Re: [PATCH] cfq: get rid of cfqq hash
From: Vasily Tarasov
Date: Tue Apr 24 2007 - 08:52:36 EST
>> From: Vasily Tarasov <vtaras@xxxxxxxxxx>
>> cfq hash is no more necessary. We always can get cfqq from io context.
>> cfq_get_io_context_noalloc() function is introduced, because we don't want
>> allocate cic on merging and checking may_queue.
>> In order to identify sync queue we've used hash key = CFQ_KEY_ASYNC. Since
>> is eliminated we need to use other criterion: sync flag for queue is added.
>> In all places where we dig in rb_tree we're in current context, so no
>> additional locking is required.
>> Advantages of this patch: no additional memory for hash, no seeking in hash,
>> code is cleaner. But it is necessary now to seek cic in per-ioc rbtree, but
>> it is faster:
>> - most processes work only with few devices
>> - most systems have only few block devices
>> - it is a rb-tree
> Vasily, thanks for doing this, it's a good cleanup. One request, though
> - care to rebase this against the cfq devel branch? I'm afraid it's
> nowhere near applying right now.
> Jens Axboe
Ouch, I see the sources are changed since the moment I was getting them...
I'll resend a fresh version!
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/