Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-02 Thread Nikolay Borisov
On 2.11.18 г. 9:13 ч., ethanlien wrote: > David Sterba 於 2018-11-02 02:02 寫到: >> On Thu, Nov 01, 2018 at 02:49:03PM +0800, Ethan Lien wrote: >>> Snapshot is expected to be fast. But if there are writers steadily >>> create dirty pages in our subvolume, the snapshot may take a very long >>> time

Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-02 Thread ethanlien
David Sterba 於 2018-11-02 02:02 寫到: On Thu, Nov 01, 2018 at 02:49:03PM +0800, Ethan Lien wrote: Snapshot is expected to be fast. But if there are writers steadily create dirty pages in our subvolume, the snapshot may take a very long time to complete. To fix the problem, we use tagged writepage

Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-02 Thread ethanlien
Nikolay Borisov 於 2018-11-01 19:57 寫到: On 1.11.18 г. 8:49 ч., Ethan Lien wrote: Snapshot is expected to be fast. But if there are writers steadily create dirty pages in our subvolume, the snapshot may take a very long time to complete. To fix the problem, we use tagged writepage for snapshot

Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-01 Thread David Sterba
On Thu, Nov 01, 2018 at 02:49:03PM +0800, Ethan Lien wrote: > Snapshot is expected to be fast. But if there are writers steadily > create dirty pages in our subvolume, the snapshot may take a very long > time to complete. To fix the problem, we use tagged writepage for snapshot > flusher as we do

Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-01 Thread Chris Mason
On 1 Nov 2018, at 6:21, ethanlien wrote: > Nikolay Borisov 於 2018-11-01 18:01 寫到: >> On 1.11.18 г. 11:56 ч., ethanlien wrote: >>> Nikolay Borisov 於 2018-11-01 16:59 寫到: On 1.11.18 г. 8:49 ч., Ethan Lien wrote: > Snapshot is expected to be fast. But if there are writers steadily >

Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-01 Thread Nikolay Borisov
On 1.11.18 г. 8:49 ч., Ethan Lien wrote: > Snapshot is expected to be fast. But if there are writers steadily > create dirty pages in our subvolume, the snapshot may take a very long > time to complete. To fix the problem, we use tagged writepage for snapshot > flusher as we do in the generic

Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-01 Thread ethanlien
Nikolay Borisov 於 2018-11-01 18:01 寫到: On 1.11.18 г. 11:56 ч., ethanlien wrote: Nikolay Borisov 於 2018-11-01 16:59 寫到: On 1.11.18 г. 8:49 ч., Ethan Lien wrote: Snapshot is expected to be fast. But if there are writers steadily create dirty pages in our subvolume, the snapshot may take a very

Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-01 Thread Nikolay Borisov
On 1.11.18 г. 11:56 ч., ethanlien wrote: > Nikolay Borisov 於 2018-11-01 16:59 寫到: >> On 1.11.18 г. 8:49 ч., Ethan Lien wrote: >>> Snapshot is expected to be fast. But if there are writers steadily >>> create dirty pages in our subvolume, the snapshot may take a very long >>> time to complete.

Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-01 Thread ethanlien
Nikolay Borisov 於 2018-11-01 16:59 寫到: On 1.11.18 г. 8:49 ч., Ethan Lien wrote: Snapshot is expected to be fast. But if there are writers steadily create dirty pages in our subvolume, the snapshot may take a very long time to complete. To fix the problem, we use tagged writepage for snapshot

Re: [PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-01 Thread Nikolay Borisov
On 1.11.18 г. 8:49 ч., Ethan Lien wrote: > Snapshot is expected to be fast. But if there are writers steadily > create dirty pages in our subvolume, the snapshot may take a very long > time to complete. To fix the problem, we use tagged writepage for snapshot > flusher as we do in the generic

[PATCH] btrfs: use tagged writepage to mitigate livelock of snapshot

2018-11-01 Thread Ethan Lien
Snapshot is expected to be fast. But if there are writers steadily create dirty pages in our subvolume, the snapshot may take a very long time to complete. To fix the problem, we use tagged writepage for snapshot flusher as we do in the generic write_cache_pages(), so we can ommit pages dirtied