrote:
>
> Good morning
>

> Thank You for help.
>
> There are some other messages from the printer.
>
> Are they important?
>
>
>
> The list gave me here a lot of URLS,
> but where ist the good driver?

Epson doesn't appear to have created one for this printer:

http://tech.epson.com.au/downloads/product.asp

http://download.ebz.epson.net/dsc/search/01/search/searchModule

and Openprinting appears to have nothing on it.
It appears you have purchased a boat anchor.
This leaves you with two options:
buy a very cheap desktop box off a recycler with Windows loaded to use
as a driver box, or
buy another printer, using the above links as reference points as to
what might be worth your money.
Cheers!

>
>
> Regards
>
> Sophie
>
>
>
> ________________________________
> Von: Thomas Schmitt <scdb...@gmx.net>
> Gesendet: Dienstag, 2. Mai 2023 11:39
> An: debia...@lists.debian.org <debia...@lists.debian.org>
> Betreff: Re: EPSON ET M 1120 new printer: If You can read this, you
> are using the wrong driver

--
A Kiwi in Australia,
doing my bit toward raising the national standard.

[Greg Wooledge]

On Sun, May 07, 2023 at 09:26:33AM +0000, Schwibinger Michael wrote:
> There are some other messages from the printer.
>
> Are they important?

How on earth would we know whether the messages are important without
seeing them?

This is why nobody is offering you any more help. You are presenting
yourself as either a troll, or as someone who is so fundamentally
incompetent that helping you is impossible.

Do you want my advice? Go find a local Linux users group, and ask them
what kind of printers they're using. Then buy one of THOSE printers,
and have the Linux users group help you set it up.

[Andrew M.A. Cater]

On Sun, May 07, 2023 at 08:51:29AM -0400, Greg Wooledge wrote:
> On Sun, May 07, 2023 at 09:26:33AM +0000, Schwibinger Michael wrote:
> > There are some other messages from the printer.
> >
> > Are they important?
>
> How on earth would we know whether the messages are important without
> seeing them?
>
> This is why nobody is offering you any more help. You are presenting
> yourself as either a troll, or as someone who is so fundamentally
> incompetent that helping you is impossible.
>

OK. I'm going to have one more go at this. For the avoidance of doubt:
I'll assume that Sophie is genuine - maybe a teenager, certainly
someone whose first language is German.

I'm going to assume good faith, despite some evidence to the contrary.**

>From looking on Epson's website:

1. They do not support this printer under Linux officially.

2. The printer is listed as a printer supported only under Windows - lots
of variants.

3. It is listed as a GDI compatible printer - this is indicative of a printer
that requires a specific Windows driver to compose the page.

4. It is compatible with older Epson printing protocols called Esc/P and
Esc/P-R.

5. Epson do have a filter program available to make this printer work
as an Esc/P printer under Linux using CUPS to manage the printer.

6. If CUPS setup is possible - you will need to read documents to be
able to set up CUPS.

See: https://www.epson.co.uk/products/printers/inkjet/consumer/ecotank-et-m1120/p/23162

See: https://download.ebz.epson.net/man/linux/escpr.html

> Do you want my advice? Go find a local Linux users group, and ask them
> what kind of printers they're using. Then buy one of THOSE printers,
> and have the Linux users group help you set it up.
>

This is possibly not the best advice: I would suggest that you find a
fellow student who uses Linux and is an enthusiast to help you out.

** Michael Tobias Schwibinger (or similar spelling) appears to be a
Dipl. Ing, interested in software, psychology and clown therapy / circus
skills and clown theory?

In the hope that this can finally put an end to this neverending thread.

With every good wish, as ever,

Andy Cater

[chris]

True 

[Brian]

On Sun 07 May 2023 at 20:27:53 +0000, Andrew M.A. Cater wrote:

I offer the following in the interest of correctness and just in case Schwibinger
Michael gets even more confused or disheartened and considers going away :).

> From looking on Epson's website:
>
> 1. They do not support this printer under Linux officially

http://download.ebz.epson.net/dsc/search/01/search/searchModule

Or, for a direct download

https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753 \

> 2. The printer is listed as a printer supported only under Windows - lots
> of variants.

brian@test-new:~$ /usr/sbin/lpinfo -m | grep -i ET-M1120
escpr:0/cups/model/epson-inkjet-printer-escpr/Epson-ET-M1120_Series-epson-escpr-en.ppd \
EPSON ET-M1120 Series , Epson Inkjet Printer Driver (ESC/P-R) for Linux

--
Briana.

[Brian]

On Sun 07 May 2023 at 23:57:58 +0100, Brian wrote:

> Or, for a direct download

https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753 \

cce3b2715b3e2fef557/epson-inkjet-printer-escpr_1.7.26-1lsb3.2_amd64.deb

--
Brian.

[Will Mengarini]

* Brian <ad...@cityscape.co.uk> [23-05/08=Mo 00:27 +0100]:
> https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753 \
> cce3b2715b3e2fef557/epson-inkjet-printer-escpr_1.7.26-1lsb3.2_amd64.deb

That includes a literal space in the middle of that hash
(because the space before the backslash is taken literally).

However, when I removed that space by hand, I still got "not found":
--------------------------------
debian/pts/3 bash3 ~ 17:03 0$HEAD https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753cce3b2715b3e2fef557/epson-inkjet-printer-escpr_1.7.26-1lsb3.2_amd64.deb
404 Not Found
Connection: close
Date: Mon, 08 May 2023 00:03:43 GMT
Accept-Ranges: bytes
Server: AkamaiNetStorage
Content-Length: 10
Client-Date: Mon, 08 May 2023 00:03:43 GMT
Client-Peer: 104.117.232.95:443
Client-Response-Num: 1
Client-SSL-Cert-Issuer: /C=US/O=DigiCert Inc/CN=DigiCert TLS RSA SHA256 2020 CA1
Client-SSL-Cert-Subject: /C=JP/ST=Nagano/L=Suwa-shi/O=SEIKO EPSON Corporation/CN=download2.ebz.epson.net
Client-SSL-Cipher: ECDHE-ECDSA-AES256-GCM-SHA384
Client-SSL-Socket-Class: IO::Socket::SSL
Client-SSL-Version: TLSv1_2
--------------------------------

(HEAD is symlinked to /usr/bin/lwp-request, from package libwww-perl.)

[Jeremy Ardley]

On 8/5/23 08:12, Will Mengarini wrote:
> * Brian <ad...@cityscape.co.uk> [23-05/08=Mo 00:27 +0100]:
>> https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753 \
>> cce3b2715b3e2fef557/epson-inkjet-printer-escpr_1.7.26-1lsb3.2_amd64.deb
> That includes a literal space in the middle of that hash
> (because the space before the backslash is taken literally).
>
> However, when I removed that space by hand, I still got "not found":

The driver is already included in the standard debian distribution

sudo apt-get install printer-driver-escpr

Then the usual cups administration to attach driver to printer using lpadmin or http://localhost:631


--
Jeremy
(Lists)

[Jeremy Ardley]

FYI The driver options are:

sudo apt-get install printer-driver-escpr

sudo lpinfo -m | grep -i epson-escpr-en | grep 1120

escpr:0/cups/model/epson-inkjet-printer-escpr/Epson-ET-M1120_Series-epson-escpr-en.ppd
EPSON ET-M1120 Series , Epson Inkjet Printer Driver (ESC/P-R) for Linux

escpr:0/cups/model/epson-inkjet-printer-escpr/Epson-M1120_Series-epson-escpr-en.ppd
EPSON M1120 Series , Epson Inkjet Printer Driver (ESC/P-R) for Linux

--
Jeremy
(Lists)

[Curt]

On 2023-05-08, Will Mengarini <sel...@eskimo.com> wrote:
>
> However, when I removed that space by hand, I still got "not found":
> --------------------------------
> debian/pts/3 bash3 ~ 17:03 0$HEAD https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753cce3b2715b3e2fef557/epson-inkjet-printer-escpr_1.7.26-1lsb3.2_amd64.deb
> 404 Not Found
> Connection: close

http://download.ebz.epson.net/dsc/du/02/DriverDownloadInfo.do?LG2=EN&CN2=&DSCMI=144815&DSCCHK=7d1f9cb6b55d10182962d13f26948e0052707a37

It's on the page, after clicking Accept. I can't seem to derive the direct
link to the file from that page.

[chris]

Are we at the point yet where this has enough attention it would have been cheaper to crowd fund a new printer?? 🤣🤣

[chris]

Any update on the status of this Epson printer? The world is dying to know the outcome of this saga

On Mon, May 8, 2023, 2:35 PM Brad Rogers <br...@fineby.me.uk> wrote:

On Mon, 8 May 2023 12:37:35 -0400
chris <tknc...@gmail.com> wrote:

Hello chris,

>Are we at the point yet where this has enough attention it would have
>been cheaper to crowd fund a new printer?? 🤣🤣

(smiley noted)

I'm betting even that wouldn't work;  At this point, I'm of the opinion
(after a quick glance through some of the earlier posts in this thread)
that the OP may have installed the driver from Debian but has not fired
up CUPS to actually make use of it.

Given their obvious difficulties with English (not their native tongue,
so entirely understandable) help from this point would have most likely
have to take the form of paying them a visit.

--
 Regards  _       "Valid sig separator is {dash}{dash}{space}"
         / )      "The blindingly obvious is never immediately apparent"
        / _)rad   "Is it only me that has a working delete key?"
I'm spending all my money and it's going up my nose
Teenage Depression - Eddie & The Hot Rods

[chris]

What is the issue with the printer?

On Wed, May 10, 2023, 10:58 AM Schwibinger Michael <hb...@hotmail.com> wrote:

Good morning

Can somebody help with the printer.

Can You wrote as topic:

"joke".

Regards

Thank You

Sophie

---

Von: Thomas Schmitt <scdb...@gmx.net>
Gesendet: Freitag, 5. Mai 2023 10:01

An: debia...@lists.debian.org <debia...@lists.debian.org>
Betreff: Re: EPSON ET M 1120 new printer: If You can read this, you are using the wrong driver

[Lee]

On 5/10/23, Schwibinger Michael wrote:

nothing of interest .. same as every other day.

*plonk*

[chris]

True

[chris]

SUCCESS

On Fri, May 12, 2023, 1:41 PM Schwibinger Michael <hb...@hotmail.com> wrote:

Good afternoon

I ll give the paper to a friend.

He is owning a scanner.

He ll scan it and I ll send it to the group.

Thank You for help.

Regards

Sophie

Thank You

---

Von: Greg Wooledge <gr...@wooledge.org>
Gesendet: Sonntag, 7. Mai 2023 12:51

An: debia...@lists.debian.org <debia...@lists.debian.org>
Betreff: Re: EPSON ET M 1120 new printer: If You can read this, you are using the wrong driver

[Andrew M.A. Cater]

On Sat, May 13, 2023 at 10:18:37AM +0000, Schwibinger Michael wrote:
> First
> You asked for the bug message:
>
> https://ibb.co/Xtbz1Qp
> [https://i.ibb.co/jDTLmNG/epsonprot.jpg]<https://ibb.co/Xtbz1Qp>
> epsonprot hosted at ImgBB<https://ibb.co/Xtbz1Qp>
> Image epsonprot hosted in ImgBB
> ibb.co
>

Unfortunately, that patge returns nothing except a page not found
error

All the very best, as ever,

Andy Cater


> Regards
> Sophie
>
>
>
> ________________________________
> Von: Andrew M.A. Cater <amac...@einval.com>
> Gesendet: Sonntag, 7. Mai 2023 20:27

> An: debia...@lists.debian.org <debia...@lists.debian.org>
> Betreff: Re: EPSON ET M 1120 new printer: If You can read this, you are using the wrong driver
>

[Greg Wooledge]

On Sat, May 13, 2023 at 10:18:37AM +0000, Schwibinger Michael wrote:

> * For Debian based distributions:
> # dpkg -i epson-inkjet-printer-escpr_<version<-<architecture>.deb
>
>
>
> What is the name of architecture?

Typically, either amd64 or i386, depending on which one you installed.
The canonical way to find out is:

unicorn:~$ dpkg --print-architecture
amd64

[Will Mengarini]

* Schwibinger Michael <hb...@hotmail.com> [23-05/14=Sun 09:32 +0000]:
> This is not working:
> https://tutorialforlinux.com/2021/03/06/step-by-step-driver-epson-et-m1100-et-m1120-ubuntu-20-04-installation/2/

We need to know what fails. Exactly what do
you do, and what results does it produce?

On Sun, May 07, 2023 at 08:51:29AM -0400, Greg Wooledge wrote:
>> How on earth would we know whether the
>> messages are important without seeing them?
>

> [...]
>
> OK. I'm going to have one more go at this. [...]

And once again, and wiser in no wise,
I chase your colored phantom on the air,
And sob and curse and fall and weep and rise
And stumble pitifully on to where,
Miserable and lost, with stinging eyes,
Once more I clasp -- and there is nothing there.
-- Edna St Vincent Millay

/* return TRUE if the monster tends to revive */
#define is_reviver(ptr) (is_rider(ptr) || (ptr)->mlet == S_TROLL)
-- https://nethackwiki.com/wiki/Source:NetHack_3.6.1/include/mondata.h

[chris]

I know its only may but this has to win thread of the year....

On Mon, May 15, 2023, 4:46 AM Schwibinger Michael <hb...@hotmail.com> wrote:

Good morning

Thank You.

EPSON said

EPSON only works with WIN.

Regards

Sophie

---

Von: Brian <ad...@cityscape.co.uk>
Gesendet: Sonntag, 7. Mai 2023 22:57

An: debia...@lists.debian.org <debia...@lists.debian.org>
Betreff: Re: EPSON ET M 1120 new printer: If You can read this, you are using the wrong driver

[Andrew M.A. Cater]

On Mon, May 15, 2023 at 08:46:22AM +0000, Schwibinger Michael wrote:
> Good morning
>
> Thank You.
>
> EPSON said
> EPSON only works with WIN.
>
> Regards
> Sophie
>
>

Dear Sophie,

Epson do not formally support Linux for many of their printers.
They do provide some uofficial Linux packages. Among these are ones for
your printer.

I only understand a little German. I am installing a Debian Linux 11 virtual
machine in German in order to help you better.

http://download.ebz.epson.net/dsc/search/01/search/ - the Epson web site.

If you put M1120 into the search box, do not put anything into operating system
and press Enter, you get 20 results.

Follow the links for the Epson printer driver for Linux - accept the license
conditions.

Download - epson-printer-utility_1.1.1-1lsb3.2_amd64.deb

Also run the command that they suggest (as root or by using sudo):

apt install lsb

Install the supporting library for Epson printers from Debian

apt install escputil

Now follow the tutorial page. Install escputil first, then the Epson printer
driver.

If this fails - tell us *exactly* what fails, error messages and so on.

All the very best, as ever,

Andy Cater

>

> ________________________________
> Von: Brian <ad...@cityscape.co.uk>
> Gesendet: Sonntag, 7. Mai 2023 22:57
> An: debia...@lists.debian.org <debia...@lists.debian.org>
> Betreff: Re: EPSON ET M 1120 new printer: If You can read this, you are using the wrong driver
>

[Anssi Saari]

Will Mengarini <sel...@eskimo.com> writes:

> * Brian <ad...@cityscape.co.uk> [23-05/08=Mo 00:27 +0100]:
>> https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753 \
>> cce3b2715b3e2fef557/epson-inkjet-printer-escpr_1.7.26-1lsb3.2_amd64.deb
>
> That includes a literal space in the middle of that hash
> (because the space before the backslash is taken literally).
>
> However, when I removed that space by hand, I still got "not found":
> --------------------------------
> debian/pts/3 bash3 ~ 17:03 0$HEAD
> https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753cce3b2715b3e2fef557/epson-inkjet-printer-escpr_1.7.26-1lsb3.2_amd64.deb

I don't understand why you guys even propose installing drivers from
Epson when printer-driver-escpr package is in Debian and should be
correct for the printer in question? Is there some established reason to
think it won't work? Or you just didn't do your homework?

I get that this saga probably never goes anywhere but I don't understand
this advice, especially from Andrew. It seems to run counter to the Debian
principle of using software that's actually packaged and tested by Debian.

[Andrew M.A. Cater]

If you reread - I suggest using the Debian package of escputil - I just wanted
Sophie to see that there was an Epson driver which might provide status
for ink tanks etc. - that's why I went through the steps of exactly how
to find the driver.

But yes, this is going nowhere - and there is no lsb package in Debian, I think.

Andy

[gene heskett]

On 5/16/23 08:29, Andrew M.A. Cater wrote:
> On Tue, May 16, 2023 at 01:55:08PM +0300, Anssi Saari wrote:
>> Will Mengarini <sel...@eskimo.com> writes:
>>
>>> * Brian <ad...@cityscape.co.uk> [23-05/08=Mo 00:27 +0100]:
>>>> https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753 \
>>>> cce3b2715b3e2fef557/epson-inkjet-printer-escpr_1.7.26-1lsb3.2_amd64.deb
>>>
>>> That includes a literal space in the middle of that hash
>>> (because the space before the backslash is taken literally).
>>>
>>> However, when I removed that space by hand, I still got "not found":
>>> --------------------------------
>>> debian/pts/3 bash3 ~ 17:03 0$HEAD
>>> https://download3.ebz.epson.net/dsc/f/03/00/14/48/15/1d37501ad39bd2b5753cce3b2715b3e2fef557/epson-inkjet-printer-escpr_1.7.26-1lsb3.2_amd64.deb
>>

Which is still missing the <> surrounding the actual link. so its still
a 403.

>> I don't understand why you guys even propose installing drivers from
>> Epson when printer-driver-escpr package is in Debian and should be
>> correct for the printer in question? Is there some established reason to
>> think it won't work? Or you just didn't do your homework?
>>
>> I get that this saga probably never goes anywhere but I don't understand
>> this advice, especially from Andrew. It seems to run counter to the Debian
>> principle of using software that's actually packaged and tested by Debian.
>>
>
> If you reread - I suggest using the Debian package of escputil - I just wanted
> Sophie to see that there was an Epson driver which might provide status
> for ink tanks etc. - that's why I went through the steps of exactly how
> to find the driver.
>
> But yes, this is going nowhere - and there is no lsb package in Debian, I think.
>
> Andy
>

> .
Couple that with my recent discovery that debian seems to be shipping
the cups from apple, last updated by its author in 2019. The new cups
site, openprinting.org copy's src cups-master.zip is about 2.5 times the
size of the debian src, and it builds on bullseye with only one option
to "./configure with-tls=no" (presumably because debian doesn't have
libtls, I couldn't find it)

Given that clue, I would be surprised to find a "cups" driver in the
debian repo's capable of driving a newer epson product.

However to update this never ending saga, I rebooted this machine into a
new security patched kernel yesterday, updating this machine to:

5.10.0-23-amd64 #1 SMP Debian 5.10.179-1 (2023-05-12) x86_64 GNU/Linux

and my bullseye armbian machines have magically gotten well. What
changed? DIIK.

Cheers, Gene Heskett.
--
"There are four boxes to be used in defense of liberty:
soap, ballot, jury, and ammo. Please use in that order."
-Ed Howdershelt (Author, 1940)
If we desire respect for the law, we must first make the law respectable.
- Louis D. Brandeis
Genes Web page <http://geneslinuxbox.net:6309/>