Another day, another readpages patchset... This one refines the original one a bit more. The main changes are: 1) this set goes back to adding the pages to the pagecache before submitting the reads on the wire. The reason for this is that we want to prevent the VM from reissuing reads for pages that already have reads in progress. 2) a reference to the cifsFileInfo is held during the I/O. It's possible that the async reads could outlive a ->release operation if it were cancelled. To prevent oopses, we need the async read jobs to hold a cifsFileInfo reference. We can't put cifsFileInfo references from cifsd however, so we need to queue the completion of the reads to a workqueue. 3) a patch has been added that limits the bdi.ra_pages according to the rsize. This ensures that the VM doesn't end up requesting "straggler" pages that would make cifs_readpages issue small reads to satisfy. This patchset uses the infrastructure added in the patchset to overhaul the receive path to allow cifs to vastly increase the rsize. It also is more efficient and does less copying as the data is read directly into the pagecache. Additionally, readpages is now done asynchronously with this set. cifs_readpages just puts the pages in the cache, fires off the reads and returns. Eventually, when the reads complete, a workqueue job is queued that will mark the pages uptodate and unlock them. With this set in place, I see a dramatic increase in performance for buffered read calls. On a simple dd test of a 1GB file to /dev/null: prepatch, with 16k rsize: 1073741824 bytes (1.1 GB) copied, 47.2119 s, 22.7 MB/s postpatch, with 1M rsize: 1073741824 bytes (1.1 GB) copied, 11.1602 s, 96.2 MB/s postpatch, with 60k rsize: 1073741824 bytes (1.1 GB) copied, 12.5183 s, 85.8 MB/s Other tests show similar results. These results are from my craptacular KVM-based test rig. I expect that the performance boost will be even more dramatic on real hardware or on higher-latency connections. Steve, I'd like to see both of these sets go into 3.2 if at all possible. Both of these sets should be bisectable, so committing them in order is highly recommended. Jeff Layton (5): cifs: fix protocol definition for READ_RSP cifs: add cifs_async_readv cifs: convert cifs_readpages to use async reads cifs: allow for larger rsize= options and change defaults cifs: tune bdi.ra_pages in accordance with the rsize fs/cifs/cifspdu.h | 4 +- fs/cifs/cifsproto.h | 24 ++++ fs/cifs/cifssmb.c | 357 +++++++++++++++++++++++++++++++++++++++++++++++++++ fs/cifs/connect.c | 159 ++++++++++++++--------- fs/cifs/file.c | 280 ++++++++++++++++------------------------ 5 files changed, 591 insertions(+), 233 deletions(-) -- 1.7.6 -- To unsubscribe from this list: send the line "unsubscribe linux-cifs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
