We need a better way to talk about this perf gain. I agree is 12% ops/
second in that particular set of benchmarks. My recollection is that
we removed LFH because it was using too much memory. We need some form
of normalized score based on memory usage. In other words 12% with 25%
more memory usage might not be in practice a gain at all in machines
with 1GB. I do agree that with all other things equal Vista is faster
than XP and the memory usage of both is quite different as well.
> We have lots of diagnostics.
How do we use them? is there a document? I am getting conflicting
information here.
The problem we're having here is a crash which
> is undetected by all tools with *or without* tcmalloc. Neither purify nor
> page heap have been able to detect this problem so far.
I am hearing the opposite here as well.
> Some heap
> corruption problems are hard to track - but blaming tcmalloc for them
> doesn't make any sense.
No, no, tcmalloc is awesome and certainly the bugs exist with out
without it. We need purify or purify like, or valgrind like runs at
check-in time. That is what I don't like. Please set me straight if
this is incorrect.
>
> The heap-checker tools you mention can probably be enabled with some amount
> of work - it's just work. There are other portions of tcmalloc which need
> still to be ported to windows. Whether they would help with locating this
> particular crash or not - I don't know. Given that none of our other tools
> are helping
Not sure about that. Lets wait for the outcome of issues that purify
found this time. I am hearing that we got at least one good lead on a
heap corruption.
--~--~---------~--~----~------------~-------~--~----~
Chromium Developers mailing list: chromium-dev@googlegroups.com
View archives, change email options, or unsubscribe:
http://groups.google.com/group/chromium-dev
-~----------~----~----~----~------~----~------~--~---
