On Mon, 18 May 2015 10:55:29 +0200
Takashi Iwai wrote:
> At Fri, 15 May 2015 15:33:13 +0200,
> Denys Vlasenko wrote:
> >
> > On 05/14/2015 10:32 PM, Giuliano Pochini wrote:
> > > On Mon, 11 May 2015 22:15:28 +0200
> > > Denys Vlasenko wrote:
> > >
On Mon, 18 May 2015 10:55:29 +0200
Takashi Iwai ti...@suse.de wrote:
At Fri, 15 May 2015 15:33:13 +0200,
Denys Vlasenko wrote:
On 05/14/2015 10:32 PM, Giuliano Pochini wrote:
On Mon, 11 May 2015 22:15:28 +0200
Denys Vlasenko dvlas...@redhat.com wrote:
There are fourteen files
On Mon, 11 May 2015 22:15:28 +0200
Denys Vlasenko wrote:
> There are fourteen files in sound/pci/echoaudio/, namely:
>
> darla20.c darla24.c echo3g.c gina20.c gina24.c indigo.c
> indigodj.c indigodjx.c indigoio.c indigoiox.c layla20.c
> layla24.c mia.c mona.c
>
> Which use the following method
On Mon, 11 May 2015 22:15:28 +0200
Denys Vlasenko dvlas...@redhat.com wrote:
There are fourteen files in sound/pci/echoaudio/, namely:
darla20.c darla24.c echo3g.c gina20.c gina24.c indigo.c
indigodj.c indigodjx.c indigoio.c indigoiox.c layla20.c
layla24.c mia.c mona.c
Which use the
On Tue, 09 Oct 2012 14:50:10 +0200
Eric Dumazet wrote:
> On Tue, 2012-10-09 at 15:36 +0300, Dan Carpenter wrote:
> > Add netdev to the CC list.
>
> netdev already in the CC list by Borislav Petkov
>
> Reporter was (kindly) requested to try 3.6-rc7 +, and we got no answer.
Sorry for the late
On Tue, 09 Oct 2012 14:50:10 +0200
Eric Dumazet eric.duma...@gmail.com wrote:
On Tue, 2012-10-09 at 15:36 +0300, Dan Carpenter wrote:
Add netdev to the CC list.
netdev already in the CC list by Borislav Petkov
Reporter was (kindly) requested to try 3.6-rc7 +, and we got no answer.
Sorry
On Tue, 25 Sep 2012 14:26:07 +0400
Alexey Vlasov wrote:
> Hi.
>
> Here it writes LOG target from syslog:
>
> Sep 25 03:23:49 l24 kernel: ip:SYN-OUTPUT-HTTP IN= OUT=eth0
> SRC= DST= LEN=60 TOS=0x00 PREC=0x00
> TTL=64 ID=22467 DF PROTO=TCP SPT=52829 DPT=80
On Tue, 25 Sep 2012 14:26:07 +0400
Alexey Vlasov ren...@renton.name wrote:
Hi.
Here it writes LOG target from syslog:
Sep 25 03:23:49 l24 kernel: ip:SYN-OUTPUT-HTTP IN= OUT=eth0
SRC= DST= LEN=60 TOS=0x00 PREC=0x00
TTL=64 ID=22467 DF PROTO=TCP SPT=52829
On Sun, 9 Dec 2007, Kevin Winchester wrote:
Convert the semaphore to a mutex in echoaudio.c
Signed-off-by: Kevin Winchester <[EMAIL PROTECTED]>
It's an 1:1 change. It looks fine to me.
Acked-by: Giuliano Pochini <[EMAIL PROTECTED]>
--
Giuliano.
--
To unsubscribe from thi
On Sun, 9 Dec 2007, Kevin Winchester wrote:
Convert the semaphore to a mutex in echoaudio.c
Signed-off-by: Kevin Winchester [EMAIL PROTECTED]
It's an 1:1 change. It looks fine to me.
Acked-by: Giuliano Pochini [EMAIL PROTECTED]
--
Giuliano.
--
To unsubscribe from this list: send
When insert a CD-R that contains data and k3b is running the machine hard
locks. k3b writes on the console:
/dev/hdd READ TOC/PMA/ATIP invalid length returned
Disk info:
[...]
Used size: [...]
Sys-rq doesn't work and there is nothing in the logs. I tested kernels back
to 2.6.14 and they all
When insert a CD-R that contains data and k3b is running the machine hard
locks. k3b writes on the console:
/dev/hdd READ TOC/PMA/ATIP invalid length returned
Disk info:
[...]
Used size: [...]
crash
Sys-rq doesn't work and there is nothing in the logs. I tested kernels back
to 2.6.14 and they
On Tue, 13 Mar 2007 09:56:52 +
Russell King <[EMAIL PROTECTED]> wrote:
> Right, here's the ARM fix which is now in the ARM tree:
> [...]
The following patch seems to fix the issue (+ minor style fix). I'm not sure
it's ok due to my poor knowledge of this code.
Signed-off-
On Tue, 13 Mar 2007 09:56:52 +
Russell King [EMAIL PROTECTED] wrote:
Right, here's the ARM fix which is now in the ARM tree:
[...]
The following patch seems to fix the issue (+ minor style fix). I'm not sure
it's ok due to my poor knowledge of this code.
Signed-off-by: Giuliano Pochini
On Mon, 12 Mar 2007, Heiko Carstens wrote:
On Sun, Mar 11, 2007 at 10:26:52PM +0100, Giuliano Pochini wrote:
Since 2.6.20 /sys/devices/system/cpu/cpuX/online isn't there anymore. The
directories exist, though. I also tested linux-2.6.21rc3. I had a look at the
archives and I found nothing
On Mon, 12 Mar 2007, Heiko Carstens wrote:
On Sun, Mar 11, 2007 at 10:26:52PM +0100, Giuliano Pochini wrote:
Since 2.6.20 /sys/devices/system/cpu/cpuX/online isn't there anymore. The
directories exist, though. I also tested linux-2.6.21rc3. I had a look at the
archives and I found nothing
Since 2.6.20 /sys/devices/system/cpu/cpuX/online isn't there anymore. The
directories exist, though. I also tested linux-2.6.21rc3. I had a look at the
archives and I found nothing about the removal of that file, which is still
documented in Documentation/cpu-hotplug.txt. I don't know if other
Since 2.6.20 /sys/devices/system/cpu/cpuX/online isn't there anymore. The
directories exist, though. I also tested linux-2.6.21rc3. I had a look at the
archives and I found nothing about the removal of that file, which is still
documented in Documentation/cpu-hotplug.txt. I don't know if other
I have a CD-R that makes linux lock hard when I start k3b.
Oops, I sent this message by mistake. I'm still investigating this issue.
--
Giuliano.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
I have a CD-R that makes linux lock hard when I start k3b. I copied these
messages from the console by hand (I hope there are no errors). NB: these
are not kernel messages (there's nothing in the logs and sysrq doesn't
work). This is what k3b prints and I'm aware it's not very useful:
[...]
I have a CD-R that makes linux lock hard when I start k3b. I copied these
messages from the console by hand (I hope there are no errors). NB: these
are not kernel messages (there's nothing in the logs and sysrq doesn't
work). This is what k3b prints and I'm aware it's not very useful:
[...]
I have a CD-R that makes linux lock hard when I start k3b.
Oops, I sent this message by mistake. I'm still investigating this issue.
--
Giuliano.
-
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
On Thu, 11 Aug 2005, n l wrote:
> could you explain its reason for using static ?
Anything which is never referenced from another file should be
static in order to keep namespace pollution low.
--
Giuliano.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body
On Thu, 11 Aug 2005, n l wrote:
could you explain its reason for using static ?
Anything which is never referenced from another file should be
static in order to keep namespace pollution low.
--
Giuliano.
-
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of
>From my logs:
Jun 29 14:19:56 Jay kernel: SCSI disk error : host 1 channel 0 id 5 lun 0
return code = 802
Jun 29 14:19:56 Jay kernel: Current sd08:11: sense key Recovered Error
Jun 29 14:19:56 Jay kernel: Additional sense indicates Recovered data with
error correction applied
Jun 29
From my logs:
Jun 29 14:19:56 Jay kernel: SCSI disk error : host 1 channel 0 id 5 lun 0
return code = 802
Jun 29 14:19:56 Jay kernel: Current sd08:11: sense key Recovered Error
Jun 29 14:19:56 Jay kernel: Additional sense indicates Recovered data with
error correction applied
Jun 29
controller,
etc. (but different eth) and they run with a load average
of 0.5-1 and 1000-2000 cs/s.
Bye.
Giuliano Pochini ->)|(<- Shiny Network {AS6665} ->)|(<-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
controller,
etc. (but different eth) and they run with a load average
of 0.5-1 and 1000-2000 cs/s.
Bye.
Giuliano Pochini -)|(- Shiny Network {AS6665} -)|(-
-
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to [EMAIL PROTECTED]
More majordomo
> recent 2.4 kernels have incredible bad performance for me when handling MO
> drives. Going back 2.2 shows better performance.
> Copying a 6.5 MByte file with cp returns nearly immediately on the
> commandline, but umount nearly takes forever. Maximum rate detected by
> xosview during umount
recent 2.4 kernels have incredible bad performance for me when handling MO
drives. Going back 2.2 shows better performance.
Copying a 6.5 MByte file with cp returns nearly immediately on the
commandline, but umount nearly takes forever. Maximum rate detected by
xosview during umount was
is lost and I have to reboot to get it
> back:
I can't try this case because I haven't a floppy. When I ehect the cd I can
recover it by unmounting it. But the CD is read-only. I can try with a MO, but
the actual problem is that eject is buggy. It's not a kernel bug. I'll fix it...
Bye.
to reboot to get it
back:
I can't try this case because I haven't a floppy. When I ehect the cd I can
recover it by unmounting it. But the CD is read-only. I can try with a MO, but
the actual problem is that eject is buggy. It's not a kernel bug. I'll fix it...
Bye.
Giuliano Pochini -)|(- Shiny
> The problem is that at the low point in the cycle, the machine is
> unusable. It is utterly unresponsive until the writes complete, which can
> take a very long time (in the case of the ppc machine, several minutes!)
> Anything that does disk I/O will block for a long time - having 'ls' take
0.2, I don't remember the author) sends a SCSI
command to eject the disk, but it's broken because it doesn't even try to
umount the partition. It gets confused by my unusual fstab. I'll fix it as
soon as I have some spare time.
Bye.
Giuliano Pochini ->)|(<- Shiny Network {AS6
, but it's broken because it doesn't even try to
umount the partition. It gets confused by my unusual fstab. I'll fix it as
soon as I have some spare time.
Bye.
Giuliano Pochini -)|(- Shiny Network {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubscribe linux-k
The problem is that at the low point in the cycle, the machine is
unusable. It is utterly unresponsive until the writes complete, which can
take a very long time (in the case of the ppc machine, several minutes!)
Anything that does disk I/O will block for a long time - having 'ls' take
two
> vmware and one or two other apps I've also seen do this. WHen you unlock the
> cdrom door as root you can unlock it even if a file system is mounted
Right, so I'll check what eject(1) does. It might eject the disk even if it
failed to unmount.
Bye.
Giuliano Pochini ->)|(<- S
elf.
>
> eject(1) line 36:
>
>If the device is currently mounted, it is unmounted before
>ejecting.
But it doesn't get unmounted. I eject the disk but I can still see
and read the (cached) files !
Bye.
Giuliano Pochini ->)|(<- Shiny Network {AS6665} ->)|(<-
The kernel should not allow someone to
>> eject a mounted media.
>
> rpm -e magicdev
Magicdev is not installed.
Ok, I'm the only one with this problem, I'll manage to find the bug by myself.
Bye.
Giuliano Pochini ->)|(<- Shiny Network {AS6665} ->)|(<-
-
To unsubscr
.
rpm -e magicdev
Magicdev is not installed.
Ok, I'm the only one with this problem, I'll manage to find the bug by myself.
Bye.
Giuliano Pochini -)|(- Shiny Network {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message
before
ejecting.
But it doesn't get unmounted. I eject the disk but I can still see
and read the (cached) files !
Bye.
Giuliano Pochini -)|(- Shiny Network {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL
vmware and one or two other apps I've also seen do this. WHen you unlock the
cdrom door as root you can unlock it even if a file system is mounted
Right, so I'll check what eject(1) does. It might eject the disk even if it
failed to unmount.
Bye.
Giuliano Pochini -)|(- Shiny Network
> > My fstab:
> >
> > /dev/cdrom /mnt/cdrom iso9660
> > noauto,user,ro 0 0
> > /dev/cdrom /mnt/cdmac hfs
> > noauto,user,ro 0 0
>
> Change your fstab to read instead:
>
> /dev/cdrom/mnt/cdromauto
My fstab:
/dev/cdrom /mnt/cdrom iso9660
noauto,user,ro 0 0
/dev/cdrom /mnt/cdmac hfs
noauto,user,ro 0 0
Change your fstab to read instead:
/dev/cdrom/mnt/cdromautonoauto,user,ro0
My fstab:
/dev/cdrom /mnt/cdrom iso9660
noauto,user,ro 0 0
/dev/cdrom /mnt/cdmac hfs
noauto,user,ro 0 0
I insert an apple cd (hfs) and mount /mnt/cdmac
If I type eject /mnt/cdrom the cd momes out but
df shows it's
> What's the PCI id of the card you are using?
Bus 1, device 3, function 0:
Class 0100: PCI device 9004:5078 (rev 3).
IRQ 24.
Master Capable. Latency=32. Min Gnt=4.Max Lat=4.
I/O at 0x1800 [0x18ff].
Non-prefetchable 32 bit memory at 0x80881000 [0x80881fff].
ning up and nothing more.
>
> Did you apply a patch, or upgrade using the tar file? If the latter,
> you're missing some changes to the SCSI layer that make the initial
> bus settle delay implimentation more sane.
:-/ I'll try the patch this night.
Bye.
Giuliano Pochini ->)|(<-
file? If the latter,
you're missing some changes to the SCSI layer that make the initial
bus settle delay implimentation more sane.
:-/ I'll try the patch this night.
Bye.
Giuliano Pochini -)|(- Shiny Network {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubs
What's the PCI id of the card you are using?
Bus 1, device 3, function 0:
Class 0100: PCI device 9004:5078 (rev 3).
IRQ 24.
Master Capable. Latency=32. Min Gnt=4.Max Lat=4.
I/O at 0x1800 [0x18ff].
Non-prefetchable 32 bit memory at 0x80881000 [0x80881fff].
My fstab:
/dev/cdrom /mnt/cdrom iso9660
noauto,user,ro 0 0
/dev/cdrom /mnt/cdmac hfs
noauto,user,ro 0 0
I insert an apple cd (hfs) and mount /mnt/cdmac
If I type eject /mnt/cdrom the cd momes out but
df shows it's
> >I have two Adaptec 2930CU (ultra narrow) cards. I modified the driver to
> >make them work in ultra mode.
>
> Can you elaborate on what you had to modify ?
I just added AHC_ULTRA to the features of 7850
AHC_AIC7850_FE = AHC_SPIOCAP|AHC_AUTOPAUSE|AHC_TARGETMODE|AHC_ULTRA,
I have two Adaptec 2930CU (ultra narrow) cards. I modified the driver to
make them work in ultra mode.
Can you elaborate on what you had to modify ?
I just added AHC_ULTRA to the features of 7850
AHC_AIC7850_FE = AHC_SPIOCAP|AHC_AUTOPAUSE|AHC_TARGETMODE|AHC_ULTRA,
> >There WERE direct overwrite media for a while that would, in theory, be
> >able to write the data directly, but a combination of high cost, >limited
> >sources, and strong questions about the permanence of the recorded data
> >severely limited the demand for these and I think that they have
I have two Adaptec 2930CU (ultra narrow) cards. I modified the driver to
make them work in ultra mode. The card connected to my CDROM and MO drive,
operating at different bus clocks, does not behave well. Transfers stop
often for 10-20 seconds and it spits out warnings like these:
Apr 3
let
you know.
> Is this a known problem ?
Only with FAT fs AFAIK. ext2 should work fine (or at least it works
fine for me since 2.1.153).
> I also tried it with 2.2.18 there it works but it seems to be utterly
> slow.
Yes, it's a request merging problem, fixed in 2.4.
Bye.
y with FAT fs AFAIK. ext2 should work fine (or at least it works
fine for me since 2.1.153).
I also tried it with 2.2.18 there it works but it seems to be utterly
slow.
Yes, it's a request merging problem, fixed in 2.4.
Bye.
Giuliano Pochini -)|(- Shiny Network {AS6665} -)|(-
-
To unsubs
I have two Adaptec 2930CU (ultra narrow) cards. I modified the driver to
make them work in ultra mode. The card connected to my CDROM and MO drive,
operating at different bus clocks, does not behave well. Transfers stop
often for 10-20 seconds and it spits out warnings like these:
Apr 3
There WERE direct overwrite media for a while that would, in theory, be
able to write the data directly, but a combination of high cost, limited
sources, and strong questions about the permanence of the recorded data
severely limited the demand for these and I think that they have been
g up file
> space (as shown in df) until it is completely closed.
Yes, I know posix, but I don't think this is the case. I'll try reproduce
it...
Bye.
Giuliano Pochini ->)|(<- Shiny Network {AS6665} ->)|(<-
-
To unsubscribe from this list: send the line "unsubscr
space (as shown in df) until it is completely closed.
Yes, I know posix, but I don't think this is the case. I'll try reproduce
it...
Bye.
Giuliano Pochini -)|(- Shiny Network {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of
[root@Jay Giu]# du -c /home
[...]
320120 /home
320120 total
[root@Jay Giu]# df
Filesystem 1k-blocks Used Available Use% Mounted on
/dev/sda8 253823 65909174807 27% /
/dev/sda7 2158320750672 1296240 37% /usr
/dev/sda5
[root@Jay Giu]# du -c /home
[...]
320120 /home
320120 total
[root@Jay Giu]# df
Filesystem 1k-blocks Used Available Use% Mounted on
/dev/sda8 253823 65909174807 27% /
/dev/sda7 2158320750672 1296240 37% /usr
/dev/sda5
somewhere beyond 1050, the machine
> suddently slows down almost top a halt and becomes totally unresponsive,
> until I stop the test (SpecWeb).
Are you using 2.2.x ? I had the same problem here until I switched
to 2.4.x. 2.2 internal locks are not fine grained enough.
Bye.
Giuliano Pochini -&
2.4.2]
Bye.
Giuliano Pochini ->)|(<- Shiny Network {AS6665} ->)|(<-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please
2.4.2]
Bye.
Giuliano Pochini -)|(- Shiny Network {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://w
nymore.
> (this part of the bugreport is maybe not related to the lockups).
>
>
> Any ideas where to start here?
This happens on my blue G3 with 2.2.x too. I think it's a bug in the IDE
driver. My old 7300 (mesh) with a SCSI cd just reported a read error on
the same disk.
Bye.
Giuli
with a SCSI cd just reported a read error on
the same disk.
Bye.
Giuliano Pochini -)|(- Shiny Network {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.
Kernel 2.4.2-SMP compiled with egcs-2.91.66.)
Bye.
Giuliano Pochini ->)|(<- Shiny Corporation {AS6665} ->)|(<-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger
2-SMP compiled with egcs-2.91.66.)
Bye.
Giuliano Pochini -)|(- Shiny Corporation {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Perhaps this is a faq...
I have a dual-800 (mb asus, no AGP) with 1GB ram,
but according to /proc/meminfo tells I only have
90KB. I tried "mem=1024" boot parameter without
success. How can I get my 128MB back ?
Bye.
Giuliano Pochini ->)|(<- Shiny Cor
Perhaps this is a faq...
I have a dual-800 (mb asus, no AGP) with 1GB ram,
but according to /proc/meminfo tells I only have
90KB. I tried "mem=1024" boot parameter without
success. How can I get my 128MB back ?
Bye.
Giuliano Pochini -)|(- Shiny Corporati
On 2.4.1 the same NFS volume can be mounted twice
on the same directory. I recall the capability of
multiple mounts on the same mountpoint was removed
during 2.3.x.
Bye.
Giuliano Pochini ->)|(<- Shiny Corporation {AS6665} ->)|(<-
-
To unsubscribe from this list: send the line
On 2.4.1 the same NFS volume can be mounted twice
on the same directory. I recall the capability of
multiple mounts on the same mountpoint was removed
during 2.3.x.
Bye.
Giuliano Pochini -)|(- Shiny Corporation {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubs
IMHO this tcpdump trace is quite strange:
20:56:25.232532 ppp0 < mc105-v-2.royaume.com.6699 > ppp12.shiny.it.33148: .
96265:97725(1460) ack 77 win 8684 (DF)
20:56:25.242532 ppp0 > ppp12.shiny.it.33148 > mc105-v-2.royaume.com.6699: .
77:77(0) ack 88073 win 62780 (DF)
20:56:25.352532 ppp0 <
IMHO this tcpdump trace is quite strange:
20:56:25.232532 ppp0 mc105-v-2.royaume.com.6699 ppp12.shiny.it.33148: .
96265:97725(1460) ack 77 win 8684 (DF)
20:56:25.242532 ppp0 ppp12.shiny.it.33148 mc105-v-2.royaume.com.6699: .
77:77(0) ack 88073 win 62780 nop,nop, sack 1 {90121:97725} (DF)
.x. e.g. in this moment, with medium load (700 httpd's),
there are around 70 zombie cgi's. There aren't processes stuck
in Z, they simply take more time to die. Strange.
Bye.
Giuliano Pochini ->)|(<- Shiny Corporation {AS6665} ->)|(<-
-
To unsubscribe from this list: send the line
.x. e.g. in this moment, with medium load (700 httpd's),
there are around 70 zombie cgi's. There aren't processes stuck
in Z, they simply take more time to die. Strange.
Bye.
Giuliano Pochini -)|(- Shiny Corporation {AS6665} -)|(-
-
To unsubscribe from this list: send the line "unsubs
> You could try instrumenting the paths in bdflush and kswapd, to see
> what really happens when they run crazy. This would help a lot.
:-( My knowledge of the kernel is too poor and I have too few time to
study it.
I tried the suggestion of A.Arcangeli about size interval. The test is
always
You could try instrumenting the paths in bdflush and kswapd, to see
what really happens when they run crazy. This would help a lot.
:-( My knowledge of the kernel is too poor and I have too few time to
study it.
I tried the suggestion of A.Arcangeli about size interval. The test is
always
Hi!
I found the time to make some tests with 2.4 and the blk-13B patch.
It performs very well, no process starvation, no missed merges,
etc., but sometimes it happens dbflush and kswapd start eating
100% CPU for about 20-30 secs.:
11:02am up 18 min, 5 users, load average: 2.74, 1.97, 1.15
When will the powerpc tree be merged ? Neither the
official 2.4 nor the -ac8 work. They don't even compile.
Bye.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
Please read the FAQ at http://www.tux.org/lkml/
When will the powerpc tree be merged ? Neither the
official 2.4 nor the -ac8 work. They don't even compile.
Bye.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
Please read the FAQ at http://www.tux.org/lkml/
Hi!
I found the time to make some tests with 2.4 and the blk-13B patch.
It performs very well, no process starvation, no missed merges,
etc., but sometimes it happens dbflush and kswapd start eating
100% CPU for about 20-30 secs.:
11:02am up 18 min, 5 users, load average: 2.74, 1.97, 1.15
2.2.18, SMP.
It seems that anything I write in /proc/sys/vm/bdflush does not make
any difference. Metadata is always flushed every 5 seconds.
Bye.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
Please read the FAQ at
2.2.18, SMP.
It seems that anything I write in /proc/sys/vm/bdflush does not make
any difference. Metadata is always flushed every 5 seconds.
Bye.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
Please read the FAQ at
How to crash kernel 2.2.17-18:
Turn on the USB printer without paper and try
to print something. Wait for the "printer.c: usblp0:
out of paper" message and turn off the printer.
Ok, now "killall gs" will freeze the system.
(kernel 2.2.17-18, I did't try 2.4, GCC 2.95.3, PowerPC750)
Bye.
-
To
How to crash kernel 2.2.17-18:
Turn on the USB printer without paper and try
to print something. Wait for the "printer.c: usblp0:
out of paper" message and turn off the printer.
Ok, now "killall gs" will freeze the system.
(kernel 2.2.17-18, I did't try 2.4, GCC 2.95.3, PowerPC750)
Bye.
-
To
I have a Mac and a PC with a 3com 595 ethernet card. The Mac is the
nfs server. When I transfer from the PC to the Mac it's all right.
When I transfer a large file (50-100MB) from the Mac to the PC often
the connection breaks completely. I can't ping the other machine
anymore. Looking at
I have a Mac and a PC with a 3com 595 ethernet card. The Mac is the
nfs server. When I transfer from the PC to the Mac it's all right.
When I transfer a large file (50-100MB) from the Mac to the PC often
the connection breaks completely. I can't ping the other machine
anymore. Looking at
> I just reproduced the problem in test10-pre7. Here's the
> output you requested:
>
> vmstat 1
> procs memoryswap io system cpu
> r b w swpd free buff cache si sobibo incs us sy id
> 0 2 2 0 45764
Where can I d/l 2.2-pre ?
Bye.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
Please read the FAQ at http://www.tux.org/lkml/
Where can I d/l 2.2-pre ?
Bye.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
Please read the FAQ at http://www.tux.org/lkml/
> The problem is not really solvable unless you fix the application to send
> smaller packets. The only way to shape traffic in IP is to drop packets
There are 3 ways: 1- dropping packets (obvious), 2- buffer packets and delay
retransmission (if the receiver gets the packet later, it will ACK
The problem is not really solvable unless you fix the application to send
smaller packets. The only way to shape traffic in IP is to drop packets
There are 3 ways: 1- dropping packets (obvious), 2- buffer packets and delay
retransmission (if the receiver gets the packet later, it will ACK it
> +static inline __u64 ___swab16(__u64 x)
> +{
> + return (__u64)((x & (__u64)0x00ffULL) << 56) |
> + (__u64)((x & (__u64)0xff00ULL) << 40) |
> + (__u64)((x & (__u64)0x00ffULL) << 24) |
> + (__u64)((x &
+static inline __u64 ___swab16(__u64 x)
+{
+ return (__u64)((x (__u64)0x00ffULL) 56) |
+ (__u64)((x (__u64)0xff00ULL) 40) |
+ (__u64)((x (__u64)0x00ffULL) 24) |
+ (__u64)((x (__u64)0xff00ULL)
> The current HUGE queue size is probably another reason for
> the very bad latencies we sometimes see...
Yes, but if the queue is short processes are likely to remain
blocked in D state for more time and the chances to merge rq
are smaller.
IMHO we should add a way to give priority to rqs from
> That's one approach; I prefer my "weighted scoring" approach. Supposing we
> have three devices: a solid state disk (instant "seeks"), a hard drive and
> a tape. The SSD will benefit from merges (fewer commands to process), but
> not hugely - set both the metrics at 1, so a 64Kb request is
That's one approach; I prefer my "weighted scoring" approach. Supposing we
have three devices: a solid state disk (instant "seeks"), a hard drive and
a tape. The SSD will benefit from merges (fewer commands to process), but
not hugely - set both the metrics at 1, so a 64Kb request is just
> >It's a good way to avoid stalls, but IMHO I thing the elevator should
>
> Here you're talking about the latency control logic.
Which is tightly dependent on the way we insert new rqs.
> >not work this way. The main problem is that it doesn't minimize head
> >movement. For example, when
1 - 100 of 111 matches
Mail list logo