commit ae29d6c64bd8d55873a2cb1df50ae4321b497447
author Stefan Hajnoczi <stefanha@redhat.com> Fri Apr 05 11:32:20 2013 +0200
committer Kevin Wolf <kwolf@redhat.com> Fri Apr 05 18:58:05 2013 +0200
tree d677532c07fcb19a2f6708eecaa185f63e92d8da
parent 5905fbc9c94ccd744c1b249472eafcc2d827548a

block: keep I/O throttling slice time constant

It is not necessary to adjust the slice time at runtime.  We already
extend the current slice in order to carry over accounting into the next
slice.  Changing the actual slice time value introduces oscillations.

The guest may experience large changes in throughput or IOPS from one
moment to the next when slice times are adjusted.

Reported-by: Benoît Canet <benoit@irqsave.net>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Tested-By: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

block.c

diff --git a/block.c b/block.c
index 25976b5..00eca27 100644
--- a/block.c
+++ b/block.c
@@ -140,7 +140,6 @@
 
     bs->slice_start = 0;
     bs->slice_end   = 0;
-    bs->slice_time  = 0;
 }
 
 static void bdrv_block_timer(void *opaque)
@@ -1432,7 +1431,6 @@
     bs_dest->enable_write_cache = bs_src->enable_write_cache;
 
     /* i/o timing parameters */
-    bs_dest->slice_time         = bs_src->slice_time;
     bs_dest->slice_start        = bs_src->slice_start;
     bs_dest->slice_end          = bs_src->slice_end;
     bs_dest->slice_submitted    = bs_src->slice_submitted;
@@ -3749,6 +3747,7 @@
                  bool is_write, double elapsed_time, uint64_t *wait)
 {
     uint64_t bps_limit = 0;
+    uint64_t extension;
     double   bytes_limit, bytes_base, bytes_res;
     double   slice_time, wait_time;
 
@@ -3796,8 +3795,10 @@
      * info can be kept until the timer fire, so it is increased and tuned
      * based on the result of experiment.
      */
-    bs->slice_time = wait_time * BLOCK_IO_SLICE_TIME * 10;
-    bs->slice_end += bs->slice_time - 3 * BLOCK_IO_SLICE_TIME;
+    extension = wait_time * NANOSECONDS_PER_SECOND;
+    extension = DIV_ROUND_UP(extension, BLOCK_IO_SLICE_TIME) *
+                BLOCK_IO_SLICE_TIME;
+    bs->slice_end += extension;
     if (wait) {
         *wait = wait_time * BLOCK_IO_SLICE_TIME * 10;
     }
@@ -3848,8 +3849,8 @@
         wait_time = 0;
     }
 
-    bs->slice_time = wait_time * BLOCK_IO_SLICE_TIME * 10;
-    bs->slice_end += bs->slice_time - 3 * BLOCK_IO_SLICE_TIME;
+    /* Exceeded current slice, extend it by another slice time */
+    bs->slice_end += BLOCK_IO_SLICE_TIME;
     if (wait) {
         *wait = wait_time * BLOCK_IO_SLICE_TIME * 10;
     }
@@ -3868,12 +3869,10 @@
     now = qemu_get_clock_ns(vm_clock);
     if ((bs->slice_start < now)
         && (bs->slice_end > now)) {
-        bs->slice_end = now + bs->slice_time;
+        bs->slice_end = now + BLOCK_IO_SLICE_TIME;
     } else {
-        bs->slice_time  =  5 * BLOCK_IO_SLICE_TIME;
         bs->slice_start = now;
-        bs->slice_end   = now + bs->slice_time;
-
+        bs->slice_end   = now + BLOCK_IO_SLICE_TIME;
         memset(&bs->slice_submitted, 0, sizeof(bs->slice_submitted));
     }
 

blockdev.c

diff --git a/blockdev.c b/blockdev.c
index 8cdc9ce..6dc999d 100644
--- a/blockdev.c
+++ b/blockdev.c
@@ -1069,7 +1069,6 @@
     }
 
     bs->io_limits = io_limits;
-    bs->slice_time = BLOCK_IO_SLICE_TIME;
 
     if (!bs->io_limits_enabled && bdrv_io_limits_enabled(bs)) {
         bdrv_io_limits_enable(bs);

include/block/block_int.h

diff --git a/include/block/block_int.h b/include/block/block_int.h
index 83941d8..9aa98b5 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -252,7 +252,6 @@
     unsigned int copy_on_read_in_flight;
 
     /* the time for latest disk I/O */
-    int64_t slice_time;
     int64_t slice_start;
     int64_t slice_end;
     BlockIOLimit io_limits;