On 2018/5/25 14:18, Jaegeuk Kim wrote:
> On 05/25, Chao Yu wrote:
>> Hi Jaegeuk,
>>
>> On 2018/5/25 13:10, Jaegeuk Kim wrote:
>>> The fstrim gathers huge number of large discard commands, and tries to issue
>>> without IO awareness, which results in long user-perceive IO latencies on
>>> READ, WRIT
On 05/25, Chao Yu wrote:
> Hi Jaegeuk,
>
> On 2018/5/25 13:10, Jaegeuk Kim wrote:
> > The fstrim gathers huge number of large discard commands, and tries to issue
> > without IO awareness, which results in long user-perceive IO latencies on
> > READ, WRITE, and FLUSH in UFS. We've observed some of
Hi Jaegeuk,
On 2018/5/25 13:10, Jaegeuk Kim wrote:
> The fstrim gathers huge number of large discard commands, and tries to issue
> without IO awareness, which results in long user-perceive IO latencies on
> READ, WRITE, and FLUSH in UFS. We've observed some of commands take several
> seconds due
On 2018/5/24 9:17, Jaegeuk Kim wrote:
> For example, if we want to format 40MB image, it'll give 12 segments for main
> area. And, it assigns 6 for current segments, 11 for ovp segments, and 10 for
> reserved segments. So, we have 5 free segments, which we can't handle:
> # of free segments < # of
The fstrim gathers huge number of large discard commands, and tries to issue
without IO awareness, which results in long user-perceive IO latencies on
READ, WRITE, and FLUSH in UFS. We've observed some of commands take several
seconds due to long discard latency.
This patch limits the maximum size
On Mon, May 07, 2018 at 02:58:11PM -0700, Jaegeuk Kim wrote:
> On 05/07, Adam Borowski wrote:
> > One offender I own has:
> > STORAGE DEVICE
> > 1404x05xe3x07QGENEx00%x00x00x00x00x00x00x00x00x00x00x00x00x170x04
> >
> > I limited it to pure ASCII only, but you might want to allow high-bit bytes,
For non-migration IO, we will keep order of data/node blocks' submitting
as allocation sequence by sorting IOs in per log io_list list, but for
migration IO, it could be out-of-order.
In LFS mode, we should keep all IOs including migration IO be ordered,
so that this patch fixes to add an addition
