Skip to contentSkip to conversation

Make NFS-Client readahead tunable

RFC Martin Knoblauch 1 participant 1 message Sep 18, 2008

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

----- Original Message ----

Quoted 20 lines

From: Greg Banks <gnb-cP1dWloDopni96+mSzHFpQC/[email protected]>
To: Martin Knoblauch <[email protected]>
Cc: linux-nfs list <[email protected]>; [email protected]
Sent: Thursday, September 18, 2008 10:45:01 AM
Subject: Re: [RFC][Resend] Make NFS-Client readahead tunable

Quoted 13 lines · Martin Knoblauch

----- Original Message ----

Quoted 9 lines

I think having a tunable for client readahead is an excellent idea, although not to solve your particular problem. The SLES10 kernel has a patch which does precisely that, perhaps Neil could post it.

I don't think there's a lot of point having both a module parameter and a sysctl.

Quoted 6 lines
Quoted 1 line

Actually there is a good reason. The module parameter can be used to set the

new value at load time and never bother again. The sysctl is very convenient when doing experiments.

Quoted 1 line

You can set module parameters after module load in /sys/module/$module/parameters.

OK, one always learns new stuff :-)

Quoted 6 lines
Quoted 1 line

As Andrew already pointed out, the best solution would be a mount option.

Yep.

Quoted 3 lines

But that seems much more involved as my workaround patch.

Yep.

Seeing Andrews Mails, it might be less involved that I thought :-) Will have a look.

Quoted 9 lines
Quoted 8 lines
Quoted 6 lines

A maximum of 15 is unwise. I've found that (at least with the older readahead mechanisms in SLES10) a multiple of 4 is required to preserve rsize-alignment of READ rpcs to the server, which helps a lot with wide RAID backends. So in SGI we tune client readahead to 16.

15 is the value that the Linux NFS client uses., at least since 2.6.3.

It's a silly value.

I was not sure whether it was just arbitrary, or caused by some other internal limit. The definition made it look like it was somehow related to RPC_DEF_SLOT.

Quoted 10 lines
Quoted 1 line

As it is not tunable up to today, the comment seems moot :-) But it opens the

questions:

Quoted 3 lines

a) should 1 be the minimum, or 0?

Turning off client RA entirely is potentially useful.

Quoted 1 line

b) can the backing_dev_info.ra_pages field safely be set to something higher

than 15?

Quoted 1 line

Yes. Did I mention 16 ?

You also mentioned that you do that at SGI. So, who knows whatelse there is changed :-) Anyway, thanks for the hint.

Quoted 9 lines
Quoted 6 lines
Quoted 4 lines

Your patch seems to have a bunch of other unrelated stuff mixed in.

Yeah, someone already pointed out, that the Makefile hunk does not belong

there. But you say "a bunch" - anything else?

Quoted 1 line

I rapidly scrolled past some stuff about 64bit inodes.

Ahh. Now I remember... when I implemented the module parameter, I found that "enable_ino64" lacks a description. Yeah, should be a separate patch.

Cheers
Martin