Re: [Gluster-users] [EXTERNAL] Re: New Gluster volume (10.3) not healing symlinks after brick offline
Hi Eli, Thanks for the response. I had hoped for a simple fix here, but I think perhaps there isn't one. I have built this as a part of a new environment, eventually replacing a much older system built with Gluster 3.10 (yes - that old). I appreciate the warning about 10.3 and will run some comparative load testing against it and 9.5 both. - Matt On Fri, Feb 24, 2023 at 8:46 AM Eli V wrote: > I've seen issues with symlinks failing to heal as well. I never found > a good solution on the glusterfs side of things. Most reliable fix I > found is just rm and recreate the symlink in the fuse volume itself. > Also, I'd strongly suggest heavy load testing before upgrading to 10.3 > in production, after upgrading from 9.5 -> 10.3 I've seen frequent > brick process crashes(glusterfsd), whereas 9.5 was quite stable. > > On Mon, Jan 23, 2023 at 3:58 PM Matt Rubright wrote: > > > > Hi friends, > > > > I have recently built a new replica 3 arbiter 1 volume on 10.3 servers > and have been putting it through its paces before getting it ready for > production use. The volume will ultimately contain about 200G of web > content files shared among multiple frontends. Each will use the gluster > fuse client to connect. > > > > What I am experiencing sounds very much like this post from 9 years ago: > https://lists.gnu.org/archive/html/gluster-devel/2013-12/msg00103.html > > > > In short, if I perform these steps I can reliably end up with symlinks > on the volume which will not heal either by initiating a 'full heal' from > the cluster or using a fuse client to read each file: > > > > 1) Verify that all nodes are healthy, the volume is healthy, and there > are no items needing to be healed > > 2) Cleanly shut down one server hosting a brick > > 3) Copy data, including some symlinks, from a fuse client to the volume > > 4) Bring the brick back online and observe the number and type of items > needing to be healed > > 5) Initiate a full heal from one of the nodes > > 6) Confirm that while files and directories are healed, symlinks are not > > > > Please help me determine if I have improper expectations here. I have > some basic knowledge of managing gluster volumes, but I may be > misunderstanding intended behavior. > > > > Here is the volume info and heal data at each step of the way: > > > > *** Verify that all nodes are healthy, the volume is healthy, and there > are no items needing to be healed *** > > > > # gluster vol info cwsvol01 > > > > Volume Name: cwsvol01 > > Type: Replicate > > Volume ID: 7b28e6e6-4a73-41b7-83fe-863a45fd27fc > > Status: Started > > Snapshot Count: 0 > > Number of Bricks: 1 x (2 + 1) = 3 > > Transport-type: tcp > > Bricks: > > Brick1: glfs02-172-20-1:/data/brick01/cwsvol01 > > Brick2: glfs01-172-20-1:/data/brick01/cwsvol01 > > Brick3: glfsarb01-172-20-1:/data/arb01/cwsvol01 (arbiter) > > Options Reconfigured: > > performance.client-io-threads: off > > nfs.disable: on > > transport.address-family: inet > > storage.fips-mode-rchecksum: on > > cluster.granular-entry-heal: on > > > > # gluster vol status > > Status of volume: cwsvol01 > > Gluster process TCP Port RDMA Port Online > Pid > > > -- > > Brick glfs02-172-20-1:/data/brick01/cwsvol0 > > 1 50253 0 Y > 1397 > > Brick glfs01-172-20-1:/data/brick01/cwsvol0 > > 1 56111 0 Y > 1089 > > Brick glfsarb01-172-20-1:/data/arb01/cwsvol > > 01 54517 0 Y > 118704 > > Self-heal Daemon on localhost N/A N/AY > 1413 > > Self-heal Daemon on glfs01-172-20-1 N/A N/AY > 3490 > > Self-heal Daemon on glfsarb01-172-20-1 N/A N/AY > 118720 > > > > Task Status of Volume cwsvol01 > > > -- > > There are no active volume tasks > > > > # gluster vol heal cwsvol01 info summary > > Brick glfs02-172-20-1:/data/brick01/cwsvol01 > > Status: Connected > > Total Number of entries: 0 > > Number of entries in heal pending: 0 > > Number of entries in split-brain: 0 > > Number of entries possibly healing: 0 > > > > Brick glfs01-172-20-1:/data/brick01/cwsvol01 > > Status: Connected > > Total Number of entries: 0 > > Number of entries in heal pending: 0 >
[Gluster-users] New Gluster volume (10.3) not healing symlinks after brick offline
Hi friends, I have recently built a new replica 3 arbiter 1 volume on 10.3 servers and have been putting it through its paces before getting it ready for production use. The volume will ultimately contain about 200G of web content files shared among multiple frontends. Each will use the gluster fuse client to connect. What I am experiencing sounds very much like this post from 9 years ago: https://lists.gnu.org/archive/html/gluster-devel/2013-12/msg00103.html In short, if I perform these steps I can reliably end up with symlinks on the volume which will not heal either by initiating a 'full heal' from the cluster or using a fuse client to read each file: 1) Verify that all nodes are healthy, the volume is healthy, and there are no items needing to be healed 2) Cleanly shut down one server hosting a brick 3) Copy data, including some symlinks, from a fuse client to the volume 4) Bring the brick back online and observe the number and type of items needing to be healed 5) Initiate a full heal from one of the nodes 6) Confirm that while files and directories are healed, symlinks are not Please help me determine if I have improper expectations here. I have some basic knowledge of managing gluster volumes, but I may be misunderstanding intended behavior. Here is the volume info and heal data at each step of the way: *** Verify that all nodes are healthy, the volume is healthy, and there are no items needing to be healed *** # gluster vol info cwsvol01 Volume Name: cwsvol01 Type: Replicate Volume ID: 7b28e6e6-4a73-41b7-83fe-863a45fd27fc Status: Started Snapshot Count: 0 Number of Bricks: 1 x (2 + 1) = 3 Transport-type: tcp Bricks: Brick1: glfs02-172-20-1:/data/brick01/cwsvol01 Brick2: glfs01-172-20-1:/data/brick01/cwsvol01 Brick3: glfsarb01-172-20-1:/data/arb01/cwsvol01 (arbiter) Options Reconfigured: performance.client-io-threads: off nfs.disable: on transport.address-family: inet storage.fips-mode-rchecksum: on cluster.granular-entry-heal: on # gluster vol status Status of volume: cwsvol01 Gluster process TCP Port RDMA Port Online Pid -- Brick glfs02-172-20-1:/data/brick01/cwsvol0 1 50253 0 Y 1397 Brick glfs01-172-20-1:/data/brick01/cwsvol0 1 56111 0 Y 1089 Brick glfsarb01-172-20-1:/data/arb01/cwsvol 01 54517 0 Y 118704 Self-heal Daemon on localhost N/A N/AY 1413 Self-heal Daemon on glfs01-172-20-1 N/A N/AY 3490 Self-heal Daemon on glfsarb01-172-20-1 N/A N/AY 118720 Task Status of Volume cwsvol01 -- There are no active volume tasks # gluster vol heal cwsvol01 info summary Brick glfs02-172-20-1:/data/brick01/cwsvol01 Status: Connected Total Number of entries: 0 Number of entries in heal pending: 0 Number of entries in split-brain: 0 Number of entries possibly healing: 0 Brick glfs01-172-20-1:/data/brick01/cwsvol01 Status: Connected Total Number of entries: 0 Number of entries in heal pending: 0 Number of entries in split-brain: 0 Number of entries possibly healing: 0 Brick glfsarb01-172-20-1:/data/arb01/cwsvol01 Status: Connected Total Number of entries: 0 Number of entries in heal pending: 0 Number of entries in split-brain: 0 Number of entries possibly healing: 0 *** Cleanly shut down one server hosting a brick *** *** Copy data, including some symlinks, from a fuse client to the volume *** # gluster vol heal cwsvol01 info summary Brick glfs02-172-20-1:/data/brick01/cwsvol01 Status: Transport endpoint is not connected Total Number of entries: - Number of entries in heal pending: - Number of entries in split-brain: - Number of entries possibly healing: - Brick glfs01-172-20-1:/data/brick01/cwsvol01 Status: Connected Total Number of entries: 810 Number of entries in heal pending: 810 Number of entries in split-brain: 0 Number of entries possibly healing: 0 Brick glfsarb01-172-20-1:/data/arb01/cwsvol01 Status: Connected Total Number of entries: 810 Number of entries in heal pending: 810 Number of entries in split-brain: 0 Number of entries possibly healing: 0 *** Bring the brick back online and observe the number and type of entities needing to be healed *** # gluster vol heal cwsvol01 info summary Brick glfs02-172-20-1:/data/brick01/cwsvol01 Status: Connected Total Number of entries: 0 Number of entries in heal pending: 0 Number of entries in split-brain: 0 Number of entries possibly healing: 0 Brick glfs01-172-20-1:/data/brick01/cwsvol01 Status: Connected Total Number of entries: 769 Number of entries in heal pending: 769 Number of entries in split-brain: 0 Number of entries possibly healing: 0 Brick glfsarb01-172-20-1:/data/arb01/cwsvol01 Status: Connected Total Number of
Re: [Gluster-users] Unable to create new files or folders using samba and vfs_glusterfs
I've been using these for a few weeks now without any issues, thank you! -Original Message- From: gluster-users-boun...@gluster.org On Behalf Of Matt Waymack Sent: Thursday, December 27, 2018 10:56 AM To: Diego Remolina Cc: gluster-users@gluster.org List Subject: Re: [Gluster-users] Unable to create new files or folders using samba and vfs_glusterfs OK, I'm back from the holiday and updated using the following packages: libsmbclient-4.8.3-4.el7.0.1.x86_64.rpm libwbclient-4.8.3-4.el7.0.1.x86_64.rpm samba-4.8.3-4.el7.0.1.x86_64.rpm samba-client-4.8.3-4.el7.0.1.x86_64.rpm samba-client-libs-4.8.3-4.el7.0.1.x86_64.rpm samba-common-4.8.3-4.el7.0.1.noarch.rpm samba-common-libs-4.8.3-4.el7.0.1.x86_64.rpm samba-common-tools-4.8.3-4.el7.0.1.x86_64.rpm samba-libs-4.8.3-4.el7.0.1.x86_64.rpm samba-vfs-glusterfs-4.8.3-4.el7.0.1.x86_64.rpm First impressions are good! We're able to create files/folders. I'll keep you updated with stability. Thank you! -Original Message- From: Diego Remolina Sent: Thursday, December 20, 2018 1:36 PM To: Matt Waymack Cc: gluster-users@gluster.org List Subject: Re: [Gluster-users] Unable to create new files or folders using samba and vfs_glusterfs Hi Matt, The update is slightly different, has the .1 at the end: Fast-track -> samba-4.8.3-4.el7.0.1.x86_64.rpm vs general -> samba-4.8.3-4.el7.x86_64 I think these are built, but not pushed to fasttrack repo until they get feedback the packages are good. So you may need to use wget to download them and update your packages with these for the test. Diego On Thu, Dec 20, 2018 at 1:06 PM Matt Waymack wrote: > > Hi all, > > > > I’m looking to update Samba from fasttrack, but I only still se 4.8.3 and yum > is not wanting to update. The test build is also showing 4.8.3. > > > > Thank you! > > > > > > From: gluster-users-boun...@gluster.org > On Behalf Of Matt Waymack > Sent: Sunday, December 16, 2018 1:55 PM > To: Diego Remolina > Cc: gluster-users@gluster.org List > Subject: Re: [Gluster-users] Unable to create new files or folders > using samba and vfs_glusterfs > > > > Hi all, sorry for the delayed response. > > > > I can test this out and will report back. It may be as late as Tuesday > before I can test the build. > > > > Thank you! > > > > On Dec 15, 2018 7:46 AM, Diego Remolina wrote: > > Matt, > > > > Can you test the updated samba packages that the CentOS team has built for > FasTrack? > > > > A NOTE has been added to this issue. > > -- > (0033351) pgreco (developer) - 2018-12-15 13:43 > https://bugs.centos.org/view.php?id=15586#c33351 > -- > @dijur...@gmail.com > Here's the link for the test build > https://buildlogs.centos.org/c7-fasttrack.x86_64/samba/20181214164659/ > 4.8.3-4.el7.0.1.x86_64/ > . > Please let us know how it goes. Thanks for testing! > Pablo. > -- > > Diego > > > > > On Fri, Dec 14, 2018 at 12:52 AM Anoop C S wrote: > > > > On Thu, 2018-12-13 at 15:31 +, Matt Waymack wrote: > > > Hi all, > > > > > > I’m having an issue on Windows clients accessing shares via smb > > > when using vfs_glusterfs. They are unable to create any file or > > > folders at the root of the share and get the error “The file is > > > too large for the destination file system.” When I change from > > > vfs_glusterfs to just using a filesystem path to the same > > > location, it works fine (except for the performance hit). All my > > > searches have led to bug 1619108, and that seems to be the > > > symptom, but there doesn’t appear to be any clear resolution. > > > > You figured out the right bug and following is the upstream Samba bug: > > > > https://bugzilla.samba.org/show_bug.cgi?id=13585 > > > > Unfortunately it is only available with v4.8.6 and higher. If > > required I can patch it up and provide a build. > > > > > I’m on the latest version of samba available on CentOS 7 (4.8.3) > > > and I’m on the latest available glusterfs 4.1 (4.1.6). Is there > > > something simple I’m missing to get this going? > > > > > > Thank you! > > > ___ > > > Gluster-users mailing list > > > Gluster-users@gluster.org > > > https://lists.gluster.org/mailman/listinfo/gluster-users > > > > ___ > > Gluster-users mailing list > > Gluster-users@gluster.org > > https://lists.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Input/output error on FUSE log
Has anyone any other ideas where to look? This is only affecting FUSE clients. SMB clients are unaffected by this problem. Thanks! From: gluster-users-boun...@gluster.org On Behalf Of Matt Waymack Sent: Monday, January 7, 2019 1:19 PM To: Raghavendra Gowdappa Cc: gluster-users@gluster.org List Subject: Re: [Gluster-users] Input/output error on FUSE log Attached are the logs from when a failure occurred with diagnostics set to trace. Thank you! From: Raghavendra Gowdappa mailto:rgowd...@redhat.com>> Sent: Saturday, January 5, 2019 8:32 PM To: Matt Waymack mailto:mwaym...@nsgdv.com>> Cc: gluster-users@gluster.org<mailto:gluster-users@gluster.org> List mailto:gluster-users@gluster.org>> Subject: Re: [Gluster-users] Input/output error on FUSE log On Sun, Jan 6, 2019 at 7:58 AM Raghavendra Gowdappa mailto:rgowd...@redhat.com>> wrote: On Sun, Jan 6, 2019 at 4:19 AM Matt Waymack mailto:mwaym...@nsgdv.com>> wrote: Hi all, I'm having a problem writing to our volume. When writing files larger than about 2GB, I get an intermittent issue where the write will fail and return Input/Output error. This is also shown in the FUSE log of the client (this is affecting all clients). A snip of a client log is below: [2019-01-05 22:39:44.581371] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51040978: WRITE => -1 gfid=82a0b5c4-7ef3-43c2-ad86-41e16673d7c2 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:44.598392] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51040979: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:47.420920] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041266: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949809b7f8 (Input/output error) [2019-01-05 22:39:47.433377] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041267: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:50.441531] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041548: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:50.451914] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041549: FLUSH() ERR => -1 (Input/output error) The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1311504267" repeated 1721 times between [2019-01-05 22:39:33.906241] and [2019-01-05 22:39:44.598371] The message "E [MSGID: 101046] [dht-common.c:1502:dht_lookup_dir_cbk] 0-gv1-dht: dict is null" repeated 1714 times between [2019-01-05 22:39:33.925981] and [2019-01-05 22:39:50.451862] The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1137142622" repeated 1707 times between [2019-01-05 22:39:39.636552] and [2019-01-05 22:39:50.451895] This looks to be a DHT issue. Some questions: * Are all subvolumes of DHT up and client is connected to them? Particularly the subvolume which contains the file in question. * Can you get all extended attributes of parent directory of the file from all bricks? * set diagnostics.client-log-level to TRACE, capture these errors again and attach the client log file. I spoke a bit early. dht_writev doesn't search hashed subvolume as its already been looked up in lookup. So, these msgs looks to be of a different issue - not writev failure. This is intermittent for most files, but eventually if a file is large enough it will not write. The workflow is SFTP tot he client which then writes to the volume over FUSE. When files get to a certain point,w e can no longer write to them. The file sizes are different as well, so it's not like they all get to the same size and just stop either. I've ruled out a free space issue, our files at their largest are only a few hundred GB and we have tens of terrabytes free on each brick. We are also sharding at 1GB. I'm not sure where to go from here as the error seems vague and I can only see it on the client log. I'm not seeing these errors on the nodes themselves. This is also seen if I mount the volume via FUSE on any of the nodes as well and it is only reflected in the FUSE log. Here is the volume info: Volume Name: gv1 Type: Distributed-Replicate Volume ID: 1472cc78-e2a0-4c3f-9571-dab840239b3c Status: Started Snapshot Count: 0 Number of Bricks: 8 x (2 + 1) = 24 Transport-type: tcp Bricks: Brick1: tpc-glus4:/exp/b1/gv1 Brick2: tpc-glus2:/exp/b1/gv1 Brick3: tpc-arbiter1:/exp/b1/gv1 (arbiter) Brick4: tpc-glus2:/exp/b2/gv1 Brick5: tpc-glus4:/exp/b2/gv1 Brick6: tpc-arbiter1:/exp/b2/gv1 (arbiter) Brick7: tpc-glus4:/exp/b3/gv1 Brick8: tpc-glus2:/exp/b3/gv1 Brick9: tpc-arbiter1:/exp/b3/gv1 (arbiter) Brick10: tpc-glus4:/exp/b4/gv1 Brick11: tpc-glus2:/exp/b4/gv1 Brick12: tpc-arbiter1:/exp/b4/gv1 (arbiter) Brick13: tpc-glus1:/exp/b5/gv1 Brick14: tpc-glus3:/exp/b5/gv1 Brick15: tpc-arbiter2
Re: [Gluster-users] [External] Re: Input/output error on FUSE log
Yep, first unmount/remounted, then rebooted clients. Stopped/started the volumes, and rebooted all nodes. From: Davide Obbi Sent: Monday, January 7, 2019 12:47 PM To: Matt Waymack Cc: Raghavendra Gowdappa ; gluster-users@gluster.org List Subject: Re: [External] Re: [Gluster-users] Input/output error on FUSE log i guess you tried already unmounting, stop/star and mounting? On Mon, Jan 7, 2019 at 7:44 PM Matt Waymack mailto:mwaym...@nsgdv.com>> wrote: Yes, all volumes use sharding. From: Davide Obbi mailto:davide.o...@booking.com>> Sent: Monday, January 7, 2019 12:43 PM To: Matt Waymack mailto:mwaym...@nsgdv.com>> Cc: Raghavendra Gowdappa mailto:rgowd...@redhat.com>>; gluster-users@gluster.org<mailto:gluster-users@gluster.org> List mailto:gluster-users@gluster.org>> Subject: Re: [External] Re: [Gluster-users] Input/output error on FUSE log are all the volumes being configured with sharding? On Mon, Jan 7, 2019 at 5:35 PM Matt Waymack mailto:mwaym...@nsgdv.com>> wrote: I think that I can rule out network as I have multiple volumes on the same nodes and not all volumes are affected. Additionally, access via SMB using samba-vfs-glusterfs is not affected, even on the same volumes. This is seemingly only affecting the FUSE clients. From: Davide Obbi mailto:davide.o...@booking.com>> Sent: Sunday, January 6, 2019 12:26 PM To: Raghavendra Gowdappa mailto:rgowd...@redhat.com>> Cc: Matt Waymack mailto:mwaym...@nsgdv.com>>; gluster-users@gluster.org<mailto:gluster-users@gluster.org> List mailto:gluster-users@gluster.org>> Subject: Re: [External] Re: [Gluster-users] Input/output error on FUSE log Hi, i would start doing some checks like: "(Input/output error)" seems returned by the operating system, this happens for instance trying to access a file system which is on a device not available so i would check the network connectivity between the client to servers and server to server during the reported time. Regards Davide On Sun, Jan 6, 2019 at 3:32 AM Raghavendra Gowdappa mailto:rgowd...@redhat.com>> wrote: On Sun, Jan 6, 2019 at 7:58 AM Raghavendra Gowdappa mailto:rgowd...@redhat.com>> wrote: On Sun, Jan 6, 2019 at 4:19 AM Matt Waymack mailto:mwaym...@nsgdv.com>> wrote: Hi all, I'm having a problem writing to our volume. When writing files larger than about 2GB, I get an intermittent issue where the write will fail and return Input/Output error. This is also shown in the FUSE log of the client (this is affecting all clients). A snip of a client log is below: [2019-01-05 22:39:44.581371] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51040978: WRITE => -1 gfid=82a0b5c4-7ef3-43c2-ad86-41e16673d7c2 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:44.598392] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51040979: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:47.420920] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041266: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949809b7f8 (Input/output error) [2019-01-05 22:39:47.433377] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041267: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:50.441531] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041548: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:50.451914] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041549: FLUSH() ERR => -1 (Input/output error) The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1311504267" repeated 1721 times between [2019-01-05 22:39:33.906241] and [2019-01-05 22:39:44.598371] The message "E [MSGID: 101046] [dht-common.c:1502:dht_lookup_dir_cbk] 0-gv1-dht: dict is null" repeated 1714 times between [2019-01-05 22:39:33.925981] and [2019-01-05 22:39:50.451862] The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1137142622" repeated 1707 times between [2019-01-05 22:39:39.636552] and [2019-01-05 22:39:50.451895] This looks to be a DHT issue. Some questions: * Are all subvolumes of DHT up and client is connected to them? Particularly the subvolume which contains the file in question. * Can you get all extended attributes of parent directory of the file from all bricks? * set diagnostics.client-log-level to TRACE, capture these errors again and attach the client log file. I spoke a bit early. dht_writev doesn't search hashed subvolume as its already been looked up in lookup. So, these msgs looks to be of a different issue - not writev failure. This is intermittent for most files, but eventually if a file is large enough it will not write. The workflow is SFTP tot he client which then writes to
Re: [Gluster-users] [External] Re: Input/output error on FUSE log
Yes, all volumes use sharding. From: Davide Obbi Sent: Monday, January 7, 2019 12:43 PM To: Matt Waymack Cc: Raghavendra Gowdappa ; gluster-users@gluster.org List Subject: Re: [External] Re: [Gluster-users] Input/output error on FUSE log are all the volumes being configured with sharding? On Mon, Jan 7, 2019 at 5:35 PM Matt Waymack mailto:mwaym...@nsgdv.com>> wrote: I think that I can rule out network as I have multiple volumes on the same nodes and not all volumes are affected. Additionally, access via SMB using samba-vfs-glusterfs is not affected, even on the same volumes. This is seemingly only affecting the FUSE clients. From: Davide Obbi mailto:davide.o...@booking.com>> Sent: Sunday, January 6, 2019 12:26 PM To: Raghavendra Gowdappa mailto:rgowd...@redhat.com>> Cc: Matt Waymack mailto:mwaym...@nsgdv.com>>; gluster-users@gluster.org<mailto:gluster-users@gluster.org> List mailto:gluster-users@gluster.org>> Subject: Re: [External] Re: [Gluster-users] Input/output error on FUSE log Hi, i would start doing some checks like: "(Input/output error)" seems returned by the operating system, this happens for instance trying to access a file system which is on a device not available so i would check the network connectivity between the client to servers and server to server during the reported time. Regards Davide On Sun, Jan 6, 2019 at 3:32 AM Raghavendra Gowdappa mailto:rgowd...@redhat.com>> wrote: On Sun, Jan 6, 2019 at 7:58 AM Raghavendra Gowdappa mailto:rgowd...@redhat.com>> wrote: On Sun, Jan 6, 2019 at 4:19 AM Matt Waymack mailto:mwaym...@nsgdv.com>> wrote: Hi all, I'm having a problem writing to our volume. When writing files larger than about 2GB, I get an intermittent issue where the write will fail and return Input/Output error. This is also shown in the FUSE log of the client (this is affecting all clients). A snip of a client log is below: [2019-01-05 22:39:44.581371] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51040978: WRITE => -1 gfid=82a0b5c4-7ef3-43c2-ad86-41e16673d7c2 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:44.598392] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51040979: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:47.420920] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041266: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949809b7f8 (Input/output error) [2019-01-05 22:39:47.433377] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041267: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:50.441531] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041548: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:50.451914] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041549: FLUSH() ERR => -1 (Input/output error) The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1311504267" repeated 1721 times between [2019-01-05 22:39:33.906241] and [2019-01-05 22:39:44.598371] The message "E [MSGID: 101046] [dht-common.c:1502:dht_lookup_dir_cbk] 0-gv1-dht: dict is null" repeated 1714 times between [2019-01-05 22:39:33.925981] and [2019-01-05 22:39:50.451862] The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1137142622" repeated 1707 times between [2019-01-05 22:39:39.636552] and [2019-01-05 22:39:50.451895] This looks to be a DHT issue. Some questions: * Are all subvolumes of DHT up and client is connected to them? Particularly the subvolume which contains the file in question. * Can you get all extended attributes of parent directory of the file from all bricks? * set diagnostics.client-log-level to TRACE, capture these errors again and attach the client log file. I spoke a bit early. dht_writev doesn't search hashed subvolume as its already been looked up in lookup. So, these msgs looks to be of a different issue - not writev failure. This is intermittent for most files, but eventually if a file is large enough it will not write. The workflow is SFTP tot he client which then writes to the volume over FUSE. When files get to a certain point,w e can no longer write to them. The file sizes are different as well, so it's not like they all get to the same size and just stop either. I've ruled out a free space issue, our files at their largest are only a few hundred GB and we have tens of terrabytes free on each brick. We are also sharding at 1GB. I'm not sure where to go from here as the error seems vague and I can only see it on the client log. I'm not seeing these errors on the nodes themselves. This is also seen if I mount the volume via FUSE on any of the nodes as well and it is only reflected in the FUSE log. Here
Re: [Gluster-users] [External] Re: Input/output error on FUSE log
I think that I can rule out network as I have multiple volumes on the same nodes and not all volumes are affected. Additionally, access via SMB using samba-vfs-glusterfs is not affected, even on the same volumes. This is seemingly only affecting the FUSE clients. From: Davide Obbi Sent: Sunday, January 6, 2019 12:26 PM To: Raghavendra Gowdappa Cc: Matt Waymack ; gluster-users@gluster.org List Subject: Re: [External] Re: [Gluster-users] Input/output error on FUSE log Hi, i would start doing some checks like: "(Input/output error)" seems returned by the operating system, this happens for instance trying to access a file system which is on a device not available so i would check the network connectivity between the client to servers and server to server during the reported time. Regards Davide On Sun, Jan 6, 2019 at 3:32 AM Raghavendra Gowdappa mailto:rgowd...@redhat.com>> wrote: On Sun, Jan 6, 2019 at 7:58 AM Raghavendra Gowdappa mailto:rgowd...@redhat.com>> wrote: On Sun, Jan 6, 2019 at 4:19 AM Matt Waymack mailto:mwaym...@nsgdv.com>> wrote: Hi all, I'm having a problem writing to our volume. When writing files larger than about 2GB, I get an intermittent issue where the write will fail and return Input/Output error. This is also shown in the FUSE log of the client (this is affecting all clients). A snip of a client log is below: [2019-01-05 22:39:44.581371] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51040978: WRITE => -1 gfid=82a0b5c4-7ef3-43c2-ad86-41e16673d7c2 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:44.598392] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51040979: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:47.420920] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041266: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949809b7f8 (Input/output error) [2019-01-05 22:39:47.433377] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041267: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:50.441531] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041548: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:50.451914] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041549: FLUSH() ERR => -1 (Input/output error) The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1311504267" repeated 1721 times between [2019-01-05 22:39:33.906241] and [2019-01-05 22:39:44.598371] The message "E [MSGID: 101046] [dht-common.c:1502:dht_lookup_dir_cbk] 0-gv1-dht: dict is null" repeated 1714 times between [2019-01-05 22:39:33.925981] and [2019-01-05 22:39:50.451862] The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1137142622" repeated 1707 times between [2019-01-05 22:39:39.636552] and [2019-01-05 22:39:50.451895] This looks to be a DHT issue. Some questions: * Are all subvolumes of DHT up and client is connected to them? Particularly the subvolume which contains the file in question. * Can you get all extended attributes of parent directory of the file from all bricks? * set diagnostics.client-log-level to TRACE, capture these errors again and attach the client log file. I spoke a bit early. dht_writev doesn't search hashed subvolume as its already been looked up in lookup. So, these msgs looks to be of a different issue - not writev failure. This is intermittent for most files, but eventually if a file is large enough it will not write. The workflow is SFTP tot he client which then writes to the volume over FUSE. When files get to a certain point,w e can no longer write to them. The file sizes are different as well, so it's not like they all get to the same size and just stop either. I've ruled out a free space issue, our files at their largest are only a few hundred GB and we have tens of terrabytes free on each brick. We are also sharding at 1GB. I'm not sure where to go from here as the error seems vague and I can only see it on the client log. I'm not seeing these errors on the nodes themselves. This is also seen if I mount the volume via FUSE on any of the nodes as well and it is only reflected in the FUSE log. Here is the volume info: Volume Name: gv1 Type: Distributed-Replicate Volume ID: 1472cc78-e2a0-4c3f-9571-dab840239b3c Status: Started Snapshot Count: 0 Number of Bricks: 8 x (2 + 1) = 24 Transport-type: tcp Bricks: Brick1: tpc-glus4:/exp/b1/gv1 Brick2: tpc-glus2:/exp/b1/gv1 Brick3: tpc-arbiter1:/exp/b1/gv1 (arbiter) Brick4: tpc-glus2:/exp/b2/gv1 Brick5: tpc-glus4:/exp/b2/gv1 Brick6: tpc-arbiter1:/exp/b2/gv1 (arbiter) Brick7: tpc-glus4:/exp/b3/gv1 Brick8: tpc-glus2:/exp/b3/gv1 Brick9: tpc-arbiter1:/exp/b3/gv1 (arbiter) Brick10: tpc-glus4:/exp/b4/gv1 Brick11: tpc-glus2:/ex
[Gluster-users] Input/output error on FUSE log
Hi all, I'm having a problem writing to our volume. When writing files larger than about 2GB, I get an intermittent issue where the write will fail and return Input/Output error. This is also shown in the FUSE log of the client (this is affecting all clients). A snip of a client log is below: [2019-01-05 22:39:44.581371] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51040978: WRITE => -1 gfid=82a0b5c4-7ef3-43c2-ad86-41e16673d7c2 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:44.598392] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51040979: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:47.420920] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041266: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949809b7f8 (Input/output error) [2019-01-05 22:39:47.433377] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041267: FLUSH() ERR => -1 (Input/output error) [2019-01-05 22:39:50.441531] W [fuse-bridge.c:2474:fuse_writev_cbk] 0-glusterfs-fuse: 51041548: WRITE => -1 gfid=0e8e1e13-97a5-478a-bc58-e81ddf3698a3 fd=0x7f949839a368 (Input/output error) [2019-01-05 22:39:50.451914] W [fuse-bridge.c:1441:fuse_err_cbk] 0-glusterfs-fuse: 51041549: FLUSH() ERR => -1 (Input/output error) The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1311504267" repeated 1721 times between [2019-01-05 22:39:33.906241] and [2019-01-05 22:39:44.598371] The message "E [MSGID: 101046] [dht-common.c:1502:dht_lookup_dir_cbk] 0-gv1-dht: dict is null" repeated 1714 times between [2019-01-05 22:39:33.925981] and [2019-01-05 22:39:50.451862] The message "W [MSGID: 109011] [dht-layout.c:163:dht_layout_search] 0-gv1-dht: no subvolume for hash (value) = 1137142622" repeated 1707 times between [2019-01-05 22:39:39.636552] and [2019-01-05 22:39:50.451895] This is intermittent for most files, but eventually if a file is large enough it will not write. The workflow is SFTP tot he client which then writes to the volume over FUSE. When files get to a certain point,w e can no longer write to them. The file sizes are different as well, so it's not like they all get to the same size and just stop either. I've ruled out a free space issue, our files at their largest are only a few hundred GB and we have tens of terrabytes free on each brick. We are also sharding at 1GB. I'm not sure where to go from here as the error seems vague and I can only see it on the client log. I'm not seeing these errors on the nodes themselves. This is also seen if I mount the volume via FUSE on any of the nodes as well and it is only reflected in the FUSE log. Here is the volume info: Volume Name: gv1 Type: Distributed-Replicate Volume ID: 1472cc78-e2a0-4c3f-9571-dab840239b3c Status: Started Snapshot Count: 0 Number of Bricks: 8 x (2 + 1) = 24 Transport-type: tcp Bricks: Brick1: tpc-glus4:/exp/b1/gv1 Brick2: tpc-glus2:/exp/b1/gv1 Brick3: tpc-arbiter1:/exp/b1/gv1 (arbiter) Brick4: tpc-glus2:/exp/b2/gv1 Brick5: tpc-glus4:/exp/b2/gv1 Brick6: tpc-arbiter1:/exp/b2/gv1 (arbiter) Brick7: tpc-glus4:/exp/b3/gv1 Brick8: tpc-glus2:/exp/b3/gv1 Brick9: tpc-arbiter1:/exp/b3/gv1 (arbiter) Brick10: tpc-glus4:/exp/b4/gv1 Brick11: tpc-glus2:/exp/b4/gv1 Brick12: tpc-arbiter1:/exp/b4/gv1 (arbiter) Brick13: tpc-glus1:/exp/b5/gv1 Brick14: tpc-glus3:/exp/b5/gv1 Brick15: tpc-arbiter2:/exp/b5/gv1 (arbiter) Brick16: tpc-glus1:/exp/b6/gv1 Brick17: tpc-glus3:/exp/b6/gv1 Brick18: tpc-arbiter2:/exp/b6/gv1 (arbiter) Brick19: tpc-glus1:/exp/b7/gv1 Brick20: tpc-glus3:/exp/b7/gv1 Brick21: tpc-arbiter2:/exp/b7/gv1 (arbiter) Brick22: tpc-glus1:/exp/b8/gv1 Brick23: tpc-glus3:/exp/b8/gv1 Brick24: tpc-arbiter2:/exp/b8/gv1 (arbiter) Options Reconfigured: performance.cache-samba-metadata: on performance.cache-invalidation: off features.shard-block-size: 1000MB features.shard: on transport.address-family: inet nfs.disable: on cluster.lookup-optimize: on I'm a bit stumped on this, any help is appreciated. Thank you! ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Unable to create new files or folders using samba and vfs_glusterfs
OK, I'm back from the holiday and updated using the following packages: libsmbclient-4.8.3-4.el7.0.1.x86_64.rpm libwbclient-4.8.3-4.el7.0.1.x86_64.rpm samba-4.8.3-4.el7.0.1.x86_64.rpm samba-client-4.8.3-4.el7.0.1.x86_64.rpm samba-client-libs-4.8.3-4.el7.0.1.x86_64.rpm samba-common-4.8.3-4.el7.0.1.noarch.rpm samba-common-libs-4.8.3-4.el7.0.1.x86_64.rpm samba-common-tools-4.8.3-4.el7.0.1.x86_64.rpm samba-libs-4.8.3-4.el7.0.1.x86_64.rpm samba-vfs-glusterfs-4.8.3-4.el7.0.1.x86_64.rpm First impressions are good! We're able to create files/folders. I'll keep you updated with stability. Thank you! -Original Message- From: Diego Remolina Sent: Thursday, December 20, 2018 1:36 PM To: Matt Waymack Cc: gluster-users@gluster.org List Subject: Re: [Gluster-users] Unable to create new files or folders using samba and vfs_glusterfs Hi Matt, The update is slightly different, has the .1 at the end: Fast-track -> samba-4.8.3-4.el7.0.1.x86_64.rpm vs general -> samba-4.8.3-4.el7.x86_64 I think these are built, but not pushed to fasttrack repo until they get feedback the packages are good. So you may need to use wget to download them and update your packages with these for the test. Diego On Thu, Dec 20, 2018 at 1:06 PM Matt Waymack wrote: > > Hi all, > > > > I’m looking to update Samba from fasttrack, but I only still se 4.8.3 and yum > is not wanting to update. The test build is also showing 4.8.3. > > > > Thank you! > > > > > > From: gluster-users-boun...@gluster.org > On Behalf Of Matt Waymack > Sent: Sunday, December 16, 2018 1:55 PM > To: Diego Remolina > Cc: gluster-users@gluster.org List > Subject: Re: [Gluster-users] Unable to create new files or folders > using samba and vfs_glusterfs > > > > Hi all, sorry for the delayed response. > > > > I can test this out and will report back. It may be as late as Tuesday > before I can test the build. > > > > Thank you! > > > > On Dec 15, 2018 7:46 AM, Diego Remolina wrote: > > Matt, > > > > Can you test the updated samba packages that the CentOS team has built for > FasTrack? > > > > A NOTE has been added to this issue. > > -- > (0033351) pgreco (developer) - 2018-12-15 13:43 > https://bugs.centos.org/view.php?id=15586#c33351 > -- > @dijur...@gmail.com > Here's the link for the test build > https://buildlogs.centos.org/c7-fasttrack.x86_64/samba/20181214164659/ > 4.8.3-4.el7.0.1.x86_64/ > . > Please let us know how it goes. Thanks for testing! > Pablo. > -- > > Diego > > > > > On Fri, Dec 14, 2018 at 12:52 AM Anoop C S wrote: > > > > On Thu, 2018-12-13 at 15:31 +, Matt Waymack wrote: > > > Hi all, > > > > > > I’m having an issue on Windows clients accessing shares via smb > > > when using vfs_glusterfs. They are unable to create any file or > > > folders at the root of the share and get the error “The file is > > > too large for the destination file system.” When I change from > > > vfs_glusterfs to just using a filesystem path to the same > > > location, it works fine (except for the performance hit). All my > > > searches have led to bug 1619108, and that seems to be the > > > symptom, but there doesn’t appear to be any clear resolution. > > > > You figured out the right bug and following is the upstream Samba bug: > > > > https://bugzilla.samba.org/show_bug.cgi?id=13585 > > > > Unfortunately it is only available with v4.8.6 and higher. If > > required I can patch it up and provide a build. > > > > > I’m on the latest version of samba available on CentOS 7 (4.8.3) > > > and I’m on the latest available glusterfs 4.1 (4.1.6). Is there > > > something simple I’m missing to get this going? > > > > > > Thank you! > > > ___ > > > Gluster-users mailing list > > > Gluster-users@gluster.org > > > https://lists.gluster.org/mailman/listinfo/gluster-users > > > > ___ > > Gluster-users mailing list > > Gluster-users@gluster.org > > https://lists.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Unable to create new files or folders using samba and vfs_glusterfs
Hi all, I'm looking to update Samba from fasttrack, but I only still se 4.8.3 and yum is not wanting to update. The test build is also showing 4.8.3. Thank you! From: gluster-users-boun...@gluster.org On Behalf Of Matt Waymack Sent: Sunday, December 16, 2018 1:55 PM To: Diego Remolina Cc: gluster-users@gluster.org List Subject: Re: [Gluster-users] Unable to create new files or folders using samba and vfs_glusterfs Hi all, sorry for the delayed response. I can test this out and will report back. It may be as late as Tuesday before I can test the build. Thank you! On Dec 15, 2018 7:46 AM, Diego Remolina mailto:dijur...@gmail.com>> wrote: Matt, Can you test the updated samba packages that the CentOS team has built for FasTrack? A NOTE has been added to this issue. -- (0033351) pgreco (developer) - 2018-12-15 13:43 https://bugs.centos.org/view.php?id=15586#c33351 -- @dijur...@gmail.com<mailto:dijur...@gmail.com> Here's the link for the test build https://buildlogs.centos.org/c7-fasttrack.x86_64/samba/20181214164659/4.8.3-4.el7.0.1.x86_64/ . Please let us know how it goes. Thanks for testing! Pablo. -- Diego On Fri, Dec 14, 2018 at 12:52 AM Anoop C S mailto:anoo...@cryptolab.net>> wrote: > > On Thu, 2018-12-13 at 15:31 +, Matt Waymack wrote: > > Hi all, > > > > I'm having an issue on Windows clients accessing shares via smb when > > using vfs_glusterfs. They are unable to create any file or folders > > at the root of the share and get the error "The file is too large for > > the destination file system." When I change from vfs_glusterfs to > > just using a filesystem path to the same location, it works fine > > (except for the performance hit). All my searches have led to bug > > 1619108, and that seems to be the symptom, but there doesn't appear > > to be any clear resolution. > > You figured out the right bug and following is the upstream Samba bug: > > https://bugzilla.samba.org/show_bug.cgi?id=13585 > > Unfortunately it is only available with v4.8.6 and higher. If required > I can patch it up and provide a build. > > > I'm on the latest version of samba available on CentOS 7 (4.8.3) and > > I'm on the latest available glusterfs 4.1 (4.1.6). Is there > > something simple I'm missing to get this going? > > > > Thank you! > > ___ > > Gluster-users mailing list > > Gluster-users@gluster.org<mailto:Gluster-users@gluster.org> > > https://lists.gluster.org/mailman/listinfo/gluster-users > > ___ > Gluster-users mailing list > Gluster-users@gluster.org<mailto:Gluster-users@gluster.org> > https://lists.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Unable to create new files or folders using samba and vfs_glusterfs
Hi all, sorry for the delayed response. I can test this out and will report back. It may be as late as Tuesday before I can test the build. Thank you! On Dec 15, 2018 7:46 AM, Diego Remolina wrote: Matt, Can you test the updated samba packages that the CentOS team has built for FasTrack? A NOTE has been added to this issue. -- (0033351) pgreco (developer) - 2018-12-15 13:43 https://bugs.centos.org/view.php?id=15586#c33351 -- @dijur...@gmail.com<mailto:dijur...@gmail.com> Here's the link for the test build https://buildlogs.centos.org/c7-fasttrack.x86_64/samba/20181214164659/4.8.3-4.el7.0.1.x86_64/ . Please let us know how it goes. Thanks for testing! Pablo. -- Diego On Fri, Dec 14, 2018 at 12:52 AM Anoop C S mailto:anoo...@cryptolab.net>> wrote: > > On Thu, 2018-12-13 at 15:31 +, Matt Waymack wrote: > > Hi all, > > > > I'm having an issue on Windows clients accessing shares via smb when > > using vfs_glusterfs. They are unable to create any file or folders > > at the root of the share and get the error "The file is too large for > > the destination file system." When I change from vfs_glusterfs to > > just using a filesystem path to the same location, it works fine > > (except for the performance hit). All my searches have led to bug > > 1619108, and that seems to be the symptom, but there doesn't appear > > to be any clear resolution. > > You figured out the right bug and following is the upstream Samba bug: > > https://bugzilla.samba.org/show_bug.cgi?id=13585 > > Unfortunately it is only available with v4.8.6 and higher. If required > I can patch it up and provide a build. > > > I'm on the latest version of samba available on CentOS 7 (4.8.3) and > > I'm on the latest available glusterfs 4.1 (4.1.6). Is there > > something simple I'm missing to get this going? > > > > Thank you! > > ___ > > Gluster-users mailing list > > Gluster-users@gluster.org<mailto:Gluster-users@gluster.org> > > https://lists.gluster.org/mailman/listinfo/gluster-users > > ___ > Gluster-users mailing list > Gluster-users@gluster.org<mailto:Gluster-users@gluster.org> > https://lists.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Unable to create new files or folders using samba and vfs_glusterfs
Hi all, I'm having an issue on Windows clients accessing shares via smb when using vfs_glusterfs. They are unable to create any file or folders at the root of the share and get the error "The file is too large for the destination file system." When I change from vfs_glusterfs to just using a filesystem path to the same location, it works fine (except for the performance hit). All my searches have led to bug 1619108, and that seems to be the symptom, but there doesn't appear to be any clear resolution. I'm on the latest version of samba available on CentOS 7 (4.8.3) and I'm on the latest available glusterfs 4.1 (4.1.6). Is there something simple I'm missing to get this going? Thank you! ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Snapshot size
Hi list, I was wondering if anyone knows if it's possible to get the size of a snapshot, ideally a list, but I'd take the size of just one? I'm aware that you can use lvs and the Data% column gives you an idea. But it's not really very neat, so I was wondering if anyone knows of a better way? Cheers, Matt ___ Gluster-users mailing list Gluster-users@gluster.org https://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] How to make sure self-heal backlog is empty ?
Mine also has a list of files that seemingly never heal. They are usually isolated on my arbiter bricks, but not always. I would also like to find an answer for this behavior. -Original Message- From: gluster-users-boun...@gluster.org [mailto:gluster-users-boun...@gluster.org] On Behalf Of Hoggins! Sent: Tuesday, December 19, 2017 12:26 PM To: gluster-usersSubject: [Gluster-users] How to make sure self-heal backlog is empty ? Hello list, I'm not sure what to look for here, not sure if what I'm seeing is the actual "backlog" (that we need to make sure is empty while performing a rolling upgrade before going to the next node), how can I tell, while reading this, if it's okay to reboot / upgrade my next node in the pool ? Here is what I do for checking : for i in `gluster volume list`; do gluster volume heal $i info; done And here is what I get : Brick ngluster-1.network.hoggins.fr:/export/brick/clem Status: Connected Number of entries: 0 Brick ngluster-2.network.hoggins.fr:/export/brick/clem Status: Connected Number of entries: 0 Brick ngluster-3.network.hoggins.fr:/export/brick/clem Status: Connected Number of entries: 0 Brick ngluster-1.network.hoggins.fr:/export/brick/mailer Status: Connected Number of entries: 0 Brick ngluster-2.network.hoggins.fr:/export/brick/mailer Status: Connected Number of entries: 0 Brick ngluster-3.network.hoggins.fr:/export/brick/mailer Status: Connected Number of entries: 1 Brick ngluster-1.network.hoggins.fr:/export/brick/rom Status: Connected Number of entries: 0 Brick ngluster-2.network.hoggins.fr:/export/brick/rom Status: Connected Number of entries: 0 Brick ngluster-3.network.hoggins.fr:/export/brick/rom Status: Connected Number of entries: 1 Brick ngluster-1.network.hoggins.fr:/export/brick/thedude Status: Connected Number of entries: 0 Brick ngluster-2.network.hoggins.fr:/export/brick/thedude Status: Connected Number of entries: 1 Brick ngluster-3.network.hoggins.fr:/export/brick/thedude Status: Connected Number of entries: 0 Brick ngluster-1.network.hoggins.fr:/export/brick/web Status: Connected Number of entries: 0 Brick ngluster-2.network.hoggins.fr:/export/brick/web Status: Connected Number of entries: 3 Brick ngluster-3.network.hoggins.fr:/export/brick/web Status: Connected Number of entries: 11 Should I be worrying with this never ending ? Thank you, Hoggins! ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Production Volume will not start
Hi thank you for the reply. Ultimately the volume did eventually start after about 1.5 hours from the volume start command. Could it have something to do with the amount of files on the volume? From: Atin Mukherjee [mailto:amukh...@redhat.com] Sent: Monday, December 18, 2017 1:26 AM To: Matt Waymack <mwaym...@nsgdv.com> Cc: gluster-users <Gluster-users@gluster.org> Subject: Re: [Gluster-users] Production Volume will not start On Sat, Dec 16, 2017 at 12:45 AM, Matt Waymack <mwaym...@nsgdv.com<mailto:mwaym...@nsgdv.com>> wrote: Hi all, I have an issue where our volume will not start from any node. When attempting to start the volume it will eventually return: Error: Request timed out For some time after that, the volume is locked and we either have to wait or restart Gluster services. In the gluserd.log, it shows the following: [2017-12-15 18:00:12.423478] I [glusterd-utils.c:5926:glusterd_brick_start] 0-management: starting a fresh brick process for brick /exp/b1/gv0 [2017-12-15 18:03:12.673885] I [glusterd-locks.c:729:gd_mgmt_v3_unlock_timer_cbk] 0-management: In gd_mgmt_v3_unlock_timer_cbk [2017-12-15 18:06:34.304868] I [MSGID: 106499] [glusterd-handler.c:4303:__glusterd_handle_status_volume] 0-management: Received status volume req for volume gv0 [2017-12-15 18:06:34.306603] E [MSGID: 106301] [glusterd-syncop.c:1353:gd_stage_op_phase] 0-management: Staging of operation 'Volume Status' failed on localhost : Volume gv0 is not started [2017-12-15 18:11:39.412700] I [glusterd-utils.c:5926:glusterd_brick_start] 0-management: starting a fresh brick process for brick /exp/b2/gv0 [2017-12-15 18:11:42.405966] I [MSGID: 106143] [glusterd-pmap.c:280:pmap_registry_bind] 0-pmap: adding brick /exp/b2/gv0 on port 49153 [2017-12-15 18:11:42.406415] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-management: setting frame-timeout to 600 [2017-12-15 18:11:42.406669] I [glusterd-utils.c:5926:glusterd_brick_start] 0-management: starting a fresh brick process for brick /exp/b3/gv0 [2017-12-15 18:14:39.737192] I [glusterd-locks.c:729:gd_mgmt_v3_unlock_timer_cbk] 0-management: In gd_mgmt_v3_unlock_timer_cbk [2017-12-15 18:35:20.856849] I [MSGID: 106143] [glusterd-pmap.c:280:pmap_registry_bind] 0-pmap: adding brick /exp/b1/gv0 on port 49152 [2017-12-15 18:35:20.857508] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-management: setting frame-timeout to 600 [2017-12-15 18:35:20.858277] I [glusterd-utils.c:5926:glusterd_brick_start] 0-management: starting a fresh brick process for brick /exp/b4/gv0 [2017-12-15 18:46:07.953995] I [MSGID: 106143] [glusterd-pmap.c:280:pmap_registry_bind] 0-pmap: adding brick /exp/b3/gv0 on port 49154 [2017-12-15 18:46:07.954432] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-management: setting frame-timeout to 600 [2017-12-15 18:46:07.971355] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-snapd: setting frame-timeout to 600 [2017-12-15 18:46:07.989392] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-nfs: setting frame-timeout to 600 [2017-12-15 18:46:07.989543] I [MSGID: 106132] [glusterd-proc-mgmt.c:83:glusterd_proc_stop] 0-management: nfs already stopped [2017-12-15 18:46:07.989562] I [MSGID: 106568] [glusterd-svc-mgmt.c:229:glusterd_svc_stop] 0-management: nfs service is stopped [2017-12-15 18:46:07.989575] I [MSGID: 106600] [glusterd-nfs-svc.c:82:glusterd_nfssvc_manager] 0-management: nfs/server.so xlator is not installed [2017-12-15 18:46:07.989601] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-glustershd: setting frame-timeout to 600 [2017-12-15 18:46:08.003011] I [MSGID: 106132] [glusterd-proc-mgmt.c:83:glusterd_proc_stop] 0-management: glustershd already stopped [2017-12-15 18:46:08.003039] I [MSGID: 106568] [glusterd-svc-mgmt.c:229:glusterd_svc_stop] 0-management: glustershd service is stopped [2017-12-15 18:46:08.003079] I [MSGID: 106567] [glusterd-svc-mgmt.c:197:glusterd_svc_start] 0-management: Starting glustershd service [2017-12-15 18:46:09.005173] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-quotad: setting frame-timeout to 600 [2017-12-15 18:46:09.005569] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-bitd: setting frame-timeout to 600 [2017-12-15 18:46:09.005673] I [MSGID: 106132] [glusterd-proc-mgmt.c:83:glusterd_proc_stop] 0-management: bitd already stopped [2017-12-15 18:46:09.005689] I [MSGID: 106568] [glusterd-svc-mgmt.c:229:glusterd_svc_stop] 0-management: bitd service is stopped [2017-12-15 18:46:09.005712] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-scrub: setting frame-timeout to 600 [2017-12-15 18:46:09.005892] I [MSGID: 106132] [glusterd-proc-mgmt.c:83:glusterd_proc_stop] 0-management: scrub already stopped [2017-12-15 18:46:09.005912] I [MSGID: 106568] [glusterd-svc-mgmt.c:229:glusterd_svc_stop] 0-management: scrub service is stopped [2017-12-15 18:46:09.026559] I [socket.c:3672:socket_submit_reply] 0-socket.management: not connected (priv->c
[Gluster-users] Production Volume will not start
Hi all, I have an issue where our volume will not start from any node. When attempting to start the volume it will eventually return: Error: Request timed out For some time after that, the volume is locked and we either have to wait or restart Gluster services. In the gluserd.log, it shows the following: [2017-12-15 18:00:12.423478] I [glusterd-utils.c:5926:glusterd_brick_start] 0-management: starting a fresh brick process for brick /exp/b1/gv0 [2017-12-15 18:03:12.673885] I [glusterd-locks.c:729:gd_mgmt_v3_unlock_timer_cbk] 0-management: In gd_mgmt_v3_unlock_timer_cbk [2017-12-15 18:06:34.304868] I [MSGID: 106499] [glusterd-handler.c:4303:__glusterd_handle_status_volume] 0-management: Received status volume req for volume gv0 [2017-12-15 18:06:34.306603] E [MSGID: 106301] [glusterd-syncop.c:1353:gd_stage_op_phase] 0-management: Staging of operation 'Volume Status' failed on localhost : Volume gv0 is not started [2017-12-15 18:11:39.412700] I [glusterd-utils.c:5926:glusterd_brick_start] 0-management: starting a fresh brick process for brick /exp/b2/gv0 [2017-12-15 18:11:42.405966] I [MSGID: 106143] [glusterd-pmap.c:280:pmap_registry_bind] 0-pmap: adding brick /exp/b2/gv0 on port 49153 [2017-12-15 18:11:42.406415] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-management: setting frame-timeout to 600 [2017-12-15 18:11:42.406669] I [glusterd-utils.c:5926:glusterd_brick_start] 0-management: starting a fresh brick process for brick /exp/b3/gv0 [2017-12-15 18:14:39.737192] I [glusterd-locks.c:729:gd_mgmt_v3_unlock_timer_cbk] 0-management: In gd_mgmt_v3_unlock_timer_cbk [2017-12-15 18:35:20.856849] I [MSGID: 106143] [glusterd-pmap.c:280:pmap_registry_bind] 0-pmap: adding brick /exp/b1/gv0 on port 49152 [2017-12-15 18:35:20.857508] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-management: setting frame-timeout to 600 [2017-12-15 18:35:20.858277] I [glusterd-utils.c:5926:glusterd_brick_start] 0-management: starting a fresh brick process for brick /exp/b4/gv0 [2017-12-15 18:46:07.953995] I [MSGID: 106143] [glusterd-pmap.c:280:pmap_registry_bind] 0-pmap: adding brick /exp/b3/gv0 on port 49154 [2017-12-15 18:46:07.954432] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-management: setting frame-timeout to 600 [2017-12-15 18:46:07.971355] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-snapd: setting frame-timeout to 600 [2017-12-15 18:46:07.989392] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-nfs: setting frame-timeout to 600 [2017-12-15 18:46:07.989543] I [MSGID: 106132] [glusterd-proc-mgmt.c:83:glusterd_proc_stop] 0-management: nfs already stopped [2017-12-15 18:46:07.989562] I [MSGID: 106568] [glusterd-svc-mgmt.c:229:glusterd_svc_stop] 0-management: nfs service is stopped [2017-12-15 18:46:07.989575] I [MSGID: 106600] [glusterd-nfs-svc.c:82:glusterd_nfssvc_manager] 0-management: nfs/server.so xlator is not installed [2017-12-15 18:46:07.989601] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-glustershd: setting frame-timeout to 600 [2017-12-15 18:46:08.003011] I [MSGID: 106132] [glusterd-proc-mgmt.c:83:glusterd_proc_stop] 0-management: glustershd already stopped [2017-12-15 18:46:08.003039] I [MSGID: 106568] [glusterd-svc-mgmt.c:229:glusterd_svc_stop] 0-management: glustershd service is stopped [2017-12-15 18:46:08.003079] I [MSGID: 106567] [glusterd-svc-mgmt.c:197:glusterd_svc_start] 0-management: Starting glustershd service [2017-12-15 18:46:09.005173] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-quotad: setting frame-timeout to 600 [2017-12-15 18:46:09.005569] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-bitd: setting frame-timeout to 600 [2017-12-15 18:46:09.005673] I [MSGID: 106132] [glusterd-proc-mgmt.c:83:glusterd_proc_stop] 0-management: bitd already stopped [2017-12-15 18:46:09.005689] I [MSGID: 106568] [glusterd-svc-mgmt.c:229:glusterd_svc_stop] 0-management: bitd service is stopped [2017-12-15 18:46:09.005712] I [rpc-clnt.c:1044:rpc_clnt_connection_init] 0-scrub: setting frame-timeout to 600 [2017-12-15 18:46:09.005892] I [MSGID: 106132] [glusterd-proc-mgmt.c:83:glusterd_proc_stop] 0-management: scrub already stopped [2017-12-15 18:46:09.005912] I [MSGID: 106568] [glusterd-svc-mgmt.c:229:glusterd_svc_stop] 0-management: scrub service is stopped [2017-12-15 18:46:09.026559] I [socket.c:3672:socket_submit_reply] 0-socket.management: not connected (priv->connected = -1) [2017-12-15 18:46:09.026568] E [rpcsvc.c:1364:rpcsvc_submit_generic] 0-rpc-service: failed to submit message (XID: 0x2, Program: GlusterD svc cli, ProgVers: 2, Proc: 27) to rpc-transport (socket.management) [2017-12-15 18:46:09.026582] E [MSGID: 106430] [glusterd-utils.c:568:glusterd_submit_reply] 0-glusterd: Reply submission failed [2017-12-15 18:56:17.962251] E [rpc-clnt.c:185:call_bail] 0-management: bailing out frame type(glusterd mgmt v3) op(--(4)) xid = 0x14 sent = 2017-12-15 18:46:09.005976. timeout = 600 for 10.17.100.208:24007 [2017-12-15 18:56:17.962324] E [MSGID:
Re: [Gluster-users] gfid entries in volume heal info that do not heal
In my case I was able to delete the hard links in the .glusterfs folders of the bricks and it seems to have done the trick, thanks! From: Karthik Subrahmanya [mailto:ksubr...@redhat.com] Sent: Monday, October 23, 2017 1:52 AM To: Jim Kinney <jim.kin...@gmail.com>; Matt Waymack <mwaym...@nsgdv.com> Cc: gluster-users <Gluster-users@gluster.org> Subject: Re: [Gluster-users] gfid entries in volume heal info that do not heal Hi Jim & Matt, Can you also check for the link count in the stat output of those hardlink entries in the .glusterfs folder on the bricks. If the link count is 1 on all the bricks for those entries, then they are orphaned entries and you can delete those hardlinks. To be on the safer side have a backup before deleting any of the entries. Regards, Karthik On Fri, Oct 20, 2017 at 3:18 AM, Jim Kinney <jim.kin...@gmail.com<mailto:jim.kin...@gmail.com>> wrote: I've been following this particular thread as I have a similar issue (RAID6 array failed out with 3 dead drives at once while a 12 TB load was being copied into one mounted space - what a mess) I have >700K GFID entries that have no path data: Example: getfattr -d -e hex -m . .glusterfs/00/00/a5ef-5af7-401b-84b5-ff2a51c10421 # file: .glusterfs/00/00/a5ef-5af7-401b-84b5-ff2a51c10421 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.bit-rot.version=0x020059b1b316000270e7 trusted.gfid=0xa5ef5af7401b84b5ff2a51c10421 [root@bmidata1<mailto:root@bmidata1> brick]# getfattr -d -n trusted.glusterfs.pathinfo -e hex -m . .glusterfs/00/00/a5ef-5af7-401b-84b5-ff2a51c10421 .glusterfs/00/00/a5ef-5af7-401b-84b5-ff2a51c10421: trusted.glusterfs.pathinfo: No such attribute I had to totally rebuild the dead RAID array and did a copy from the live one before activating gluster on the rebuilt system. I accidentally copied over the .glusterfs folder from the working side (replica 2 only for now - adding arbiter node as soon as I can get this one cleaned up). I've run the methods from "http://docs.gluster.org/en/latest/Troubleshooting/gfid-to-path/; with no results using random GFIDs. A full systemic run using the script from method 3 crashes with "too many nested links" error (or something similar). When I run gluster volume heal volname info, I get 700K+ GFIDs. Oh. gluster 3.8.4 on Centos 7.3 Should I just remove the contents of the .glusterfs folder on both and restart gluster and run a ls/stat on every file? When I run a heal, it no longer has a decreasing number of files to heal so that's an improvement over the last 2-3 weeks :-) On Tue, 2017-10-17 at 14:34 +, Matt Waymack wrote: Attached is the heal log for the volume as well as the shd log. Run these commands on all the bricks of the replica pair to get the attrs set on the backend. [root@tpc-cent-glus1-081017 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 getfattr: Removing leading '/' from absolute path names # file: exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-2=0x0001 trusted.gfid=0x108694dbc0394b7cbd3dad6a15d811a2 trusted.gfid2path.9a2f5ada22eb9c45=0x38633262623330322d323466332d346463622d393630322d3839356136396461363131662f435f564f4c2d623030312d693637342d63642d63772e6d6435 [root@tpc-cent-glus2-081017 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 getfattr: Removing leading '/' from absolute path names # file: exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-2=0x0001 trusted.gfid=0x108694dbc0394b7cbd3dad6a15d811a2 trusted.gfid2path.9a2f5ada22eb9c45=0x38633262623330322d323466332d346463622d393630322d3839356136396461363131662f435f564f4c2d623030312d693637342d63642d63772e6d6435 [root@tpc-arbiter1-100617 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 getfattr: /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2: No such file or directory [root@tpc-cent-glus1-081017 ~]# getfattr -d -e hex -m . /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 getfattr: Removing leading '/' from absolute path names # file: exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-11=0x0001 trusted.gfid=0xe0c56bf78b
Re: [Gluster-users] gfid entries in volume heal info that do not heal
It looks like these entries don't have a corresponding file path, they exist only in .glusters and appear to be orphaned: [root@tpc-cent-glus2-081017 ~]# find /exp/b4/gv0 -samefile /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 [root@tpc-cent-glus2-081017 ~]# find /exp/b4/gv0 -samefile /exp/b4/gv0/.glusterfs/6f/0a/6f0a0549-8669-46de-8823-d6677fdca8e3 /exp/b4/gv0/.glusterfs/6f/0a/6f0a0549-8669-46de-8823-d6677fdca8e3 [root@tpc-cent-glus1-081017 ~]# find /exp/b1/gv0 -samefile /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 [root@tpc-cent-glus1-081017 ~]# find /exp/b4/gv0 -samefile /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 Occasionally I would get these gfid entries in the heal info output but would just run tree against the volume. After that the files would trigger self-heal, and the gfid entries would be updated with their volume paths. That does not seem to be the case here so I feel that all of these entries are orphaned. From: Karthik Subrahmanya [mailto:ksubr...@redhat.com] Sent: Wednesday, October 18, 2017 4:34 AM To: Matt Waymack <mwaym...@nsgdv.com> Cc: gluster-users <Gluster-users@gluster.org> Subject: Re: [Gluster-users] gfid entries in volume heal info that do not heal Hey Matt, From the xattr output, it looks like the files are not present on the arbiter brick & needs healing. But on the parent it does not have the pending markers set for those entries. The workaround for this is you need to do a lookup on the file which needs heal from the mount, so it will create the entry on the arbiter brick and then run the volume heal to do the healing. Follow these steps to resolve the issue: (first try this on one file and check whether it gets healed. If it gets healed then do this for all the remaining files) 1. Get the file path for the gfids you got from heal info output. find -samefile // 2. Do ls/stat on the file from mount. 3. Run volume heal. 4. Check the heal info output to see whether the file got healed. If one file gets healed, then do step 1 & 2 for the rest of the files and do step 3 & 4 once at the end. Let me know if that resolves the issue. Thanks & Regards, Karthik On Tue, Oct 17, 2017 at 8:04 PM, Matt Waymack <mailto:mwaym...@nsgdv.com> wrote: Attached is the heal log for the volume as well as the shd log. >> Run these commands on all the bricks of the replica pair to get the attrs >> set on the backend. [root@tpc-cent-glus1-081017 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 getfattr: Removing leading '/' from absolute path names # file: exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-2=0x0001 trusted.gfid=0x108694dbc0394b7cbd3dad6a15d811a2 trusted.gfid2path.9a2f5ada22eb9c45=0x38633262623330322d323466332d346463622d393630322d3839356136396461363131662f435f564f4c2d623030312d693637342d63642d63772e6d6435 [root@tpc-cent-glus2-081017 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 getfattr: Removing leading '/' from absolute path names # file: exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-2=0x0001 trusted.gfid=0x108694dbc0394b7cbd3dad6a15d811a2 trusted.gfid2path.9a2f5ada22eb9c45=0x38633262623330322d323466332d346463622d393630322d3839356136396461363131662f435f564f4c2d623030312d693637342d63642d63772e6d6435 [root@tpc-arbiter1-100617 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 getfattr: /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2: No such file or directory [root@tpc-cent-glus1-081017 ~]# getfattr -d -e hex -m . /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 getfattr: Removing leading '/' from absolute path names # file: exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-11=0x0001 trusted.gfid=0xe0c56bf78bfe46cabde1e46b92d33df3 trusted.gfid2path.be3ba24c3ef95ff2=0x63323366353834652d353566652d343033382d393131622d3866373063656334616136662f435f564f4c2d623030332d69313331342d63642d636d2d63722e6d6435 [root@tpc-cent-glus2-081017 ~]# getfattr -d -e hex -m . /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e4
Re: [Gluster-users] gfid entries in volume heal info that do not heal
Attached is the heal log for the volume as well as the shd log. >> Run these commands on all the bricks of the replica pair to get the attrs >> set on the backend. [root@tpc-cent-glus1-081017 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 getfattr: Removing leading '/' from absolute path names # file: exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-2=0x0001 trusted.gfid=0x108694dbc0394b7cbd3dad6a15d811a2 trusted.gfid2path.9a2f5ada22eb9c45=0x38633262623330322d323466332d346463622d393630322d3839356136396461363131662f435f564f4c2d623030312d693637342d63642d63772e6d6435 [root@tpc-cent-glus2-081017 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 getfattr: Removing leading '/' from absolute path names # file: exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-2=0x0001 trusted.gfid=0x108694dbc0394b7cbd3dad6a15d811a2 trusted.gfid2path.9a2f5ada22eb9c45=0x38633262623330322d323466332d346463622d393630322d3839356136396461363131662f435f564f4c2d623030312d693637342d63642d63772e6d6435 [root@tpc-arbiter1-100617 ~]# getfattr -d -e hex -m . /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2 getfattr: /exp/b1/gv0/.glusterfs/10/86/108694db-c039-4b7c-bd3d-ad6a15d811a2: No such file or directory [root@tpc-cent-glus1-081017 ~]# getfattr -d -e hex -m . /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 getfattr: Removing leading '/' from absolute path names # file: exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-11=0x0001 trusted.gfid=0xe0c56bf78bfe46cabde1e46b92d33df3 trusted.gfid2path.be3ba24c3ef95ff2=0x63323366353834652d353566652d343033382d393131622d3866373063656334616136662f435f564f4c2d623030332d69313331342d63642d636d2d63722e6d6435 [root@tpc-cent-glus2-081017 ~]# getfattr -d -e hex -m . /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 getfattr: Removing leading '/' from absolute path names # file: exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 security.selinux=0x73797374656d5f753a6f626a6563745f723a756e6c6162656c65645f743a733000 trusted.afr.dirty=0x trusted.afr.gv0-client-11=0x0001 trusted.gfid=0xe0c56bf78bfe46cabde1e46b92d33df3 trusted.gfid2path.be3ba24c3ef95ff2=0x63323366353834652d353566652d343033382d393131622d3866373063656334616136662f435f564f4c2d623030332d69313331342d63642d636d2d63722e6d6435 [root@tpc-arbiter1-100617 ~]# getfattr -d -e hex -m . /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3 getfattr: /exp/b4/gv0/.glusterfs/e0/c5/e0c56bf7-8bfe-46ca-bde1-e46b92d33df3: No such file or directory >> And the output of "gluster volume heal info split-brain" [root@tpc-cent-glus1-081017 ~]# gluster volume heal gv0 info split-brain Brick tpc-cent-glus1-081017:/exp/b1/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-cent-glus2-081017:/exp/b1/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-arbiter1-100617:/exp/b1/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-cent-glus1-081017:/exp/b2/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-cent-glus2-081017:/exp/b2/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-arbiter1-100617:/exp/b2/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-cent-glus1-081017:/exp/b3/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-cent-glus2-081017:/exp/b3/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-arbiter1-100617:/exp/b3/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-cent-glus1-081017:/exp/b4/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-cent-glus2-081017:/exp/b4/gv0 Status: Connected Number of entries in split-brain: 0 Brick tpc-arbiter1-100617:/exp/b4/gv0 Status: Connected Number of entries in split-brain: 0 -Matt From: Karthik Subrahmanya [mailto:ksubr...@redhat.com] Sent: Tuesday, October 17, 2017 1:26 AM To: Matt Waymack <mwaym...@nsgdv.com> Cc: gluster-users <Gluster-users@gluster.org> Subject: Re: [Gluster-users] gfid entries in volume heal info that do not heal Hi Matt, Run these commands on all the bricks of the replica pair to get the attrs set on the backend. On the bricks of first replica set: getfattr -d -e hex -m . /.glusterfs/10/86/108694db-c
Re: [Gluster-users] gfid entries in volume heal info that do not heal
OK, so here’s my output of the volume info and the heal info. I have not yet tracked down physical location of these files, any tips to finding them would be appreciated, but I’m definitely just wanting them gone. I forgot to mention earlier that the cluster is running 3.12 and was upgraded from 3.10; these files were likely stuck like this when it was on 3.10. [root@tpc-cent-glus1-081017 ~]# gluster volume info gv0 Volume Name: gv0 Type: Distributed-Replicate Volume ID: 8f07894d-e3ab-4a65-bda1-9d9dd46db007 Status: Started Snapshot Count: 0 Number of Bricks: 4 x (2 + 1) = 12 Transport-type: tcp Bricks: Brick1: tpc-cent-glus1-081017:/exp/b1/gv0 Brick2: tpc-cent-glus2-081017:/exp/b1/gv0 Brick3: tpc-arbiter1-100617:/exp/b1/gv0 (arbiter) Brick4: tpc-cent-glus1-081017:/exp/b2/gv0 Brick5: tpc-cent-glus2-081017:/exp/b2/gv0 Brick6: tpc-arbiter1-100617:/exp/b2/gv0 (arbiter) Brick7: tpc-cent-glus1-081017:/exp/b3/gv0 Brick8: tpc-cent-glus2-081017:/exp/b3/gv0 Brick9: tpc-arbiter1-100617:/exp/b3/gv0 (arbiter) Brick10: tpc-cent-glus1-081017:/exp/b4/gv0 Brick11: tpc-cent-glus2-081017:/exp/b4/gv0 Brick12: tpc-arbiter1-100617:/exp/b4/gv0 (arbiter) Options Reconfigured: nfs.disable: on transport.address-family: inet [root@tpc-cent-glus1-081017 ~]# gluster volume heal gv0 info Brick tpc-cent-glus1-081017:/exp/b1/gv0 Status: Connected Number of entries: 118 Brick tpc-cent-glus2-081017:/exp/b1/gv0 Status: Connected Number of entries: 118 Brick tpc-arbiter1-100617:/exp/b1/gv0 Status: Connected Number of entries: 0 Brick tpc-cent-glus1-081017:/exp/b2/gv0 Status: Connected Number of entries: 0 Brick tpc-cent-glus2-081017:/exp/b2/gv0 Status: Connected Number of entries: 0 Brick tpc-arbiter1-100617:/exp/b2/gv0 Status: Connected Number of entries: 0 Brick tpc-cent-glus1-081017:/exp/b3/gv0 Status: Connected Number of entries: 0 Brick tpc-cent-glus2-081017:/exp/b3/gv0 Status: Connected Number of entries: 0 Brick tpc-arbiter1-100617:/exp/b3/gv0 Status: Connected Number of entries: 0 Brick tpc-cent-glus1-081017:/exp/b4/gv0 Status: Connected Number of entries: 24 Brick tpc-cent-glus2-081017:/exp/b4/gv0 Status: Connected Number of entries: 24 Brick tpc-arbiter1-100617:/exp/b4/gv0 Status: Connected Number of entries: 0 Thank you for your help! From: Karthik Subrahmanya [mailto:ksubr...@redhat.com] Sent: Monday, October 16, 2017 10:27 AM To: Matt Waymack <mwaym...@nsgdv.com> Cc: gluster-users <Gluster-users@gluster.org> Subject: Re: [Gluster-users] gfid entries in volume heal info that do not heal Hi Matt, The files might be in split brain. Could you please send the outputs of these? gluster volume info gluster volume heal info And also the getfattr output of the files which are in the heal info output from all the bricks of that replica pair. getfattr -d -e hex -m . Thanks & Regards Karthik On 16-Oct-2017 8:16 PM, "Matt Waymack" <mwaym...@nsgdv.com<mailto:mwaym...@nsgdv.com>> wrote: Hi all, I have a volume where the output of volume heal info shows several gfid entries to be healed, but they’ve been there for weeks and have not healed. Any normal file that shows up on the heal info does get healed as expected, but these gfid entries do not. Is there any way to remove these orphaned entries from the volume so they are no longer stuck in the heal process? Thank you! ___ Gluster-users mailing list Gluster-users@gluster.org<mailto:Gluster-users@gluster.org> http://lists.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] gfid entries in volume heal info that do not heal
Hi all, I have a volume where the output of volume heal info shows several gfid entries to be healed, but they've been there for weeks and have not healed. Any normal file that shows up on the heal info does get healed as expected, but these gfid entries do not. Is there any way to remove these orphaned entries from the volume so they are no longer stuck in the heal process? Thank you! ___ Gluster-users mailing list Gluster-users@gluster.org http://lists.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Cache performance degrades over time
Hello list, I have about a half a dozen nginx servers sitting in front of Gluster (3.4.6, I know it's old) serving a mix videos and images. It's a moderate amount of traffic, each of two geo-repped sites will do 2-4 gigs/second throughout the day. Here's the problem. Reads from gluster, due to the way nginx buffers the video, can far exceed what's being served out to the internet. Serving 1 gig of video may read 3 gigs from Gluster. I can fix this by setting the performance cache on the volume to a pretty large size, right now it's at 2 gigs. This works great, gluster uses 1.5 - 2 gigs of RAM and the in/out bandwidth on the nginx machines becomes a healthy 1:1 or better. For a few days. Over time, as the machines vfs cache fills, gluster starts to use less RAM, and that ratio gets worse. Rebooting the nginx boxes (or I presume, simply dropping their caches) fixes it immediately. I'm going to try increasing vfs.cache_pressure on the nginx boxes, as this doc recommends: https://gluster.readthedocs.io/en/latest/Administrator%20Guide/Linux%20Kernel%20Tuning/#vmvfs95cache95pressure Does that make sense to tune this on the clients? Is Gluster competing with the kernel cache? That's sort of my understanding but I can't find a clear explanation. Other recommendations would be welcome, though tweaking the direct-io options is unfortunately not an option in my setup. -Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] to RAID or not?
If you don't trust the hardware raid, then steer clear of raid-6 as mdadm raid 6 is stupidly slow. I don't completely trust hardware raid either, but rebuild times should be under a day and in order to lose a raid-6 array you have to lose 3 disks. My own systems are hardware raid-6. If you're not terribly worried about maximising usable storage, then mdadm raid-10 is your friend. > On 4 Jul 2016, at 18:15:26, Gandalf Corvotempesta > <gandalf.corvotempe...@gmail.com> wrote: > > 2016-07-04 17:01 GMT+02:00 Matt Robinson <m.robin...@sheffield.ac.uk>: >> Hi Gandalf, >> >> Are you using hardware raid or mdadm? >> On high quality hardware raid, a 12 disk raid-6 is pretty solid. With mdadm >> any raid6 (especially with 12 disks) will be rubbish. > > I can use both. > I don't like very much hardware raid, even high quality. Recently i'm > having too many issue with hardware raid (like multiple disks kicked > out with no apparent reasons and virtual-disk failed with data loss) > > A RAID-6 with 12x2TB SATA disks would take days to rebuild, in the > meanwhile, multiple disks could fail resulting in data loss. > Yes, gluster is able to recover from this, but I prefere to avoid have > to resync 24TB of data via networks. > > What about a software RAID-1 ? 6 raid for each gluster nodes and 6 > disks wasted but SATA disks are cheaper. ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] to RAID or not?
Hi Gandalf, Are you using hardware raid or mdadm? On high quality hardware raid, a 12 disk raid-6 is pretty solid. With mdadm any raid6 (especially with 12 disks) will be rubbish. Matt. > On 4 Jul 2016, at 15:54:44, Gandalf Corvotempesta > <gandalf.corvotempe...@gmail.com> wrote: > > No suggestions ? > > Il 14 giu 2016 10:01 AM, "Gandalf Corvotempesta" > <gandalf.corvotempe...@gmail.com> ha scritto: > Let's assume a small cluster made by 3 servers, 12 disks/bricks each. > This cluster would be expanded to a maximum of 15 servers in near future. > > What do you suggest, a JBOD or a RAID? Which RAID level? > > 15 servers with 12 disks/bricks in JBOD are 180 bricks. Is this an > acceptable value? > Multiple raid6 for each servers? In example, RAID-6 with 6 disks and > another RAID-6 with the other 6 disks. I'll loose 4 disks on each > servers, performance would be affected and rebuild times would be huge > (by using 2TB/4TB disks) > > Any suggestions? > ___ > Gluster-users mailing list > Gluster-users@gluster.org > http://www.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] root-squash permission denied on rename
Hi, I'm fairly new to gluster so please forgive me if I'm in any way out of protocol for this list. I have a distributed volume with 2 servers hosting bricks and a third just managing the system. I really want root squashing, as there are a large number of clients and I do not want a bad keystroke on one to wipe out the contents of the gluster file-system. I'm using gluster 3.7.10 on Scientific Linux 6.7. I just cannot get gluster to work properly for normal users with root-squashing enabled. The problem is easiest to reproduce if one creates a directory with mkdir, creates a file with say 'echo hi > filename' and then tries to rename the latter to place it in the former using mv. This fails about 50% of the time. My reading suggests that it occurs when gluster decides to move the file from one brick to another as it renames it. rebalance and fix-layout have been run, but have long finished and the problem persists. I've spent a fair amount of time googling this issue and it's clearly not unprecedented, but it's supposedly fixed long before v3.7.10. I really would appreciate it if somebody could rescue me. For the moment I'm running with server.root-squash turned off. Thanks, Matt. ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] [ovirt-users] Gluster + ovirt + resize2fs
Thanks Sahina; an item I should have added as well. On Wed, Jun 1, 2016 at 10:58 PM Sahina Bose <sab...@redhat.com> wrote: > [+gluster-users] > > > On 06/01/2016 11:30 PM, Matt Wells wrote: > > Apologies, it's XFS so would be an xfs_growfs > > On Wed, Jun 1, 2016 at 10:58 AM, Matt Wells <matt.we...@mosaic451.com> > wrote: > >> Hi everyone, I had a quick question that I really needed to bounce off >> someone; one of those measure twice cut once moments. >> >> My primary datastore is on a gluster volume and the short story is I'm >> going to grow it. I've thought of two options >> >> 1 - add a brick with the new space >> ** Was wondering from the gluster point of view if anyone had a best >> practice for this. I've looked around and find many people explaining >> their stories but not a definitive best practices. >> >> >> 2 - as I'm sitting atop LVMs grow the LVM. >> ** This is the one that makes me a little nervous. I've done many >> resize2fs and never had issues, but I've never had gluster running atop >> that volume and my VM's atop that. Has anyone had any experiences they >> could share? >> >> Thanks all - >> Wells >> > > > ___ > Users mailing listUsers@ovirt.orghttp://lists.ovirt.org/mailman/listinfo/users > > > ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] lots of nfs.log activity since upgrading to 3.4.6
We have all these sites setup in a test environment, I'll see about updating. On Fri, Mar 27, 2015 at 3:47 PM, Justin Clift jus...@gluster.org wrote: As a thought, would you be ok to test our just-released 3.4.7 beta4, and verify back to us if its fixed for you? :) http://download.gluster.org/pub/gluster/glusterfs/qa-releases/3.4.7beta4/ + Justin On 27 Mar 2015, at 20:05, Matt m...@mattlantis.com wrote: Wonderful, thanks. On Thu, Mar 26, 2015 at 6:04 AM, Nithya Balachandran nbala...@redhat.com wrote: Hi Matt, The fix is available at : http://review.gluster.org/#/c/10008 This will be taken in for 3.4.7. Regards, Nithya -- GlusterFS - http://www.gluster.org An open source, distributed file system scaling to several petabytes, and handling thousands of clients. My personal twitter: twitter.com/realjustinclift ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Geo-replication stops every few days
-aux-mount-6Hn48F'. $ cat 8ed3c554-8d5d-4304-9cd1-cb9a17c0fd64:gluster%3A%2F%2F127.0.0.1%3Agtmmedia-storage.log [2015-03-16 13:19:54.624100] I [gsyncd(slave):404:main_i] top: syncing: gluster://localhost:media-vol [2015-03-16 13:19:55.752953] I [resource(slave):483:service_loop] GLUSTER: slave listening [2015-03-16 14:02:40.654535] I [repce(slave):78:service_loop] RepceServer: terminating on reaching EOF. [2015-03-16 14:02:40.661967] I [syncdutils(slave):148:finalize] top: exiting. [2015-03-16 14:02:51.987721] I [gsyncd(slave):404:main_i] top: syncing: gluster://localhost:media-vol [2015-03-16 14:02:53.141150] I [resource(slave):483:service_loop] GLUSTER: slave listening [2015-03-17 17:31:25.696300] I [repce(slave):78:service_loop] RepceServer: terminating on reaching EOF. [2015-03-17 17:31:25.703775] I [syncdutils(slave):148:finalize] top: exiting. [2015-03-17 17:31:37.139935] I [gsyncd(slave):404:main_i] top: syncing: gluster://localhost:media-vol [2015-03-17 17:31:38.228033] I [resource(slave):483:service_loop] GLUSTER: slave listening [2015-03-19 20:51:55.965342] I [resource(slave):489:service_loop] GLUSTER: connection inactive for 120 seconds, stopping [2015-03-19 20:51:55.979207] I [syncdutils(slave):148:finalize] top: exiting. Thanks, -Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] lots of nfs.log activity since upgrading to 3.4.6
Wonderful, thanks. On Thu, Mar 26, 2015 at 6:04 AM, Nithya Balachandran nbala...@redhat.com wrote: Hi Matt, The fix is available at : http://review.gluster.org/#/c/10008 This will be taken in for 3.4.7. Regards, Nithya - Original Message - From: Matt m...@mattlantis.com To: Nithya Balachandran nbala...@redhat.com Sent: Wednesday, 25 March, 2015 6:24:25 PM Subject: Re: [Gluster-users] lots of nfs.log activity since upgrading to 3.4.6 Thanks. Sounds like it is just the log level at least, no big problem. Could it be fixed in 3.4.7 before the 3.4 series closes out? I've never opened a bug for Gluster before, but I guess I could get on that. On Wed, Mar 25, 2015 at 3:48 AM, Nithya Balachandran nbala...@redhat.com wrote: Hi, This was inadvertently introduced with another patch. The fix was made to master (http://review.gluster.org/#/c/8621/) 3.6 and 3.5 but it looks like it was not backported to the 3.4 branch Regards, Nithya - Original Message - From: Matt m...@mattlantis.com To: gluster-users@gluster.org Sent: Tuesday, March 24, 2015 7:29:23 PM Subject: [Gluster-users] lots of nfs.log activity since upgrading to 3.4.6 Hello list, I have a few Wordpress sites served via NFS on Gluster. Since upgrading 3.4.6, I'm seeing a non-trivial amount (1-2 million depending on how busy the blogs are, about 4 gigs in the last three weeks) entries like this appear in nfs.log: [2015-03-24 13:49:17.314003] I [dht-common.c:1000:dht_lookup_everywhere_done] 0-wpblog-storage-dht: STATUS: hashed_subvol wpblog-storage-replicate-0 cached_subvol null [2015-03-24 13:49:17.355722] I [dht-common.c:1000:dht_lookup_everywhere_done] 0-wpblog-storage-dht: STATUS: hashed_subvol wpblog-storage-replicate-0 cached_subvol null [2015-03-24 13:49:17.616073] I [dht-common.c:1000:dht_lookup_everywhere_done] 0-wpblog-storage-dht: STATUS: hashed_subvol wpblog-storage-replicate-0 cached_subvol null It doesn't seem to be a big problem, it's just an INFO log, but it definitely wasn't there with 3.4.5. Can anyone give me any insight into what's going on? -Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] lots of nfs.log activity since upgrading to 3.4.6
Hello list, I have a few Wordpress sites served via NFS on Gluster. Since upgrading 3.4.6, I'm seeing a non-trivial amount (1-2 million depending on how busy the blogs are, about 4 gigs in the last three weeks) entries like this appear in nfs.log: [2015-03-24 13:49:17.314003] I [dht-common.c:1000:dht_lookup_everywhere_done] 0-wpblog-storage-dht: STATUS: hashed_subvol wpblog-storage-replicate-0 cached_subvol null [2015-03-24 13:49:17.355722] I [dht-common.c:1000:dht_lookup_everywhere_done] 0-wpblog-storage-dht: STATUS: hashed_subvol wpblog-storage-replicate-0 cached_subvol null [2015-03-24 13:49:17.616073] I [dht-common.c:1000:dht_lookup_everywhere_done] 0-wpblog-storage-dht: STATUS: hashed_subvol wpblog-storage-replicate-0 cached_subvol null It doesn't seem to be a big problem, it's just an INFO log, but it definitely wasn't there with 3.4.5. Can anyone give me any insight into what's going on? -Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Diagnosing Intermittent Performance Problems Possibly Caused by Gremlins
Thanks Pranith, Will do. Sunday night we put some things in place seem to be mitigating it and thankfully haven't seen it again, but if we do I'll send the profile info to the list. I was able to collect some profile info under normal load. We added some caching to some files we noticed had become really popular, and when that didn't entirely stop the problem, also stopped the most recently added gluster volume. It's odd that volume would have any impact as it was only used to archive backups and was almost never active, but several times we'd stop it during the month just because it was most recently added and the issue would go away, start it back up and it would come back. Since then it's been quiet. On Thu, Feb 5, 2015 at 5:14 AM, Pranith Kumar Karampuri pkara...@redhat.com wrote: On 02/03/2015 11:16 AM, Matt wrote: Hello List, So I've been frustraded by intermittent performance problems throughout January. The problem occurs on a two node setup running 3.4.5, 16 gigs of ram with a bunch of local disk. For sometimes an hour for sometimes weeks at a time (I have extensive graphs in OpenNMS) our Gluster boxes will get their CPUs pegged, and in vmstat they'll show extremely high numbers of context switches and interrupts. Eventually things calm down. During this time, memory usage actually drops. Overall usage on the box goes from between 6-10 gigs to right around 4 gigs, and stays there. That's what really puzzles me. When performance is problematic, sar shows one device, the device corresponding to the glusterfsd problem using all the CPU doing lots of little reads, Sometimes 70k/second, very small avg rq size, say 10-12. Afraid I don't have any saved output handy, but I can try to capture some next time it happens. I have tons of information frankly, but am trying to keep this reasonably brief. There are more than a dozen volumes on this two node setup. The CPU usage is pretty much entirely contained to one volume, a 1.5 TB volume that is just shy of 70% full. It stores uploaded files for a web app. What I hate about this app and so am always suspicious of, is that it stores a directory for every user in one level, so under the /data directory in the volume, there are 450,000 sub directories at this point. The only real mitigation step that's been taken so far was to turn off the self-heal daemon on the volume, as I thought maybe crawling that large directory was getting expensive. This doesn't seem to have done anything as the problem still occurs. At this point I figure there are one of two things sorts of things happening really broadly: one we're running into some sort of bug or performance problem with gluster we should either fix perhaps by upgrading or tuning around, or two, some process we're running but not aware of is hammering the file system causing problems. If it's the latter option, can anyone give me any tips on figuring out what might be hammering the system? I can use volume top to see what a brick is doing, but I can't figure out how to tell what clients are doing what. Apologies for the somewhat broad nature of the question, any input thoughts would be much appreciated. I can certainly provide more info about some things if it would help, but I've tried not to write a novel here. Thanks, Could you enable 'gluster volume profile volname start' for this volume? When next time this issue happens, keep collecting 'gluster volume profile volname info' outputs. Mail them and lets see what is happening. Pranith -Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Diagnosing Intermittent Performance Problems Possibly Caused by Gremlins
I’ve been trying for weeks to reproduce the performance problems in our preproduction environments but can’t. As a result, selling that just upgrading to 3.6.x and hoping it goes away might be tricky. 3.6 is perceived as a little too bleeding edge, and we’ve actually had some other not fully explained issues with this cluster recently that make us hesitate. I don’t think they’re related. On Tue, Feb 3, 2015 at 4:58 AM, Justin Clift jus...@gluster.org wrote: - Original Message - Hello List, So I've been frustraded by intermittent performance problems throughout January. The problem occurs on a two node setup running 3.4.5, 16 gigs of ram with a bunch of local disk. For sometimes an hour for sometimes weeks at a time (I have extensive graphs in OpenNMS) our Gluster boxes will get their CPUs pegged, and in vmstat they'll show extremely high numbers of context switches and interrupts. Eventually things calm down. During this time, memory usage actually drops. Overall usage on the box goes from between 6-10 gigs to right around 4 gigs, and stays there. That's what really puzzles me. When performance is problematic, sar shows one device, the device corresponding to the glusterfsd problem using all the CPU doing lots of little reads, Sometimes 70k/second, very small avg rq size, say 10-12. Afraid I don't have any saved output handy, but I can try to capture some next time it happens. I have tons of information frankly, but am trying to keep this reasonably brief. There are more than a dozen volumes on this two node setup. The CPU usage is pretty much entirely contained to one volume, a 1.5 TB volume that is just shy of 70% full. It stores uploaded files for a web app. What I hate about this app and so am always suspicious of, is that it stores a directory for every user in one level, so under the /data directory in the volume, there are 450,000 sub directories at this point. The only real mitigation step that's been taken so far was to turn off the self-heal daemon on the volume, as I thought maybe crawling that large directory was getting expensive. This doesn't seem to have done anything as the problem still occurs. At this point I figure there are one of two things sorts of things happening really broadly: one we're running into some sort of bug or performance problem with gluster we should either fix perhaps by upgrading or tuning around, or two, some process we're running but not aware of is hammering the file system causing problems. If it's the latter option, can anyone give me any tips on figuring out what might be hammering the system? I can use volume top to see what a brick is doing, but I can't figure out how to tell what clients are doing what. Apologies for the somewhat broad nature of the question, any input thoughts would be much appreciated. I can certainly provide more info about some things if it would help, but I've tried not to write a novel here. Out of curiosity, are you able to test using GlusterFS 3.6.2? We've had a bunch of pretty in-depth upstream testing at decent scale (100+ nodes) from 3.5.x onwards, with lots of performance issues identified and fixed on the way through. So, I'm kinda hopeful the problem you're describing is fixed in newer releases. :D Regards and best wishes, Justin Clift -- GlusterFS - http://www.gluster.org An open source, distributed file system scaling to several petabytes, and handling thousands of clients. My personal twitter: twitter.com/realjustinclift ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Diagnosing Intermittent Performance Problems Possibly Caused by Gremlins
Hello List, So I've been frustraded by intermittent performance problems throughout January. The problem occurs on a two node setup running 3.4.5, 16 gigs of ram with a bunch of local disk. For sometimes an hour for sometimes weeks at a time (I have extensive graphs in OpenNMS) our Gluster boxes will get their CPUs pegged, and in vmstat they'll show extremely high numbers of context switches and interrupts. Eventually things calm down. During this time, memory usage actually drops. Overall usage on the box goes from between 6-10 gigs to right around 4 gigs, and stays there. That's what really puzzles me. When performance is problematic, sar shows one device, the device corresponding to the glusterfsd problem using all the CPU doing lots of little reads, Sometimes 70k/second, very small avg rq size, say 10-12. Afraid I don't have any saved output handy, but I can try to capture some next time it happens. I have tons of information frankly, but am trying to keep this reasonably brief. There are more than a dozen volumes on this two node setup. The CPU usage is pretty much entirely contained to one volume, a 1.5 TB volume that is just shy of 70% full. It stores uploaded files for a web app. What I hate about this app and so am always suspicious of, is that it stores a directory for every user in one level, so under the /data directory in the volume, there are 450,000 sub directories at this point. The only real mitigation step that's been taken so far was to turn off the self-heal daemon on the volume, as I thought maybe crawling that large directory was getting expensive. This doesn't seem to have done anything as the problem still occurs. At this point I figure there are one of two things sorts of things happening really broadly: one we're running into some sort of bug or performance problem with gluster we should either fix perhaps by upgrading or tuning around, or two, some process we're running but not aware of is hammering the file system causing problems. If it's the latter option, can anyone give me any tips on figuring out what might be hammering the system? I can use volume top to see what a brick is doing, but I can't figure out how to tell what clients are doing what. Apologies for the somewhat broad nature of the question, any input thoughts would be much appreciated. I can certainly provide more info about some things if it would help, but I've tried not to write a novel here. Thanks, -Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://www.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Gluster 3.4.2 on Ubuntu 12.04 LTS Server - Upstart No Go
I could be completely off-base, but were you trying to mount with noatime? I ran into a similar problem where, after upgrading to 3.4.2, all my client mounts failed. I discovered (by accident) that it was only due to incompatible mount options (namely noatime). In previous versions, the client just gave a warning message about unsupported options, but now it fails without mentioning the cause. I believe there is a bug report for this issue (that I discovered afterwards). Anyways, I thought this had a chance of being the issue, but maybe it's something different in your case. Matt On Tue, Mar 4, 2014 at 2:09 PM, Brock Nanson br...@nanson.net wrote: I thought I would share my experience in case it helps someone else avoid a bruised forehead. I'm running the semiosis Gluster 3.4.2 on Ubuntu 12.04 (two nodes, replicated) as server and client on both. Going through all the typical configuration work, all seemed good. The problem came when I tried to get the boxes to start Gluster and mount the volume at boot... without user intervention. Thinking that the most difficult part of the installation should be configuring Gluster (newbie to distributed file systems in general, never used Gluster before), I foolishly wasted a pile of time trying to fix the *simple* boot problem. Well, I did fix it, but only by finally disabling the upstart files bundled in the install (glusterfs-server.conf and mounting-glusterfs.conf). This was a clean install of Ubuntu 12.04. Actually, two clean installs for testing. And then another clean install on one box to rule out the original install! Same behaviour on all installs. I spent some time experimenting with different fstab entries and found I could change the mount behaviour, but only to determine *when* the mount would fail... it always failed! My solution was to disable the two Gluster upstart conf files with .override files containing 'manual'. Then a simple script to a) start glusterfs-server; b) sleep for a few seconds; c) mount the Gluster volume. The script is called from rc.local. Hardly an elegant solution I know, but at some point *'works'* beats *'pretty but non-functional'*. It's possible there is something quirky with my install that could be responsible. But given that other than installing and configuring Gluster, nothing on the servers was tweaked, I'm thinking there is a problem with the Gluster upstart conf files. Or something in 12.04 has rendered them inoperable. Or maybe it's as a friend in Poland says... (direct translation) it's the Malice of Things... Truly a better description than anything we have in English! ;-) I'm not looking for a solution unless someone has an obvious fix that Google couldn't locate. I have a quick and dirty work around that works. I just hope to save someone else the pain. ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
[Gluster-users] Gluster, Samba, and VFS
Stumbled upon https://forge.gluster.org/samba-glusterfs/samba-glusterfs-vfs/commits/masterwhen trying to find info on how to make Gluster and Samba play nice as a general purpose file server. I have had severe performance problems in the past with mounting the Gluster volume as a Fuse mount, then exporting the Fuse mount thru Samba. As I found out after setting up the cluster this is somewhat expected when serving out lots of small files. Was hoping VFS would provide better performance when serving out lots and lots of small files. Is anyone using VFS extensions in production? Is it ready for prime time? I could not find a single reference to it on Gluster's main website (maybe I am looking in the wrong place), so not sure of the stability or supported-ness of this. ___ Gluster-users mailing list Gluster-users@gluster.org http://supercolony.gluster.org/mailman/listinfo/gluster-users
Re: [Gluster-users] Typical setup questions
Guys, Thanks for the responses it is appreciated. On 8/28/12 5:28 PM, Bryan Whitehead wrote: I'f found pricing for Infiniband switches / cards to be cheaper than 10G cards/switches with the addition of being 4X fast. I will look into this but putting all of our compute on Infiniband may be cost prohibitive. On Tue, Aug 28, 2012 at 11:44 AM, Joe Topjian j...@topjian.net wrote: Hi Matt, On Tue, Aug 28, 2012 at 9:29 AM, Matt Weil mw...@genome.wustl.edu wrote: Since we are on the subject of hardware what would be the perfect fit for a gluster brick. We where looking at a PowerEdge C2100 Rack Server. Just a note: the c2100 has been superseded by the Dell r720xd. Although the r720 is not part of the c-series, it's their official replacement. I looked at these but they only hold 8 3.5 drives verses 12 and two on the inside on the 2100. I will ask our rep about this. Do you typically run hot spares or just keep cold spares handy? During testing I found it pretty easy to saturate 1 Gig network links. This was also the case when multiple links where bonded together. Are there any cheap 10 gig switch alternatives that anyone would suggest? While not necessarily cheap, I've had great luck with Arista 7050 switches. also looking at dell's new force 10 switches. Wonder how they compare price wise. We implement them in sets of two, linked together. We then use dual-port 10gb NICs and connect each NIC to each switch. It gives multiple layers of redundancy + a theoretical 20gb throughput per server. Thanks, Joe ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Typical setup questions
Brian thanks for this response. Since we are on the subject of hardware what would be the perfect fit for a gluster brick. We where looking at a PowerEdge C2100 Rack Server. During testing I found it pretty easy to saturate 1 Gig network links. This was also the case when multiple links where bonded together. Are there any cheap 10 gig switch alternatives that anyone would suggest? Matt On 8/24/12 4:28 PM, Brian Candler wrote: On Fri, Aug 24, 2012 at 10:51:24AM -0500, Matt Weil wrote: I am curious what is used typically for the file system replication and how do you make sure that it is consistent. So for example when using large 3TB+ sata/NL-sas drives. Is is typical to replicate three times to get similar protection to raid 6? Gluster sits on top of existing filesystems on the storage bricks, so it's fine to continue to use RAID10 (for performance) or RAID6 (for capacity) on those nodes. Gluster replicated volumes, and/or gluster geo-replication, then give you an additional layer of replication on top of that, and the ability to handle entire servers going out of service. If I were you, I would not want to have a non-resilient array like a RAID0 on my storage bricks. Whilst in principle you could have lots of separate 3TB filesystems and put them into a large distributed/replicated set, I think this is likely to be difficult to manage. In particular, the process of replacing a failed disk requires more skill than a simple RAID drive swap. One word of warning: when choosing 3TB SATA drives, ensure they support error recovery control (a.k.a. time-limited error recovery). Enterprise drives do, but many consumer ones don't. The Hitachi consumer ones do, for now anyway; Seagate ones do not. To attempt to enable it on a particular drive: # smartctl -l scterc,70,70 /dev/sda If the drive supports it, you'll see: SCT Error Recovery Control set to: Read: 70 (7.0 seconds) Write: 70 (7.0 seconds) There's plenty of discussion on the linux-raid mailing list if you want to go through the archives. Also what is typically done to ensure that all replicas are in place and consistent? A cron that stats of ls's the file system from a single client? I don't have a good answer to that. Stat'ing all files recursively used to be required for gluster 3.3 to force healing. As of gluster 3.3, there is a self-healing daemon which handles this automatically. So basically, you trust gluster to do its job. I guess there could be value in running a recursive md5sum on each replica locally and comparing the results (but you'd have to allow for files which were in the process of changing during the scan) Regards, Brian. ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] gluster + firefox/sqlite
On Fri, 6 Jan 2012, Harshavardhana wrote: Users have mounted /home for years now, its nothing new. I was dying to use it for home for it's replication capability, but ran into issues with locking and sockets when using nfs clients. I have 2 systems I've been able to do tests on; everything's Scientific Linux 6.1: client1 (nfs): firefox-3.6.24-3.el6_1.x86_64 homedir serverpair1 (replicate): glusterfs-{core,fuse}-3.2.5-2.el6.x86_64 (from gluster.org) client2 (nfs or gluster native): same as client1 plus: glusterfs-{,fuse}3.2.5-4.el6.x86_64 (from epel-testing) homedir servercluster2 (distribute): glusterfs-{core,fuse}-3.2.4-1.x86_64 (from gluster.org) on client1, with nfs homedir on serverpair1, firefox takes *forever* to startup. An strace shows it's hanging up getting various locks (sqlite stuff and others). And when it finally does start, it pops up a red banner saying: The bookmarks and history system will not be functional because one of Firefox's files is in use by another application. Some security software can cause this problem Interestingly, this does not happen on client 2 with nfs homedir on servercluster2, which is running a slightly older version of gluster. And sockets get created as pipes!?! and fail to function. $ mksock testsock $ ls -al testsock prwxrwxr-x. 1 glustertest glustertest 0 Jan 6 14:13 testsock ^ This happens in both nfs homedir setups. On client2, with a native gluster homedir from server2, everything works fine. I would go native everywhere, but it would be painful to maintain on some legacy systems, I think I read 32bit systems aren't really supported(?), and I'd like to avoid all the clients doubling their homedir io. -matt ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] Transport endpoint is not connected
All, Is this normal? Can this be corrected? Thanks in advance for your responses. [2011-12-06 17:56:59.48153] I [glusterd-rpc-ops.c:1243:glusterd3_1_commit_op_cbk] 0-glusterd: Received ACC from uuid: fc5e6659-a90a-4e25-a3a7-11de9a7de81d [2011-12-06 17:56:59.48811] I [glusterd-rpc-ops.c:1243:glusterd3_1_commit_op_cbk] 0-glusterd: Received ACC from uuid: d1216f43-2ae6-42bd-a597-c0ab6a101d6b [2011-12-06 17:56:59.49073] I [glusterd-rpc-ops.c:1243:glusterd3_1_commit_op_cbk] 0-glusterd: Received ACC from uuid: 4bf94e6e-69ca-4d51-9a85-c1d98a95325d [2011-12-06 17:56:59.49137] I [glusterd-rpc-ops.c:1243:glusterd3_1_commit_op_cbk] 0-glusterd: Received ACC from uuid: 154cdbb2-6a53-449d-b6e3-bfd84091d90c [2011-12-06 17:56:59.49567] I [glusterd-rpc-ops.c:1243:glusterd3_1_commit_op_cbk] 0-glusterd: Received ACC from uuid: 4c9d68d6-d573-43d0-aec5-07173c1699d0 [2011-12-06 17:56:59.49803] I [glusterd-rpc-ops.c:818:glusterd3_1_cluster_unlock_cbk] 0-glusterd: Received ACC from uuid: fc5e6659-a90a-4e25-a3a7-11de9a7de81d [2011-12-06 17:56:59.49850] I [glusterd-rpc-ops.c:818:glusterd3_1_cluster_unlock_cbk] 0-glusterd: Received ACC from uuid: d1216f43-2ae6-42bd-a597-c0ab6a101d6b [2011-12-06 17:56:59.50228] I [glusterd-rpc-ops.c:818:glusterd3_1_cluster_unlock_cbk] 0-glusterd: Received ACC from uuid: 4bf94e6e-69ca-4d51-9a85-c1d98a95325d [2011-12-06 17:56:59.50285] I [glusterd-rpc-ops.c:818:glusterd3_1_cluster_unlock_cbk] 0-glusterd: Received ACC from uuid: 154cdbb2-6a53-449d-b6e3-bfd84091d90c [2011-12-06 17:56:59.50346] I [glusterd-rpc-ops.c:818:glusterd3_1_cluster_unlock_cbk] 0-glusterd: Received ACC from uuid: 4c9d68d6-d573-43d0-aec5-07173c1699d0 [2011-12-06 17:56:59.50375] I [glusterd-op-sm.c:7250:glusterd_op_txn_complete] 0-glusterd: Cleared local lock [2011-12-06 17:56:59.52105] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (127.0.0.1:694) [2011-12-06 17:56:59.168257] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.11:730) [2011-12-06 17:56:59.168357] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.11:728) [2011-12-06 17:56:59.168441] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.11:726) [2011-12-06 17:56:59.168503] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.11:724) [2011-12-06 17:56:59.168591] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.11:722) [2011-12-06 17:56:59.168672] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.11:720) [2011-12-06 17:56:59.169287] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.15:730) [2011-12-06 17:56:59.169359] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.15:728) [2011-12-06 17:56:59.169398] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.13:730) [2011-12-06 17:56:59.169438] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.13:728) [2011-12-06 17:56:59.169476] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.15:726) [2011-12-06 17:56:59.169529] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.13:726) [2011-12-06 17:56:59.169581] W [socket.c:1494:__socket_proto_state_machine] 0-socket.management: reading from socket failed. Error (Transport endpoint is not connected), peer (10.0.30.13:724) ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] folders with no permissions.
Just some simply iozone testing failed due to folder permissions. The tmp folder is created by iozone. six nodes with stripe 6 and underlying EXT4 file system. The ext4 filesystems where not mounted with the -o acl option. Any Ideas? in both cases it created a folder with no permissions. 188K d- 2 rootroot 24K 2011-12-06 11:28 tmp/ iozone$ rm -rf tmp rm: cannot remove directory `tmp': Permission denied test$ cd iozone.broke/ iozone.broke$ ls ./ ../ tmp/ iozone.broke$ ls -lash total 580K 288K drwxrwxrwx 6 rootroot 24K 2011-12-04 14:28 ../ 4.0K d- 2 rootroot 4.0K 2011-12-06 11:32 tmp/ each node has error trying to set permissions on that folder. [2011-12-06 12:23:36.593604] E [marker.c:2018:marker_setattr_cbk] 0-gluster1-marker: Operation not permitted occured during setattr of nul [2011-12-06 12:23:36.593669] I [server3_1-fops.c:1526:server_setattr_cbk] 0-gluster1-server: 433: SETATTR /test/iozone/tmp (-734804259) == -1 (Operation not permitted) [2011-12-06 12:23:36.593669] I [server3_1-fops.c:1526:server_setattr_cbk] 0-gluster1-server: 433: SETATTR /test/iozone/tmp (-734804259) == -1 (Operation not permitted) 188K d- 2 rootroot 24K 2011-12-06 11:28 tmp/ iozone$ chmod +rw tmp/ chmod: changing permissions of `tmp/': Operation not permitted iozone$ ls -lash ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] folders with no permissions.
On 12/7/11 12:53 PM, Matt Weil wrote: Just some simply iozone testing failed due to folder permissions. The tmp folder is created by iozone. six nodes with stripe 6 and underlying EXT4 file system. The ext4 filesystems where not mounted with out the -o acl option. I meant with out the -o acl option. Any Ideas? in both cases it created a folder with no permissions. 188K d- 2 root root 24K 2011-12-06 11:28 tmp/ iozone$ rm -rf tmp rm: cannot remove directory `tmp': Permission denied test$ cd iozone.broke/ iozone.broke$ ls ./ ../ tmp/ iozone.broke$ ls -lash total 580K 288K drwxrwxrwx 6 root root 24K 2011-12-04 14:28 ../ 4.0K d- 2 root root 4.0K 2011-12-06 11:32 tmp/ each node has error trying to set permissions on that folder. [2011-12-06 12:23:36.593604] E [marker.c:2018:marker_setattr_cbk] 0-gluster1-marker: Operation not permitted occured during setattr of nul [2011-12-06 12:23:36.593669] I [server3_1-fops.c:1526:server_setattr_cbk] 0-gluster1-server: 433: SETATTR /test/iozone/tmp (-734804259) == -1 (Operation not permitted) [2011-12-06 12:23:36.593669] I [server3_1-fops.c:1526:server_setattr_cbk] 0-gluster1-server: 433: SETATTR /test/iozone/tmp (-734804259) == -1 (Operation not permitted) 188K d- 2 root root 24K 2011-12-06 11:28 tmp/ iozone$ chmod +rw tmp/ chmod: changing permissions of `tmp/': Operation not permitted iozone$ ls -lash ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] syslog options for gluster
are there any options to have glusterd use syslog? Would like the logs to go to a central server. Thanks Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] ESXi Gluster setup options
Chris Haumesser ch@... writes: The native FUSE client has built-in failover if you mount using the server and volume name (e.g. `mount -t glusterfs server1:/foo /mnt/foo`). When mounting this way, the gluster client downloads a list of all the bricks, and if one goes down, automatically fails over to another available brick server.Note, however, that at mount-time, the client needs to be able to reach the brick server specified in the mount command. You could use simple roundrobin DNS to make sure your clients always reach an available brick.As others stated previously, NFS failover requires ucarp or an alternative ha framework.Cheers,-C- On Thu, May 26, 2011 at 2:37 PM, paul simpson paul at realisestudio.com wrote:i'm also interested in this. is there any pro/con to using native gluster FUSE client for xen images? i would have thought that would mitigate the use of ucarp (apart from initial connect). -p On 26 May 2011 21:39, Whit Blauvelt whit.glus...@transpect.com wrote: On Thu, May 26, 2011 at 08:28:29PM +, Matt Temple wrote: We've been looking for a way to have HA for our VMWare datastore, too. (Our single server had a kernel panic last night and took down the VMs.) We're very much interested in a similar setup, using Gluster, but I have a question ... with Gluster NFS, don't you have to choose a specific address of a server to connect to? And if yes, if that node goes down, how does VMWare respond? Pretty much the standard thing to do is use a virtual IP address with ucarp handling reassignment if the primary node goes down. I've yet to run that through thorough tests to see if how transparent it is in a case of failure. It's simple to set up though. There are, of course, plenty of more complicated alternatives to ucarp in the HA world - heartbeat, pacemaker, corosync Whit ___ Gluster-users mailing listGluster-users at gluster.orghttp://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing listGluster-users@gluster.orghttp://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@... http://gluster.org/cgi-bin/mailman/listinfo/gluster-users All, We just set up UCARP on our simple replicating 3.2 server, but when we tried to connect to the virtual address as an NFS store from VCenter, the connection was rejected. When we used the real ip address of the server, it connected. Is anyone successfully using UCARP/Gluster with VMWare for storage using NFSconnections. Or are we just doing something wrong? HA on the VMWare storagefor the VMDKs is pretty important and automatic NFS failover would really be terrific. Doesn't NFS have to much context to simply failover? (If this were KVM, I'm sure we'd be able to use a native gluster client, but that's another story.) Any help would be appreciated. We could document all the steps to a working example. Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] ESXi Gluster setup options
Krishna Srinivas krishna@... writes: Troy, Yes it would work, you can setup 4 servers in a distributed replicated setup acting as NFS data store for VMWare. If any one of the storage node goes down it will not be seen by the ESX hosts. Many users use this type of config for storage HA for NFS datastores. You can use SATA or SAS. Since you are using 10gb performance should not be a problem. Backend disks would be the bottleneck and hence you should experiment with a good raid setup to get maximum backend disk throughput. On Thu, Apr 21, 2011 at 9:54 PM, Troy Swaine troy.swaine@... wrote: All, We are in the process of determining a virtualized infrastructure and wanted to hear from current users of Gluster and VMWare. What we were looking to setup was an HA ESXi cluster (2 heads) with gluster backend (4 bricks to start, replicated/distributed), all backend connectivity would be 10Gbe. Mainly the storage would be for VM images but may include NAS files later. Thanks, Troy Hello, We've been looking for a way to have HA for our VMWare datastore, too. (Our single server had a kernel panic last night and took down the VMs.) We're very much interested in a similar setup, using Gluster, but I have a question ... with Gluster NFS, don't you have to choose a specific address of a server to connect to? And if yes, if that node goes down, how does VMWare respond? Matt Temple ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Gluster 3.1.1 64-bit only?
FYI: its been working great so far... Havn't had any issues with it on a self compiled i386 rpm. On Tue, Dec 14, 2010 at 11:16 AM, Liam Slusser lslus...@gmail.com wrote: You can - its just not supported or very well tested. liam On Mon, Dec 13, 2010 at 10:07 AM, Matt Keating matt.keating.li...@gmail.com wrote: Will it not run at all if I compile on a 32bit system? ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Gluster 3.1 bailout error
Hi Matt, Can you attach entire client and server log files? regards, What part of the logs do you need exactly, as the logs are about 14mb. The error comes up ALOT... - Original Message - From: Matt Keating matt.keating.li...@gmail.com To: gluster-users@gluster.org Sent: Sunday, December 5, 2010 3:39:34 AM Subject: [Gluster-users] Gluster 3.1 bailout error Hi, I've got a GlusterFS share serving web pages and I'm finding that imagecache isn't always able to create new files on the mount. Since upgrading to GlusterFS 3.1, I'm having ALOT of these errors appearing in the logs: logs/EBS-drupal-shared-.log:[2010-11-29 10:29:18.141045] E [rpc-clnt.c:199:call_bail] drupal-client-0: bailing out frame type(GlusterFS 3.1) op(FINODELK(30)) xid = 0xb69cc sent = 2010-11-29 09:59:10.112834. timeout = 1800 logs/EBS-drupal-shared-.log:[2010-11-29 10:42:58.365735] E [rpc-clnt.c:199:call_bail] drupal-client-0: bailing out frame type(GlusterFS 3.1) op(FINODELK(30)) xid = 0xb863e sent = 2010-11-29 10:12:54.584124. timeout = 1800 logs/EBS-drupal-shared-.log:[2010-11-29 12:00:02.572679] E [rpc-clnt.c:199:call_bail] drupal-client-0: bailing out frame type(GlusterFS 3.1) op(FINODELK(30)) xid = 0xbe36f sent = 2010-11-29 11:29:57.497653. timeout = 1800 Could anyone shed any light on whats happening/wrong? Thanks, Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] Gluster 3.1.1 64-bit only?
Will it not run at all if I compile on a 32bit system? ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] Gluster 3.1 bailout error
Hi, I've got a GlusterFS share serving web pages and I'm finding that imagecache isn't always able to create new files on the mount. Since upgrading to GlusterFS 3.1, I'm having ALOT of these errors appearing in the logs: logs/EBS-drupal-shared-.log:[2010-11-29 10:29:18.141045] E [rpc-clnt.c:199:call_bail] drupal-client-0: bailing out frame type(GlusterFS 3.1) op(FINODELK(30)) xid = 0xb69cc sent = 2010-11-29 09:59:10.112834. timeout = 1800 logs/EBS-drupal-shared-.log:[2010-11-29 10:42:58.365735] E [rpc-clnt.c:199:call_bail] drupal-client-0: bailing out frame type(GlusterFS 3.1) op(FINODELK(30)) xid = 0xb863e sent = 2010-11-29 10:12:54.584124. timeout = 1800 logs/EBS-drupal-shared-.log:[2010-11-29 12:00:02.572679] E [rpc-clnt.c:199:call_bail] drupal-client-0: bailing out frame type(GlusterFS 3.1) op(FINODELK(30)) xid = 0xbe36f sent = 2010-11-29 11:29:57.497653. timeout = 1800 Could anyone shed any light on whats happening/wrong? Thanks, Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] filling gluster cluster with large file doesn't crash the system?!
craig, A) stat on server that generated the file: j...@riff:/mnt/gluster$ stat y.out File: `y.out' Size: 214574579712Blocks: 291441832 IO Block: 65536 regular file Device: 16h/22dInode: 14213316644377695875 Links: 1 Access: (0777/-rwxrwxrwx) Uid: (0/root) Gid: (0/root) Access: 2010-11-09 10:32:16.0 -0800 Modify: 2010-11-09 13:57:05.0 -0800 Change: 2010-11-09 13:57:05.0 -0800 B) stat on gluster brick (brick2) that is housing the file: [r...@brick2 ~]# stat /exp2/y.out File: `/exp2/y.out' Size: 214574579712Blocks: 291441832 IO Block: 4096 regular file Device: fd00h/64768dInode: 655412 Links: 1 Access: (0777/-rwxrwxrwx) Uid: (0/root) Gid: (0/root) Access: 2010-11-09 10:32:16.0 -0800 Modify: 2010-11-09 13:57:05.0 -0800 Change: 2010-11-09 13:57:05.0 -0800 c) df on brick 2 [r...@brick2 ~]# df -h FilesystemSize Used Avail Use% Mounted on /dev/mapper/VolGroup00-LogVol00 143G 143G 0 100% / /dev/hda1 99M 13M 82M 13% /boot tmpfs 470M 0 470M 0% /dev/shm 172.16.1.76:/gs-test 283G 158G 119G 58% /mnt/gluster interesting that block size is different depending on who you ask. [r...@brick2 ~]# dumpe2fs /dev/hda1 | grep -i 'Block size' dumpe2fs 1.39 (29-May-2006) Block size: 1024 -Matt On Nov 11, 2010, at 9:44 PM, Craig Carl wrote: Matt, Based on your Gluster servers configs that file is bigger than the available disk space, obviously that isn't right. Can you send us the output of `stat y.out` taken from the Gluster mount point and from the back end of the server Gluster created the file on I'm also going to try and reproduce the problem here on 3.1 and 3.1.1qa5. Thanks, Craig -- Craig Carl Gluster, Inc. Cell - (408) 829-9953 (California, USA) Gtalk - craig.c...@gmail.com From: Matt Hodson ma...@geospiza.com To: Craig Carl cr...@gluster.com Cc: Jeff Kozlowski j...@genesifter.net, gluster-users@gluster.org Sent: Wednesday, November 10, 2010 9:21:40 AM Subject: Re: [Gluster-users] filling gluster cluster with large file doesn't crash the system?! Craig, inline... On Nov 10, 2010, at 7:17 AM, Craig Carl wrote: Matt - A couple of questions - What is your volume config? (`gluster volume info all`) gluster volume info all Volume Name: gs-test Type: Distribute Status: Started Number of Bricks: 2 Transport-type: tcp Bricks: Brick1: 172.16.1.76:/exp1 Brick2: 172.16.2.117:/exp2 What is the hardware config for each storage server? brick 1 = 141GB brick 2 = 143GB What command did you run to create the test data? #perl -e 'print rand while 1' y.out What process is still writing to the file? same one as above. Thanks, Craig -- Craig Carl Gluster, Inc. Cell - (408) 829-9953 (California, USA) Gtalk - craig.c...@gmail.com From: Matt Hodson ma...@geospiza.com To: gluster-users@gluster.org Cc: Jeff Kozlowski j...@genesifter.net Sent: Tuesday, November 9, 2010 10:46:04 AM Subject: Re: [Gluster-users] filling gluster cluster with large file doesn'tcrash the system?! I should also note that on this non-production test rig the block size on both bricks is 1KB (1024) so the theoretical file size limit is 16GB. so how then did i get a file of 200GB? -matt On Nov 9, 2010, at 10:34 AM, Matt Hodson wrote: craig et al, I have a 2 brick distributed 283GB gluster cluster on CentoOS 5. we nfs mounted the cluster from a 3rd machine and wrote random junk to a file. i watched the file grow to 200GB on the cluster when it appeared to stop. however the machine writing to the file still lists the file as growing. it's now at over 320GB. what's going on? -matt --- Matt Hodson Scientific Customer Support, Geospiza (206) 633-4403, Ext. 111 http://www.geospiza.com ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] filling gluster cluster with large file doesn't crash the system?!
Craig, inline... On Nov 10, 2010, at 7:17 AM, Craig Carl wrote: Matt - A couple of questions - What is your volume config? (`gluster volume info all`) gluster volume info all Volume Name: gs-test Type: Distribute Status: Started Number of Bricks: 2 Transport-type: tcp Bricks: Brick1: 172.16.1.76:/exp1 Brick2: 172.16.2.117:/exp2 What is the hardware config for each storage server? brick 1 = 141GB brick 2 = 143GB What command did you run to create the test data? #perl -e 'print rand while 1' y.out What process is still writing to the file? same one as above. Thanks, Craig -- Craig Carl Gluster, Inc. Cell - (408) 829-9953 (California, USA) Gtalk - craig.c...@gmail.com From: Matt Hodson ma...@geospiza.com To: gluster-users@gluster.org Cc: Jeff Kozlowski j...@genesifter.net Sent: Tuesday, November 9, 2010 10:46:04 AM Subject: Re: [Gluster-users] filling gluster cluster with large file doesn'tcrash the system?! I should also note that on this non-production test rig the block size on both bricks is 1KB (1024) so the theoretical file size limit is 16GB. so how then did i get a file of 200GB? -matt On Nov 9, 2010, at 10:34 AM, Matt Hodson wrote: craig et al, I have a 2 brick distributed 283GB gluster cluster on CentoOS 5. we nfs mounted the cluster from a 3rd machine and wrote random junk to a file. i watched the file grow to 200GB on the cluster when it appeared to stop. however the machine writing to the file still lists the file as growing. it's now at over 320GB. what's going on? -matt --- Matt Hodson Scientific Customer Support, Geospiza (206) 633-4403, Ext. 111 http://www.geospiza.com ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] filling gluster cluster with large file doesn't crash the system?!
craig et al, I have a 2 brick distributed 283GB gluster cluster on CentoOS 5. we nfs mounted the cluster from a 3rd machine and wrote random junk to a file. i watched the file grow to 200GB on the cluster when it appeared to stop. however the machine writing to the file still lists the file as growing. it's now at over 320GB. what's going on? -matt --- Matt Hodson Scientific Customer Support, Geospiza (206) 633-4403, Ext. 111 http://www.geospiza.com ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] filling gluster cluster with large file doesn't crash the system?!
I should also note that on this non-production test rig the block size on both bricks is 1KB (1024) so the theoretical file size limit is 16GB. so how then did i get a file of 200GB? -matt On Nov 9, 2010, at 10:34 AM, Matt Hodson wrote: craig et al, I have a 2 brick distributed 283GB gluster cluster on CentoOS 5. we nfs mounted the cluster from a 3rd machine and wrote random junk to a file. i watched the file grow to 200GB on the cluster when it appeared to stop. however the machine writing to the file still lists the file as growing. it's now at over 320GB. what's going on? -matt --- Matt Hodson Scientific Customer Support, Geospiza (206) 633-4403, Ext. 111 http://www.geospiza.com ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] filling gluster cluster with large file doesn't crash the system?!
approx 141GB+143GB=283 avail to the cluster. see below. Brick #1 (main gluster server) ma...@meathouse|11:01:56 $ df -h FilesystemSize Used Avail Use% Mounted on /dev/mapper/VolGroup00-LogVol00 141G 15G 119G 12% / Brick #2 (slave) [r...@localhost ~]# df -h FilesystemSize Used Avail Use% Mounted on /dev/mapper/VolGroup00-LogVol00 143G 143G 0 100% / /dev/hda1 99M 13M 82M 13% /boot tmpfs 470M 0 470M 0% /dev/shm 172.16.1.76:/gs-test 283G 158G 119G 58% /mnt/gluster -matt --- Matt Hodson Scientific Customer Support, Geospiza (206) 633-4403, Ext. 111 http://www.geospiza.com On Nov 9, 2010, at 10:57 AM, Luis E. Cerezo wrote: what's the size of the storage bricks? On Nov 9, 2010, at 12:46 PM, Matt Hodson wrote: I should also note that on this non-production test rig the block size on both bricks is 1KB (1024) so the theoretical file size limit is 16GB. so how then did i get a file of 200GB? -matt On Nov 9, 2010, at 10:34 AM, Matt Hodson wrote: craig et al, I have a 2 brick distributed 283GB gluster cluster on CentoOS 5. we nfs mounted the cluster from a 3rd machine and wrote random junk to a file. i watched the file grow to 200GB on the cluster when it appeared to stop. however the machine writing to the file still lists the file as growing. it's now at over 320GB. what's going on? -matt --- Matt Hodson Scientific Customer Support, Geospiza (206) 633-4403, Ext. 111 http://www.geospiza.com ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users Luis E. Cerezo blog: http://www.luiscerezo.org fotofun: http://www.flickr.com/photos/luiscerezo/ twitter: http://twitter.com/luiscerezo/ Voice: +1 412 223 7396 ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] monitor connections and activity?
Is there a way using gluster to monitor number of mounts to a gluster cluster and any current activity? --- Matt Hodson Scientific Customer Support, Geospiza (206) 633-4403, Ext. 111 http://www.geospiza.com ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] cannot nfs mount glusterFS
I just installed distributed gluster FS on 2 CentOS 5 boxes. install and configuration seemed to go fine. gluterd is running. firewalls/ iptables are off. however for the life of me i cannot nfs mount the main gluster server from either a OSX or a CentOS 5 box. I use NFS often and have a fair amount of experience with it so i've reviewed most of the common pitfalls. here's the command that fails from centos: $ sudo mount -v -t nfs 172.16.1.76:/gs-test /mnt/gluster/ mount: trying 172.16.1.76 prog 13 vers 3 prot tcp port 2049 mount: trying 172.16.1.76 prog 15 vers 3 prot udp port 909 mount: 172.16.1.76:/gs-test failed, reason given by server: No such file or directory and the same one from OSX 10.5 sudo mount -v -t nfs 172.16.1.76:/gs-test /gluster/ mount_nfs: can't access /gs-test: No such file or directory what's weird is that i can mount actual dirs on the gluster server, just not the gluster VOLNMAE. in other words, this command works fine because it's mounting an actual dir. $sudo mount -v -t nfs 172.16.1.76:/ /mnt/gluster/ help? thanks, -matt --- Matt Hodson Scientific Customer Support, Geospiza (206) 633-4403, Ext. 111 http://www.geospiza.com ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] cannot nfs mount glusterFS
HA! that was it. dolt! thank you. i was going crazy looking at other stuff. -matt --- Matt Hodson Scientific Customer Support, Geospiza (206) 633-4403, Ext. 111 http://www.geospiza.com On Nov 3, 2010, at 11:26 AM, Vikas Gorur wrote: On Nov 3, 2010, at 11:18 AM, Matt Hodson wrote: I just installed distributed gluster FS on 2 CentOS 5 boxes. install and configuration seemed to go fine. gluterd is running. firewalls/iptables are off. however for the life of me i cannot nfs mount the main gluster server from either a OSX or a CentOS 5 box. I use NFS often and have a fair amount of experience with it so i've reviewed most of the common pitfalls. here's the command that fails from centos: $ sudo mount -v -t nfs 172.16.1.76:/gs-test /mnt/gluster/ mount: trying 172.16.1.76 prog 13 vers 3 prot tcp port 2049 mount: trying 172.16.1.76 prog 15 vers 3 prot udp port 909 mount: 172.16.1.76:/gs-test failed, reason given by server: No such file or directory and the same one from OSX 10.5 sudo mount -v -t nfs 172.16.1.76:/gs-test /gluster/ mount_nfs: can't access /gs-test: No such file or directory what's weird is that i can mount actual dirs on the gluster server, just not the gluster VOLNMAE. in other words, this command works fine because it's mounting an actual dir. $sudo mount -v -t nfs 172.16.1.76:/ /mnt/gluster/ You have the kernel NFS service running. That is why you can mount regular directories on the gluster server. When you try to mount Gluster the kernel NFS server is actually looking for a directory called /gs-test, which ofcourse does not exist. You need to stop the kernel NFS service and stop and start the gluster volume. -- Vikas Gorur Engineer - Gluster, Inc. -- ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] GlusterFS behavior with 2 clients
Hello, I recently discovered GlusterFS and followed the installation instructions and the relatively brief tutorials that describe setting up test-volume but the behavior I am seeing is odd. I have 4 machines set up to test GlusterFS: 2 servers and 2 clients. All the machines are running RHEL5U4 x86_64. The servers were set up as so: 192.168.56.101 server1 192.168.56.102 server2 192.168.56.103 client1 192.168.56.104 client2 glusterfs-core-3.1.0-1 and glusterfs-fuse-3.1.0-1 were installed on all 4 nodes. glusterd was started on all 4 nodes (though I expect only the bricks/peers need it). The commands executed on server1 were: gluster peer probe server2 (no problems here) gluster peer status (it returned the correct results but I don't have the output handy) gluster volume create test-volume replica 2 transport tcp server1:/exp1 server2:/exp2 (the command succeeded and it created an /exp1 directory on server1 and /exp2 on server2) gluster volume start test-volume (again, no problems) Now, on the clients... Mount test-volume on the clients: [r...@client1 tmp]# mount -t glusterfs server1:/test-volume /mnt [r...@client2 ~]# mount -t glusterfs server1:/test-volume /mnt Make a file on test-volume using client1: [r...@client1 tmp]# echo 1234 /mnt/foo [r...@client1 tmp]# cat /mnt/foo 1234 [r...@client1 tmp]# ls -al /mnt/foo -rw-r--r-- 1 root root 5 Oct 28 19:34 /mnt/foo Make sure the file is seen on client2: [r...@client2 ~]# cat /mnt/foo 1234 [r...@client2 ~]# ls -al /mnt/foo -rw-r--r-- 1 root root 5 Oct 28 19:34 /mnt/foo Append to the file using client2: [r...@client2 ~]# echo 5678 /mnt/foo [r...@client2 ~]# ls -al /mnt/foo -rw-r--r-- 1 root root 10 Oct 28 19:35 /mnt/foo [r...@client2 ~]# md5sum /mnt/foo 9053253e972cf40443a4083f452f24d4 /mnt/foo Now check and see that client1 sees the changes: [r...@client1 tmp]# cat /mnt/foo 1234 [r...@client1 tmp]# ls -al /mnt/foo -rw-r--r-- 1 root root 10 Oct 28 19:35 /mnt/foo [r...@client1 tmp]# md5sum /mnt/foo e7df7cd2ca07f4f1ab415d457a6e1c13 /mnt/foo If I check server1:/exp1/foo and server2:/exp2/foo, the files are in agreement with what client2 thinks the file should look like. client1 sees the new file size according to ls but cat and md5sum still only think the file in its original 1234 state is there. If I unmount and remount test-volume on client1, it sees the modified file as it exists on server1 and server2. I've tried this same test on both RHEL5U4 and Fedora Core 13 with the same results so I must be doing something wrong. Can someone please tell me what I have done incorrectly? Thank you for your patience with a newbie. - Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] Nufa deprecated?
Hi, (i) a note at the top on the NUFA with single process page http://www.gluster.com/community/documentation/index.php/NUFA_with_single_process declares NUFA as deprecated. Does this mean any Nufa setup is scheduled to be unsupported of is it just the NUFA with single process as client and server processes have been merged. (ii) In setting up Nufa/replicate with a single process I am right now starting the glusterfsd daemon by locally mounting my Nufa/replicate volume. This is a pretty strange way to start a daemon but first starting the daemon and then trying to mount locally does not work with my single .vol file. (iii) I am also wondering about my NUFA/replicate/distribute setup as described in http://gluster.org/pipermail/gluster-users/2010-July/004988.html is this considered by the glusterFS developers an unsupported setup? (iv) Would it be possible to re-introduce the unify translator to get a replicated NUFA setup with multiple local discs working? (I am quite willing to not have the files distributed across local bricks.) Thanks for the help! Regards, Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] trouble combining nufa, distribute and replicate
On Jul 7, 2010, at 19:03 , Jeff Darcy wrote: On 07/07/2010 07:13 AM, Matthias Munnich wrote: thanks a lot for your comment! It sounds like I hit a bug here. Would you still feel queasy if I added option lookup-unhashed yes to avoid dht? I don't think that will really avoid dht, especially the extended-attribute parts that are the likely cause of conflict with nufa. What I reported here was some initial testing. In the end I like to use glusterfs to provide a uniform name space for our O(20) workstations with lokal storage of 4 to 16TB. The data should be mirrored (once) for reliability and stored locally were possible for speed. I also would prefer not to glue together local disk using LVM or software raid to keep it easy to add/remove disks without having to expand a filesystem. Any hints how to set this up with glusterfs? I think you can get close enough with just nufa on top of replicate. If you have two disks per machine, no matter how many machines you have, assign one to be active and one passive. Pair each active to a passive on another node however you like using cluster/replicate, then combine all of those using cluster/nufa with local-volume-name pointing to the replica pair where the active half is local. If you had more than two disks per machine, this wouldn't work quite as well but the differences should be minor. If that's not good enough, I just looked at the code and it doesn't seem like it would be hard to make nufa recognize multiple volumes (instead of just one) as local. If you'd like, I could try generating and submitting a patch for that. This would be REAL COOL!!! Most of our machines hold 4 disk and a few up to 8. Thanks so much for the help! ... Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users Matt langel...@gmx.net ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] NUFA/replicate setup
Hi James, did you ever figure out how to combine replicate with nufa. I always run into stale NFS handle errors when I try to do this. Thanks for your help! (I'll send a detailed description of my tries to the gluster-users list) Matt langel...@gmx.net ___ Gluster-users mailing list Gluster-users@gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] DHT and AFR question
Hi, I'm setting up gluster to share /usr/local among 24 compute nodes. The basic goal is to be able to change files in /usr/local in one place, and have it replicate out to all the other nodes. What I'd like to avoid is having a single point of failure where one (or several) nodes go down and the gluster volume becomes unavailable everywhere. I've begun to set it up using this example http://www.gluster.org/docs/index.php/Mixing_DHT_and_AFR. If all the nodes are both client and servers, how many replicate volumes should I have? I don't want a ton of replication traffic, but redundancy is important. Maximizing the size of the volume is less important to me since I'm just reclaiming otherwise unused local disk space on the nodes. Thanks, Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
Re: [Gluster-users] Problem with fs hang
Stephan von Krawczynski wrote: Hello all, I am evaluating glusterfs currently and therefore use a testbed consisting of four (real) boxes, two configured as fileservers, two as clients, see configs below. All I have to do to make the fs hang on both clients (sooner or later) is to run bonnie (a simple fs check program) constantly on the mounted tree. I'm seeing similar problems with 2.0.1 -- any log entries? I get a lot of these in glusterfs.log when mine hangs: [2009-06-11 05:10:51] E [client-protocol.c:292:call_bail] zircon: bailing out frame STATFS(15) frame sent = 2009-06-11 04:40:50. frame-timeout = 1800 [2009-06-11 05:10:52] W [client-protocol.c:5869:protocol_client_interpret] zircon: no frame for callid=1913585 type=4 op=29 [2009-06-11 05:10:52] W [client-protocol.c:5869:protocol_client_interpret] zircon: no frame for callid=2706745 type=4 op=40 My setup is very close to yours -- using replicate, iocache, readahead, and writebehind on the client and iothreads on the servers. The thread below sounds like my problem, but I don't have autoscaling (explicitly) turned on: http://www.mail-archive.com/gluster-de...@nongnu.org/msg06140.html ...so I'm wondering if it could be something else. -Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
[Gluster-users] another NFS vs glusterfs performance question
Hi All, I'm new to gluster and have a basic test environment of three old PCs: two servers and one client. I've currently got it configured to do AFR on the two servers and HA on the client, according to this example: http://www.gluster.org/docs/index.php/High-availability_storage_using_server-side_AFR I'm trying to figure out why NFS seems significantly faster in my (basic) tests. My config files and results are below. Any help is greatly appreciated! server1 (garnet) is SUSE SLES 9(OES1), gluster 2.0.0rc7, FUSE 2.5.3, 2.6.5-7.316-smp server2 (or) is SUSE SLES 10, gluster 2.0.0rc7, FUSE 2.7.2, 2.6.16.60-0.34-default client1 (charon) is SUSE SLES 10, gluster 2.0.0rc7, FUSE 2.7.2, 2.6.16.60-0.34-default RESULTS all tests performed on the client -- /gfs is my glusterfs mount and /nfs is the gluster FS shared from server1 via NFS: GFS - no performance translators time find /gfs/users/1 -type f 0.768u 1.460s 1:59.09 1.8% 0+0k 0+0io 0pf+0w GFS - w/readahead and writeback: 0.784u 1.860s 1:59.62 2.2% 0+0k 0+0io 0pf+0w NFS time find /nfs/users/1 -type f 0.584u 3.796s 0:37.96 11.5% 0+0k 0+0io 0pf+0w NFS - after an umount/mount time find /nfs/users/1 -type f 0.556u 3.224s 0:40.57 9.2% 0+0k 0+0io 0pf+0w GFS - dd Directory: /gfs/users [charon: users]# time sh -c dd if=/dev/zero of=ddfile bs=8k count=200 sync 200+0 records in 200+0 records out 1638400 bytes (16 GB) copied, 7065.52 seconds, 2.3 MB/s 1.488u 13.440s 1:57:45.64 0.2% 0+0k 0+0io 1pf+0w NFS - dd (unmount NFS volume, remount it) Directory: /nfs/users [charon: users]# time sh -c dd if=/dev/zero of=ddfile bs=8k count=200 sync 200+0 records in 200+0 records out 1638400 bytes (16 GB) copied, 1582.31 seconds, 10.4 MB/s 2.640u 125.299s 26:22.70 8.0% 0+0k 0+0io 5pf+0w CONFIGS: -- server1 (garnet) [garnet: users]# cat /etc/gluster/glusterfsd-ha-afr.vol # dataspace on garnet volume gfs-ds type storage/posix option directory /export/home end-volume # posix locks volume gfs-ds-locks type features/posix-locks subvolumes gfs-ds end-volume # dataspace on or volume gfs-or-ds type protocol/client option transport-type tcp/client option remote-host 152.xx.xx.xx option remote-subvolume gfs-ds-locks option transport-timeout 10 end-volume # automatic file replication translator for dataspace volume gfs-ds-afr type cluster/afr subvolumes gfs-ds-locks gfs-or-ds# local and remote dataspaces end-volume # the actual volume to export volume users type performance/io-threads option thread-count 8 subvolumes gfs-ds-afr end-volume # make the home volume available as a server share volume server type protocol/server option transport-type tcp subvolumes users option auth.addr.gfs-ds-locks.allow 152.xx.xx.* option auth.addr.users.allow 152.xx.xx.* end-volume -- server2 (or) [or: gluster]# cat /etc/gluster/glusterfsd-ha-afr.vol # dataspace on or volume gfs-ds type storage/posix option directory /export/home end-volume # posix locks volume gfs-ds-locks type features/posix-locks subvolumes gfs-ds end-volume # dataspace on garent volume gfs-garnet-ds type protocol/client option transport-type tcp/client option remote-host 152.xx.xx.xx option remote-subvolume gfs-ds-locks option transport-timeout 10 end-volume # automatic file replication translator for dataspace volume gfs-ds-afr type cluster/afr subvolumes gfs-ds-locks gfs-garnet-ds# local and remote dataspaces end-volume # the actual volume to export volume users type performance/io-threads option thread-count 8 subvolumes gfs-ds-afr end-volume # make the users volume available as a server share volume server type protocol/server option transport-type tcp subvolumes users option auth.addr.gfs-ds-locks.allow 152.xx.xx.* option auth.addr.users.allow 152.xx.xx.* end-volume -- client1 (charon) [r...@charon:users]# cat /etc/gluster/glusterfs-ha.vol # the exported volume to mount volume gluster type protocol/client option transport-type tcp/client option remote-host gluster.example.com # RRDNS option remote-subvolume users# exported volume option transport-timeout 10 end-volume # performance block for gluster volume writeback type performance/write-behind option aggregate-size 131072 subvolumes gluster end-volume # performance block for gluster volume readahead type performance/read-ahead option page-size 65536 option page-count 16 subvolumes writeback end-volume volume ioc type performance/io-cache option cache-size 128MB subvolumes readahead end-volume Thanks! -Matt ___ Gluster-users mailing list Gluster-users@gluster.org http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users