We deeply regret to inform GPFS users that the 188.8.131.52 service update contains a serious flaw. When parsing some RPCs sent by nodes running GPFS 184.108.40.206 or earlier, the code in 220.127.116.11 incorrectly processes certain data structures, resulting in GPFS crashes. The most typical symptom of this issue is the "((diskNum > 0) && (diskNum <= sgP->getNDisks())" assert in LogFile::append, although other symptoms are possible. The problem occurs most readily when metadata is not replicated (mmlsfs shows -m 1); metadata replication mitigates the problem to a large extent, but not completely. Full data and metadata replication would prevent the problem from happening.
The problem is limited to the scenarios where 18.104.22.168 and pre-22.214.171.124 nodes are present in the same cluster, accessing the same file systems. If you are considering upgrading GPFS from a pre-126.96.36.199 level (including 3.3.0.X), do not upgrade to the unpatched 188.8.131.52. Clusters running only 184.108.40.206 or later nodes, including 220.127.116.11, are not affected.
The problem will be fixed in 18.104.22.168. An efix for 22.214.171.124 is also available via IBM Service.
Pinned topic Backward compatibility problem in GPFS 126.96.36.199
Answered question This question has been answered.
Unanswered question This question has not been answered yet.
Updated on 2012-05-02T18:48:32Z at 2012-05-02T18:48:32Z by firstname.lastname@example.org
email@example.com 060000T9GF521 Posts
Re: Backward compatibility problem in GPFS 188.8.131.52012-05-02T18:48:32ZThis is the accepted answer. This is the accepted answer.To expand on the previous post: both 184.108.40.206 and 220.127.116.11 levels contain the same backward compatibility issue. All of the 18.104.22.168 warnings and workarounds also apply to 22.214.171.124.