- ONTAP 9
- Clustered ONTAP 8.x
- Data ONTAP 7-mode
- If no performance impact, then the occasional long Consistency Point (CP) are normal and expected.
- Although more frequent long CPs events may be an indication of other issues and should be investigated.
ONTAP can do several background tasks in CP. If latency is low and the system has idle cycles, rather than waste them, ONTAP will devote idle cycles to background work. A few examples are deswizzling, various wafl scans, or deletions.
CPs happen asynchronously of the write path, as writes are acknowledged when written to NVRAM. Latency is unaffected as writes can be buffered until CP completion. Latency will be observed during this time as being stead.
Examples of messages logged:
- ONTAP 9:
Mon Dec 23 00:20:36 EST [FilerA: wafl_exempt08: wafl.cp.toolong:error]: Aggregate fas_01_DATA_AGGR experienced a long CP...
This message occurs when a WAFL(R) consistency point (CP) takes longer than 30 seconds. A CP lasting more than 30 seconds might cause client latency and potentially a client outage.
- Clustered ONTAP 8.x, Data ONTAP 7-mode:
Mon Feb 22 16:14:08 CLT [FilerA: wafl_CP_proc: wafl.cp.toolong.warning:warning]: params: ...
Mon Feb 22 16:14:08 CLT [FilerA: wafl_CP_proc: wafl.cp.slovol.warning:warning]: params: ...