[libvirt] [PATCHv6 3/7] Support block I/O throttle in XML

From: Lei Li <lilei(a)linux.vnet.ibm.com&gt; Enable block I/O throttle for per-disk in XML, as the first per-disk IO tuning parameter. Signed-off-by: Lei Li <lilei(a)linux.vnet.ibm.com&gt; Signed-off-by: Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com&gt; Signed-off-by: Eric Blake <eblake(a)redhat.com&gt; --- docs/formatdomain.html.in | 39 +++++++++++++ docs/schemas/domaincommon.rng | 122 +++++++++++++++++++++++++++++------------ src/conf/domain_conf.c | 90 ++++++++++++++++++++++++++++++- src/conf/domain_conf.h | 14 +++++ 4 files changed, 228 insertions(+), 37 deletions(-) diff --git a/docs/formatdomain.html.in b/docs/formatdomain.html.in index 61123ac..f45d0ce 100644 --- a/docs/formatdomain.html.in +++ b/docs/formatdomain.html.in @@ -922,6 +922,11 @@ &lt;driver name="tap" type="aio" cache="default"/&gt; &lt;source file='/var/lib/xen/images/fv0'/ startupPolicy='optional'&gt; &lt;target dev='hda' bus='ide'/&gt; + &lt;iotune&gt; + &lt;total_bytes_sec&gt;10000000&lt;/total_bytes_sec&gt; + &lt;read_iops_sec&gt;400000&lt;/read_iops_sec&gt; + &lt;write_iops_sec&gt;100000&lt;/write_iops_sec&gt; + &lt;/iotune&gt; &lt;boot order='2'/&gt; &lt;encryption type='...'&gt; ... @@ -1039,6 +1044,40 @@ <span class="since">Since 0.0.3; <code>bus</code> attribute since 0.4.3; "usb" attribute value since after 0.4.4; "sata" attribute value since 0.9.7</span></dd> + <dt><code>iotune</code></dt> + <dd>The optional <code>iotune</code> element provides the + ability to provide additional per-device I/O tuning, with + values that can vary for each device (contrast this to + the <a href="#elementsBlockTuning"><code>&lt;blkiotune&gt;</code></a> + element, which applies globally to the domain). Currently, + the only tuning available is Block I/O throttling for qemu. + This element has optional sub-elements; any sub-element not + specified or given with a value of 0 implies no + limit. <span class="since">Since 0.9.8</span> + <dl> + <dt><code>total_bytes_sec</code></dt> + <dd>The optional <code>total_bytes_sec</code> element is the + total throughput limit in bytes per second. This cannot + appear with <code>read_bytes_sec</code> + or <code>write_bytes_sec</code>.</dd> + <dt><code>read_bytes_sec</code></dt> + <dd>The optional <code>read_bytes_sec</code> element is the + read throughput limit in bytes per second.</dd> + <dt><code>write_bytes_sec</code></dt> + <dd>The optional <code>write_bytes_sec</code> element is the + write throughput limit in bytes per second.</dd> + <dt><code>total_iops_sec</code></dt> + <dd>The optional <code>total_iops_sec</code> element is the + total I/O operations per second. This cannot + appear with <code>read_iops_sec</code> + or <code>write_iops_sec</code>.</dd> + <dt><code>read_iops_sec</code></dt> + <dd>The optional <code>read_iops_sec</code> element is the + read I/O operations per second.</dd> + <dt><code>write_iops_sec</code></dt> + <dd>The optional <code>write_iops_sec</code> element is the + write I/O operations per second.</dd> + </dl> <dt><code>driver</code></dt> <dd> The optional driver element allows specifying further details diff --git a/docs/schemas/domaincommon.rng b/docs/schemas/domaincommon.rng index 8968ee6..bb6d94d 100644 --- a/docs/schemas/domaincommon.rng +++ b/docs/schemas/domaincommon.rng @@ -599,42 +599,47 @@ </element> </define> <define name="diskspec"> - <optional> - <ref name="driver"/> - </optional> - <optional> - <ref name="diskAuth"/> - </optional> - <ref name="target"/> - <optional> - <ref name="deviceBoot"/> - </optional> - <optional> - <element name="readonly"> - <empty/> - </element> - </optional> - <optional> - <element name="shareable"> - <empty/> - </element> - </optional> - <optional> - <element name="transient"> - <empty/> - </element> - </optional> - <optional> - <element name="serial"> - <ref name="diskSerial"/> - </element> - </optional> - <optional> - <ref name="encryption"/> - </optional> - <optional> - <ref name="address"/> - </optional> + <interleave> + <optional> + <ref name="driver"/> + </optional> + <optional> + <ref name="diskAuth"/> + </optional> + <ref name="target"/> + <optional> + <ref name="deviceBoot"/> + </optional> + <optional> + <element name="readonly"> + <empty/> + </element> + </optional> + <optional> + <element name="shareable"> + <empty/> + </element> + </optional> + <optional> + <element name="transient"> + <empty/> + </element> + </optional> + <optional> + <element name="serial"> + <ref name="diskSerial"/> + </element> + </optional> + <optional> + <ref name="encryption"/> + </optional> + <optional> + <ref name="diskIoTune"/> + </optional> + <optional> + <ref name="address"/> + </optional> + </interleave> </define> <define name="snapshot"> <attribute name="snapshot"> @@ -2596,6 +2601,51 @@ </element> </define> + <define name='diskIoTune'> + <element name="iotune"> + <interleave> + <choice> + <element name="total_bytes_sec"> + <data type="unsignedLong"/> + </element> + <group> + <interleave> + <optional> + <element name="read_bytes_sec"> + <data type="unsignedLong"/> + </element> + </optional> + <optional> + <element name="write_bytes_sec"> + <data type="unsignedLong"/> + </element> + </optional> + </interleave> + </group> + </choice> + <choice> + <element name="total_iops_sec"> + <data type="unsignedLong"/> + </element> + <group> + <interleave> + <optional> + <element name="read_iops_sec"> + <data type="unsignedLong"/> + </element> + </optional> + <optional> + <element name="write_iops_sec"> + <data type="unsignedLong"/> + </element> + </optional> + </interleave> + </group> + </choice> + </interleave> + </element> + </define> + <!-- Optional hypervisor extensions in their own namespace: QEmu diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c index d365cee..a2702c5 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -2394,6 +2394,7 @@ cleanup: static virDomainDiskDefPtr virDomainDiskDefParseXML(virCapsPtr caps, xmlNodePtr node, + xmlXPathContextPtr ctxt, virBitmapPtr bootMap, unsigned int flags) { @@ -2594,6 +2595,50 @@ virDomainDiskDefParseXML(virCapsPtr caps, } child = child->next; } + } else if (xmlStrEqual(cur->name, BAD_CAST "iotune")) { + if (virXPathULongLong("string(./devices/disk/iotune/total_bytes_sec)", + ctxt, &def->blkdeviotune.total_bytes_sec) < 0) { + def->blkdeviotune.total_bytes_sec = 0; + } + + if (virXPathULongLong("string(./devices/disk/iotune/read_bytes_sec)", + ctxt, &def->blkdeviotune.read_bytes_sec) < 0) { + def->blkdeviotune.read_bytes_sec = 0; + } + + if (virXPathULongLong("string(./devices/disk/iotune/write_bytes_sec)", + ctxt, &def->blkdeviotune.write_bytes_sec) < 0) { + def->blkdeviotune.write_bytes_sec = 0; + } + + if (virXPathULongLong("string(./devices/disk/iotune/total_iops_sec)", + ctxt, &def->blkdeviotune.total_iops_sec) < 0) { + def->blkdeviotune.total_iops_sec = 0; + } + + if (virXPathULongLong("string(./devices/disk/iotune/read_iops_sec)", + ctxt, &def->blkdeviotune.read_iops_sec) < 0) { + def->blkdeviotune.read_iops_sec = 0; + } + + if (virXPathULongLong("string(./devices/disk/iotune/write_iops_sec)", + ctxt, &def->blkdeviotune.write_iops_sec) < 0) { + def->blkdeviotune.write_iops_sec = 0; + } + + if ((def->blkdeviotune.total_bytes_sec && def->blkdeviotune.read_bytes_sec) + || (def->blkdeviotune.total_bytes_sec && def->blkdeviotune.write_bytes_sec)) { + virDomainReportError(VIR_ERR_XML_ERROR, + _("total and read/write bytes_sec cannot be set at the same time")); + goto error; + } + + if ((def->blkdeviotune.total_iops_sec && def->blkdeviotune.read_iops_sec) + || (def->blkdeviotune.total_iops_sec && def->blkdeviotune.write_iops_sec)) { + virDomainReportError(VIR_ERR_XML_ERROR, + _("total and read/write iops_sec cannot be set at the same time")); + goto error; + } } else if (xmlStrEqual(cur->name, BAD_CAST "readonly")) { def->readonly = 1; } else if (xmlStrEqual(cur->name, BAD_CAST "shareable")) { @@ -6078,7 +6123,7 @@ virDomainDeviceDefPtr virDomainDeviceDefParse(virCapsPtr caps, if (xmlStrEqual(node->name, BAD_CAST "disk")) { dev->type = VIR_DOMAIN_DEVICE_DISK; - if (!(dev->data.disk = virDomainDiskDefParseXML(caps, node, + if (!(dev->data.disk = virDomainDiskDefParseXML(caps, node, ctxt, NULL, flags))) goto error; } else if (xmlStrEqual(node->name, BAD_CAST "lease")) { @@ -7148,6 +7193,7 @@ static virDomainDefPtr virDomainDefParseXML(virCapsPtr caps, for (i = 0 ; i < n ; i++) { virDomainDiskDefPtr disk = virDomainDiskDefParseXML(caps, nodes[i], + ctxt, bootMap, flags); if (!disk) @@ -9589,6 +9635,48 @@ virDomainDiskDefFormat(virBufferPtr buf, virBufferAsprintf(buf, " <target dev='%s' bus='%s'/>\n", def->dst, bus); + /*disk I/O throttling*/ + if (def->blkdeviotune.total_bytes_sec || + def->blkdeviotune.read_bytes_sec || + def->blkdeviotune.write_bytes_sec || + def->blkdeviotune.total_iops_sec || + def->blkdeviotune.read_iops_sec || + def->blkdeviotune.write_iops_sec) { + virBufferAddLit(buf, " <iotune>\n"); + if (def->blkdeviotune.total_bytes_sec) { + virBufferAsprintf(buf, " <total_bytes_sec>%llu</total_bytes_sec>\n", + def->blkdeviotune.total_bytes_sec); + } + + if (def->blkdeviotune.read_bytes_sec) { + virBufferAsprintf(buf, " <read_bytes_sec>%llu</read_bytes_sec>\n", + def->blkdeviotune.read_bytes_sec); + + } + + if (def->blkdeviotune.write_bytes_sec) { + virBufferAsprintf(buf, " <write_bytes_sec>%llu</write_bytes_sec>\n", + def->blkdeviotune.write_bytes_sec); + } + + if (def->blkdeviotune.total_iops_sec) { + virBufferAsprintf(buf, " <total_iops_sec>%llu</total_iops_sec>\n", + def->blkdeviotune.total_iops_sec); + } + + if (def->blkdeviotune.read_iops_sec) { + virBufferAsprintf(buf, " <read_iops_sec>%llu</read_iops_sec>", + def->blkdeviotune.read_iops_sec); + } + + if (def->blkdeviotune.write_iops_sec) { + virBufferAsprintf(buf, " <write_iops_sec>%llu</write_iops_sec>", + def->blkdeviotune.write_iops_sec); + } + + virBufferAddLit(buf, " </iotune>\n"); + } + if (def->bootIndex) virBufferAsprintf(buf, " <boot order='%d'/>\n", def->bootIndex); if (def->readonly) diff --git a/src/conf/domain_conf.h b/src/conf/domain_conf.h index 7511178..ff6921a 100644 --- a/src/conf/domain_conf.h +++ b/src/conf/domain_conf.h @@ -313,6 +313,17 @@ enum virDomainDiskSecretType { VIR_DOMAIN_DISK_SECRET_TYPE_LAST }; +typedef struct _virDomainBlockIoTuneInfo virDomainBlockIoTuneInfo; +struct _virDomainBlockIoTuneInfo { + unsigned long long total_bytes_sec; + unsigned long long read_bytes_sec; + unsigned long long write_bytes_sec; + unsigned long long total_iops_sec; + unsigned long long read_iops_sec; + unsigned long long write_iops_sec; +}; +typedef virDomainBlockIoTuneInfo *virDomainBlockIoTuneInfoPtr; + /* Stores the virtual disk configuration */ typedef struct _virDomainDiskDef virDomainDiskDef; typedef virDomainDiskDef *virDomainDiskDefPtr; @@ -335,6 +346,9 @@ struct _virDomainDiskDef { } auth; char *driverName; char *driverType; + + virDomainBlockIoTuneInfo blkdeviotune; + char *serial; int cachemode; int error_policy; /* enum virDomainDiskErrorPolicy */ -- 1.7.7.3