On Fri, Apr 26, 2013 at 7:44 PM, Maxim V. Patlasov
wrote:
> I'm for accounting NR_WRITEBACK_TEMP because balance_dirty_pages is already
> overcomplicated (imho) and adding new clauses for FUSE makes me sick.
Agreed.
But instead of further complexifying balance_dirty_pages() fuse
specific throttl
Miklos, MM folks,
04/26/2013 06:02 PM, Miklos Szeredi пишет:
On Fri, Apr 26, 2013 at 12:32:24PM +0400, Maxim V. Patlasov wrote:
The idea is that fuse filesystems should not go over the bdi limit even if
the global limit hasn't been reached.
This might work, but kicking flusher every time some
On Fri, Apr 26, 2013 at 12:32:24PM +0400, Maxim V. Patlasov wrote:
> > The idea is that fuse filesystems should not go over the bdi limit even if
> > the global limit hasn't been reached.
>
> This might work, but kicking flusher every time someone write to
> fuse mount and dives into balance_dirt
Hi Miklos,
04/26/2013 12:43 AM, Miklos Szeredi пишет:
On Thu, Apr 25, 2013 at 08:16:45PM +0400, Maxim V. Patlasov wrote:
As Mel Gorman pointed out, fuse daemon diving into
balance_dirty_pages should not kick flusher judging on
NR_WRITEBACK_TEMP. Essentially, all we need in balance_dirty_pages
i
On Thu, Apr 25, 2013 at 08:16:45PM +0400, Maxim V. Patlasov wrote:
>
> As Mel Gorman pointed out, fuse daemon diving into
> balance_dirty_pages should not kick flusher judging on
> NR_WRITEBACK_TEMP. Essentially, all we need in balance_dirty_pages
> is:
>
> if (I'm not fuse daemon)
>
Hi,
04/25/2013 07:49 PM, Miklos Szeredi пишет:
On Thu, Apr 25, 2013 at 4:29 PM, Maxim V. Patlasov
wrote:
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 0713bfb..c47bcd4 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1235,7 +1235,8 @@ static void balance_dirty_page
On Thu, Apr 25, 2013 at 4:29 PM, Maxim V. Patlasov
wrote:
>> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
>> index 0713bfb..c47bcd4 100644
>> --- a/mm/page-writeback.c
>> +++ b/mm/page-writeback.c
>> @@ -1235,7 +1235,8 @@ static void balance_dirty_pages(struct address_space
>> *mapping,
Hi Miklos,
04/01/2013 02:42 PM, Maxim V. Patlasov пишет:
Make balance_dirty_pages start the throttling when the WRITEBACK_TEMP
counter is high enough. This prevents us from having too many dirty
pages on fuse, thus giving the userspace part of it a chance to write
stuff properly.
Note, that the
Make balance_dirty_pages start the throttling when the WRITEBACK_TEMP
counter is high enough. This prevents us from having too many dirty
pages on fuse, thus giving the userspace part of it a chance to write
stuff properly.
Note, that the existing balance logic is per-bdi, i.e. if the fuse
user ta
Make balance_dirty_pages start the throttling when the WRITEBACK_TEMP
counter is high enough. This prevents us from having too many dirty
pages on fuse, thus giving the userspace part of it a chance to write
stuff properly.
Note, that the existing balance logic is per-bdi, i.e. if the fuse
user ta
On 11/21/2012 08:01 PM, Maxim Patlasov wrote:
Added linux-mm@ to cc:. The patch can stand on it's own.
Make balance_dirty_pages start the throttling when the WRITEBACK_TEMP
counter is high enough. This prevents us from having too many dirty
pages on fuse, thus giving the userspace part of it a
Hi,
11/22/2012 05:27 PM, Jaegeuk Hanse пишет:
On 11/21/2012 08:01 PM, Maxim Patlasov wrote:
Added linux-mm@ to cc:. The patch can stand on it's own.
Make balance_dirty_pages start the throttling when the WRITEBACK_TEMP
counter is high enough. This prevents us from having too many dirty
pages
Added linux-mm@ to cc:. The patch can stand on it's own.
> Make balance_dirty_pages start the throttling when the WRITEBACK_TEMP
> counter is high enough. This prevents us from having too many dirty
> pages on fuse, thus giving the userspace part of it a chance to write
> stuff properly.
>
> Note
Make balance_dirty_pages start the throttling when the WRITEBACK_TEMP
counter is high enough. This prevents us from having too many dirty
pages on fuse, thus giving the userspace part of it a chance to write
stuff properly.
Note, that the existing balance logic is per-bdi, i.e. if the fuse
user ta
14 matches
Mail list logo
