Re: [PATCH] max-swap-rate=swaps/sec option for Rock cache_dir

On 10/03/2011 02:43 PM, Alex Rousskov wrote:
> Hello,
>
> The new option introduced by this patch limits Squid I/O rate to
> smooth out OS disk commit activity and to avoid blocking Rock diskers
> (or even other processes!) on I/O. It should be used when swap demand
> exceeds disk performance limits but the underlying file system does not
> slow down incoming I/Os, allowing the situation to get out of control.
>
> Lab and limited deployment tests show that without this option, Squid
> may write to the OS buffers much faster than the OS is able to write to
> disk. This disbalance eventually (and quite suddenly!) blocks any
> process trying to do I/O for a second or two, which results in very poor
> overall performance. Tuning file system parameters may help, but
> sometimes is not enough.
>
>
> The new max-swap-rate option is meant to be used together with the
> existing swap-timeout option. Otherwise, the problem simply shifts one
> layer up, with unrestricted workers overflowing restricted Rock I/O
> queues. The swap-timeout option allows a worker to skip Store operations
> when there are "too many" I/O pending already.
>
> The code seems to work well, but can be further optimized to minimize
> read (hit) delays and to better enforce configured swap timeouts.

Merged from lp:3p2-rock as trunk r11767 before I got any reviews on
squid-dev because these earlier-in-the-branch changes were blocking more
urgent fixes posted by Dmitry, and bzr does not support cherry picking
merge.

The code has been tested in production. Reviews are still gladly
accepted, and I can revert that commit or disable the feature if needed.

Thank you,

Alex.
Received on Thu Oct 06 2011 - 17:47:27 MDT