[LU-11798] cur_grant goes to 0 and never increases with 2.8 client and 2.10 server

• Type: Bug
• Resolution: Fixed
• Priority: Major
• Fix Version/s: Lustre 2.13.0, Lustre 2.12.1
• Affects Version/s: Lustre 2.8.0, Lustre 2.10.5
• Labels: llnl
• Environment: client: ; lustre-2.8.2_5.chaos-1.ch6.x86_64 ; ; servers: ; zfs-0.7.11-4llnl.ch6.x86_64 ; lustre-2.10.5_2.chaos-3.ch6.x86_64
• Severity: 3
• Assignee: Alex Zhuravlev
• Reporter: Olaf Faaland

Description

The Lustre 2.10.5 / zfs 0.7.11 OST is not allocating grant to the clients.

I set +cache debug flag on both client and server.

On the client, under /proc/fs/lustre/osc/lustre3-OST....:
cur_dirty_bytes == 0
cur_grant_bytes starts out as 2097152

I then issue
dd if=/dev/urandom of=/p/lustre3/foo/toss-4377/ost0/test.10M bs=5K count=2000

cur_grant_bytes goes down, and never up, as writes to the OST occur. Eventually it reaches 0 and then stays == 0.

There is no connection issue - no log messages indicating connections lost/reconnects, and osc/lustre3-OSTXXXX.*/state has "current_state: FULL" for all OSTs.

Issue Links

• is related to: LU-11844 IO pattern causing writes to hang to OST
• is related to: LU-11663 corrupt data after page-unaligned write with zfs backend lustre 2.10