[Dovecot] Design: Asynchronous I/O for single/multi-dbox

Stan Hoeppner stan at hardwarefreak.com
Tue Mar 16 09:45:53 EET 2010

Timo Sirainen put forth on 3/14/2010 6:46 AM:

>  - open file 1
>  - read contents of file 1
>  - open file 2
>  - read contents of file 2
>  - ..etc..
> All of this when processing a single client connection's command(s). And while waiting for I/O replies Dovecot can do other work. So user sees results earlier.

Concentrate on rewriting imapd into a threaded model, and get it right.
Once you've done so I think you will have eliminated the perceived need for AIO.

Regarding memory usage, on Linux anyway, you should really read this Timo.
It would be mutually beneficial to Dovecot (and Postfix, and etc).  I've not
played with it yet, and I don't have a busy server to test it on, but I'm
betting it would seriously benefit those running servers with hundreds of
concurrent users.  I'm going to spin this into my next kernel and play with it.

Docs on KSM:

How to use the Kernel Samepage Merging feature

KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
added to the Linux kernel in 2.6.32.  See mm/ksm.c for its implementation,
and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/

The KSM daemon ksmd periodically scans those areas of user memory which
have been registered with it, looking for pages of identical content which
can be replaced by a single write-protected page (which is automatically
copied if a process later wants to update its content).

KSM was originally developed for use with KVM (where it was known as
Kernel Shared Memory), to fit more virtual machines into physical memory,
by sharing the data common between them.  But it can be useful to any
application which generates many instances of the same data.

KSM only merges anonymous (private) pages, never pagecache (file) pages.
KSM's merged pages are at present locked into kernel memory for as long
as they are shared: so cannot be swapped out like the user pages they
replace (but swapping KSM pages should follow soon in a later release).

KSM only operates on those areas of address space which an application
has advised to be likely candidates for merging, by using the madvise(2)
system call: int madvise(addr, length, MADV_MERGEABLE).

The app may call int madvise(addr, length, MADV_UNMERGEABLE) to cancel
that advice and restore unshared pages: whereupon KSM unmerges whatever
it merged in that range.  Note: this unmerging call may suddenly require
more memory than is available - possibly failing with EAGAIN, but more
probably arousing the Out-Of-Memory killer.

If KSM is not configured into the running kernel, madvise MADV_MERGEABLE
and MADV_UNMERGEABLE simply fail with EINVAL.  If the running kernel was
built with CONFIG_KSM=y, those calls will normally succeed: even if the
the KSM daemon is not currently running, MADV_MERGEABLE still registers
the range for whenever the KSM daemon is started; even if the range
cannot contain any pages which KSM could actually merge; even if
MADV_UNMERGEABLE is applied to a range which was never MADV_MERGEABLE.

Like other madvise calls, they are intended for use on mapped areas of
the user address space: they will report ENOMEM if the specified range
includes unmapped gaps (though working on the intervening mapped areas),
and might fail with EAGAIN if not enough memory for internal structures.

Applications should be considerate in their use of MADV_MERGEABLE,
restricting its use to areas likely to benefit.  KSM's scans may use
a lot of processing power, and its kernel-resident pages are a limited
resource.  Some installations will disable KSM for these reasons.

The KSM daemon is controlled by sysfs files in /sys/kernel/mm/ksm/,
readable by all but writable only by root:

max_kernel_pages - set to maximum number of kernel pages that KSM may use
                   e.g. "echo 100000 > /sys/kernel/mm/ksm/max_kernel_pages"
                   Value 0 imposes no limit on the kernel pages KSM may use;
                   but note that any process using MADV_MERGEABLE can cause
                   KSM to allocate these pages, unswappable until it exits.
                   Default: quarter of memory (chosen to not pin too much)

pages_to_scan    - how many present pages to scan before ksmd goes to sleep
                   e.g. "echo 100 > /sys/kernel/mm/ksm/pages_to_scan"
                   Default: 100 (chosen for demonstration purposes)

sleep_millisecs  - how many milliseconds ksmd should sleep before next scan
                   e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
                   Default: 20 (chosen for demonstration purposes)

run              - set 0 to stop ksmd from running but keep merged pages,
                   set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
                   set 2 to stop ksmd and unmerge all pages currently merged,
                         but leave mergeable areas registered for next run
                   Default: 0 (must be changed to 1 to activate KSM,
                               except if CONFIG_SYSFS is disabled)

The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/:

pages_shared     - how many shared unswappable kernel pages KSM is using
pages_sharing    - how many more sites are sharing them i.e. how much saved
pages_unshared   - how many pages unique but repeatedly checked for merging
pages_volatile   - how many pages changing too fast to be placed in a tree
full_scans       - how many times all mergeable areas have been scanned

A high ratio of pages_sharing to pages_shared indicates good sharing, but
a high ratio of pages_unshared to pages_sharing indicates wasted effort.
pages_volatile embraces several different kinds of activity, but a high
proportion there would also indicate poor use of madvise MADV_MERGEABLE.

Izik Eidus,
Hugh Dickins, 24 Sept 2009


More information about the dovecot mailing list