On Fri, 8 Mar 2013, Stan Hoeppner wrote:
The default MaxTransmitBufferSize is actually quite low, 16644 bytes if
system RAM is >512MB, and 4356 bytes if RAM <512MB. You can get it up
to 60KB read and 64KB write by modifying some other reg values. This
applies all the way up to Server 2008. But transmit buffers size isn't
the problem in this case.
Indeed, found this:
http://blogs.msdn.com/b/openspecification/archive/2009/04/10/smb-maximum-transmit-buffer-size-and-performance-tuning.aspx
It's not clear to me how the transmit buffers interact with reading from
drive. If the 60 kilobyte read request comes in, 60 kilobytes (or
whatever) is read, sent out, wait, new 60 kilobyte request comes in, needs
to be read from drive, sent, wait. If automatic read-ahead isn't done and
the blocks read are cached, I can see this going very inefficient very
quickly.
Yes, SMB 2.0 was introduced with Vista and 2008. It has higher
throughput over high latency links due to pipelining, but this doesn't
yield much on a LAN, even Fast Ethernet. W2K/XP default SMB can hit the
25MB/s peak duplex data rate of 100FDX.
Yes, if latency is low, this isn't a problem.
--
Mikael Abrahamsson email: swmike@xxxxxxxxx
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
