Merge remote-tracking branch 'remotes/stefanha/tags/block-pull-request' into staging

# gpg: Signature made Fri 21 Apr 2017 10:43:04 BST
# gpg:                using RSA key 0x9CA4ABB381AB73C8
# gpg: Good signature from "Stefan Hajnoczi <stefanha@redhat.com>"
# gpg:                 aka "Stefan Hajnoczi <stefanha@gmail.com>"
# Primary key fingerprint: 8695 A8BF D3F9 7CDA AC35  775A 9CA4 ABB3 81AB 73C8

* remotes/stefanha/tags/block-pull-request:
  MAINTAINERS: update my email address
  MAINTAINERS: update Wen's email address
  migration/block: use blk_pwrite_zeroes for each zero cluster
  throttle: make throttle_config(throttle_get_config()) symmetric
  throttle: do not use invalid config in test
  qemu-options: explain disk I/O throttling options

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

5 files changed, 77 insertions, 8 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index c60235eaf6..cae3b09f9c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1817,8 +1817,8 @@ S: Supported
 F: tests/image-fuzzer/
 
 Replication
-M: Wen Congyang <wency@cn.fujitsu.com>
-M: Changlong Xie <xiecl.fnst@cn.fujitsu.com>
+M: Wen Congyang <wencongyang2@huawei.com>
+M: Xie Changlong <xiechanglong.d@gmail.com>
 S: Supported
 F: replication*
 F: block/replication.c
diff --git a/migration/block.c b/migration/block.c
index 7734ff728a..060087fa32 100644
--- a/migration/block.c
+++ b/migration/block.c
@@ -885,6 +885,8 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
     int64_t total_sectors = 0;
     int nr_sectors;
     int ret;
+    BlockDriverInfo bdi;
+    int cluster_size = BLOCK_SIZE;
 
     do {
         addr = qemu_get_be64(f);
@@ -919,6 +921,15 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                     error_report_err(local_err);
                     return -EINVAL;
                 }
+
+                ret = bdrv_get_info(blk_bs(blk), &bdi);
+                if (ret == 0 && bdi.cluster_size > 0 &&
+                    bdi.cluster_size <= BLOCK_SIZE &&
+                    BLOCK_SIZE % bdi.cluster_size == 0) {
+                    cluster_size = bdi.cluster_size;
+                } else {
+                    cluster_size = BLOCK_SIZE;
+                }
             }
 
             if (total_sectors - addr < BDRV_SECTORS_PER_DIRTY_CHUNK) {
@@ -932,10 +943,30 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
                                         nr_sectors * BDRV_SECTOR_SIZE,
                                         BDRV_REQ_MAY_UNMAP);
             } else {
+                int i;
+                int64_t cur_addr;
+                uint8_t *cur_buf;
+
                 buf = g_malloc(BLOCK_SIZE);
                 qemu_get_buffer(f, buf, BLOCK_SIZE);
-                ret = blk_pwrite(blk, addr * BDRV_SECTOR_SIZE, buf,
-                                 nr_sectors * BDRV_SECTOR_SIZE, 0);
+                for (i = 0; i < BLOCK_SIZE / cluster_size; i++) {
+                    cur_addr = addr * BDRV_SECTOR_SIZE + i * cluster_size;
+                    cur_buf = buf + i * cluster_size;
+
+                    if ((!block_mig_state.zero_blocks ||
+                        cluster_size < BLOCK_SIZE) &&
+                        buffer_is_zero(cur_buf, cluster_size)) {
+                        ret = blk_pwrite_zeroes(blk, cur_addr,
+                                                cluster_size,
+                                                BDRV_REQ_MAY_UNMAP);
+                    } else {
+                        ret = blk_pwrite(blk, cur_addr, cur_buf,
+                                         cluster_size, 0);
+                    }
+                    if (ret < 0) {
+                        break;
+                    }
+                }
                 g_free(buf);
             }
 
diff --git a/qemu-options.hx b/qemu-options.hx
index 99af8edf5f..9171bd5eec 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -635,6 +635,30 @@ file sectors into the image file.
 conversion of plain zero writes by the OS to driver specific optimized
 zero write commands. You may even choose "unmap" if @var{discard} is set
 to "unmap" to allow a zero write to be converted to an UNMAP operation.
+@item bps=@var{b},bps_rd=@var{r},bps_wr=@var{w}
+Specify bandwidth throttling limits in bytes per second, either for all request
+types or for reads or writes only.  Small values can lead to timeouts or hangs
+inside the guest.  A safe minimum for disks is 2 MB/s.
+@item bps_max=@var{bm},bps_rd_max=@var{rm},bps_wr_max=@var{wm}
+Specify bursts in bytes per second, either for all request types or for reads
+or writes only.  Bursts allow the guest I/O to spike above the limit
+temporarily.
+@item iops=@var{i},iops_rd=@var{r},iops_wr=@var{w}
+Specify request rate limits in requests per second, either for all request
+types or for reads or writes only.
+@item iops_max=@var{bm},iops_rd_max=@var{rm},iops_wr_max=@var{wm}
+Specify bursts in requests per second, either for all request types or for reads
+or writes only.  Bursts allow the guest I/O to spike above the limit
+temporarily.
+@item iops_size=@var{is}
+Let every @var{is} bytes of a request count as a new request for iops
+throttling purposes.  Use this option to prevent guests from circumventing iops
+limits by sending fewer but larger requests.
+@item group=@var{g}
+Join a throttling quota group with given name @var{g}.  All drives that are
+members of the same group are accounted for together.  Use this option to
+prevent guests from circumventing throttling limits by using many small disks
+instead of a single larger disk.
 @end table
 
 By default, the @option{cache=writeback} mode is used. It will report data
diff --git a/tests/test-throttle.c b/tests/test-throttle.c
index bd7c501b2e..a9201b1fea 100644
--- a/tests/test-throttle.c
+++ b/tests/test-throttle.c
@@ -205,8 +205,8 @@ static void test_config_functions(void)
     orig_cfg.buckets[THROTTLE_OPS_READ].avg  = 69;
     orig_cfg.buckets[THROTTLE_OPS_WRITE].avg = 23;
 
-    orig_cfg.buckets[THROTTLE_BPS_TOTAL].max = 0; /* should be corrected */
-    orig_cfg.buckets[THROTTLE_BPS_READ].max  = 1; /* should not be corrected */
+    orig_cfg.buckets[THROTTLE_BPS_TOTAL].max = 0;
+    orig_cfg.buckets[THROTTLE_BPS_READ].max  = 56;
     orig_cfg.buckets[THROTTLE_BPS_WRITE].max = 120;
 
     orig_cfg.buckets[THROTTLE_OPS_TOTAL].max = 150;
@@ -246,8 +246,8 @@ static void test_config_functions(void)
     g_assert(final_cfg.buckets[THROTTLE_OPS_READ].avg  == 69);
     g_assert(final_cfg.buckets[THROTTLE_OPS_WRITE].avg == 23);
 
-    g_assert(final_cfg.buckets[THROTTLE_BPS_TOTAL].max == 15.3);/* fixed */
-    g_assert(final_cfg.buckets[THROTTLE_BPS_READ].max  == 1);   /* not fixed */
+    g_assert(final_cfg.buckets[THROTTLE_BPS_TOTAL].max == 0);
+    g_assert(final_cfg.buckets[THROTTLE_BPS_READ].max  == 56);
     g_assert(final_cfg.buckets[THROTTLE_BPS_WRITE].max == 120);
 
     g_assert(final_cfg.buckets[THROTTLE_OPS_TOTAL].max == 150);
diff --git a/util/throttle.c b/util/throttle.c
index 3817d9b904..3570ed25fc 100644
--- a/util/throttle.c
+++ b/util/throttle.c
@@ -380,6 +380,14 @@ static void throttle_fix_bucket(LeakyBucket *bkt)
     }
 }
 
+/* undo internal bucket parameter changes (see throttle_fix_bucket()) */
+static void throttle_unfix_bucket(LeakyBucket *bkt)
+{
+    if (bkt->max < bkt->avg) {
+        bkt->max = 0;
+    }
+}
+
 /* take care of canceling a timer */
 static void throttle_cancel_timer(QEMUTimer *timer)
 {
@@ -420,7 +428,13 @@ void throttle_config(ThrottleState *ts,
  */
 void throttle_get_config(ThrottleState *ts, ThrottleConfig *cfg)
 {
+    int i;
+
     *cfg = ts->cfg;
+
+    for (i = 0; i < BUCKETS_COUNT; i++) {
+        throttle_unfix_bucket(&cfg->buckets[i]);
+    }
 }