-
Notifications
You must be signed in to change notification settings - Fork 1.8k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Crash with 0.6.5.4 #4295
Comments
Please post more hardware specs (ECC ?, how much RAM, processor, harddrive models ? etc. ), how is health of the harddrives ? you are copying from ext4 to ZFS ? or reverse ? search terms for google: referencing: |
Hi, the system is a: Intel(R) Core(TM) i7-3930K CPU @ 3.20GHz 64 GB memory, no ECC (but memory-Test for 48h without problems) The disk drives are fine according to the SMART values. Hard drives are 3 or 4 TB models from Seagate, WD and HGST. I doubt that this is a "write error problem" as the problem disappears when downgrading to 0.6.5.3 while it can be almost immediately reproduced with 0.6.5.4. The copy goes from a file system on ZFS to a luks encrypted file system with ext4, e.g.: cp /pool3/temp/some_file [ZFS file system] /data/misc [ext4 formatted luks file system on pool2] The system is stable with 0.6.5.3 but can be brought down almost immediately with 0.6.5.4. |
@ronnyegner |
@tuxoko: I do it tomorrow. |
So i tried the whole day to reproduce the issue without any success so far. BEFORE
AFTER
I will try maybe one more day and then close the issue... seems solved. |
Hi,
i have recently updated to ZFS&SPL 0.6.5.4. With that version i am observing frequent and reproducible crashes when doing medium load on my system (e.g. copy a few files with one cp process from one cryptsetup file system to another cryptsetup file system).
When this happens top shows:
Note that the system here is freshly booted (14 minutes uptime).
The I/O then stops completely after 15 seconds and does not resume. The following stack traces are shown:
I had to reboot the system.
The system is an Ubuntu 14.04.3 (LTS) with kernel: 3.14.43-031443-generic
The setup consists of four pools:
Deduplication is not in use.
The only thing worth mentioning is that pool2 currently has a broken disk which was "replaced" with a file stored on pool3:
I was unable to capture the ARC Stats... however a system running with 0.6.5.3 (i downgraded to fix the issue) looks like this:
If you need more details please let me know.
The text was updated successfully, but these errors were encountered: