CentOS 6.4, current, Dell PE R720.
Had an issue today with a bus error, and googling only found two year old
references to problems with non-Dell drives (we just added two WD Reds,
and mdadm raided them).
So, looking through dmesg and /var/log/messages, I ran into a *lot* of
G
gran_size: 128K chunk_size: 256K num_reg: 10 lose cover
RAM:
0G
gran_size: 128K chunk_size: 512K num_reg: 10 lose cover
RAM:
0G
gran_size: 128K chunk_size: 1M num_reg: 10 lose cover RAM: 0G
gran_size: 128K chunk_size: 2M num_reg: 10 lose cover RAM: 0G
gran_size: 128K chunk_size: 4M num_reg: 10 lose cover RAM: 0G
gran_size: 128K chunk_size: 8M num_reg: 10 lose cover RAM: 0G
gran_size: 128K chunk_size: 16M num_reg: 10 lose cover
RAM:
0G
gran_size: 128K chunk_size: 32M num_reg: 10 lose cover
RAM:
0G
gran_size: 128K chunk_size: 64M num_reg: 10 lose cover
RAM:
0G
gran_size: 128K chunk_size: 128M num_reg: 10 lose cover
RAM:
0G
gran_size: 128K chunk_size: 256M num_reg: 10 lose cover
RAM:
0G
gran_size: 128K chunk_size: 512M num_reg: 10 lose cover
RAM:
0G
gran_size: 128K chunk_size: 1G num_reg: 10 lose cover RAM: 0G
*BAD*gran_size: 128K chunk_size: 2G num_reg: 10 lose cover RAM: -1G
Googling finds various threads, and a bug or two, and one person has an
answer of setting this in the kernel line in grub. HOWEVER, the one person
who gave that thread's O/P what to put never responded to *how* he chose
those parms.
Anyone here have any idea how to chose them?
mark
