[ceph-users] bad crc/signature errors

Ilya Dryomov idryomov at gmail.com
Thu Oct 5 02:47:17 PDT 2017


On Thu, Oct 5, 2017 at 7:53 AM, Adrian Saul
<Adrian.Saul at tpgtelecom.com.au> wrote:
>
> We see the same messages and are similarly on a 4.4 KRBD version that is affected by this.
>
> I have seen no impact from it so far that I know about
>
>
>> -----Original Message-----
>> From: ceph-users [mailto:ceph-users-bounces at lists.ceph.com] On Behalf Of
>> Jason Dillaman
>> Sent: Thursday, 5 October 2017 5:45 AM
>> To: Gregory Farnum <gfarnum at redhat.com>
>> Cc: ceph-users <ceph-users at lists.ceph.com>; Josy
>> <josy at colossuscloudtech.com>
>> Subject: Re: [ceph-users] bad crc/signature errors
>>
>> Perhaps this is related to a known issue on some 4.4 and later kernels [1]
>> where the stable write flag was not preserved by the kernel?
>>
>> [1] http://tracker.ceph.com/issues/19275

The stable pages bug manifests as multiple sporadic connection resets,
because in that case CRCs computed by the kernel don't always match the
data that gets sent out.  When the mismatch is detected on the OSD
side, OSDs reset the connection and you'd see messages like

  libceph: osd1 1.2.3.4:6800 socket closed (con state OPEN)
  libceph: osd2 1.2.3.4:6804 socket error on write

This is a different issue.  Josy, Adrian, Olivier, do you also see
messages of the "libceph: read_partial_message ..." type or is it just
"libceph: ... bad crc/signature" errors?

Thanks,

                Ilya


More information about the ceph-users mailing list