[svn.haxx.se] · SVN Dev · SVN Users · SVN Org · TSVN Dev · TSVN Users · Subclipse Dev · Subclipse Users · this month's index

Re: faster client pre-1.0: neon prefetching, multithreading

From: Greg Hudson <ghudson_at_MIT.EDU>
Date: 2003-02-11 20:15:51 CET

I had no idea that ra_dav was using appreciably more connections than
ra_svn. Every time I've looked at the code, it looks like it opens two
sessions in ra_lib->open and continues to reuse them. Is the repeated
reconnecting being done inside neon?

If that's not the source of the problem, I have an idea for narrowing it
down. Do a tcpdump of a Subversion operation with timestamps. Using
the timestamps, find out whether most of the time is spent in the client
or in the server, and if there are particular steps of the operation
which require lots of time.

On Tue, 2003-02-11 at 13:37, Branko ╚ibej wrote:
> Besides, sending deltas for checkout and import is total nonsense.

It's not total nonsense; it's a space versus time issue. If we're
spending 10% of import time in vdelta(), then eliminating checkout and
import deltas will only speed up imports by about 10%, and at some cost
in bandwidth. And computers will get faster more quickly than bandwidth
will get cheaper.

> The fix is not speeding up vdelta (bet: you won't get a 2x speedup
> anyway), but to remove it from the checkout and import code path
> entirely.

But speeding up vdelta will also help updates. But you're probably
right; short of hand-coded assembly, we can probably only make small
improvements, like inlining svn_txdelta__insert_op.

---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscribe@subversion.tigris.org
For additional commands, e-mail: dev-help@subversion.tigris.org
Received on Tue Feb 11 20:16:37 2003

This is an archived mail posted to the Subversion Dev mailing list.