The "Cell underflow at the state stage" message reports a cell arriving late at the egress PFE This is a Troubleshooting Article for a PFE ASIC Syslog Event. To view other documented syslog events related to XMCHIP, XLCHIP, MQCHIP, LUCHIP, EACHIP, and PECHIP, see KB31893 - Master Index of Articles for Troubleshooting PFE ASIC Syslog Events [juniper.net] .
When a "Cell underflow at the state stage" event occurs, a message similar to the following is reported:
Jul 25 16:14:50.881 router0: %PFE-3: fpc8 MQSS(0): FI: Cell underflow at the state stage (Cell behind reorder window) - Stream 0, Count 0
Indications:
Service impact depends on number of cells dropped
counter value presents the number of 64B cell drops
With the fix for PR1184761 , a minor alarm will be raised if the rate is higher than 100/second
The is due to the fabric cells arriving late on the egress PFE behind the reorder window.
Perform these steps to determine the cause and resolve the problem (if any). Continue through each step until the problem is resolved.
Collect the show command output.
show log messages show log chassisd start shell network pfe <fpc#> show nvram show syslog messages exit
Analyze the show command output.
In the 'show log messages', review the events that occurred at or just before the appearance of the "Cell underflow at the state stage" message. Frequently, these events help identify the cause.
No RMA is required
It could be triggered due to fabric congestion because of some specific traffic flow characteristics on the affected PFE
We suggest to restart the FPC under a MW, in order to prevent this from re-occurring.
> request chassis fpc offline slot #
<Wait 2 minutes>
> request chassis fpc online slot #
If there are excessive and sustained out of order events due to fabric congestion it could expose a possible fabric stream wedge which is solved in PR1276301
Contact your technical support representative if the issue is persistent.
This article is indexed in KB31893 - Primary Index of Articles for Troubleshooting PFE ASIC Syslog Events [juniper.net] ; tag EACHIPTSG
Tip: When looking at an event in the logs, it is important to focus on the first error message in a collection of syslog messages. The first error message is usually the cause of all the follow-on error messages. The follow-on collateral damage error messages can be ignored.
2026-03-13: minor update