I tried "echo 3 > /proc/sys/vm/drop_caches" and dentry_pinned_count dropped.
Thanks for your help.
On Thu, Apr 30, 2015 at 11:34 PM Yan, Zheng <ukernel@xxxxxxxxx> wrote:
On Thu, Apr 30, 2015 at 4:37 PM, Dexter Xiong <dxtxiong@xxxxxxxxx> wrote:
> Hi,
> I got these message when I remount:
> 2015-04-30 15:47:58.199837 7f9ad30a27c0 -1 asok(0x3c83480)
> AdminSocketConfigObs::init: failed: AdminSocket::bind_and_listen: failed to
> bind the UNIX domain socket to '/var/run/ceph/ceph-client.admin.asok': (17)
> File exists
> fuse: bad mount point `ceph-fuse': No such file or directory
> ceph-fuse[2576]: fuse failed to initialize
> 2015-04-30 15:47:58.199980 7f9ad30a27c0 -1 init, newargv = 0x3ca9b00
> newargc=14
> 2015-04-30 15:47:58.200020 7f9ad30a27c0 -1 fuse_parse_cmdline failed.
> ceph-fuse[2574]: mount failed: (22) Invalid argument.
>
> It seems that FUSE doesn't support remount? This link is google result.
>
please try "echo 3 > /proc/sys/vm/drop_caches". check if the pinned
dentries count drops after executing the command.
Regards
Yan, Zheng
> I am using ceph-dokan too. And I got the similar memory problem. I don't
> know if it is the same problem. I switched to use kernel module and Samba to
> replace previous solution temporarily.
> I'm trying to read and track the ceph & ceph-dokan source code to find
> more useful information.
>
>
> I don't know if my previous email arrived the list(Maybe the attachment
> is too large). Here is its content:
>
> I wrote a test case with Python:
> '''
> import os
> for i in range(200):
> dir_name = '/srv/ceph_fs/test/d%s'%i
> os.mkdir(dir_name)
> for j in range(3):
> with open('%s/%s'%(dir_name, j), 'w') as f:
> f.write('0')
> '''
>
> The output of status command after test on a fresh mount:
> {
> "metadata": {
> "ceph_sha1": "e4bfad3a3c51054df7e537a724c8d0bf9be972ff",
> "ceph_version": "ceph version 0.94.1
> (e4bfad3a3c51054df7e537a724c8d0bf9be972ff)",
> "entity_id": "admin",
> "hostname": "local-share-server",
> "mount_point": "\/srv\/ceph_fs"
> },
> "dentry_count": 204,
> "dentry_pinned_count": 201,
> "inode_count": 802,
> "mds_epoch": 25,
> "osd_epoch": 177,
> "osd_epoch_barrier": 176
> }
> It seems that all pinned dentrys are directories from dump cache command
> output.
>
> Attachment is a package of debug log and dump cache content.
>
>
> On Thu, Apr 30, 2015 at 2:55 PM Yan, Zheng <ukernel@xxxxxxxxx> wrote:
>>
>> On Wed, Apr 29, 2015 at 4:33 PM, Dexter Xiong <dxtxiong@xxxxxxxxx> wrote:
>> > The output of status command of fuse daemon:
>> > "dentry_count": 128966,
>> > "dentry_pinned_count": 128965,
>> > "inode_count": 409696,
>> > I saw the pinned dentry is nearly the same as dentry.
>> > So I enabled debug log(debug client = 20/20) and read Client.cc source
>> > code in general. I found that an entry will not be trimed if it is
>> > pinned.
>> > But how can I unpin dentrys?
>>
>> Maybe these dentries are pinned by fuse kernel module (ceph-fuse does
>> not try trimming kernel cache when its cache size >
>> client_cache_size). Could you please run "mount -o remount <mount
>> point>", then run the status command again. check if number of pinned
>> dentries drops.
>>
>> Regards
>> Yan, Zheng
>>
>>
>> >
>> > On Wed, Apr 29, 2015 at 12:19 PM Dexter Xiong <dxtxiong@xxxxxxxxx>
>> > wrote:
>> >>
>> >> I tried set client cache size = 100, but it doesn't solve the problem.
>> >> I tested ceph-fuse with kernel version 3.13.0-24 3.13.0-49 and
>> >> 3.16.0-34.
>> >>
>> >>
>> >>
>> >> On Tue, Apr 28, 2015 at 7:39 PM John Spray <john.spray@xxxxxxxxxx>
>> >> wrote:
>> >>>
>> >>>
>> >>>
>> >>> On 28/04/2015 06:55, Dexter Xiong wrote:
>> >>> > Hi,
>> >>> > I've deployed a small hammer cluster 0.94.1. And I mount it via
>> >>> > ceph-fuse on Ubuntu 14.04. After several hours I found that the
>> >>> > ceph-fuse process crashed. The end is the crash log from
>> >>> > /var/log/ceph/ceph-client.admin.log. The memory cost of ceph-fuse
>> >>> > process was huge(more than 4GB) when it crashed.
>> >>> > Then I did some test and found these actions will increase
>> >>> > memory
>> >>> > cost of ceph-fuse rapidly and the memory cost never seem to
>> >>> > decrease:
>> >>> >
>> >>> > * rsync command to sync small files(rsync -a /mnt/some_small
>> >>> > /srv/ceph)
>> >>> > * chown command/ chmod command(chmod 775 /srv/ceph -R)
>> >>> >
>> >>> > But chown/chmod command on accessed files will not increase the
>> >>> > memory
>> >>> > cost.
>> >>> > It seems that ceph-fuse caches the file nodes but never releases
>> >>> > them.
>> >>> > I don't know if there is an option to control the cache size. I
>> >>> > set mds cache size = 2147483647 option to improve the performance of
>> >>> > mds, and I tried to set mds cache size = 1000 at client side but it
>> >>> > doesn't effect the result.
>> >>>
>> >>> The setting for client-side cache limit is "client cache size",
>> >>> default
>> >>> is 16384
>> >>>
>> >>> What kernel version are you using on the client? There have been some
>> >>> issues with cache trimming vs. fuse in recent kernels, but we thought
>> >>> we
>> >>> had workarounds in place...
>> >>>
>> >>> Cheers,
>> >>> John
>> >>>
>> >
>> > _______________________________________________
>> > ceph-users mailing list
>> > ceph-users@xxxxxxxxxxxxxx
>> > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
>> >
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
