That is a good suggestion, thanks.
thanks.
Andreas Dilger wrote on 2020/8/7 16:15:
> It would be good to include these performance results in the commit message,
> so that the results are available to the patch reviewers and in the future if
> this code is changed.
>
> On Wed, Aug 5, 2020 at
Add more... , As we expected, the running time of the test process is
reduced significantly.
Running time on unrepaired kernel：
[root@TENCENT64 ~]# time taskset 0x01 ./sparse /data1/sparce.dat
real 0m2.051s
user 0m0.008s
sys 0m2.026s
Running time on repaired kernel：
[root@TENCENT64 ~]#
Thx for your reply~. In our application scenario, we format an ext3
file system, and then create a daemon to write data to a sparse file.
During the business operation, we found that the sys of some cpu is
very high. Using the crash tool, we observe that the length of the
prealloc list of the
On Aug 4, 2020, at 7:02 PM, brookxu wrote:
>
> In the scenario of writing sparse files, the Per-inode prealloc list may
> be very long, resulting in high overhead for ext4_mb_use_preallocated().
> To circumvent this problem, we limit the maximum length of per-inode
> prealloc list to 512 and
In the scenario of writing sparse files, the Per-inode prealloc list may
be very long, resulting in high overhead for ext4_mb_use_preallocated().
To circumvent this problem, we limit the maximum length of per-inode
prealloc list to 512 and allow users to modify it.
Signed-off-by: Chunguang Xu
5 matches
Mail list logo
