Any takers on this review?  It's a pretty significant change, in terms of
both lines of code and improvement.

  https://reviews.csiden.org/r/145/

>From the bug report:

Currently, every buffer cached in the L2ARC is accompanied by a 240-byte
header in memory, leading to very high memory consumption when using very
large cache devices. These changes significantly reduce this overhead.

Currently:

L1-only header = 176 bytes

L1 + L2 or L2-only header = 176 bytes + 32 byte checksum + 32 byte l2hdr =
240 bytes

Memory-optimized:

L1-only header = 176 bytes

L1 + L2 header = 176 bytes + 32 byte checksum = 208 bytes

L2-only header = 96 bytes + 32 byte checksum = 128 bytes

For an average blocksize of 8KB, this means that for the L2ARC, the ratio
of metadata to data has gone down from about 2.92% to 1.56%. For a 'storage
optimized' EC2 instance with 1600GB of SSD and 60GB of RAM, this means that
we expect a completely full L2ARC to use (1600 GB * 0.0156) / 60GB = 41% of
the available memory, down from 78%.

--matt
_______________________________________________
developer mailing list
[email protected]
http://lists.open-zfs.org/mailman/listinfo/developer

Reply via email to