The shared memory log

Poul-Henning Kamp phk at
Thu Mar 23 14:32:38 CET 2006

I've been thinking about the shared memory log som more, and come up
with a few minor course adjustments.

The first is that since we control the API on both sides of the shared
memory, the actual layout of the shared memory need not be the exact
XML format we have decided, as long as the API produces that.

The reason why this is interesting is that we will be logging more
data than any one log-consumer will want to look at, so sorting it
into per request "log lines" in the cache process is not actually necessary.

So instead of putting XML into the log, I think I will put only XML
tags into the log and let the client side, sort these into XML "lines"
as appropriate.

Imagine if the "final" log output line would be:

The initial idea was to write all this to shared memory at the end of
the transaction, but that means that the cache process needs to somewhere
to keep it until then, and that means copying/formatting the log entry
into dynamically allocated memory, and then copying it to shared
memory at the end of the request.

It would be far cheaper to stick the individual bits directly into
shared memory as soon as we have them, but that means that different
requests will be intereleaved which the logclient will have to sort
that out.

But, since the logclient is likely to want to ignore some number of
the 'fields', doing so is actually cheaper if they can be ignored
at first sight, instead of having to 'edit them out' of the full record.

So in this new scheme of things, we write shared memory in records
like these:

	1 byte:	field type
		0x00 = NEW log record
		0x01 = CLIENT
		0x02 = URL
		0x03 = ...
		0xff = end of log record
	2 byte: magic number
	1 byte: length  (possibly 2 bytes ?)

and the above example would look like:

	[0x00, 0x1838, 0]       	NEW log entry with magic 0x1838
	[0x01, 0x1838, 13] ""
	[0x02, 0x1838, 16] ""
	[0x03, 0x1838, 5] "65023"
	[0x04, 0x1838, 4] "1.24"
	[0xff, 0x1838, 0]		End record

I belive this will be quite a bit faster than the other way around...

Poul-Henning Kamp       | UNIX since Zilog Zeus 3.20
phk at FreeBSD.ORG         | TCP/IP since RFC 956
FreeBSD committer       | BSD since 4.3-tahoe    
Never attribute to malice what can adequately be explained by incompetence.

More information about the varnish-dev mailing list