Re: [PATCH] Re: PATCH: killing read_ahead[]

From: Jeff V. Merkey (jmerkey@timpanogas.org)
Date: Wed Oct 25 2000 - 13:30:28 EST


Rik,

I've reviewed the patch. It's affect seems minimal and will not break
NWFS as proposed -- it looks like, however, it will reduce the
performance slightly of EXT2/3 with iozone for read ahead since the
first section of the patch limits the read ahead window size. NWFS uses
it's own read ahead underneath Linux page cache, so our performance is
unaffected. I was concerned about interface issues between the FS and
page cache interface. THe impact seems iminmal. I'm sorry to be on the
edge of my seat, but we've got a 2.4 based Linux distribution nearly
ready to go out the door, and even minor changes could push us out
further.

2.4 is as solid as any release of W2K or NetWare I've seen (NetWare
ships when the bug count of level II and III bugs (non-Oopes) hits 300.
Microsoft ships when the bug count is under 1000.) 2.4 is way under
these numbers, but since it's open source, the whole planet gets to know
about every single bug, no matter how minor. I think it's ready -- I've
got servers here that have been running it for weeks, and it's looking
solid on everything except PCMCIA (still some problems that are Level I
here) and some of the more exotic features added of late. With the DVD
fixes, it's on par with W2K as is.

:-)

Jeff

"Jeff V. Merkey" wrote:
>
> Where's the patch located? It's not attached to this email.
>
> Jeff
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Tue Oct 31 2000 - 21:00:16 EST