| To: | Roy Sigurd Karlsbakk <roy@xxxxxxxxxxxxx> |
|---|---|
| Subject: | Re: Q: Filesystem block sizes available? |
| From: | Steve Lord <lord@xxxxxxx> |
| Date: | 13 Nov 2001 09:07:10 -0600 |
| Cc: | Seth Mos <knuffie@xxxxxxxxx>, XFS Mailing list <linux-xfs@xxxxxxxxxxx> |
| In-reply-to: | <Pine.LNX.4.30.0111131602280.1160-100000@xxxxxxxxxxxxxxxxx> |
| References: | <Pine.LNX.4.30.0111131602280.1160-100000@xxxxxxxxxxxxxxxxx> |
| Sender: | owner-linux-xfs@xxxxxxxxxxx |
On Tue, 2001-11-13 at 09:04, Roy Sigurd Karlsbakk wrote: > > The fs blocksize has not much to do with the amount it writes in one go. > > XFS uses delayed allocation so it will probably write a lot of data at once > > anyways. > > How about reading? The reading is really essensial here - writing is done > by batch, and can take whatever time it likes (almost :-) Reading in Linux does readahead - but I do not think it asks for more than 32 pages at once. We are using mostly the generic linux code paths for read unless you use O_DIRECT. Steve -- Steve Lord voice: +1-651-683-3511 Principal Engineer, Filesystem Software email: lord@xxxxxxx |
| Previous by Date: | TAKE - add informative warning to dmapi set_eventlist test, Dean Roehrich |
|---|---|
| Next by Date: | Re: Q: Filesystem block sizes available?, Roy Sigurd Karlsbakk |
| Previous by Thread: | Re: Q: Filesystem block sizes available?, Roy Sigurd Karlsbakk |
| Next by Thread: | Re: Q: Filesystem block sizes available?, Roy Sigurd Karlsbakk |
| Indexes: | [Date] [Thread] [Top] [All Lists] |