On Thu, Jul 27, 2000 at 07:49:50PM +0200, Daniel Phillips wrote: > So now it's time to start asking questions. Just jumping in at a place I > felt I knew pretty well back in 2.2.13, I'm now looking at the 2.4.0 getblk, > and I see it's changed somewhat. Finding and removing a block from the free > list is now bracketed by a spinlock pair. First question: why do we use > atomic_set to set the initial buffer use count if this is already protected > by a spinlock? Also, I'd /still/ like to know what stops another CPU from adding the buffer head we were looking for between the call to get_hash_table returning NULL and insert_into_queues. AFAICS, getblk() isn't always called with the BKL.
- Questions about the buffer+page cache in 2.4.0 Daniel Phillips
- Re: Questions about the buffer+page cache in 2.4.0 Tigran Aivazian
- Re: Questions about the buffer+page cache in 2.4.... Tigran Aivazian
- Re: Questions about the buffer+page cache in 2.4.0 Andi Kleen
- Re: Questions about the buffer+page cache in 2.4.0 Matthew Wilcox
- Re: Questions about the buffer+page cache in 2.4.0 Steve Dodd
- Re: Questions about the buffer+page cache in 2.4.0 Daniel Phillips
- Re: Questions about the buffer+page cache in 2.4.... Gary Funck
- Re: Questions about the buffer+page cache in ... Andi Kleen
- Re: Questions about the buffer+page cache... Gary Funck
- Re: Questions about the buffer+page ... Andi Kleen
- Re: Questions about the buffer+p... Gary Funck
- Re: Questions about the buffer+page cache in ... Kurt Garloff
- Re: Questions about the buffer+page cache in 2.4.... Daniel Phillips
- Re: Questions about the buffer+page cache in ... Chris Mason
- Re: Questions about the buffer+page cache... Daniel Phillips