After heavily stressing EROFS with several images which include a
hand-crafted image of repeated patterns for more than 46 days, I found
two chains could be linked with each other almost simultaneously and
form a loop so that the entire loop won't be submitted. As a
consequence, the corresponding
As Sandeep shown [1], high priority RT per-cpu kthreads are
typically helpful for Android scenarios to minimize the scheduling
latencies.
Switch EROFS_FS_PCPU_KTHREAD_HIPRI on by default if
EROFS_FS_PCPU_KTHREAD is on since it's the typical use cases for
EROFS_FS_PCPU_KTHREAD.
Also clean up unnee
Make a read splice from a DAX file go directly to copy_splice_read() to do
the reading as filemap_splice_read() is unlikely to find any pagecache to
splice.
I think this affects only erofs, Ext2, Ext4, fuse and XFS.
Signed-off-by: David Howells
Reviewed-by: Christoph Hellwig
Reviewed-by: Christ
defconfig gcc
alpharandconfig-r002-20230522 gcc
alpharandconfig-r013-20230521 gcc
alpharandconfig-r025-20230521 gcc
alpharandconfig-r025-20230522 gcc
alpharandconfig-r036-20230522 gcc
arc
On Mon, 22 May 2023 17:21:41 +0800
Gao Xiang wrote:
> As Sandeep shown [1], high priority RT per-cpu kthreads are
> typically helpful for Android scenarios to minimize the scheduling
> latencies.
>
> Switch EROFS_FS_PCPU_KTHREAD_HIPRI on by default if
> EROFS_FS_PCPU_KTHREAD is on since it's the
On 2023/5/23 17:52, Yue Hu wrote:
On Mon, 22 May 2023 17:21:41 +0800
Gao Xiang wrote:
As Sandeep shown [1], high priority RT per-cpu kthreads are
typically helpful for Android scenarios to minimize the scheduling
latencies.
Switch EROFS_FS_PCPU_KTHREAD_HIPRI on by default if
EROFS_FS_PCPU_
On Tue, 23 May 2023 09:53:06 +0800
Gao Xiang wrote:
> On 2023/5/23 17:52, Yue Hu wrote:
> > On Mon, 22 May 2023 17:21:41 +0800
> > Gao Xiang wrote:
> >
> >> As Sandeep shown [1], high priority RT per-cpu kthreads are
> >> typically helpful for Android scenarios to minimize the scheduling
> >>
On Mon, May 22, 2023 at 2:21 AM Gao Xiang wrote:
>
> As Sandeep shown [1], high priority RT per-cpu kthreads are
> typically helpful for Android scenarios to minimize the scheduling
> latencies.
>
> Switch EROFS_FS_PCPU_KTHREAD_HIPRI on by default if
> EROFS_FS_PCPU_KTHREAD is on since it's the ty
On 2023/5/22 17:21, Gao Xiang wrote:
As Sandeep shown [1], high priority RT per-cpu kthreads are
typically helpful for Android scenarios to minimize the scheduling
latencies.
Switch EROFS_FS_PCPU_KTHREAD_HIPRI on by default if
EROFS_FS_PCPU_KTHREAD is on since it's the typical use cases for
EROF
On Mon, May 01, 2023 at 05:05:06PM +0800, Turritopsis Dohrnii Teo En Ming wrote:
> Article: EROFS Receives Some Useful Improvements With Linux 6.4
> Link: https://www.phoronix.com/news/Linux-6.4-EROFS
Linux 6.4 is on -rc phase (currently v6.4-rc3). Can you try it with
erofs enabled and report any
On 2023/5/23 20:47, Bagas Sanjaya wrote:
On Mon, May 01, 2023 at 05:05:06PM +0800, Turritopsis Dohrnii Teo En Ming wrote:
Article: EROFS Receives Some Useful Improvements With Linux 6.4
Link: https://www.phoronix.com/news/Linux-6.4-EROFS
Linux 6.4 is on -rc phase (currently v6.4-rc3). Can y
On 2023/5/15 17:57, Yue Hu wrote:
From: Yue Hu
The function of pcpubuf.c is just for low-latency decompression
algorithms (e.g. lz4).
Signed-off-by: Yue Hu
Reviewed-by: Gao Xiang
Reviewed-by: Chao Yu
Thanks,
On 2023/5/15 18:39, Jingbo Xu wrote:
Fragments and dedupe share one feature bit, and thus packed inode may not
exist when fragment feature bit (dedupe feature bit exactly) is set, e.g.
when deduplication feature is in use while fragments feature is not. In
this case, sbi->packed_inode could be N
13 matches
Mail list logo