Could you please run "echo 1 > /proc/sys/kernel/sysrq; echo t >
/proc/sysrq-trigger" when this warning happens again. then send the
kernel message to us.
Regards
Yan, Zheng
On Tue, Jun 23, 2015 at 10:25 PM, Barclay Jameson
wrote:
> Sure,
> I guess it's actually a
gt; vim +2865 fs/ceph/mds_client.c
>>
>> a687ecaf John Spray 2014-09-19 2859
>> ceph_session_state_name(session->s_state));
>> 2f2dc053 Sage Weil 2009-10-06 2860
>> 99a9c273 Yan, Zheng 2013-09-22 2861
>> spin_lock(&session->s_gen_ttl_
27;s not sufficient.
>
> Is there supposed to be something preventing this kind of race? If not
> I can work something out in the code but I've not done much work in
> that bit and there are enough pieces that I wonder if I'm missing some
> other issue.
I think calling (*
Hi Loic.
Yes, https://github.com/ceph/ceph/pull/5222 is problematic. Do you mean should
we include these RPs in v0.94.3? These RPs fix a bug in rare configure, I
think it’s not a big deal to not include it in v0.94.3
Regards
Yan, Zheng
> On Aug 4, 2015, at 00:32, Loic Dachary wr
On Thu, Aug 6, 2015 at 5:26 AM, Sage Weil wrote:
> Today I learned that syncfs(2) does an O(n) search of the superblock's
> inode list searching for dirty items. I've always assumed that it was
> only traversing dirty inodes (e.g., a list of dirty inodes), but that
> appears not to be the case, e
if (file->f_flags & O_CREAT)
> parent_inode =
> ceph_get_dentry_parent_inode(file->f_path.dentry);
> err = ceph_mdsc_do_request(mdsc, parent_inode, req);
> iput(parent_inode);
In this case, we do not need parent_inode because file alread
On Thu, Aug 13, 2015 at 8:34 PM, Sage Weil wrote:
> On Thu, 13 Aug 2015, Yan, Zheng wrote:
>> On Thu, Aug 13, 2015 at 5:01 PM, Ma, Jianpeng wrote:
>> > Because flags removed the O_CREAT, so we should use file->f_flags.
>> >
>> > Signed-off-by: Jianpen
It seems all of your patches are malformed. please use 'git send-email’ to send
patch.
Regards
Yan, Zheng
> On Aug 17, 2015, at 16:43, Ma, Jianpeng wrote:
>
> For ceph_open, it already get the parent inode. So no need to get again.
>
> Signed-off-by: Jianpeng Ma
> -
request(req);
> —
I fixed your patches (all tabs are replaced by spaces in your patches) and
added them to our testing branch
Thanks
Yan, Zheng
> 2.4.3
>
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Signed-off-by: Yan, Zheng
---
include/linux/ceph/libceph.h | 2 ++
include/linux/ceph/messenger.h | 4 +++
include/linux/ceph/msgr.h | 4 ++-
net/ceph/ceph_common.c | 18 -
net/ceph/messenger.c | 60 ++
net/ceph
> On Sep 2, 2015, at 17:12, Ilya Dryomov wrote:
>
> On Wed, Sep 2, 2015 at 5:22 AM, Yan, Zheng wrote:
>> timespec_to_jiffies() does not work this way. it convert time delta in form
>> of timespec to time delta in form of jiffies.
>
> Ah sorry, con->last_keepal
does not
recognize CEPH_MSGR_TAG_KEEPALIVE2 tag). I think it's better to not
advertise support for keepalive2.
Regards
Yan, Zheng
>
> Signed-off-by: Ilya Dryomov
> ---
> include/linux/ceph/ceph_features.h | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/incl
> + ceph_encode_timespec(&con->out_temp_keepalive2, &now);
> + con_out_kvec_add(con, sizeof(con->out_temp_keepalive2),
> + &con->out_temp_keepalive2);
> } else {
> con_out_kvec_add(
On Wed, Sep 16, 2015 at 3:39 PM, Ilya Dryomov wrote:
> On Wed, Sep 16, 2015 at 9:28 AM, Yan, Zheng wrote:
>> On Mon, Sep 14, 2015 at 9:51 PM, Ilya Dryomov wrote:
>>> We are the client, but advertise keepalive2 anyway - for consistency,
>>> if nothing else. In the f
pagevlen);
> +pages = kmalloc(sizeof(*pages) * npages, GFP_NOFS);
> +if (!pages)
> +return ERR_PTR(-ENOMEM);
> + for (n = 0; n < npages; n += m) {
> +m = calc_pages_for((ulong)data, len);
> +if (n + m > npages)
> +m = npages - n;
&g
ceph virtual inode (id + snaphot) */
> + /* use ceph virtual inode (id + snapshot) */
> klen = sizeof(ci->i_vino);
> if (klen > maxbuf)
> return 0;
Applied, thank you.
Yan, Zheng
> --
> 1.9.1
>
>
--
To unsubscribe from this list: send
ith each other in the principle.
why? I think it's easy to replace dio_alloc_pagev() by
iov_iter_get_pages(). We just need to use dio_get_pagevlen() to
calculate how many page to get each time.
Regards
Yan, Zheng
>
> The patch for the newest kernel branch is below.
>
> Best Regards
>
multiple machines.
Regards
Yan, Zheng--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
pathlen1 + pathlen2 + 2*(1 + sizeof(u32) + sizeof(u64)) +
> - sizeof(struct timespec);
> + sizeof(struct ceph_timespec);
>
> /* calculate (max) length for cap releases */
> len += sizeof(struct ceph_mds_request_release) *
>
Applied. t
0)) {
> -ret = n;
> +n = len;
> +pages = dio_alloc_pagev(from, len, false, &start,
> +&num_pages);
> +if (IS_ERR(pages)) {
> ceph_osdc_put_request(req);
> +ret = PTR_ERR(pages);
> brea
ncapsulate
> ceph_x_authorizer cleanup and switch to it. This fixes ceph_x_destroy(),
> which currently always leaks key and ceph_x_build_authorizer() error
> paths.
>
> Cc: Yan, Zheng
> Signed-off-by: Ilya Dryomov
> ---
> net/ceph/auth_x.c | 28 +-
On Mon, Oct 26, 2015 at 6:31 PM, Jevon Qiao wrote:
> Hi Sage,
>
> Here comes another question, does ceph-fuse support Unix OS(like HP-UNIX or
> AIX)?
It supports OSX and FreeBSD. (I tested it a few weeks ago. current
development branch may require some minor modification)
>
> Thanks,
> Jevon
>
>
On Mon, Nov 2, 2015 at 12:28 PM, Jaze Lee wrote:
> Hello,
>I find only ceph.client.admin can mount cephfs.
>
> [root@ceph-base-0 ceph]# ceph auth get client.cephfs_user
> exported keyring for client.cephfs_user
> [client.cephfs_user]
> key = AQDZ3DZWR7nqBxAAzSoU/yRz1oJsOYdYrTAzcw==
> caps mds
ceph_common.c | 18 +-
> net/ceph/messenger.c | 32
> net/ceph/osd_client.c | 14 ++++--
> 7 files changed, 53 insertions(+), 53 deletions(-)
>
Reviewed-by: Yan, Zheng
--
To unsubscribe from this list: send the lin
le32_to_cpu(head->op) ==
> CEPH_MDS_OP_RMSNAP,
> + &realm);
> downgrade_write(&mdsc->snap_rwsem);
> } else {
> down_read(&mdsc->snap_rwsem);
> }
> +
> + if (err)
> +
ceph_fill_dirfrag(d_inode(parent), rinfo->dir_dir);
> + if (rinfo->dir_dir) {
> + err = ceph_fill_dirfrag(d_inode(parent),
> rinfo->dir_dir);
> + if (err)
> + goto out;
> + }
>
turn (v & ceph_frag_mask(f)) == ceph_frag_value(f);
> }
> --
> 1.9.1
both applied
Thanks
Yan, Zheng
>
>
>
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
ase this value to see the
> performance difference, but are there other options we can try to increase
> single read performance?
>
try setting client_readahead_max_bytes to 4M
Yan, Zheng
--
To unsubscribe from this list: send the line
ceph client log, we found each read
> request's size (ll_read) is limited to 128KB, which should be the limitation
> of kernel fuse's FUSE_MAX_PAGES_PER_REQ = 32. We may try to increase this
> value to see the performance difference, but are there other options we can
> try to i
without-tcmalloc --without-libaio
--without-libxfs
gmake
I don't know extact list of packages dependencies. But ./configure
should tell you what is missing.
Yan, Zheng
>
>
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a mess
see https://github.com/ceph/ceph/pull/6770. The code can be compiled
on FreeBSD/OSX, most client programs can connect to ceph servers on
Linux.
Regards
Yan. Zheng
On Wed, Dec 2, 2015 at 2:43 AM, Willem Jan Withagen wrote:
> On 1-12-2015 19:36, Sage Weil wrote:
>>
>> On Tue, 1
On Thu, Dec 3, 2015 at 4:52 AM, Willem Jan Withagen wrote:
> On 2-12-2015 15:13, Yan, Zheng wrote:
>> see https://github.com/ceph/ceph/pull/6770. The code can be compiled
>> on FreeBSD/OSX, most client programs can connect to ceph servers on
>> Linux.
>
> Hi,
>
On Mon, Dec 7, 2015 at 10:51 AM, Wuxiangwei wrote:
> Hi, Everyone
>
> Recently I'm trying to figure out how to use ceph-fuse. If we mount cephfs as
> the kernel client, there is a 'cephfs' command tool (though it seems to be
> 'deprecated') with 'map' and 'show_location' commands to show the RAD
Tel : 0571-86760875
> 2014 UIS 2, TEAM BORE
>
>
> -邮件原件-
> 发件人: Yan, Zheng [mailto:uker...@gmail.com]
> 发送时间: 2015年12月7日 11:22
> 收件人: wuxiangwei 09660 (RD)
> 抄送: ceph-devel@vger.kernel.org; ceph-us...@lists.ceph.com
> 主题: Re: how to see file object-mappin
://github.com/ceph/ceph-client.git wip-mds-cluster
Regards
Yan, Zheng
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Signed-off-by: Yan, Zheng
---
fs/ceph/mds_client.c | 19 +++
fs/ceph/strings.c| 2 ++
include/linux/ceph/ceph_fs.h | 2 ++
3 files changed, 23 insertions(+)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 1fd655a..7c00dd5 100644
--- a/fs/ceph
Version 3 cap import message includes the ID of the exported
caps. It allow us to remove the exported caps if we still haven't
received the corresponding cap export message.
We remove the exported caps because they are stale, keeping them
can compromise consistence.
Signed-off-by: Yan,
- don't trim auth cap if there are flusing caps
- don't trim auth cap if any 'write' cap is wanted
- allow trimming non-auth cap even if the inode is dirty
Signed-off-by: Yan, Zheng
---
fs/ceph/mds_client.c | 17 +++--
1 file changed, 11 insertions(+), 6 deleti
Signed-off-by: Yan, Zheng
---
fs/ceph/mds_client.c | 51 ---
fs/ceph/mds_client.h | 2 ++
2 files changed, 38 insertions(+), 15 deletions(-)
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 7c00dd5..f4f050a 100644
--- a/fs/ceph
d-off-by: Yan, Zheng
---
fs/ceph/caps.c | 220
fs/ceph/inode.c | 4 +-
fs/ceph/super.h | 4 +-
3 files changed, 146 insertions(+), 82 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 44373dc..18c1dc3 100644
--- a/fs/ceph/c
handle following sequence of events:
- non-auth MDS revokes Fc cap. queue invalidate work
- auth MDS issues Fc cap through request reply. i_rdcache_gen gets
increased.
- invalidate work runs. it finds i_rdcache_revoking != i_rdcache_gen,
so it does nothing.
Signed-off-by: Yan, Zheng
---
fs
Some inodes in readdir reply may have no caps. Getattr mds request
for these inodes can return -ESTALE. The fix is consider dentry that
links to inode with no caps as invalid. Invalid dentry causes a
lookup request to send to the mds, the MDS will send caps back.
Signed-off-by: Yan, Zheng
Signed-off-by: Yan, Zheng
---
include/linux/ceph/ceph_features.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/linux/ceph/ceph_features.h
b/include/linux/ceph/ceph_features.h
index 5f42e44..d21b34d 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include
Signed-off-by: Yan, Zheng
---
fs/ceph/caps.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 1012099..2c39d9f 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -628,7 +628,7 @@ retry:
cap->cap_id = cap_id;
cap->
Send requests that operate on path to directory's auth MDS if
mode == USE_AUTH_MDS. Always retry using the auth MDS if got
-ESTALE reply from non-auth MDS. Also clean up the code that
handles auth MDS change.
Signed-off-by: Yan, Zheng
---
fs/ceph/mds_client.c
auth cap may change after releasing the i_ceph_lock
Signed-off-by: Yan, Zheng
---
fs/ceph/caps.c | 16
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 80dad0d..1012099 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
On 01/21/2014 01:22 PM, Sage Weil wrote:
> On Tue, 21 Jan 2014, Yan, Zheng wrote:
>> Version 3 cap import message includes the ID of the exported
>> caps. It allow us to remove the exported caps if we still haven't
>> received the corresponding cap export message.
>>
return -EEXIST if XATTR_CREATE is set and xattr alread exists.
return -ENODATA if XATTR_REPLACE is set but xattr does not exist.
Signed-off-by: Yan, Zheng
---
fs/ceph/xattr.c | 38 ++
1 file changed, 26 insertions(+), 12 deletions(-)
diff --git a/fs/ceph
If acl is equivalent to file mode permission bits, ceph_set_acl()
needs to remove any existing acl xattr. Use __ceph_setxattr() to
handle both setting and removing acl xattr cases, it doesn't return
-ENODATA when there is no acl xattr.
Signed-off-by: Yan, Zheng
---
fs/ceph/acl.c | 6 +---
Signed-off-by: Yan, Zheng
---
fs/ceph/dir.c | 9 +
fs/ceph/file.c | 1 +
2 files changed, 6 insertions(+), 4 deletions(-)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 6da4df8..3bbd0eb 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -695,9 +695,8 @@ static int ceph_mknod(struct
Signed-off-by: Yan, Zheng
---
fs/ceph/xattr.c | 9 +
1 file changed, 9 insertions(+)
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 28f9793..6ed0e5a 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -12,6 +12,9 @@
#define XATTR_CEPH_PREFIX "ceph."
Signed-off-by: Yan, Zheng
---
fs/ceph/xattr.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 6ed0e5a..79f9c12 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -463,7 +463,7 @@ static int __remove_xattr(struct ceph_inode_info *ci
On Tue, Feb 11, 2014 at 10:47 PM, Alex Elder wrote:
> On 02/10/2014 11:30 PM, Yan, Zheng wrote:
>> Signed-off-by: Yan, Zheng
>
> You really need to explain better under what circumstances
> a zero-size xattr is getting removed.
>
> But apparently it's only when yo
On 02/12/2014 01:25 AM, Alex Elder wrote:
> On 02/11/2014 09:10 AM, Yan, Zheng wrote:
>> On Tue, Feb 11, 2014 at 10:47 PM, Alex Elder wrote:
>>> On 02/10/2014 11:30 PM, Yan, Zheng wrote:
>>>> Signed-off-by: Yan, Zheng
>>>
>>> You really need to ex
On 02/12/2014 10:43 AM, Sage Weil wrote:
> On Wed, 12 Feb 2014, Yan, Zheng wrote:
>> On 02/12/2014 01:25 AM, Alex Elder wrote:
>>> On 02/11/2014 09:10 AM, Yan, Zheng wrote:
>>>> On Tue, Feb 11, 2014 at 10:47 PM, Alex Elder wrote:
>>>>> On 02/10/2014
checking if a given dentry is after the
the position of readdir, __dcache_readdir() compares numerical value
of frag_t directly. This is wrong, it should use ceph_frag_compare().
Signed-off-by: Yan, Zheng
---
fs/ceph/dir.c | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
diff
updated patch
---
>From 9c517a5af5af472a0bee9c900b7df400b10f3098 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng"
Date: Tue, 11 Feb 2014 12:55:05 +0800
Subject: [PATCH 4/5] ceph: add missing init_acl() for mkdir() and
atomic_open()
Signed-off-by: Yan, Zheng
---
fs/cep
On 02/14/2014 01:46 PM, Guangliang Zhao wrote:
> On Tue, Feb 11, 2014 at 01:30:11PM +0800, Yan Zheng wrote:
>
> This looks good, but there maybe some hiccups, see below.
>
> The symlink also need ceph_init_acl() as Alex mentioned, I have
> add it in the patch.
wi
This doesn't make sense neither.
Old_offset should be ceph_make_fpos(fi->frag, fi->next_offset).
Signed-off-by: Yan, Zheng
---
fs/ceph/dir.c | 12 ++--
fs/ceph/super.h | 2 +-
2 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 4
When changing readdir postion, fi->next_offset should be set to 0
if the new postion is not in the first dirfrag.
Signed-off-by: Yan, Zheng
---
fs/ceph/dir.c | 9 ++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index a7eaf96..8ce8833 100
On Fri, Feb 28, 2014 at 10:05 PM, Alex Elder wrote:
> On 02/27/2014 03:07 AM, Yan, Zheng wrote:
>> Comparing offset with inode->i_sb->s_maxbytes doesn't make sense for
>> directory. For a fragmented directory, offset (frag_t, off) can be
>> larger than inode->
MDS handles LOOKUPHASH and LOOKUPINO MDS requests in the same way.
So __cfh_to_dentry() is redundant.
Signed-off-by: Yan, Zheng
---
fs/ceph/export.c | 167 +++
1 file changed, 32 insertions(+), 135 deletions(-)
diff --git a/fs/ceph/export.c b
The callback uses LOOKUPPARENT MDS request to find parent.
Signed-off-by: Yan, Zheng
---
fs/ceph/export.c | 44
1 file changed, 44 insertions(+)
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 017af26..817d370 100644
--- a/fs/ceph/export.c
Signed-off-by: Yan, Zheng
---
fs/ceph/debugfs.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 6d59006..a9b5103 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -93,6 +93,8 @@ static int mdsc_show(struct seq_file *s, void *p
ceph_fh_to_parent() finds the inode that corresponds to the 'ino' field
of struct ceph_nfs_confh. This is wrong, it should find the inode that
corresponds to the 'parent_ino' field.
Signed-off-by: Yan, Zheng
---
fs/ceph/export.c | 38 +
eaddir 'offset' if
the readdir reply is different than the requested one.
Signed-off-by: Yan, Zheng
---
fs/ceph/dir.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 94b80f4..ff2864a 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -322,9 +3
Signed-off-by: Yan, Zheng
---
fs/ceph/locks.c | 12
1 file changed, 12 insertions(+)
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 133e006..f91a569a 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -87,6 +87,12 @@ int ceph_lock(struct file *file, int cmd, struct
VFS does not directly pass the flock's operation to the filesystem's
flock callback directly. It translates the flock's operation to posix
lock's command.
Signed-off-by: Yan, Zheng
---
fs/ceph/locks.c | 21 +
1 file changed, 9 insertions(+), 12 deletions
On 03/06/2014 01:17 AM, Sage Weil wrote:
> On Sat, 1 Mar 2014, Yan, Zheng wrote:
>> ceph_fh_to_parent() finds the inode that corresponds to the 'ino' field
>> of struct ceph_nfs_confh. This is wrong, it should find the inode that
>> corresponds to the 'parent_
Set WANT_DENTRY flag for the LOOKUPINO MDS request. The flag makes
MDS reply contain dentry trace.
Signed-off-by: Yan, Zheng
---
fs/ceph/export.c | 45 +
fs/ceph/inode.c | 51 ++-
2 files changed, 95
From: David Howells
Make __d_materialise_dentry() set the materialised dentry name correctly by
flipping the arguments to switch_names().
switch_names() is lazy: if both names are internal to their dentries, it'll
overwrite that of the first dentry with that of the second, and won't update
that
On 03/07/2014 12:45 AM, Sage Weil wrote:
> On Thu, 6 Mar 2014, Yan, Zheng wrote:
>> Set WANT_DENTRY flag for the LOOKUPINO MDS request. The flag makes
>> MDS reply contain dentry trace.
>>
>> Signed-off-by: Yan, Zheng
>&
e this information, or
>
> - change getcwd to use LOOKUPINO + WANT_DENTRY to make it work.
I prefer to change getcwd. The problem of old LOOKUPPARENT semantic is that
client can't lock the parent inode in advance, This breaks VFS locking rules
for lookup.
I added the getcwd fix to h
Changes since v1:
make ceph_fh_to_parent() use LOOKUPPARENT to find parent dentry.
if LOOKUPPARENT fails, retry finding the dentry that corresponds
to the 'parent_ino'
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majord...@vger.kernel.org
M
ceph_fh_to_parent() returns dentry that corresponds to the 'ino' field
of struct ceph_nfs_confh. This is wrong, it should return dentry that
corresponds to the 'parent_ino' field.
Signed-off-by: Yan, Zheng
---
fs/ceph/export.c | 42 +
The callback uses LOOKUPPARENT MDS request to find parent.
Signed-off-by: Yan, Zheng
---
fs/ceph/export.c | 53 +
1 file changed, 53 insertions(+)
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 976d341..3794255 100644
--- a/fs/ceph
MDS handles LOOKUPHASH and LOOKUPINO MDS requests in the same way.
So __cfh_to_dentry() is redundant.
Signed-off-by: Yan, Zheng
---
fs/ceph/export.c | 167 +++
1 file changed, 32 insertions(+), 135 deletions(-)
diff --git a/fs/ceph/export.c b
Signed-off-by: Yan, Zheng
---
fs/ceph/debugfs.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 8c6f313..16b54aa 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -93,6 +93,8 @@ static int mdsc_show(struct seq_file *s, void *p
Set WANT_DENTRY flag for the LOOKUPINO MDS request. The flag makes
MDS reply contain dentry trace.
Signed-off-by: Yan, Zheng
---
fs/ceph/export.c | 45 +
fs/ceph/inode.c | 51 ++-
2 files changed, 95
how about the below patch and corresponding mds change in
https://github.com/ceph/ceph/commit/617ce6761edd7264893f3638c33fd229c71751a0
Regards
Yan, Zheng
---
>From 0fa1971741b1d3c236ee6fa3a7feb5a74fbd7f2f Mon Sep 17 00:00:00 2001
From: "Yan, Zheng"
Date: Thu, 6 Mar 2014 16:40:32
Only auth MDS can't issue write caps to clients, so don't consider
write caps registered with non-auth MDS as valid.
Signed-off-by: Yan, Zheng
---
fs/ceph/caps.c | 5 -
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 1754338..d9ef
e
in 'open' request reply is equal to the cached inode's version.
- client requests new max size. The MDS ignores the request because
it does not affect client's write range
Signed-off-by: Yan, Zheng
---
fs/ceph/inode.c | 16
1 file changed, 8 insertio
id_namespace' into consideration when checking conflict
locks.
Signed-off-by: Yan, Zheng
---
fs/ceph/locks.c | 44
include/linux/ceph/ceph_fs.h | 4 ++--
2 files changed, 26 insertions(+), 22 deletions(-)
diff --git a/fs/ceph/loc
On 03/10/2014 09:43 AM, Sage Weil wrote:
> On Sat, 8 Mar 2014, Yan, Zheng wrote:
>> how about the below patch and corresponding mds change in
>> https://github.com/ceph/ceph/commit/617ce6761edd7264893f3638c33fd229c71751a0
>
> I like this better, thanks!
>
> O
On 03/10/2014 09:49 AM, Sage Weil wrote:
> On Sat, 8 Mar 2014, Yan, Zheng wrote:
>> how about the below patch and corresponding mds change in
>> https://github.com/ceph/ceph/commit/617ce6761edd7264893f3638c33fd229c71751a0
>>
>> Regards
>&
On 03/10/2014 12:12 PM, Sage Weil wrote:
> On Mon, 10 Mar 2014, Yan, Zheng wrote:
>> On 03/10/2014 09:49 AM, Sage Weil wrote:
>>> On Sat, 8 Mar 2014, Yan, Zheng wrote:
>>>> how about the below patch and corresponding mds change in
>>&g
On 03/10/2014 12:21 PM, Sage Weil wrote:
> On Mon, 10 Mar 2014, Yan, Zheng wrote:
>> flock and posix lock should use fl->fl_file instead of process ID
>> as owner identifier. (posix lock uses fl->fl_owner, fl->fl_owner
>> is usually equal to fl->fl_file in most
On 03/10/2014 12:42 PM, Sage Weil wrote:
> On Mon, 10 Mar 2014, Yan, Zheng wrote:
>> On 03/10/2014 12:21 PM, Sage Weil wrote:
>>> On Mon, 10 Mar 2014, Yan, Zheng wrote:
>>>> flock and posix lock should use fl->fl_file instead of process ID
>>>> as ow
the flock code to not
take the 'pid_namespace' into consideration when checking conflict
locks.
Signed-off-by: Yan, Zheng
---
fs/ceph/locks.c | 62 ++--
fs/ceph/super.c | 1 +
fs/ceph/super.h | 1 +
include/lin
x27; field. MDS can
use that bit to distinguish between old and new clients.
The MDS counterpart of this patch modifies the flock code to not
take the 'pid_namespace' into consideration when checking conflict
locks.
Signed-off-by: Yan, Zheng
---
fs/ceph/locks.c | 61 +
On 03/14/2014 08:44 AM, Sage Weil wrote:
> Hey Zheng,
>
> What workloads have you been testing against NFS?
kernel build, fsstress, dbench, blogbench.
Regards
Yan, Zheng
Do you mind adding them
> to the knfs tests in ceph-qa-suite? I suggest we add anything that you
>
When there is no more data, ceph_msg_data_pagelist_advance() should
not move on to the next page.
Signed-off-by: Yan, Zheng
---
net/ceph/messenger.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 30efc5c..8859f2e 100644
--- a/net/ceph
When there is no more data, ceph_msg_data_{pages,pagelist}_advance()
should not move on to the next page.
Signed-off-by: Yan, Zheng
---
net/ceph/messenger.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 30efc5c..4f55f9c 100644
--- a
On Sun, Mar 23, 2014 at 7:10 AM, Alex Elder wrote:
> On 03/22/2014 05:54 PM, Yan, Zheng wrote:
>> When there is no more data, ceph_msg_data_pagelist_advance() should
>> not move on to the next page.
>
> Without looking very hard at this, this looks right.
> Does ceph_msg_d
send_mds_reconnect() may call discard_cap_releases() after all
release messages have been dropped by cleanup_cap_releases()
Signed-off-by: Yan, Zheng
---
fs/ceph/mds_client.c | 21 -
1 file changed, 12 insertions(+), 9 deletions(-)
diff --git a/fs/ceph/mds_client.c b/fs
Signed-off-by: Yan, Zheng
---
fs/ceph/xattr.c | 34 +-
1 file changed, 25 insertions(+), 9 deletions(-)
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 2dbd668..28549d5 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -64,32 +64,48 @@ static bool
This avoids 'cp -a' modifying layout of new files/directories.
Signed-off-by: Yan, Zheng
---
fs/ceph/xattr.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 28549d5..c9c2b88 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ce
es 18 minutes. After this operation the MDS uses ~10 GB of
>> memory (10k per directory for one entry).
>
> Hmm. That's more than I would expect, but not impossibly so if the MDS
> was having trouble keeping the relevant directories in-memory. We have
> not done any optimizati
fix this issue
---
>From 15a26a1d78f24a4a83a2ee319ad10701eb68cd56 Mon Sep 17 00:00:00 2001
From: "Yan, Zheng"
Date: Sat, 29 Mar 2014 13:41:15 +0800
Subject: [PATCH] ceph: preallocate buffer for readdir reply
Preallocate buffer for readdir reply. Limit number of entries in
readdir
Preallocate buffer for readdir reply. Limit number of entries in
readdir reply according to the buffer size.
Signed-off-by: Yan, Zheng
---
fs/ceph/dir.c| 10
fs/ceph/mds_client.c | 66
fs/ceph/mds_client.h | 4 +++-
3 files
1 - 100 of 708 matches
Mail list logo
