| To: | Iustin Pop <iusty@xxxxxxxxx> |
|---|---|
| Subject: | Re: mkfs.xfs questions |
| From: | Christian Kujau <christian@xxxxxxxxxxxxxxx> |
| Date: | Tue, 5 Dec 2006 17:46:15 +0000 (GMT) |
| Cc: | xfs@xxxxxxxxxxx, jasmin@xxxxxxxxxxx |
| In-reply-to: | <20061202111546.GA18661@teal.hq.k1024.org> |
| References: | <20061129174553.e0ef3465.jasmin@pacifica.ch> <Pine.LNX.4.64.0612010410530.3735@sheep.housecafe.de> <20061201183034.GA20595@teal.hq.k1024.org> <Pine.LNX.4.64.0612012349020.3735@sheep.housecafe.de> <20061202111546.GA18661@teal.hq.k1024.org> |
| Sender: | xfs-bounce@xxxxxxxxxxx |
On Sat, 2 Dec 2006, Iustin Pop wrote:
Hmm, I am pretty sure that it makes a difference, but only from personal experience, not from benchmarks. A while ago, mkfs.xfs used to make <8M logs even for big filesystems[0]. Nowadays it chooses a more sane value. I could not stand my own curiosity, so here it is: http://nerdbynature.de/wp/?cat=4 I think I'll repeat the benchmarks with bigger test sizes. The testscript can easily be adjusted to test more options/values. Christian. -- BOFH excuse #248: Too much radiation coming from the soil. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: Review: Reduce in-core superblock lock contention near ENOSPC, Klaus Strebel |
|---|---|
| Next by Date: | Re: mkfs.xfs questions, Iustin Pop |
| Previous by Thread: | Re: mkfs.xfs questions, Iustin Pop |
| Next by Thread: | Re: mkfs.xfs questions, Iustin Pop |
| Indexes: | [Date] [Thread] [Top] [All Lists] |