From: Dan Williams Date: Wed, 13 Oct 2010 22:43:10 +0000 (-0700) Subject: ioat2: fix performance regression X-Git-Tag: v2.6.36-rc8~4^2 X-Git-Url: http://bbs.cooldavid.org/git/?p=net-next-2.6.git;a=commitdiff_plain;h=c50a898fd4e736623ee175920db056194e0bb483 ioat2: fix performance regression Commit 0793448 "DMAENGINE: generic channel status v2" changed the interface for how dma channel progress is retrieved. It inadvertently exported an internal helper function ioat_tx_status() instead of ioat_dma_tx_status(). The latter polls the hardware to get the latest completion state, while the helper just evaluates the current state without touching hardware. The effect is that we end up waiting for completion timeouts or descriptor allocation errors before the completion state is updated. iperf (before fix): [SUM] 0.0-41.3 sec 364 MBytes 73.9 Mbits/sec iperf (after fix): [SUM] 0.0- 4.5 sec 499 MBytes 940 Mbits/sec This is a regression starting with 2.6.35. Cc: Cc: Dave Jiang Cc: Jesse Brandeburg Cc: Linus Walleij Cc: Maciej Sosnowski Reported-by: Richard Scobie Signed-off-by: Dan Williams --- diff --git a/drivers/dma/ioat/dma_v2.c b/drivers/dma/ioat/dma_v2.c index 216f9d383b5..effd140fc04 100644 --- a/drivers/dma/ioat/dma_v2.c +++ b/drivers/dma/ioat/dma_v2.c @@ -879,7 +879,7 @@ int __devinit ioat2_dma_probe(struct ioatdma_device *device, int dca) dma->device_issue_pending = ioat2_issue_pending; dma->device_alloc_chan_resources = ioat2_alloc_chan_resources; dma->device_free_chan_resources = ioat2_free_chan_resources; - dma->device_tx_status = ioat_tx_status; + dma->device_tx_status = ioat_dma_tx_status; err = ioat_probe(device); if (err)