Hello, guys.
I updated all three patchsets to reflect the accumulated fixes and the
mapping_congested() change pointed out by Vivek, which BTW is now
inode_congested() - the whole function was a bit botched from
conversion from the multi-wb dirtying support, should be fine now.
Hello, guys.
I updated all three patchsets to reflect the accumulated fixes and the
mapping_congested() change pointed out by Vivek, which BTW is now
inode_congested() - the whole function was a bit botched from
conversion from the multi-wb dirtying support, should be fine now.
Hello, Vivek.
On Wed, Mar 25, 2015 at 11:40:22AM -0400, Vivek Goyal wrote:
> I have 32G of RAM on my system and I setup a write bandwidth of 1MB/s
> on the disk and allowed a dd to run. That dd quickly consumed 5G of
> page cache before it reached to a steady state. Sounds like too much
> of
On Mon, Mar 23, 2015 at 12:54:11AM -0400, Tejun Heo wrote:
>
>
> How to test
> ---
>
> * Boot with kernel option "cgroup__DEVEL__legacy_files_on_dfl".
>
> * umount /sys/fs/cgroup/memory
> umount /sys/fs/cgroup/blkio
> mkdir /sys/fs/cgroup/unified
> mount -t cgroup -o
Hello, Vivek.
On Wed, Mar 25, 2015 at 11:40:22AM -0400, Vivek Goyal wrote:
I have 32G of RAM on my system and I setup a write bandwidth of 1MB/s
on the disk and allowed a dd to run. That dd quickly consumed 5G of
page cache before it reached to a steady state. Sounds like too much
of cache
On Mon, Mar 23, 2015 at 12:54:11AM -0400, Tejun Heo wrote:
How to test
---
* Boot with kernel option cgroup__DEVEL__legacy_files_on_dfl.
* umount /sys/fs/cgroup/memory
umount /sys/fs/cgroup/blkio
mkdir /sys/fs/cgroup/unified
mount -t cgroup -o __DEVEL__sane_behavior
Hello,
This is v2 of cgroup writeback support patchset. Changes from the
last take[L] are
* Dropped dirtying an inode against multiple cgroups at the same time.
At a given time, an inode always belongs to one cgroup
bdi_writeback. It's currently associated on the first-use but a
later
Hello,
This is v2 of cgroup writeback support patchset. Changes from the
last take[L] are
* Dropped dirtying an inode against multiple cgroups at the same time.
At a given time, an inode always belongs to one cgroup
bdi_writeback. It's currently associated on the first-use but a
later
8 matches
Mail list logo