On 26/08/2020 18:40, Grant Taylor wrote:
On 8/21/20 10:15 PM, Caveman Al Toraboran wrote:
just to double check i got you right. due to flushing the buffer to
disk, this would mean that mail's throughput is limited by disk i/o?
Yes.
This speed limitation is viewed as a necessary limitation for the safety
of email passing through the system.
Nothing states that it must be a single disk (block device). It's
entirely possible that a fancy MTA can rotate through many disks (block
devices), using a different one for each SMTP connection. Thus in
theory allowing some to operate in close lock step with each other
without depending on / being blocked by any given disk (block device).
Thank you for the detailed explanation Ashley.
Or think back to the old days - network was slow and disks were
relatively fast. The disk was more than capable of keeping up with the
network, and simple winchesters didn't lie about saving to the rotating
rust ...
As Ashley explained, some MTAs trust the kernel. I've heard of others
issuing a sync after the write. But that is up to each MTA's
developers. They have all taken reasonable steps to ensure the safety
of email. Some have taken more-than-reasonable steps.
Depends on the filesystem. "sync after write" was an EXTREMELY daft idea
on ext4 in the early days - that would really have killed system response.
Nowadays you could stick an SSD cache in front of a raid array ...
Cheers,
Wol
