fsdev: add IO throttle support to fsdev devices

This patchset adds the throttle support for the 9p-local driver.
For now this functionality can be enabled only through qemu cli options.
QMP interface and support to other drivers need further extensions.
To make it simple for other 9p drivers, the throttle code has been put in
separate files.
Signed-off-by: NPradeep Jagadeesh <pradeep.jagadeesh@huawei.com>
Reviewed-by: NAlberto Garcia <berto@igalia.com>
(pass extra NULL CoMutex * argument to qemu_co_queue_wait(),
 added options to qemu-options.hx, Greg Kurz)
Signed-off-by: NGreg Kurz <groug@kaod.org>

fsdev/Makefile.objs

@@ -5,7 +5,7 @@ common-obj-y = qemu-fsdev.o 9p-marshal.o 9p-iov-marshal.o
 else
 common-obj-y = qemu-fsdev-dummy.o
 endif
-common-obj-y += qemu-fsdev-opts.o
+common-obj-y += qemu-fsdev-opts.o qemu-fsdev-throttle.o
 
 # Toplevel always builds this; targets without virtio will put it in
 # common-obj-y

fsdev/file-op-9p.h

@@ -17,6 +17,7 @@
 #include <dirent.h>
 #include <utime.h>
 #include <sys/vfs.h>
+#include "qemu-fsdev-throttle.h"
 
 #define SM_LOCAL_MODE_BITS    0600
 #define SM_LOCAL_DIR_MODE_BITS    0700
@@ -74,6 +75,7 @@ typedef struct FsDriverEntry {
     char *path;
     int export_flags;
     FileOperations *ops;
+    FsThrottle fst;
 } FsDriverEntry;
 
 typedef struct FsContext
@@ -83,6 +85,7 @@ typedef struct FsContext
     int export_flags;
     struct xattr_operations **xops;
     struct extended_ops exops;
+    FsThrottle *fst;
     /* fs driver specific data */
     void *private;
 } FsContext;

fsdev/qemu-fsdev-opts.c

@@ -37,8 +37,83 @@ static QemuOptsList qemu_fsdev_opts = {
         }, {
             .name = "sock_fd",
             .type = QEMU_OPT_NUMBER,
+        }, {
+            .name = "throttling.iops-total",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit total I/O operations per second",
+        }, {
+            .name = "throttling.iops-read",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit read operations per second",
+        }, {
+            .name = "throttling.iops-write",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit write operations per second",
+        }, {
+            .name = "throttling.bps-total",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit total bytes per second",
+        }, {
+            .name = "throttling.bps-read",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit read bytes per second",
+        }, {
+            .name = "throttling.bps-write",
+            .type = QEMU_OPT_NUMBER,
+            .help = "limit write bytes per second",
+        }, {
+            .name = "throttling.iops-total-max",
+            .type = QEMU_OPT_NUMBER,
+            .help = "I/O operations burst",
+        }, {
+            .name = "throttling.iops-read-max",
+            .type = QEMU_OPT_NUMBER,
+            .help = "I/O operations read burst",
+        }, {
+            .name = "throttling.iops-write-max",
+            .type = QEMU_OPT_NUMBER,
+            .help = "I/O operations write burst",
+        }, {
+            .name = "throttling.bps-total-max",
+            .type = QEMU_OPT_NUMBER,
+            .help = "total bytes burst",
+        }, {
+            .name = "throttling.bps-read-max",
+            .type = QEMU_OPT_NUMBER,
+            .help = "total bytes read burst",
+        }, {
+            .name = "throttling.bps-write-max",
+            .type = QEMU_OPT_NUMBER,
+            .help = "total bytes write burst",
+        }, {
+            .name = "throttling.iops-total-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-total-max burst period, in seconds",
+        }, {
+            .name = "throttling.iops-read-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-read-max burst period, in seconds",
+        }, {
+            .name = "throttling.iops-write-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the iops-write-max burst period, in seconds",
+        }, {
+            .name = "throttling.bps-total-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-total-max burst period, in seconds",
+        }, {
+            .name = "throttling.bps-read-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-read-max burst period, in seconds",
+        }, {
+            .name = "throttling.bps-write-max-length",
+            .type = QEMU_OPT_NUMBER,
+            .help = "length of the bps-write-max burst period, in seconds",
+        }, {
+            .name = "throttling.iops-size",
+            .type = QEMU_OPT_NUMBER,
+            .help = "when limiting by iops max size of an I/O in bytes",
         },
-
         { /*End of list */ }
     },
 };

fsdev/qemu-fsdev-throttle.c

+/*
+ * Fsdev Throttle
+ *
+ * Copyright (C) 2016 Huawei Technologies Duesseldorf GmbH
+ *
+ * Author: Pradeep Jagadeesh <pradeep.jagadeesh@huawei.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.
+ *
+ * See the COPYING file in the top-level directory for details.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qemu/error-report.h"
+#include "qemu-fsdev-throttle.h"
+#include "qemu/iov.h"
+
+static void fsdev_throttle_read_timer_cb(void *opaque)
+{
+    FsThrottle *fst = opaque;
+    qemu_co_enter_next(&fst->throttled_reqs[false]);
+}
+
+static void fsdev_throttle_write_timer_cb(void *opaque)
+{
+    FsThrottle *fst = opaque;
+    qemu_co_enter_next(&fst->throttled_reqs[true]);
+}
+
+void fsdev_throttle_parse_opts(QemuOpts *opts, FsThrottle *fst, Error **errp)
+{
+    throttle_config_init(&fst->cfg);
+    fst->cfg.buckets[THROTTLE_BPS_TOTAL].avg =
+        qemu_opt_get_number(opts, "throttling.bps-total", 0);
+    fst->cfg.buckets[THROTTLE_BPS_READ].avg  =
+        qemu_opt_get_number(opts, "throttling.bps-read", 0);
+    fst->cfg.buckets[THROTTLE_BPS_WRITE].avg =
+        qemu_opt_get_number(opts, "throttling.bps-write", 0);
+    fst->cfg.buckets[THROTTLE_OPS_TOTAL].avg =
+        qemu_opt_get_number(opts, "throttling.iops-total", 0);
+    fst->cfg.buckets[THROTTLE_OPS_READ].avg =
+        qemu_opt_get_number(opts, "throttling.iops-read", 0);
+    fst->cfg.buckets[THROTTLE_OPS_WRITE].avg =
+        qemu_opt_get_number(opts, "throttling.iops-write", 0);
+
+    fst->cfg.buckets[THROTTLE_BPS_TOTAL].max =
+        qemu_opt_get_number(opts, "throttling.bps-total-max", 0);
+    fst->cfg.buckets[THROTTLE_BPS_READ].max  =
+        qemu_opt_get_number(opts, "throttling.bps-read-max", 0);
+    fst->cfg.buckets[THROTTLE_BPS_WRITE].max =
+        qemu_opt_get_number(opts, "throttling.bps-write-max", 0);
+    fst->cfg.buckets[THROTTLE_OPS_TOTAL].max =
+        qemu_opt_get_number(opts, "throttling.iops-total-max", 0);
+    fst->cfg.buckets[THROTTLE_OPS_READ].max =
+        qemu_opt_get_number(opts, "throttling.iops-read-max", 0);
+    fst->cfg.buckets[THROTTLE_OPS_WRITE].max =
+        qemu_opt_get_number(opts, "throttling.iops-write-max", 0);
+
+    fst->cfg.buckets[THROTTLE_BPS_TOTAL].burst_length =
+        qemu_opt_get_number(opts, "throttling.bps-total-max-length", 1);
+    fst->cfg.buckets[THROTTLE_BPS_READ].burst_length  =
+        qemu_opt_get_number(opts, "throttling.bps-read-max-length", 1);
+    fst->cfg.buckets[THROTTLE_BPS_WRITE].burst_length =
+        qemu_opt_get_number(opts, "throttling.bps-write-max-length", 1);
+    fst->cfg.buckets[THROTTLE_OPS_TOTAL].burst_length =
+        qemu_opt_get_number(opts, "throttling.iops-total-max-length", 1);
+    fst->cfg.buckets[THROTTLE_OPS_READ].burst_length =
+        qemu_opt_get_number(opts, "throttling.iops-read-max-length", 1);
+    fst->cfg.buckets[THROTTLE_OPS_WRITE].burst_length =
+        qemu_opt_get_number(opts, "throttling.iops-write-max-length", 1);
+    fst->cfg.op_size =
+        qemu_opt_get_number(opts, "throttling.iops-size", 0);
+
+    throttle_is_valid(&fst->cfg, errp);
+}
+
+void fsdev_throttle_init(FsThrottle *fst)
+{
+    if (throttle_enabled(&fst->cfg)) {
+        throttle_init(&fst->ts);
+        throttle_timers_init(&fst->tt,
+                             qemu_get_aio_context(),
+                             QEMU_CLOCK_REALTIME,
+                             fsdev_throttle_read_timer_cb,
+                             fsdev_throttle_write_timer_cb,
+                             fst);
+        throttle_config(&fst->ts, &fst->tt, &fst->cfg);
+        qemu_co_queue_init(&fst->throttled_reqs[0]);
+        qemu_co_queue_init(&fst->throttled_reqs[1]);
+    }
+}
+
+void coroutine_fn fsdev_co_throttle_request(FsThrottle *fst, bool is_write,
+                                            struct iovec *iov, int iovcnt)
+{
+    if (throttle_enabled(&fst->cfg)) {
+        if (throttle_schedule_timer(&fst->ts, &fst->tt, is_write) ||
+            !qemu_co_queue_empty(&fst->throttled_reqs[is_write])) {
+            qemu_co_queue_wait(&fst->throttled_reqs[is_write], NULL);
+        }
+
+        throttle_account(&fst->ts, is_write, iov_size(iov, iovcnt));
+
+        if (!qemu_co_queue_empty(&fst->throttled_reqs[is_write]) &&
+            !throttle_schedule_timer(&fst->ts, &fst->tt, is_write)) {
+            qemu_co_queue_next(&fst->throttled_reqs[is_write]);
+        }
+    }
+}
+
+void fsdev_throttle_cleanup(FsThrottle *fst)
+{
+    if (throttle_enabled(&fst->cfg)) {
+        throttle_timers_destroy(&fst->tt);
+    }
+}

fsdev/qemu-fsdev-throttle.h

+/*
+ * Fsdev Throttle
+ *
+ * Copyright (C) 2016 Huawei Technologies Duesseldorf GmbH
+ *
+ * Author: Pradeep Jagadeesh <pradeep.jagadeesh@huawei.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or
+ * (at your option) any later version.
+ *
+ * See the COPYING file in the top-level directory for details.
+ *
+ */
+
+#ifndef _FSDEV_THROTTLE_H
+#define _FSDEV_THROTTLE_H
+
+#include "block/aio.h"
+#include "qemu/main-loop.h"
+#include "qemu/coroutine.h"
+#include "qapi/error.h"
+#include "qemu/throttle.h"
+
+typedef struct FsThrottle {
+    ThrottleState ts;
+    ThrottleTimers tt;
+    ThrottleConfig cfg;
+    CoQueue      throttled_reqs[2];
+} FsThrottle;
+
+void fsdev_throttle_parse_opts(QemuOpts *, FsThrottle *, Error **);
+
+void fsdev_throttle_init(FsThrottle *);
+
+void coroutine_fn fsdev_co_throttle_request(FsThrottle *, bool ,
+                                            struct iovec *, int);
+
+void fsdev_throttle_cleanup(FsThrottle *);
+#endif /* _FSDEV_THROTTLE_H */

hw/9pfs/9p-local.c

@@ -1208,6 +1208,7 @@ static int local_parse_opts(QemuOpts *opts, struct FsDriverEntry *fse)
 {
     const char *sec_model = qemu_opt_get(opts, "security_model");
     const char *path = qemu_opt_get(opts, "path");
+    Error *err = NULL;
 
     if (!sec_model) {
         error_report("Security model not specified, local fs needs security model");
@@ -1236,6 +1237,13 @@ static int local_parse_opts(QemuOpts *opts, struct FsDriverEntry *fse)
         error_report("fsdev: No path specified");
         return -1;
     }
+
+    fsdev_throttle_parse_opts(opts, &fse->fst, &err);
+    if (err) {
+        error_reportf_err(err, "Throttle configuration is not valid: ");
+        return -1;
+    }
+
     fse->path = g_strdup(path);
 
     return 0;

hw/9pfs/9p.c

@@ -3529,6 +3529,10 @@ int v9fs_device_realize_common(V9fsState *s, Error **errp)
         error_setg(errp, "share path %s is not a directory", fse->path);
         goto out;
     }
+
+    s->ctx.fst = &fse->fst;
+    fsdev_throttle_init(s->ctx.fst);
+
     v9fs_path_free(&path);
 
     rc = 0;
@@ -3549,6 +3553,7 @@ void v9fs_device_unrealize_common(V9fsState *s, Error **errp)
     if (s->ops->cleanup) {
         s->ops->cleanup(&s->ctx);
     }
+    fsdev_throttle_cleanup(s->ctx.fst);
     g_free(s->tag);
     g_free(s->ctx.fs_root);
 }

hw/9pfs/cofile.c

@@ -247,6 +247,7 @@ int coroutine_fn v9fs_co_pwritev(V9fsPDU *pdu, V9fsFidState *fidp,
     if (v9fs_request_cancelled(pdu)) {
         return -EINTR;
     }
+    fsdev_co_throttle_request(s->ctx.fst, true, iov, iovcnt);
     v9fs_co_run_in_worker(
         {
             err = s->ops->pwritev(&s->ctx, &fidp->fs, iov, iovcnt, offset);
@@ -266,6 +267,7 @@ int coroutine_fn v9fs_co_preadv(V9fsPDU *pdu, V9fsFidState *fidp,
     if (v9fs_request_cancelled(pdu)) {
         return -EINTR;
     }
+    fsdev_co_throttle_request(s->ctx.fst, false, iov, iovcnt);
     v9fs_co_run_in_worker(
         {
             err = s->ops->preadv(&s->ctx, &fidp->fs, iov, iovcnt, offset);

qemu-options.hx

@@ -744,7 +744,12 @@ ETEXI
 
 DEF("fsdev", HAS_ARG, QEMU_OPTION_fsdev,
     "-fsdev fsdriver,id=id[,path=path,][security_model={mapped-xattr|mapped-file|passthrough|none}]\n"
-    " [,writeout=immediate][,readonly][,socket=socket|sock_fd=sock_fd]\n",
+    " [,writeout=immediate][,readonly][,socket=socket|sock_fd=sock_fd]\n"
+    " [[,throttling.bps-total=b]|[[,throttling.bps-read=r][,throttling.bps-write=w]]]\n"
+    " [[,throttling.iops-total=i]|[[,throttling.iops-read=r][,throttling.iops-write=w]]]\n"
+    " [[,throttling.bps-total-max=bm]|[[,throttling.bps-read-max=rm][,throttling.bps-write-max=wm]]]\n"
+    " [[,throttling.iops-total-max=im]|[[,throttling.iops-read-max=irm][,throttling.iops-write-max=iwm]]]\n"
+    " [[,throttling.iops-size=is]]\n",
     QEMU_ARCH_ALL)
 
 STEXI