Re: squid-2.4 release ?

Yury Shevchuk wrote:

> On Sun, Jan 07, 2001 at 07:43:31PM -0600, Joe Cooper wrote:
>
>> Over the past several days I've had some time for performing benchmarks.
>> I'll be posting the results in another day or two. I'm running into a
>> few issues of stability under load, as well as slight performance
>> degradation from 2.2STABLE5 (and obviously slower than reiser_raw, as is
>> expected).
>
>
> Note that reiserfs_raw kernels have some hacks (in particular, on
> inode cache) that may adversely impact performance in non-reiserfs_raw
> mode. So to be just, you should use non-reiserfs_raw kernel for
> non-reiserfs_raw tests.

Yep. I'm running 2.2.17 for these tests. Nothing but the plain
ReiserFS patch, and a few other patches for hardware support.

 
>> Oh, and I also see a few of these in there too:
>>
>> 2001/01/07 03:09:17| comm_open: socket failure: (105) No buffer space
>> available
>
>
> Kernel VM subsystem fails to keep up with kernel memory allocation
> requests. I remember running into this (with 2.2 kernels, though).
> You can try to tune bdflush to flush dirty buffers more aggressively,
> to make life easier for the vm subsystem.

I'll give that a try. I'll also give it a couple of runs on the new
kernel 2.4. It may very well be an issue of the kernel rather than
Squid. It is definitely only happening on a loaded box...but the load
that it's able to handle is, I think, a little less than the last time I
benched Squid 2.4DEVEL.

More later.
                                   --
                      Joe Cooper <joe@swelltech.com>
                  Affordable Web Caching Proxy Appliances
                         http://www.swelltech.com
Received on Mon Jan 08 2001 - 02:26:20 MST