Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Repo info
Activity
  • 17:33

    beevans on not-null

    Ex-1842 filesync: remove not nu… (compare)

  • 17:29
    ip1981 review_requested #2285
  • 17:29
    ip1981 review_requested #2285
  • 17:28
    ip1981 synchronize #2285
  • 17:28

    ip1981 on 2283-shell-completion

    Add shell completions for CLI … (compare)

  • 17:28
    ip1981 edited #2285
  • 17:28
    ip1981 edited #2285
  • 17:27
    ip1981 synchronize #2285
  • 17:27

    ip1981 on 2283-shell-completion

    Add completions for CLI Signed… (compare)

  • 17:26
    johnsonw synchronize #2154
  • 17:26

    johnsonw on EX-1476

    EX-1476 Create step to create a… (compare)

  • 17:15

    jgrund on graphql-fqdn

    (compare)

  • 17:15

    jgrund on master

    graphql: Return fqdn from get_f… (compare)

  • 17:15
    jgrund closed #2287
  • 17:15
    jgrund review_requested #2287
  • 17:06
    ip1981 edited #2295
  • 17:06
    ip1981 edited #2295
  • 17:05
    johnsonw synchronize #2154
  • 17:05

    johnsonw on EX-1476

    EX-1476 Create step to create a… (compare)

  • 17:05
    ip1981 labeled #2295
Joe Grund
@jgrund
Retriggerd that run
Joe Grund
@jgrund

@jgrund Regarding stack, you do share services between nodes or bind them all to one and the same?

All on one node, for now anyway

Alex Talker
@AlexTalker
@jgrund Also, regarding whamcloud/integrated-manager-for-lustre#917 I've got a suggestion that this fix somehow doesn't work on production installation and I think I saw there reverse situation(volume node, associated with target on passive node were deleted after it fail-back) but I could not reproduce this case on Docker and I reproduced this case a few times and it always ended up successfully, so I think this one good to go when you decide it is appropriate to.
But I'll look into it tomorrow I think, should be okay
@jgrund Also, regarding issue with device-scanner if you remember. I dig into the problem why multipath triggered events and it seems every time somebody opens device-mapper device for writing and closes the file description, the event is generated. Even if nothing has been written. Since it requires deep kernel knowledge, I delegated this task but you still might want to check if data you supply has actually changed and supply it only if it is.
@jgrund You can reproduce it if you write with dd on a multipath disk, as often dd ends - so often the even is triggered.
Alex Talker
@AlexTalker
@jgrund I do not know for sure but I think this triggers device-aggregator on server side and since nothing changes, it is useless to go further than device-scanner process
Joe Grund
@jgrund
I’ll take a look at that.

In regards to filtering, I have an issue that I still need to get to for that:

whamcloud/device-scanner#193

Alex Talker
@AlexTalker
The issue seems to cover my problem
Unfortunately, we required to interact with devices so often by design. Yet another way to implement HA, you know
But if we'll figure out how to disable triggering this event, I'll let you know
Joe Grund
@jgrund
Are the UEvents emitted identical for each write?
Alex Talker
@AlexTalker
@jgrund The only thing that changes is ID, no particular change in data that I could notice via udevadm monitor -p. Can't remember how ID's named now :/
Amit Kumar
@ahkumar
@jgrund Hi Joe, I am was able to get iml5 after reproving the OS to remove previous version of postgress. I have IML up and now I don't see that the OST's are going offline
@jgrund this one looks great!!
Joe Grund
@jgrund
@ahkumar Ok, I can stop by and take a look at what’s happening next break
@ahkumar Thanks :)
Amit Kumar
@ahkumar
@jgrund thank you!!
Amit Kumar
@ahkumar
@jgrund Wondering if this doc https://whamcloud.github.io/Online-Help/docs/Contributor_Docs/cd_Installing_IML_On_Vagrant.html is available offline? so I can work offline ?
Joe Grund
@jgrund

Not really. If you have IML installed, those docs are bundled in under the help link, but I suspect you want a standalone solution.

We have an open that describes a way to do so (which we plan to automate) here: whamcloud/Online-Help#142

But there are also plugins available that can download webpages for you in Chrome or Firefox if you want to go that route.

Amit Kumar
@ahkumar
@jgrund Cool will try other options you mention, thank you!!
Alex Talker
@AlexTalker
@jgrund whamcloud/device-scanner#270 We checked and udev event is triggered on closing multipath device only on systems with IML. I asked to find out why systemd-udevd actually triggers the event.
Joe Grund
@jgrund
Ok, I’ll take a look
Amit Kumar
@ahkumar
@jgrund : i have a vagrant setup of the latest IML. Interestingly after I resized my MDT to a bigger disk size, I am not able to see the updated MDT size when I am selecting disks to create a file system. How can I get IML to redetect the targets to find its correct size. On the mds host itself I can see the disk size to be the updated size but not in the web interface?
Joe Grund
@jgrund
@ahkumar Is this a ZFS or ldiskfs setup?
Amit Kumar
@ahkumar
@jgrund ldiskfs
Joe Grund
@jgrund
Using the mpath devices?
Amit Kumar
@ahkumar
yup
Joe Grund
@jgrund
How are you expanding the disk?
Amit Kumar
@ahkumar
I removed the original mdt created by initial setup: and then created a new fixed disk and attached it to stat controller port where the original disk was connected on the iscsi host
*sata controller port
Joe Grund
@jgrund
This is all while IML was running?
Amit Kumar
@ahkumar
Yes
Joe Grund
@jgrund
Ok. Can you look at the output of echo '"Stream"' | socat - UNIX-CONNECT:/var/run/device-scanner.sock | jq (you may need to install jq) on the storage node the iscsi target is attached to?
And check to see that the size is as you expect for that device
Amit Kumar
@ahkumar
should I run the above on adm host?
i mean iscsi host?
Joe Grund
@jgrund
on mds1
or mds2
Amit Kumar
@ahkumar
I confirm that the size reported by the above command: "size": "10737418240" is the correct size 10G original setup i had trimmed it down 1G; So that looks good. Is it just the browser cache may be?
Amit Kumar
@ahkumar
ls
Amit Kumar
@ahkumar
@jgrund you can ignore my request. When I click into the details of the MDT i see that it says 10G. but the mdt selection page was incorrectly reporting it. In any case this is minor and not worry about. thank you for guiding. I am liking this new IML.
Joe Grund
@jgrund
Ok. If you can open an issue with screenshots of the bug we will look into it further.
Alex Talker
@AlexTalker
@jgrund In this PR whamcloud/device-scanner#279 you changed master code for device-scanner. But as far as I know, this version is not available in repository for IML 5.0. When this version will be available there?
Joe Grund
@jgrund

It’s going to be a few weeks until I can get it promoted to 5.0.

I need to make sure the new version works well enough for managed and monitored modes and upgrades.
I think I have managed mode working well, I need to spend some time now making sure monitored mode works.

There are patches on the agent and manager sides as well that will need to land:

whamcloud/iml-agent#98
whamcloud/integrated-manager-for-lustre#947

@jgrund From here? https://copr-be.cloud.fedoraproject.org/results/managerforlustre/device-scanner-devel/epel-7-x86_64/

Yes, that’s where the devel patches are being built

Alex Talker
@AlexTalker
I'm just hanging around this problem with "VolumeNode does not exists" problem but I'm going on a vacation next week. So I would really like to resolve the problem before it but since I debug only monitored mode, your current direction of resolving this issue is a bit deviated from mine
Which arises a problem that we look on different behavior directions