From: Michal Hocko <mhocko@kernel.org>
To: "Theodore Ts'o" <tytso@mit.edu>
Cc: Jan Kara <jack@suse.cz>,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>,
Dave Chinner <david@fromorbit.com>,
djwong@kernel.org, Chris Mason <clm@fb.com>,
David Sterba <dsterba@suse.cz>,
ceph-devel@vger.kernel.org, cluster-devel@redhat.com,
linux-nfs@vger.kernel.org, logfs@logfs.org,
linux-xfs@vger.kernel.org, linux-ext4@vger.kernel.org,
linux-btrfs@vger.kernel.org, linux-mtd@lists.infradead.org,
reiserfs-devel@vger.kernel.org,
linux-ntfs-dev@lists.sourceforge.net,
linux-f2fs-devel@lists.sourceforge.net,
linux-afs@lists.infradead.org,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 8/8] Revert "ext4: fix wrong gfp type under transaction"
Date: Fri, 27 Jan 2017 10:37:35 +0100 [thread overview]
Message-ID: <20170127093735.GB4143@dhcp22.suse.cz> (raw)
In-Reply-To: <20170127061318.xd2qxashbl4dajez@thunk.org>
On Fri 27-01-17 01:13:18, Theodore Ts'o wrote:
> On Thu, Jan 26, 2017 at 08:44:55AM +0100, Michal Hocko wrote:
> > > > I'm convinced the current series is OK, only real life will tell us whether
> > > > we missed something or not ;)
> > >
> > > I would like to extend the changelog of "jbd2: mark the transaction
> > > context with the scope GFP_NOFS context".
> > >
> > > "
> > > Please note that setups without journal do not suffer from potential
> > > recursion problems and so they do not need the scope protection because
> > > neither ->releasepage nor ->evict_inode (which are the only fs entry
> > > points from the direct reclaim) can reenter a locked context which is
> > > doing the allocation currently.
> > > "
> >
> > Could you comment on this Ted, please?
>
> I guess.... so there still is one way this could screw us, and it's this reason for GFP_NOFS:
>
> - to prevent from stack overflows during the reclaim because
> the allocation is performed from a deep context already
>
> The writepages call stack can be pretty deep. (Especially if we're
> using ext4 in no journal mode over, say, iSCSI.)
>
> How much stack space can get consumed by a reclaim?
./scripts/stackusage with allyesconfig says:
./mm/page_alloc.c:3745 __alloc_pages_nodemask 264 static
./mm/page_alloc.c:3531 __alloc_pages_slowpath 520 static
./mm/vmscan.c:2946 try_to_free_pages 216 static
./mm/vmscan.c:2753 do_try_to_free_pages 304 static
./mm/vmscan.c:2517 shrink_node 352 static
./mm/vmscan.c:2317 shrink_node_memcg 560 static
./mm/vmscan.c:1692 shrink_inactive_list 688 static
./mm/vmscan.c:908 shrink_page_list 608 static
So this would be 3512 for the standard LRUs reclaim whether we have
GFP_FS or not. shrink_page_list can recurse to releasepage but there is
no NOFS protection there so it doesn't make much sense to check this
path. So we are left with the slab shrinkers path
./mm/page_alloc.c:3745 __alloc_pages_nodemask 264 static
./mm/page_alloc.c:3531 __alloc_pages_slowpath 520 static
./mm/vmscan.c:2946 try_to_free_pages 216 static
./mm/vmscan.c:2753 do_try_to_free_pages 304 static
./mm/vmscan.c:2517 shrink_node 352 static
./mm/vmscan.c:427 shrink_slab 336 static
./fs/super.c:56 super_cache_scan 104 static << here we have the NOFS protection
./fs/dcache.c:1089 prune_dcache_sb 152 static
./fs/dcache.c:939 shrink_dentry_list 96 static
./fs/dcache.c:509 __dentry_kill 72 static
./fs/dcache.c:323 dentry_unlink_inode 64 static
./fs/inode.c:1527 iput 80 static
./fs/inode.c:532 evict 72 static
This is where the fs specific callbacks play role and I am not sure
which paths can pass through for ext4 in the nojournal mode and how much
of the stack this can eat. But currently we are at +536 wrt. NOFS
context. This is quite a lot but still much less (2632 vs. 3512) than
the regular reclaim. So there is quite some stack space to eat... I am
wondering whether we have to really treat nojournal mode any special
just because of the stack usage?
If this ever turn out to be a problem and with the vmapped stacks we
have good chances to get a proper stack traces on a potential overflow
we can add the scope API around the problematic code path with the
explanation why it is needed.
Does that make sense to you?
Thanks!
--
Michal Hocko
SUSE Labs
WARNING: multiple messages have this Message-ID (diff)
From: Michal Hocko <mhocko@kernel.org>
To: Theodore Ts'o <tytso@mit.edu>
Cc: Jan Kara <jack@suse.cz>,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
Andrew Morton <akpm@linux-foundation.org>,
Dave Chinner <david@fromorbit.com>,
djwong@kernel.org, Chris Mason <clm@fb.com>,
David Sterba <dsterba@suse.cz>,
ceph-devel@vger.kernel.org, cluster-devel@redhat.com,
linux-nfs@vger.kernel.org, logfs@logfs.org,
linux-xfs@vger.kernel.org, linux-ext4@vger.kernel.org,
linux-btrfs@vger.kernel.org, linux-mtd@lists.infradead.org,
reiserfs-devel@vger.kernel.org,
linux-ntfs-dev@lists.sourceforge.net,
linux-f2fs-devel@lists.sourceforge.net,
linux-afs@lists.infradead.org,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 8/8] Revert "ext4: fix wrong gfp type under transaction"
Date: Fri, 27 Jan 2017 10:37:35 +0100 [thread overview]
Message-ID: <20170127093735.GB4143@dhcp22.suse.cz> (raw)
In-Reply-To: <20170127061318.xd2qxashbl4dajez@thunk.org>
On Fri 27-01-17 01:13:18, Theodore Ts'o wrote:
> On Thu, Jan 26, 2017 at 08:44:55AM +0100, Michal Hocko wrote:
> > > > I'm convinced the current series is OK, only real life will tell us whether
> > > > we missed something or not ;)
> > >
> > > I would like to extend the changelog of "jbd2: mark the transaction
> > > context with the scope GFP_NOFS context".
> > >
> > > "
> > > Please note that setups without journal do not suffer from potential
> > > recursion problems and so they do not need the scope protection because
> > > neither ->releasepage nor ->evict_inode (which are the only fs entry
> > > points from the direct reclaim) can reenter a locked context which is
> > > doing the allocation currently.
> > > "
> >
> > Could you comment on this Ted, please?
>
> I guess.... so there still is one way this could screw us, and it's this reason for GFP_NOFS:
>
> - to prevent from stack overflows during the reclaim because
> the allocation is performed from a deep context already
>
> The writepages call stack can be pretty deep. (Especially if we're
> using ext4 in no journal mode over, say, iSCSI.)
>
> How much stack space can get consumed by a reclaim?
./scripts/stackusage with allyesconfig says:
./mm/page_alloc.c:3745 __alloc_pages_nodemask 264 static
./mm/page_alloc.c:3531 __alloc_pages_slowpath 520 static
./mm/vmscan.c:2946 try_to_free_pages 216 static
./mm/vmscan.c:2753 do_try_to_free_pages 304 static
./mm/vmscan.c:2517 shrink_node 352 static
./mm/vmscan.c:2317 shrink_node_memcg 560 static
./mm/vmscan.c:1692 shrink_inactive_list 688 static
./mm/vmscan.c:908 shrink_page_list 608 static
So this would be 3512 for the standard LRUs reclaim whether we have
GFP_FS or not. shrink_page_list can recurse to releasepage but there is
no NOFS protection there so it doesn't make much sense to check this
path. So we are left with the slab shrinkers path
./mm/page_alloc.c:3745 __alloc_pages_nodemask 264 static
./mm/page_alloc.c:3531 __alloc_pages_slowpath 520 static
./mm/vmscan.c:2946 try_to_free_pages 216 static
./mm/vmscan.c:2753 do_try_to_free_pages 304 static
./mm/vmscan.c:2517 shrink_node 352 static
./mm/vmscan.c:427 shrink_slab 336 static
./fs/super.c:56 super_cache_scan 104 static << here we have the NOFS protection
./fs/dcache.c:1089 prune_dcache_sb 152 static
./fs/dcache.c:939 shrink_dentry_list 96 static
./fs/dcache.c:509 __dentry_kill 72 static
./fs/dcache.c:323 dentry_unlink_inode 64 static
./fs/inode.c:1527 iput 80 static
./fs/inode.c:532 evict 72 static
This is where the fs specific callbacks play role and I am not sure
which paths can pass through for ext4 in the nojournal mode and how much
of the stack this can eat. But currently we are at +536 wrt. NOFS
context. This is quite a lot but still much less (2632 vs. 3512) than
the regular reclaim. So there is quite some stack space to eat... I am
wondering whether we have to really treat nojournal mode any special
just because of the stack usage?
If this ever turn out to be a problem and with the vmapped stacks we
have good chances to get a proper stack traces on a potential overflow
we can add the scope API around the problematic code path with the
explanation why it is needed.
Does that make sense to you?
Thanks!
--
Michal Hocko
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
WARNING: multiple messages have this Message-ID (diff)
From: Michal Hocko <mhocko@kernel.org>
To: cluster-devel.redhat.com
Subject: [Cluster-devel] [PATCH 8/8] Revert "ext4: fix wrong gfp type under transaction"
Date: Fri, 27 Jan 2017 10:37:35 +0100 [thread overview]
Message-ID: <20170127093735.GB4143@dhcp22.suse.cz> (raw)
In-Reply-To: <20170127061318.xd2qxashbl4dajez@thunk.org>
On Fri 27-01-17 01:13:18, Theodore Ts'o wrote:
> On Thu, Jan 26, 2017 at 08:44:55AM +0100, Michal Hocko wrote:
> > > > I'm convinced the current series is OK, only real life will tell us whether
> > > > we missed something or not ;)
> > >
> > > I would like to extend the changelog of "jbd2: mark the transaction
> > > context with the scope GFP_NOFS context".
> > >
> > > "
> > > Please note that setups without journal do not suffer from potential
> > > recursion problems and so they do not need the scope protection because
> > > neither ->releasepage nor ->evict_inode (which are the only fs entry
> > > points from the direct reclaim) can reenter a locked context which is
> > > doing the allocation currently.
> > > "
> >
> > Could you comment on this Ted, please?
>
> I guess.... so there still is one way this could screw us, and it's this reason for GFP_NOFS:
>
> - to prevent from stack overflows during the reclaim because
> the allocation is performed from a deep context already
>
> The writepages call stack can be pretty deep. (Especially if we're
> using ext4 in no journal mode over, say, iSCSI.)
>
> How much stack space can get consumed by a reclaim?
./scripts/stackusage with allyesconfig says:
./mm/page_alloc.c:3745 __alloc_pages_nodemask 264 static
./mm/page_alloc.c:3531 __alloc_pages_slowpath 520 static
./mm/vmscan.c:2946 try_to_free_pages 216 static
./mm/vmscan.c:2753 do_try_to_free_pages 304 static
./mm/vmscan.c:2517 shrink_node 352 static
./mm/vmscan.c:2317 shrink_node_memcg 560 static
./mm/vmscan.c:1692 shrink_inactive_list 688 static
./mm/vmscan.c:908 shrink_page_list 608 static
So this would be 3512 for the standard LRUs reclaim whether we have
GFP_FS or not. shrink_page_list can recurse to releasepage but there is
no NOFS protection there so it doesn't make much sense to check this
path. So we are left with the slab shrinkers path
./mm/page_alloc.c:3745 __alloc_pages_nodemask 264 static
./mm/page_alloc.c:3531 __alloc_pages_slowpath 520 static
./mm/vmscan.c:2946 try_to_free_pages 216 static
./mm/vmscan.c:2753 do_try_to_free_pages 304 static
./mm/vmscan.c:2517 shrink_node 352 static
./mm/vmscan.c:427 shrink_slab 336 static
./fs/super.c:56 super_cache_scan 104 static << here we have the NOFS protection
./fs/dcache.c:1089 prune_dcache_sb 152 static
./fs/dcache.c:939 shrink_dentry_list 96 static
./fs/dcache.c:509 __dentry_kill 72 static
./fs/dcache.c:323 dentry_unlink_inode 64 static
./fs/inode.c:1527 iput 80 static
./fs/inode.c:532 evict 72 static
This is where the fs specific callbacks play role and I am not sure
which paths can pass through for ext4 in the nojournal mode and how much
of the stack this can eat. But currently we are@+536 wrt. NOFS
context. This is quite a lot but still much less (2632 vs. 3512) than
the regular reclaim. So there is quite some stack space to eat... I am
wondering whether we have to really treat nojournal mode any special
just because of the stack usage?
If this ever turn out to be a problem and with the vmapped stacks we
have good chances to get a proper stack traces on a potential overflow
we can add the scope API around the problematic code path with the
explanation why it is needed.
Does that make sense to you?
Thanks!
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2017-01-27 9:38 UTC|newest]
Thread overview: 167+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-01-06 14:10 [PATCH 0/8 v3] scope GFP_NOFS api Michal Hocko
2017-01-06 14:10 ` [Cluster-devel] " Michal Hocko
2017-01-06 14:10 ` Michal Hocko
2017-01-06 14:10 ` Michal Hocko
2017-01-06 14:10 ` Michal Hocko
2017-01-06 14:11 ` [PATCH 1/8] lockdep: allow to disable reclaim lockup detection Michal Hocko
2017-01-06 14:11 ` [Cluster-devel] " Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-09 12:56 ` Vlastimil Babka
2017-01-09 12:56 ` [Cluster-devel] " Vlastimil Babka
2017-01-09 12:56 ` Vlastimil Babka
2017-01-06 14:11 ` [PATCH 2/8] xfs: abstract PF_FSTRANS to PF_MEMALLOC_NOFS Michal Hocko
2017-01-06 14:11 ` [Cluster-devel] " Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-09 12:59 ` Vlastimil Babka
2017-01-09 12:59 ` [Cluster-devel] " Vlastimil Babka
2017-01-09 12:59 ` Vlastimil Babka
2017-01-09 14:29 ` Michal Hocko
2017-01-09 14:29 ` [Cluster-devel] " Michal Hocko
2017-01-09 14:29 ` Michal Hocko
2017-01-09 20:58 ` Darrick J. Wong
2017-01-09 20:58 ` [Cluster-devel] " Darrick J. Wong
2017-01-09 20:58 ` Darrick J. Wong
2017-01-06 14:11 ` [PATCH 3/8] mm: introduce memalloc_nofs_{save,restore} API Michal Hocko
2017-01-06 14:11 ` [Cluster-devel] [PATCH 3/8] mm: introduce memalloc_nofs_{save, restore} API Michal Hocko
2017-01-06 14:11 ` [PATCH 3/8] mm: introduce memalloc_nofs_{save,restore} API Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-09 13:04 ` Vlastimil Babka
2017-01-09 13:04 ` [Cluster-devel] [PATCH 3/8] mm: introduce memalloc_nofs_{save, restore} API Vlastimil Babka
2017-01-09 13:04 ` [PATCH 3/8] mm: introduce memalloc_nofs_{save,restore} API Vlastimil Babka
2017-01-09 13:42 ` Michal Hocko
2017-01-09 13:42 ` [Cluster-devel] [PATCH 3/8] mm: introduce memalloc_nofs_{save, restore} API Michal Hocko
2017-01-09 13:42 ` [PATCH 3/8] mm: introduce memalloc_nofs_{save,restore} API Michal Hocko
2017-01-09 13:59 ` Michal Hocko
2017-01-09 13:59 ` [Cluster-devel] [PATCH 3/8] mm: introduce memalloc_nofs_{save, restore} API Michal Hocko
2017-01-09 13:59 ` [PATCH 3/8] mm: introduce memalloc_nofs_{save,restore} API Michal Hocko
2017-01-09 14:04 ` Vlastimil Babka
2017-01-09 14:04 ` [Cluster-devel] [PATCH 3/8] mm: introduce memalloc_nofs_{save, restore} API Vlastimil Babka
2017-01-09 14:04 ` [PATCH 3/8] mm: introduce memalloc_nofs_{save,restore} API Vlastimil Babka
2017-01-06 14:11 ` [PATCH 4/8] xfs: use memalloc_nofs_{save,restore} instead of memalloc_noio* Michal Hocko
2017-01-06 14:11 ` [Cluster-devel] [PATCH 4/8] xfs: use memalloc_nofs_{save, restore} " Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` [PATCH 4/8] xfs: use memalloc_nofs_{save,restore} " Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-09 14:08 ` Vlastimil Babka
2017-01-09 14:08 ` [Cluster-devel] [PATCH 4/8] xfs: use memalloc_nofs_{save, restore} " Vlastimil Babka
2017-01-09 14:08 ` [PATCH 4/8] xfs: use memalloc_nofs_{save,restore} " Vlastimil Babka
2017-01-09 14:25 ` Michal Hocko
2017-01-09 14:25 ` [Cluster-devel] [PATCH 4/8] xfs: use memalloc_nofs_{save, restore} " Michal Hocko
2017-01-09 14:25 ` [PATCH 4/8] xfs: use memalloc_nofs_{save,restore} " Michal Hocko
2017-01-09 15:56 ` Brian Foster
2017-01-09 15:56 ` [Cluster-devel] [PATCH 4/8] xfs: use memalloc_nofs_{save, restore} " Brian Foster
2017-01-09 15:56 ` [PATCH 4/8] xfs: use memalloc_nofs_{save,restore} " Brian Foster
2017-01-09 20:59 ` Darrick J. Wong
2017-01-09 20:59 ` [Cluster-devel] [PATCH 4/8] xfs: use memalloc_nofs_{save, restore} " Darrick J. Wong
2017-01-09 20:59 ` [PATCH 4/8] xfs: use memalloc_nofs_{save,restore} " Darrick J. Wong
2017-01-06 14:11 ` [PATCH 5/8] jbd2: mark the transaction context with the scope GFP_NOFS context Michal Hocko
2017-01-06 14:11 ` [Cluster-devel] " Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` [PATCH 6/8] jbd2: make the whole kjournald2 kthread NOFS safe Michal Hocko
2017-01-06 14:11 ` [Cluster-devel] " Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` [PATCH 7/8] Revert "ext4: avoid deadlocks in the writeback path by using sb_getblk_gfp" Michal Hocko
2017-01-06 14:11 ` [Cluster-devel] " Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-17 3:01 ` Theodore Ts'o
2017-01-17 3:01 ` [Cluster-devel] " Theodore Ts'o
2017-01-17 3:01 ` Theodore Ts'o
2017-01-17 7:54 ` Michal Hocko
2017-01-17 7:54 ` [Cluster-devel] " Michal Hocko
2017-01-17 7:54 ` Michal Hocko
2017-03-06 11:59 ` Michal Hocko
2017-03-06 11:59 ` [Cluster-devel] " Michal Hocko
2017-03-06 11:59 ` Michal Hocko
2017-01-06 14:11 ` [PATCH 8/8] Revert "ext4: fix wrong gfp type under transaction" Michal Hocko
2017-01-06 14:11 ` [Cluster-devel] " Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-06 14:11 ` Michal Hocko
2017-01-17 2:56 ` Theodore Ts'o
2017-01-17 2:56 ` [Cluster-devel] " Theodore Ts'o
2017-01-17 2:56 ` Theodore Ts'o
2017-01-17 8:24 ` Michal Hocko
2017-01-17 8:24 ` [Cluster-devel] " Michal Hocko
2017-01-17 8:24 ` Michal Hocko
2017-01-17 15:18 ` Michal Hocko
2017-01-17 15:18 ` [Cluster-devel] " Michal Hocko
2017-01-17 15:18 ` Michal Hocko
2017-01-17 15:18 ` Michal Hocko
2017-01-17 15:59 ` Theodore Ts'o
2017-01-17 15:59 ` [Cluster-devel] " Theodore Ts'o
2017-01-17 15:59 ` Theodore Ts'o
2017-01-17 16:16 ` Michal Hocko
2017-01-17 16:16 ` [Cluster-devel] " Michal Hocko
2017-01-17 16:16 ` Michal Hocko
2017-01-17 17:29 ` Jan Kara
2017-01-17 17:29 ` [Cluster-devel] " Jan Kara
2017-01-17 17:29 ` Jan Kara
2017-01-19 8:39 ` Michal Hocko
2017-01-19 8:39 ` [Cluster-devel] " Michal Hocko
2017-01-19 8:39 ` Michal Hocko
2017-01-19 9:22 ` Jan Kara
2017-01-19 9:22 ` [Cluster-devel] " Jan Kara
2017-01-19 9:22 ` Jan Kara
2017-01-19 9:44 ` Michal Hocko
2017-01-19 9:44 ` [Cluster-devel] " Michal Hocko
2017-01-19 9:44 ` Michal Hocko
2017-01-26 7:44 ` Michal Hocko
2017-01-26 7:44 ` [Cluster-devel] " Michal Hocko
2017-01-26 7:44 ` Michal Hocko
2017-01-27 6:13 ` Theodore Ts'o
2017-01-27 6:13 ` [Cluster-devel] " Theodore Ts'o
2017-01-27 6:13 ` Theodore Ts'o
2017-01-27 6:13 ` Theodore Ts'o
2017-01-27 9:37 ` Michal Hocko [this message]
2017-01-27 9:37 ` [Cluster-devel] " Michal Hocko
2017-01-27 9:37 ` Michal Hocko
2017-01-27 16:40 ` Theodore Ts'o
2017-01-27 16:40 ` [Cluster-devel] " Theodore Ts'o
2017-01-27 16:40 ` Theodore Ts'o
2017-01-28 7:32 ` [Cluster-devel] " Christoph Hellwig
2017-01-28 7:32 ` Christoph Hellwig
2017-01-28 7:32 ` Christoph Hellwig
2017-01-28 8:17 ` David Lang
2017-01-28 8:17 ` David Lang
2017-01-28 8:17 ` David Lang
2017-01-30 8:12 ` Michal Hocko
2017-01-30 8:12 ` [Cluster-devel] " Michal Hocko
2017-01-30 8:12 ` Michal Hocko
2017-02-03 15:32 ` Michal Hocko
2017-02-03 15:32 ` [Cluster-devel] " Michal Hocko
2017-02-03 15:32 ` Michal Hocko
2017-01-17 21:04 ` Andreas Dilger
2017-01-17 21:04 ` [Cluster-devel] " Andreas Dilger
2017-01-17 21:04 ` Andreas Dilger
2017-01-18 8:29 ` Michal Hocko
2017-01-18 8:29 ` [Cluster-devel] " Michal Hocko
2017-01-18 8:29 ` Michal Hocko
2017-01-06 14:18 ` [DEBUG PATCH 0/2] debug explicit GFP_NO{FS,IO} usage from the scope context Michal Hocko
2017-01-06 14:18 ` [Cluster-devel] [DEBUG PATCH 0/2] debug explicit GFP_NO{FS, IO} " Michal Hocko
2017-01-06 14:18 ` Michal Hocko
2017-01-06 14:18 ` [DEBUG PATCH 0/2] debug explicit GFP_NO{FS,IO} " Michal Hocko
2017-01-06 14:18 ` Michal Hocko
2017-01-06 14:18 ` Michal Hocko
2017-01-06 14:18 ` [DEBUG PATCH 1/2] mm, debug: report when GFP_NO{FS,IO} is used explicitly from memalloc_no{fs,io}_{save,restore} context Michal Hocko
2017-01-06 14:18 ` [Cluster-devel] [DEBUG PATCH 1/2] mm, debug: report when GFP_NO{FS, IO} is used explicitly from memalloc_no{fs, io}_{save, restore} context Michal Hocko
2017-01-06 14:18 ` Michal Hocko
2017-01-06 14:18 ` [DEBUG PATCH 1/2] mm, debug: report when GFP_NO{FS,IO} is used explicitly from memalloc_no{fs,io}_{save,restore} context Michal Hocko
2017-01-06 14:18 ` Michal Hocko
2017-01-06 14:18 ` Michal Hocko
2017-01-06 14:18 ` [DEBUG PATCH 2/2] silent warnings which we cannot do anything about Michal Hocko
2017-01-06 14:18 ` [Cluster-devel] " Michal Hocko
2017-01-06 14:18 ` Michal Hocko
2017-01-06 14:18 ` Michal Hocko
2017-01-06 14:18 ` Michal Hocko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20170127093735.GB4143@dhcp22.suse.cz \
--to=mhocko@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=ceph-devel@vger.kernel.org \
--cc=clm@fb.com \
--cc=cluster-devel@redhat.com \
--cc=david@fromorbit.com \
--cc=djwong@kernel.org \
--cc=dsterba@suse.cz \
--cc=jack@suse.cz \
--cc=linux-afs@lists.infradead.org \
--cc=linux-btrfs@vger.kernel.org \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-f2fs-devel@lists.sourceforge.net \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-mtd@lists.infradead.org \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-ntfs-dev@lists.sourceforge.net \
--cc=linux-xfs@vger.kernel.org \
--cc=logfs@logfs.org \
--cc=reiserfs-devel@vger.kernel.org \
--cc=tytso@mit.edu \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.