<div dir="auto">Updates on this critical bug ?</div><div class="gmail_extra"><br><div class="gmail_quote">Il 18 apr 2017 8:24 PM, "Gandalf Corvotempesta" <<a href="mailto:gandalf.corvotempesta@gmail.com">gandalf.corvotempesta@gmail.com</a>> ha scritto:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Any update ?<br>
In addition, if this is a different bug but the "workflow" is the same<br>
as the previous one, how is possible that fixing the previous bug<br>
triggered this new one ?<br>
<br>
Is possible to have some details ?<br>
<br>
2017-04-04 16:11 GMT+02:00 Krutika Dhananjay <<a href="mailto:kdhananj@redhat.com">kdhananj@redhat.com</a>>:<br>
> Nope. This is a different bug.<br>
><br>
> -Krutika<br>
><br>
> On Mon, Apr 3, 2017 at 5:03 PM, Gandalf Corvotempesta<br>
> <<a href="mailto:gandalf.corvotempesta@gmail.com">gandalf.corvotempesta@gmail.<wbr>com</a>> wrote:<br>
>><br>
>> This is a good news<br>
>> Is this related to the previously fixed bug?<br>
>><br>
>> Il 3 apr 2017 10:22 AM, "Krutika Dhananjay" <<a href="mailto:kdhananj@redhat.com">kdhananj@redhat.com</a>> ha<br>
>> scritto:<br>
>>><br>
>>> So Raghavendra has an RCA for this issue.<br>
>>><br>
>>> Copy-pasting his comment here:<br>
>>><br>
>>> <RCA><br>
>>><br>
>>> Following is a rough algorithm of shard_writev:<br>
>>><br>
>>> 1. Based on the offset, calculate the shards touched by current write.<br>
>>> 2. Look for inodes corresponding to these shard files in itable.<br>
>>> 3. If one or more inodes are missing from itable, issue mknod for<br>
>>> corresponding shard files and ignore EEXIST in cbk.<br>
>>> 4. resume writes on respective shards.<br>
>>><br>
>>> Now, imagine a write which falls to an existing "shard_file". For the<br>
>>> sake of discussion lets consider a distribute of three subvols - s1, s2, s3<br>
>>><br>
>>> 1. "shard_file" hashes to subvolume s2 and is present on s2<br>
>>> 2. add a subvolume s4 and initiate a fix layout. The layout of ".shard"<br>
>>> is fixed to include s4 and hash ranges are changed.<br>
>>> 3. write that touches "shard_file" is issued.<br>
>>> 4. The inode for "shard_file" is not present in itable after a graph<br>
>>> switch and features/shard issues an mknod.<br>
>>> 5. With new layout of .shard, lets say "shard_file" hashes to s3 and<br>
>>> mknod (shard_file) on s3 succeeds. But, the shard_file is already present on<br>
>>> s2.<br>
>>><br>
>>> So, we have two files on two different subvols of dht representing same<br>
>>> shard and this will lead to corruption.<br>
>>><br>
>>> </RCA><br>
>>><br>
>>> Raghavendra will be sending out a patch in DHT to fix this issue.<br>
>>><br>
>>> -Krutika<br>
>>><br>
>>><br>
>>> On Tue, Mar 28, 2017 at 11:49 PM, Pranith Kumar Karampuri<br>
>>> <<a href="mailto:pkarampu@redhat.com">pkarampu@redhat.com</a>> wrote:<br>
>>>><br>
>>>><br>
>>>><br>
>>>> On Mon, Mar 27, 2017 at 11:29 PM, Mahdi Adnan <<a href="mailto:mahdi.adnan@outlook.com">mahdi.adnan@outlook.com</a>><br>
>>>> wrote:<br>
>>>>><br>
>>>>> Hi,<br>
>>>>><br>
>>>>><br>
>>>>> Do you guys have any update regarding this issue ?<br>
>>>><br>
>>>> I do not actively work on this issue so I do not have an accurate<br>
>>>> update, but from what I heard from Krutika and Raghavendra(works on DHT) is:<br>
>>>> Krutika debugged initially and found that the issue seems more likely to be<br>
>>>> in DHT, Satheesaran who helped us recreate this issue in lab found that just<br>
>>>> fix-layout without rebalance also caused the corruption 1 out of 3 times.<br>
>>>> Raghavendra came up with a possible RCA for why this can happen.<br>
>>>> Raghavendra(CCed) would be the right person to provide accurate update.<br>
>>>>><br>
>>>>><br>
>>>>><br>
>>>>> --<br>
>>>>><br>
>>>>> Respectfully<br>
>>>>> Mahdi A. Mahdi<br>
>>>>><br>
>>>>> ______________________________<wbr>__<br>
>>>>> From: Krutika Dhananjay <<a href="mailto:kdhananj@redhat.com">kdhananj@redhat.com</a>><br>
>>>>> Sent: Tuesday, March 21, 2017 3:02:55 PM<br>
>>>>> To: Mahdi Adnan<br>
>>>>> Cc: Nithya Balachandran; Gowdappa, Raghavendra; Susant Palai;<br>
>>>>> <a href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a> List<br>
>>>>><br>
>>>>> Subject: Re: [Gluster-users] Gluster 3.8.10 rebalance VMs corruption<br>
>>>>><br>
>>>>> Hi,<br>
>>>>><br>
>>>>> So it looks like Satheesaran managed to recreate this issue. We will be<br>
>>>>> seeking his help in debugging this. It will be easier that way.<br>
>>>>><br>
>>>>> -Krutika<br>
>>>>><br>
>>>>> On Tue, Mar 21, 2017 at 1:35 PM, Mahdi Adnan <<a href="mailto:mahdi.adnan@outlook.com">mahdi.adnan@outlook.com</a>><br>
>>>>> wrote:<br>
>>>>>><br>
>>>>>> Hello and thank you for your email.<br>
>>>>>> Actually no, i didn't check the gfid of the vms.<br>
>>>>>> If this will help, i can setup a new test cluster and get all the data<br>
>>>>>> you need.<br>
>>>>>><br>
>>>>>> Get Outlook for Android<br>
>>>>>><br>
>>>>>><br>
>>>>>> From: Nithya Balachandran<br>
>>>>>> Sent: Monday, March 20, 20:57<br>
>>>>>> Subject: Re: [Gluster-users] Gluster 3.8.10 rebalance VMs corruption<br>
>>>>>> To: Krutika Dhananjay<br>
>>>>>> Cc: Mahdi Adnan, Gowdappa, Raghavendra, Susant Palai,<br>
>>>>>> <a href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a> List<br>
>>>>>><br>
>>>>>> Hi,<br>
>>>>>><br>
>>>>>> Do you know the GFIDs of the VM images which were corrupted?<br>
>>>>>><br>
>>>>>> Regards,<br>
>>>>>><br>
>>>>>> Nithya<br>
>>>>>><br>
>>>>>> On 20 March 2017 at 20:37, Krutika Dhananjay <<a href="mailto:kdhananj@redhat.com">kdhananj@redhat.com</a>><br>
>>>>>> wrote:<br>
>>>>>><br>
>>>>>> I looked at the logs.<br>
>>>>>><br>
>>>>>> From the time the new graph (since the add-brick command you shared<br>
>>>>>> where bricks 41 through 44 are added) is switched to (line 3011 onwards in<br>
>>>>>> nfs-gfapi.log), I see the following kinds of errors:<br>
>>>>>><br>
>>>>>> 1. Lookups to a bunch of files failed with ENOENT on both replicas<br>
>>>>>> which protocol/client converts to ESTALE. I am guessing these entries got<br>
>>>>>> migrated to<br>
>>>>>><br>
>>>>>> other subvolumes leading to 'No such file or directory' errors.<br>
>>>>>><br>
>>>>>> DHT and thereafter shard get the same error code and log the<br>
>>>>>> following:<br>
>>>>>><br>
>>>>>> 0 [2017-03-17 14:04:26.353444] E [MSGID: 109040]<br>
>>>>>> [dht-helper.c:1198:dht_<wbr>migration_complete_check_task] 17-vmware2-dht:<br>
>>>>>> <gfid:a68ce411-e381-46a3-93cd-<wbr>d2af6a7c3532>: failed to lookup the file<br>
>>>>>> on vmware2-dht [Stale file handle]<br>
>>>>>> 1 [2017-03-17 14:04:26.353528] E [MSGID: 133014]<br>
>>>>>> [shard.c:1253:shard_common_<wbr>stat_cbk] 17-vmware2-shard: stat failed:<br>
>>>>>> a68ce411-e381-46a3-93cd-<wbr>d2af6a7c3532 [Stale file handle]<br>
>>>>>><br>
>>>>>> which is fine.<br>
>>>>>><br>
>>>>>> 2. The other kind are from AFR logging of possible split-brain which I<br>
>>>>>> suppose are harmless too.<br>
>>>>>> [2017-03-17 14:23:36.968883] W [MSGID: 108008]<br>
>>>>>> [afr-read-txn.c:228:afr_read_<wbr>txn] 17-vmware2-replicate-13: Unreadable<br>
>>>>>> subvolume -1 found with event generation 2 for gfid<br>
>>>>>> 74d49288-8452-40d4-893e-<wbr>ff4672557ff9. (Possible split-brain)<br>
>>>>>><br>
>>>>>> Since you are saying the bug is hit only on VMs that are undergoing IO<br>
>>>>>> while rebalance is running (as opposed to those that remained powered off),<br>
>>>>>><br>
>>>>>> rebalance + IO could be causing some issues.<br>
>>>>>><br>
>>>>>> CC'ing DHT devs<br>
>>>>>><br>
>>>>>> Raghavendra/Nithya/Susant,<br>
>>>>>><br>
>>>>>> Could you take a look?<br>
>>>>>><br>
>>>>>> -Krutika<br>
>>>>>><br>
>>>>>><br>
>>>>>> On Sun, Mar 19, 2017 at 4:55 PM, Mahdi Adnan <<a href="mailto:mahdi.adnan@outlook.com">mahdi.adnan@outlook.com</a>><br>
>>>>>> wrote:<br>
>>>>>><br>
>>>>>> Thank you for your email mate.<br>
>>>>>><br>
>>>>>> Yes, im aware of this but, to save costs i chose replica 2, this<br>
>>>>>> cluster is all flash.<br>
>>>>>><br>
>>>>>> In version 3.7.x i had issues with ping timeout, if one hosts went<br>
>>>>>> down for few seconds the whole cluster hangs and become unavailable, to<br>
>>>>>> avoid this i adjusted the ping timeout to 5 seconds.<br>
>>>>>><br>
>>>>>> As for choosing Ganesha over gfapi, VMWare does not support Gluster<br>
>>>>>> (FUSE or gfapi) im stuck with NFS for this volume.<br>
>>>>>><br>
>>>>>> The other volume is mounted using gfapi in oVirt cluster.<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> --<br>
>>>>>><br>
>>>>>> Respectfully<br>
>>>>>> Mahdi A. Mahdi<br>
>>>>>><br>
>>>>>> From: Krutika Dhananjay <<a href="mailto:kdhananj@redhat.com">kdhananj@redhat.com</a>><br>
>>>>>> Sent: Sunday, March 19, 2017 2:01:49 PM<br>
>>>>>><br>
>>>>>> To: Mahdi Adnan<br>
>>>>>> Cc: <a href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a><br>
>>>>>> Subject: Re: [Gluster-users] Gluster 3.8.10 rebalance VMs corruption<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> While I'm still going through the logs, just wanted to point out a<br>
>>>>>> couple of things:<br>
>>>>>><br>
>>>>>> 1. It is recommended that you use 3-way replication (replica count 3)<br>
>>>>>> for VM store use case<br>
>>>>>><br>
>>>>>> 2. network.ping-timeout at 5 seconds is way too low. Please change it<br>
>>>>>> to 30.<br>
>>>>>><br>
>>>>>> Is there any specific reason for using NFS-Ganesha over gfapi/FUSE?<br>
>>>>>><br>
>>>>>> Will get back with anything else I might find or more questions if I<br>
>>>>>> have any.<br>
>>>>>><br>
>>>>>> -Krutika<br>
>>>>>><br>
>>>>>> On Sun, Mar 19, 2017 at 2:36 PM, Mahdi Adnan <<a href="mailto:mahdi.adnan@outlook.com">mahdi.adnan@outlook.com</a>><br>
>>>>>> wrote:<br>
>>>>>><br>
>>>>>> Thanks mate,<br>
>>>>>><br>
>>>>>> Kindly, check the attachment.<br>
>>>>>><br>
>>>>>> --<br>
>>>>>><br>
>>>>>> Respectfully<br>
>>>>>> Mahdi A. Mahdi<br>
>>>>>><br>
>>>>>> From: Krutika Dhananjay <<a href="mailto:kdhananj@redhat.com">kdhananj@redhat.com</a>><br>
>>>>>> Sent: Sunday, March 19, 2017 10:00:22 AM<br>
>>>>>><br>
>>>>>> To: Mahdi Adnan<br>
>>>>>> Cc: <a href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a><br>
>>>>>> Subject: Re: [Gluster-users] Gluster 3.8.10 rebalance VMs corruption<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> In that case could you share the ganesha-gfapi logs?<br>
>>>>>><br>
>>>>>> -Krutika<br>
>>>>>><br>
>>>>>> On Sun, Mar 19, 2017 at 12:13 PM, Mahdi Adnan<br>
>>>>>> <<a href="mailto:mahdi.adnan@outlook.com">mahdi.adnan@outlook.com</a>> wrote:<br>
>>>>>><br>
>>>>>> I have two volumes, one is mounted using libgfapi for ovirt mount, the<br>
>>>>>> other one is exported via NFS-Ganesha for VMWare which is the one im testing<br>
>>>>>> now.<br>
>>>>>><br>
>>>>>> --<br>
>>>>>><br>
>>>>>> Respectfully<br>
>>>>>> Mahdi A. Mahdi<br>
>>>>>><br>
>>>>>> From: Krutika Dhananjay <<a href="mailto:kdhananj@redhat.com">kdhananj@redhat.com</a>><br>
>>>>>> Sent: Sunday, March 19, 2017 8:02:19 AM<br>
>>>>>><br>
>>>>>> To: Mahdi Adnan<br>
>>>>>> Cc: <a href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a><br>
>>>>>> Subject: Re: [Gluster-users] Gluster 3.8.10 rebalance VMs corruption<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> On Sat, Mar 18, 2017 at 10:36 PM, Mahdi Adnan<br>
>>>>>> <<a href="mailto:mahdi.adnan@outlook.com">mahdi.adnan@outlook.com</a>> wrote:<br>
>>>>>><br>
>>>>>> Kindly, check the attached new log file, i dont know if it's helpful<br>
>>>>>> or not but, i couldn't find the log with the name you just described.<br>
>>>>>><br>
>>>>>><br>
>>>>>> No. Are you using FUSE or libgfapi for accessing the volume? Or is it<br>
>>>>>> NFS?<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> -Krutika<br>
>>>>>><br>
>>>>>> --<br>
>>>>>><br>
>>>>>> Respectfully<br>
>>>>>> Mahdi A. Mahdi<br>
>>>>>><br>
>>>>>> From: Krutika Dhananjay <<a href="mailto:kdhananj@redhat.com">kdhananj@redhat.com</a>><br>
>>>>>> Sent: Saturday, March 18, 2017 6:10:40 PM<br>
>>>>>><br>
>>>>>> To: Mahdi Adnan<br>
>>>>>> Cc: <a href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a><br>
>>>>>> Subject: Re: [Gluster-users] Gluster 3.8.10 rebalance VMs corruption<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> mnt-disk11-vmware2.log seems like a brick log. Could you attach the<br>
>>>>>> fuse mount logs? It should be right under /var/log/glusterfs/ directory<br>
>>>>>><br>
>>>>>> named after the mount point name, only hyphenated.<br>
>>>>>><br>
>>>>>> -Krutika<br>
>>>>>><br>
>>>>>> On Sat, Mar 18, 2017 at 7:27 PM, Mahdi Adnan <<a href="mailto:mahdi.adnan@outlook.com">mahdi.adnan@outlook.com</a>><br>
>>>>>> wrote:<br>
>>>>>><br>
>>>>>> Hello Krutika,<br>
>>>>>><br>
>>>>>> Kindly, check the attached logs.<br>
>>>>>><br>
>>>>>> --<br>
>>>>>><br>
>>>>>> Respectfully<br>
>>>>>> Mahdi A. Mahdi<br>
>>>>>><br>
>>>>>> From: Krutika Dhananjay <<a href="mailto:kdhananj@redhat.com">kdhananj@redhat.com</a>><br>
>>>>>><br>
>>>>>><br>
>>>>>> Sent: Saturday, March 18, 2017 3:29:03 PM<br>
>>>>>> To: Mahdi Adnan<br>
>>>>>> Cc: <a href="mailto:gluster-users@gluster.org">gluster-users@gluster.org</a><br>
>>>>>> Subject: Re: [Gluster-users] Gluster 3.8.10 rebalance VMs corruption<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> Hi Mahdi,<br>
>>>>>><br>
>>>>>> Could you attach mount, brick and rebalance logs?<br>
>>>>>><br>
>>>>>> -Krutika<br>
>>>>>><br>
>>>>>> On Sat, Mar 18, 2017 at 12:14 AM, Mahdi Adnan<br>
>>>>>> <<a href="mailto:mahdi.adnan@outlook.com">mahdi.adnan@outlook.com</a>> wrote:<br>
>>>>>><br>
>>>>>> Hi,<br>
>>>>>><br>
>>>>>> I have upgraded to Gluster 3.8.10 today and ran the add-brick<br>
>>>>>> procedure in a volume contains few VMs.<br>
>>>>>><br>
>>>>>> After the completion of rebalance, i have rebooted the VMs, some of<br>
>>>>>> ran just fine, and others just crashed.<br>
>>>>>><br>
>>>>>> Windows boot to recovery mode and Linux throw xfs errors and does not<br>
>>>>>> boot.<br>
>>>>>><br>
>>>>>> I ran the test again and it happened just as the first one, but i have<br>
>>>>>> noticed only VMs doing disk IOs are affected by this bug.<br>
>>>>>><br>
>>>>>> The VMs in power off mode started fine and even md5 of the disk file<br>
>>>>>> did not change after the rebalance.<br>
>>>>>><br>
>>>>>> anyone else can confirm this ?<br>
>>>>>><br>
>>>>>> Volume info:<br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>> Volume Name: vmware2<br>
>>>>>><br>
>>>>>> Type: Distributed-Replicate<br>
>>>>>><br>
>>>>>> Volume ID: 02328d46-a285-4533-aa3a-<wbr>fb9bfeb688bf<br>
>>>>>><br>
>>>>>> Status: Started<br>
>>>>>><br>
>>>>>> Snapshot Count: 0<br>
>>>>>><br>
>>>>>> Number of Bricks: 22 x 2 = 44<br>
>>>>>><br>
>>>>>> Transport-type: tcp<br>
>>>>>><br>
>>>>>> Bricks:<br>
>>>>>><br>
>>>>>> Brick1: gluster01:/mnt/disk1/vmware2<br>
>>>>>><br>
>>>>>> Brick2: gluster03:/mnt/disk1/vmware2<br>
>>>>>><br>
>>>>>> Brick3: gluster02:/mnt/disk1/vmware2<br>
>>>>>><br>
>>>>>> Brick4: gluster04:/mnt/disk1/vmware2<br>
>>>>>><br>
>>>>>> Brick5: gluster01:/mnt/disk2/vmware2<br>
>>>>>><br>
>>>>>> Brick6: gluster03:/mnt/disk2/vmware2<br>
>>>>>><br>
>>>>>> Brick7: gluster02:/mnt/disk2/vmware2<br>
>>>>>><br>
>>>>>> Brick8: gluster04:/mnt/disk2/vmware2<br>
>>>>>><br>
>>>>>> Brick9: gluster01:/mnt/disk3/vmware2<br>
>>>>>><br>
>>>>>> Brick10: gluster03:/mnt/disk3/vmware2<br>
>>>>>><br>
>>>>>> Brick11: gluster02:/mnt/disk3/vmware2<br>
>>>>>><br>
>>>>>> Brick12: gluster04:/mnt/disk3/vmware2<br>
>>>>>><br>
>>>>>> Brick13: gluster01:/mnt/disk4/vmware2<br>
>>>>>><br>
>>>>>> Brick14: gluster03:/mnt/disk4/vmware2<br>
>>>>>><br>
>>>>>> Brick15: gluster02:/mnt/disk4/vmware2<br>
>>>>>><br>
>>>>>> Brick16: gluster04:/mnt/disk4/vmware2<br>
>>>>>><br>
>>>>>> Brick17: gluster01:/mnt/disk5/vmware2<br>
>>>>>><br>
>>>>>> Brick18: gluster03:/mnt/disk5/vmware2<br>
>>>>>><br>
>>>>>> Brick19: gluster02:/mnt/disk5/vmware2<br>
>>>>>><br>
>>>>>> Brick20: gluster04:/mnt/disk5/vmware2<br>
>>>>>><br>
>>>>>> Brick21: gluster01:/mnt/disk6/vmware2<br>
>>>>>><br>
>>>>>> Brick22: gluster03:/mnt/disk6/vmware2<br>
>>>>>><br>
>>>>>> Brick23: gluster02:/mnt/disk6/vmware2<br>
>>>>>><br>
>>>>>> Brick24: gluster04:/mnt/disk6/vmware2<br>
>>>>>><br>
>>>>>> Brick25: gluster01:/mnt/disk7/vmware2<br>
>>>>>><br>
>>>>>> Brick26: gluster03:/mnt/disk7/vmware2<br>
>>>>>><br>
>>>>>> Brick27: gluster02:/mnt/disk7/vmware2<br>
>>>>>><br>
>>>>>> Brick28: gluster04:/mnt/disk7/vmware2<br>
>>>>>><br>
>>>>>> Brick29: gluster01:/mnt/disk8/vmware2<br>
>>>>>><br>
>>>>>> Brick30: gluster03:/mnt/disk8/vmware2<br>
>>>>>><br>
>>>>>> Brick31: gluster02:/mnt/disk8/vmware2<br>
>>>>>><br>
>>>>>> Brick32: gluster04:/mnt/disk8/vmware2<br>
>>>>>><br>
>>>>>> Brick33: gluster01:/mnt/disk9/vmware2<br>
>>>>>><br>
>>>>>> Brick34: gluster03:/mnt/disk9/vmware2<br>
>>>>>><br>
>>>>>> Brick35: gluster02:/mnt/disk9/vmware2<br>
>>>>>><br>
>>>>>> Brick36: gluster04:/mnt/disk9/vmware2<br>
>>>>>><br>
>>>>>> Brick37: gluster01:/mnt/disk10/vmware2<br>
>>>>>><br>
>>>>>> Brick38: gluster03:/mnt/disk10/vmware2<br>
>>>>>><br>
>>>>>> Brick39: gluster02:/mnt/disk10/vmware2<br>
>>>>>><br>
>>>>>> Brick40: gluster04:/mnt/disk10/vmware2<br>
>>>>>><br>
>>>>>> Brick41: gluster01:/mnt/disk11/vmware2<br>
>>>>>><br>
>>>>>> Brick42: gluster03:/mnt/disk11/vmware2<br>
>>>>>><br>
>>>>>> Brick43: gluster02:/mnt/disk11/vmware2<br>
>>>>>><br>
>>>>>> Brick44: gluster04:/mnt/disk11/vmware2<br>
>>>>>><br>
>>>>>> Options Reconfigured:<br>
>>>>>><br>
>>>>>> cluster.server-quorum-type: server<br>
>>>>>><br>
>>>>>> nfs.disable: on<br>
>>>>>><br>
>>>>>> performance.readdir-ahead: on<br>
>>>>>><br>
>>>>>> transport.address-family: inet<br>
>>>>>><br>
>>>>>> performance.quick-read: off<br>
>>>>>><br>
>>>>>> performance.read-ahead: off<br>
>>>>>><br>
>>>>>> performance.io-cache: off<br>
>>>>>><br>
>>>>>> performance.stat-prefetch: off<br>
>>>>>><br>
>>>>>> cluster.eager-lock: enable<br>
>>>>>><br>
>>>>>> network.remote-dio: enable<br>
>>>>>><br>
>>>>>> features.shard: on<br>
>>>>>><br>
>>>>>> cluster.data-self-heal-<wbr>algorithm: full<br>
>>>>>><br>
>>>>>> features.cache-invalidation: on<br>
>>>>>><br>
>>>>>> ganesha.enable: on<br>
>>>>>><br>
>>>>>> features.shard-block-size: 256MB<br>
>>>>>><br>
>>>>>> client.event-threads: 2<br>
>>>>>><br>
>>>>>> server.event-threads: 2<br>
>>>>>><br>
>>>>>> cluster.favorite-child-policy: size<br>
>>>>>><br>
>>>>>> storage.build-pgfid: off<br>
>>>>>><br>
>>>>>> network.ping-timeout: 5<br>
>>>>>><br>
>>>>>> cluster.enable-shared-storage: enable<br>
>>>>>><br>
>>>>>> nfs-ganesha: enable<br>
>>>>>><br>
>>>>>> cluster.server-quorum-ratio: 51%<br>
>>>>>><br>
>>>>>> Adding bricks:<br>
>>>>>><br>
>>>>>> gluster volume add-brick vmware2 replica 2<br>
>>>>>> gluster01:/mnt/disk11/vmware2 gluster03:/mnt/disk11/vmware2<br>
>>>>>> gluster02:/mnt/disk11/vmware2 gluster04:/mnt/disk11/vmware2<br>
>>>>>><br>
>>>>>> starting fix layout:<br>
>>>>>><br>
>>>>>> gluster volume rebalance vmware2 fix-layout start<br>
>>>>>><br>
>>>>>> Starting rebalance:<br>
>>>>>><br>
>>>>>> gluster volume rebalance vmware2 start<br>
>>>>>><br>
>>>>>><br>
>>>>>> --<br>
>>>>>><br>
>>>>>> Respectfully<br>
>>>>>> Mahdi A. Mahdi<br>
>>>>>><br>
>>>>>> ______________________________<wbr>_________________<br>
>>>>>> Gluster-users mailing list<br>
>>>>>> <a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>
>>>>>> <a href="http://lists.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">http://lists.gluster.org/<wbr>mailman/listinfo/gluster-users</a><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>>><br>
>>>>><br>
>>>>><br>
>>>>> ______________________________<wbr>_________________<br>
>>>>> Gluster-users mailing list<br>
>>>>> <a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>
>>>>> <a href="http://lists.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">http://lists.gluster.org/<wbr>mailman/listinfo/gluster-users</a><br>
>>>><br>
>>>><br>
>>>><br>
>>>><br>
>>>> --<br>
>>>> Pranith<br>
>>><br>
>>><br>
>>><br>
>>> ______________________________<wbr>_________________<br>
>>> Gluster-users mailing list<br>
>>> <a href="mailto:Gluster-users@gluster.org">Gluster-users@gluster.org</a><br>
>>> <a href="http://lists.gluster.org/mailman/listinfo/gluster-users" rel="noreferrer" target="_blank">http://lists.gluster.org/<wbr>mailman/listinfo/gluster-users</a><br>
><br>
><br>
</blockquote></div></div>