[DRBD-user] Initial sync grinds to a halt

Kushnir, Michael (NIH/NLM/LHC) [C] michael.kushnir at nih.gov
Mon Apr 7 19:34:32 CEST 2014

Note: "permalinks" may not be as permanent as we would like,
direct links of old sources may well be a few messages off.

Hello Everyone,

We are setting up an 8.4 cluster (elrepo RPMs -- drbd84-utils-8.4.4-2.el6.elrepo.x86_64.rpm<http://mirror.symnds.com/distributions/elrepo/elrepo/el6/x86_64/RPMS/drbd84-utils-8.4.4-2.el6.elrepo.x86_64.rpm> and kmod-drbd84-8.4.4-1.el6.elrepo.x86_64.rpm<http://mirror.symnds.com/distributions/elrepo/elrepo/el6/x86_64/RPMS/kmod-drbd84-8.4.4-1.el6.elrepo.x86_64.rpm>) on RHEL 6.

I have two SuperMicro storage boxes with 2 x 4 core Xeons, 48GB RAM, LSI 9280-24i-4e cards, 2 x 512GB SSDs set up as a RAID1 CacheCade, 21 x 2TB WD RE4 drives set up in a 36TB RAID50, and 10GbE over fiber connecting the two machines. DRBD volume is on top of an LVM logical volume.

For some reason, a few hours after starting the initial sync, network activity between the boxes dies down and DRBD shows that the nodes are syncing but the numbers are not changing.

I don't see any errors anywhere in the logs.

I am running the same RPMs, same version of RHEL, and same kernel, and a largely similar (smaller) setup on other systems and do not see the same problem.



Michael Kushnir
System Architect
Communications Engineering Branch
Lister Hill National Center for Biomedical Communications
National Library of Medicine

8600 Rockville Pike, Building 38A, Floor 10
Besthesda, MD 20894

Phone: 301-435-3219
Email: michael.kushnir at nih.gov<mailto:michael.kushnir at nih.gov>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.linbit.com/pipermail/drbd-user/attachments/20140407/a28f77d8/attachment.htm>

More information about the drbd-user mailing list