|To:||Christoph Hellwig <hch@xxxxxxxxxxxxx>|
|Subject:||Re: concurrent direct IO write in xfs|
|From:||Zheng Da <zhengda1936@xxxxxxxxx>|
|Date:||Mon, 16 Jan 2012 14:44:30 -0500|
|Dkim-signature:||v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=M862dDcAjIpALZXjhxVqoMN+tJgsdBkTqIrc1Otlghw=; b=qHI5cv7XaYg5f6GcZZ4G55Ry+gG8EMjk5abv8Yks/vzSCizacYYN6mqPRZAqshlllP e6dyNta3MBpUbPKSr5tSMI1HPhqiE+EVohQqizGCGb1MKdSzFVTeZBXyvYkFhtJx+ZN1 GUEA8ROE1YOJ/bTZAI+xdcfSxN0dBUhuJykMI=|
Right now I'm using kernel 3.2.
My test program writes 4G of data to a file that has been preallocated and each time it writes a page of data randomly to the file. It's always overwriting, and no appending. The offset of each write is always aligned to the page size. There is no overlapping between writes as I said before.
I also tried mixing reads and writes and got the similar result.
Can you write data to a file with multiple threads and the performance can scale up with more threads?
On Mon, Jan 16, 2012 at 12:48 PM, Christoph Hellwig <hch@xxxxxxxxxxxxx> wrote:
|<Prev in Thread]||Current Thread||[Next in Thread>|
|Previous by Date:||Re: [PATCH 08/11] xfs: remove the i_size field in struct xfs_inode, Ben Myers|
|Next by Date:||Re: [PATCH 08/11] xfs: remove the i_size field in struct xfs_inode, Ben Myers|
|Previous by Thread:||Re: concurrent direct IO write in xfs, Christoph Hellwig|
|Next by Thread:||Re: concurrent direct IO write in xfs, Dave Chinner|
|Indexes:||[Date] [Thread] [Top] [All Lists]|