On Fri, 25 Aug 2017, Tom Yan wrote:
> On 20 August 2017 at 01:34, Mikulas Patocka wrote:
> >
> > If you issue a single ioctl that takes extreme amount of time - the kernel
> > warns about being blocked for extreme amount of time - what else should it
> > do?
> >
>
> But as I said, it does NOT
On 20 August 2017 at 01:34, Mikulas Patocka wrote:
>
> If you issue a single ioctl that takes extreme amount of time - the kernel
> warns about being blocked for extreme amount of time - what else should it
> do?
>
But as I said, it does NOT warn about being blocked if the ioctl is
issued for a S
> "Mikulas" == Mikulas Patocka writes:
Mikulas> On Fri, 18 Aug 2017, John Stoffel wrote:
Mikulas> The limit can't be changed. I expect that no one will run a system
with
Mikulas> such a tight requirements that the memory is used up to the last 2%.
>>
Mikulas> If the user is near hitting t
On Wed, 16 Aug 2017, Tom Yan wrote:
> What I find suspicious is `blkdiscard -z` the underlying device does
> not lead to those warning (while it takes the same amount of time), it
> makes me wonder if it's like, the dm layer is not doing certain thing
> it should do to inform the block layer or
On Fri, 2017-08-18 at 20:18 -0400, Mikulas Patocka wrote:
> Some times ago I made a patch that limits the number of in-flight bios in
> device mapper - see this:
> http://people.redhat.com/~mpatocka/patches/kernel/dm-limit-outstanding-bios/
It would be great to have this functionality upstream ..
On Fri, 18 Aug 2017, John Stoffel wrote:
> Mikulas> The limit can't be changed. I expect that no one will run a system
> with
> Mikulas> such a tight requirements that the memory is used up to the last 2%.
>
> Mikulas> If the user is near hitting the memory limit, he can just add swap
> spac
> "Mikulas" == Mikulas Patocka writes:
Mikulas> On Thu, 17 Aug 2017, John Stoffel wrote:
>> > "Mikulas" == Mikulas Patocka writes:
>>
Mikulas> On Mon, 14 Aug 2017, John Stoffel wrote:
>>
>> >> > "Mikulas" == Mikulas Patocka writes:
>> >>
Mikulas> dm-crypt consumes excessive amou
On Thu, 17 Aug 2017, John Stoffel wrote:
> > "Mikulas" == Mikulas Patocka writes:
>
> Mikulas> On Mon, 14 Aug 2017, John Stoffel wrote:
>
> >> > "Mikulas" == Mikulas Patocka writes:
> >>
> Mikulas> dm-crypt consumes excessive amount memory when the user attempts to
> zero
> Mikulas
> "Mikulas" == Mikulas Patocka writes:
Mikulas> On Mon, 14 Aug 2017, John Stoffel wrote:
>> > "Mikulas" == Mikulas Patocka writes:
>>
Mikulas> dm-crypt consumes excessive amount memory when the user attempts to
zero
Mikulas> a dm-crypt device with "blkdiscard -z". The command "blkdisc
On 15 August 2017 at 08:20, Mikulas Patocka wrote:
>
> It happens because encryption is too slow, it takes more than 120 seconds
> to clear the device. I don't know what else it should do. It is not easy
> to interrupt the operation because you would then have to deal with
> dangling bios.
>
What
Just tested the patch with kernel 4.12.6. Well it sort of worked. No
more OOM or kernel panic. Memory takeup is around ~250M on a machine
with 8G RAM. However I keep getting this:
Aug 15 04:04:10 archlinux kernel: INFO: task blkdiscard:538 blocked
for more than 120 seconds.
Aug 15 04:04:10 archlin
On Tue, 15 Aug 2017, Tom Yan wrote:
> Just tested the patch with kernel 4.12.6. Well it sort of worked. No
> more OOM or kernel panic. Memory takeup is around ~250M on a machine
> with 8G RAM. However I keep getting this:
>
> Aug 15 04:04:10 archlinux kernel: INFO: task blkdiscard:538 blocked
>
On Mon, 14 Aug 2017, John Stoffel wrote:
> > "Mikulas" == Mikulas Patocka writes:
>
> Mikulas> dm-crypt consumes excessive amount memory when the user attempts to
> zero
> Mikulas> a dm-crypt device with "blkdiscard -z". The command "blkdiscard -z"
> calls
> Mikulas> the BLKZEROOUT ioctl
> "Mikulas" == Mikulas Patocka writes:
Mikulas> dm-crypt consumes excessive amount memory when the user attempts to
zero
Mikulas> a dm-crypt device with "blkdiscard -z". The command "blkdiscard -z"
calls
Mikulas> the BLKZEROOUT ioctl, it goes to the function __blkdev_issue_zeroout,
Mikulas>
dm-crypt consumes excessive amount memory when the user attempts to zero
a dm-crypt device with "blkdiscard -z". The command "blkdiscard -z" calls
the BLKZEROOUT ioctl, it goes to the function __blkdev_issue_zeroout,
__blkdev_issue_zeroout sends large amount of write bios that contain the
zero page
15 matches
Mail list logo