[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] [PATCH 20/27] tools/libxl: Infrastructure for writing a v2 stream



On 06/15/2015 09:44 PM, Andrew Cooper wrote:
> From: Ross Lagerwall <ross.lagerwall@xxxxxxxxxx>
> 
> Signed-off-by: Ross Lagerwall <ross.lagerwall@xxxxxxxxxx>
> Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
> CC: Ian Campbell <Ian.Campbell@xxxxxxxxxx>
> CC: Ian Jackson <Ian.Jackson@xxxxxxxxxxxxx>
> CC: Wei Liu <wei.liu2@xxxxxxxxxx>
> ---
>  tools/libxl/Makefile             |    2 +-
>  tools/libxl/libxl_internal.h     |   33 +++
>  tools/libxl/libxl_stream_write.c |  536 
> ++++++++++++++++++++++++++++++++++++++
>  3 files changed, 570 insertions(+), 1 deletion(-)
>  create mode 100644 tools/libxl/libxl_stream_write.c
> 
> diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile
> index ca0ae3e..63e32f7 100644
> --- a/tools/libxl/Makefile
> +++ b/tools/libxl/Makefile
> @@ -94,7 +94,7 @@ LIBXL_OBJS = flexarray.o libxl.o libxl_create.o libxl_dm.o 
> libxl_pci.o \
>                       libxl_dom.o libxl_exec.o libxl_xshelp.o libxl_device.o \
>                       libxl_internal.o libxl_utils.o libxl_uuid.o \
>                       libxl_json.o libxl_aoutils.o libxl_numa.o libxl_vnuma.o 
> \
> -                     libxl_stream_read.o \
> +                     libxl_stream_read.o libxl_stream_write.o \
>                       libxl_save_callout.o _libxl_save_msgs_callout.o \
>                       libxl_convert_callout.o \
>                       libxl_qmp.o libxl_event.o libxl_fork.o $(LIBXL_OBJS-y)
> diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
> index 5482950..82cd792 100644
> --- a/tools/libxl/libxl_internal.h
> +++ b/tools/libxl/libxl_internal.h
> @@ -2868,6 +2868,38 @@ typedef void libxl__domain_suspend_cb(libxl__egc*,
>  typedef void libxl__save_device_model_cb(libxl__egc*,
>                                           libxl__domain_suspend_state*, int 
> rc);
>  
> +/* State for writing a libxl migration v2 stream */
> +typedef struct libxl__stream_write_state libxl__stream_write_state;
> +
> +struct libxl__stream_write_state {
> +    /* filled by the user */
> +    libxl__ao *ao;
> +    int fd;
> +    uint32_t domid;
> +    void (*completion_callback)(libxl__egc *egc,
> +                                libxl__domain_suspend_state *dss,
> +                                int rc);
> +    /* Private */
> +    int rc;
> +    int joined_rc;
> +    size_t padding;
> +    bool running;
> +    libxl__datacopier_state dc;
> +};
> +
> +_hidden void libxl__stream_write_start(libxl__egc *egc,
> +                                       libxl__stream_write_state *stream);
> +
> +_hidden void libxl__stream_write_abort(libxl__egc *egc,
> +                                       libxl__stream_write_state *stream,
> +                                       int rc);
> +
> +static inline bool libxl__stream_write_inuse(
> +    const libxl__stream_write_state *stream)
> +{
> +    return stream->running;
> +}
> +
>  typedef struct libxl__logdirty_switch {
>      const char *cmd;
>      const char *cmd_path;
> @@ -2907,6 +2939,7 @@ struct libxl__domain_suspend_state {
>      /* private for libxl__domain_save_device_model */
>      libxl__save_device_model_cb *save_dm_callback;
>      libxl__datacopier_state save_dm_datacopier;
> +    libxl__stream_write_state sws;
>  };
>  
>  
> diff --git a/tools/libxl/libxl_stream_write.c 
> b/tools/libxl/libxl_stream_write.c
> new file mode 100644
> index 0000000..856d72e
> --- /dev/null
> +++ b/tools/libxl/libxl_stream_write.c
> @@ -0,0 +1,536 @@
> +/*
> + * Copyright (C) 2015      Citrix Ltd.
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU Lesser General Public License as published
> + * by the Free Software Foundation; version 2.1 only. with the special
> + * exception on linking described in file LICENSE.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> + * GNU Lesser General Public License for more details.
> + */
> +
> +#include "libxl_osdeps.h" /* must come before any other headers */
> +
> +#include "libxl_internal.h"
> +
> +/*
> + * Infrastructure for writing a domain to a libxl migration v2 stream.
> + *
> + * Entry points from outside:
> + *  - libxl__stream_write_start()
> + *     - Start writing a stream from the start.
> + *
> + * In normal operation, there are two tasks running at once; this stream
> + * processing, and the the libxl-save-helper.  check_stream_finished() is 
> used
> + * to join all the tasks in both success and error cases.
> + *
> + * Nomenclature for event callbacks:
> + *  - $FOO_done(): Completion callback for $FOO
> + *  - write_$FOO(): Set up writing a $FOO
> + *  - $BAR_header(): A $BAR record header only
> + *  - $BAR_record(): A complete $BAR record with header and content
> + *
> + * The main loop for a plain VM writes:
> + *  - Stream header
> + *  - Libxc record
> + *  - Toolstack record
> + *  - if (hvm), Qemu record
> + *  - End record
> + */
> +
> +static const uint8_t zero_padding[1U << REC_ALIGN_ORDER] = { 0 };
> +
> +static void stream_success(libxl__egc *egc,
> +                           libxl__stream_write_state *stream);
> +static void stream_failed(libxl__egc *egc,
> +                          libxl__stream_write_state *stream, int ret);
> +static void stream_done(libxl__egc *egc,
> +                        libxl__stream_write_state *stream);
> +
> +static void check_stream_finished(libxl__egc *egc,
> +                                  libxl__domain_suspend_state *dcs,
> +                                  int rc, const char *what);
> +
> +/* Event callbacks for plain VM. */
> +static void stream_header_done(libxl__egc *egc,
> +                               libxl__datacopier_state *dc,
> +                               int onwrite, int errnoval);
> +static void libxc_header_done(libxl__egc *egc,
> +                              libxl__datacopier_state *dc,
> +                              int onwrite, int errnoval);
> +/* libxl__xc_domain_save_done() lives here, event-order wise. */
> +static void write_toolstack_record(libxl__egc *egc,
> +                                   libxl__stream_write_state *stream);
> +static void toolstack_record_done(libxl__egc *egc,
> +                                  libxl__datacopier_state *dc,
> +                                  int onwrite, int errnoval);
> +static void write_emulator_record(libxl__egc *egc,
> +                                  libxl__stream_write_state *stream);
> +static void emulator_body_done(libxl__egc *egc,
> +                               libxl__datacopier_state *dc,
> +                               int onwrite, int errnoval);
> +static void emulator_padding_done(libxl__egc *egc,
> +                                  libxl__datacopier_state *dc,
> +                                  int onwrite, int errnoval);
> +static void write_end_record(libxl__egc *egc,
> +                             libxl__stream_write_state *stream);
> +static void end_record_done(libxl__egc *egc,
> +                            libxl__datacopier_state *dc,
> +                            int onwrite, int errnoval);
> +
> +void libxl__stream_write_start(libxl__egc *egc,
> +                               libxl__stream_write_state *stream)
> +{
> +    libxl__datacopier_state *dc = &stream->dc;
> +    STATE_AO_GC(stream->ao);
> +    struct libxl_sr_hdr hdr = { 0 };
> +    int ret = 0;
> +
> +    assert(!stream->running);
> +    stream->running = true;
> +
> +    memset(dc, 0, sizeof(*dc));
> +    dc->readwhat = "";
> +    dc->copywhat = "suspend header";
> +    dc->writewhat = "save/migration stream";
> +    dc->ao = ao;
> +    dc->readfd = -1;
> +    dc->writefd = stream->fd;
> +    dc->maxsz = INT_MAX;
> +    dc->bytes_to_read = INT_MAX;
> +    dc->callback = stream_header_done;
> +
> +    ret = libxl__datacopier_start(dc);
> +    if (ret)
> +        goto err;
> +
> +    hdr.ident   = htobe64(RESTORE_STREAM_IDENT);
> +    hdr.version = htobe32(RESTORE_STREAM_VERSION);
> +    hdr.options = htobe32(0);
> +
> +    libxl__datacopier_prefixdata(egc, dc, &hdr, sizeof(hdr));
> +    return;
> +
> + err:
> +    assert(ret);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +void libxl__stream_write_abort(libxl__egc *egc,
> +                               libxl__stream_write_state *stream, int rc)
> +{
> +    stream_failed(egc, stream, rc);
> +}
> +
> +static void stream_success(libxl__egc *egc, libxl__stream_write_state 
> *stream)
> +{
> +    stream->rc = 0;
> +    stream->running = false;
> +
> +    stream_done(egc, stream);
> +}
> +
> +static void stream_failed(libxl__egc *egc,
> +                          libxl__stream_write_state *stream, int rc)
> +{
> +    assert(rc);
> +    stream->rc = rc;
> +
> +    if (stream->running) {
> +        stream->running = false;
> +        stream_done(egc, stream);
> +    }
> +}
> +
> +static void stream_done(libxl__egc *egc,
> +                        libxl__stream_write_state *stream)
> +{
> +    libxl__domain_suspend_state *dss = CONTAINER_OF(stream, *dss, sws);
> +
> +    assert(!stream->running);
> +
> +    check_stream_finished(egc, dss, stream->rc, "stream");
> +}
> +
> +static void check_stream_finished(libxl__egc *egc,
> +                                  libxl__domain_suspend_state *dss,
> +                                  int rc, const char *what)
> +{
> +    libxl__stream_write_state *stream = &dss->sws;
> +    STATE_AO_GC(dss->ao);
> +
> +    LOG(INFO, "Task '%s' joining (rc %d)", what, rc);
> +
> +    if (rc && !stream->joined_rc) {
> +        bool skip = false;
> +        /* First reported failure from joining tasks.  Tear everything down 
> */
> +        stream->joined_rc = rc;
> +
> +        if (libxl__stream_write_inuse(&dss->sws)) {
> +            skip = true;
> +            libxl__stream_write_abort(egc, &dss->sws, rc);
> +        }
> +
> +        if (libxl__save_helper_inuse(&dss->shs)) {
> +            skip = true;
> +            libxl__save_helper_abort(egc, &dss->shs);
> +        }
> +
> +        /* There is at least one more active task to join - wait for its
> +           callback */
> +        if ( skip )
> +            return;
> +    }
> +
> +    if (libxl__stream_write_inuse(&dss->sws))
> +        LOG(DEBUG, "stream still in use");
> +    else if (libxl__save_helper_inuse(&dss->shs))
> +        LOG(DEBUG, "save/restore still in use");
> +    else {
> +        LOG(INFO, "Join complete: result %d", stream->joined_rc);
> +        stream->completion_callback(egc, dss, stream->joined_rc);
> +    }
> +}
> +
> +static void stream_header_done(libxl__egc *egc,
> +                               libxl__datacopier_state *dc,
> +                               int onwrite, int errnoval)
> +{
> +    libxl__stream_write_state *stream = CONTAINER_OF(dc, *stream, dc);
> +    STATE_AO_GC(stream->ao);
> +    struct libxl_sr_rec_hdr rec = { REC_TYPE_LIBXC_CONTEXT, 0 };
> +    int ret = 0;
> +
> +    if (onwrite || errnoval) {
> +        ret = ERROR_FAIL;
> +        goto err;
> +    }
> +
> +    dc->copywhat = "suspend footer";
> +    dc->writewhat = "save/migration stream";
> +    dc->callback = libxc_header_done;
> +
> +    ret = libxl__datacopier_start(dc);
> +    if (ret)
> +        goto err;
> +
> +    libxl__datacopier_prefixdata(egc, dc, &rec, sizeof(rec));
> +    return;
> +
> + err:
> +    assert(ret);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +static void libxc_header_done(libxl__egc *egc,
> +                              libxl__datacopier_state *dc,
> +                              int onwrite, int errnoval)
> +{
> +    libxl__stream_write_state *stream = CONTAINER_OF(dc, *stream, dc);
> +    libxl__domain_suspend_state *dss = CONTAINER_OF(stream, *dss, sws);
> +    STATE_AO_GC(stream->ao);
> +    int ret = 0;
> +
> +    if (onwrite || errnoval) {
> +        ret = ERROR_FAIL;
> +        goto err;
> +    }
> +
> +    libxl__xc_domain_save(egc, dss);
> +    return;
> +
> + err:
> +    assert(ret);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +static void __attribute__((used))
> +will_be_libxl__xc_domain_save_done(libxl__egc *egc, void *dss_void,
> +                                int rc, int retval, int errnoval)
> +{
> +    libxl__domain_suspend_state *dss = dss_void;
> +    libxl__stream_write_state *stream = &dss->sws;
> +    STATE_AO_GC(dss->ao);
> +
> +    if (rc)
> +        goto err;
> +
> +    if (retval) {
> +        LOGEV(ERROR, errnoval, "saving domain: %s",
> +                         dss->guest_responded ?
> +                         "domain responded to suspend request" :
> +                         "domain did not respond to suspend request");
> +        if ( !dss->guest_responded )
> +            rc = ERROR_GUEST_TIMEDOUT;
> +        else
> +            rc = ERROR_FAIL;
> +        goto err;
> +    }
> +
> +    write_toolstack_record(egc, stream);
> +    return;
> +
> + err:
> +    assert(rc);
> +    check_stream_finished(egc, dss, rc, "save/restore helper");
> +}
> +
> +static void write_toolstack_record(libxl__egc *egc,
> +                                   libxl__stream_write_state *stream)
> +{
> +    libxl__domain_suspend_state *dss = CONTAINER_OF(stream, *dss, sws);
> +    libxl__datacopier_state *dc = &stream->dc;
> +    STATE_AO_GC(stream->ao);
> +    struct libxl_sr_rec_hdr rec = { REC_TYPE_XENSTORE_DATA, 0 };
> +    int ret = 0;
> +    uint8_t *toolstack_buf = NULL; /* We must free this. */
> +    uint32_t toolstack_len, padding_len;
> +
> +    ret = libxl__toolstack_save(dss->domid, &toolstack_buf,
> +                                &toolstack_len, dss);
> +    if (ret)
> +        goto err;
> +
> +    dc->copywhat = "toolstack record";
> +    dc->writewhat = "save/migration stream";
> +    dc->callback = toolstack_record_done;
> +
> +    ret = libxl__datacopier_start(dc);
> +    if (ret)
> +        goto err;
> +
> +    rec.length = toolstack_len;
> +
> +    libxl__datacopier_prefixdata(egc, dc, &rec, sizeof(rec));
> +    libxl__datacopier_prefixdata(egc, dc, toolstack_buf, toolstack_len);
> +
> +    padding_len = ROUNDUP(rec.length, REC_ALIGN_ORDER) - rec.length;
> +    if (padding_len)
> +        libxl__datacopier_prefixdata(egc, dc, zero_padding, padding_len);
> +
> +    free(toolstack_buf);
> +    return;
> +
> + err:
> +    assert(ret);
> +    free(toolstack_buf);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +static void toolstack_record_done(libxl__egc *egc,
> +                                  libxl__datacopier_state *dc,
> +                                  int onwrite, int errnoval)
> +{
> +    libxl__stream_write_state *stream = CONTAINER_OF(dc, *stream, dc);
> +    libxl__domain_suspend_state *dss = CONTAINER_OF(stream, *dss, sws);
> +    STATE_AO_GC(stream->ao);
> +    int ret = 0;
> +
> +    if (onwrite || errnoval) {
> +        ret = ERROR_FAIL;
> +        goto err;
> +    }
> +
> +    if (dss->type == LIBXL_DOMAIN_TYPE_HVM)
> +        write_emulator_record(egc, stream);
> +    else
> +        write_end_record(egc, stream);
> +
> +    return;
> +
> + err:
> +    assert(ret);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +static void write_emulator_record(libxl__egc *egc,
> +                                  libxl__stream_write_state *stream)
> +{
> +    libxl__domain_suspend_state *dss = CONTAINER_OF(stream, *dss, sws);
> +    libxl__datacopier_state *dc = &stream->dc;
> +    STATE_AO_GC(stream->ao);
> +    struct libxl_sr_rec_hdr rec = { REC_TYPE_EMULATOR_CONTEXT, 0 };
> +    struct libxl_sr_emulator_hdr ehdr = { 0 };
> +    struct stat st;
> +    int ret = 0;
> +    uint32_t qemu_state_len;
> +
> +    assert(dss->type == LIBXL_DOMAIN_TYPE_HVM);
> +
> +    /* Convenience aliases */
> +    const char *const filename = dss->dm_savefile;
> +    const uint32_t domid = dss->domid;
> +
> +    switch(libxl__device_model_version_running(gc, domid)) {
> +    case LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL:
> +        ehdr.id = EMULATOR_QEMU_TRADITIONAL;
> +        break;
> +
> +    case LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN:
> +        ehdr.id = EMULATOR_QEMU_UPSTREAM;
> +        break;
> +
> +    default:
> +        ret = ERROR_FAIL;
> +        goto err;
> +    }
> +
> +    ret = libxl__domain_suspend_device_model(gc, dss);

We have called it when suspending the guest. For migration, calling
this function twice is OK, but for remus, it will cause a problem:
the guest is running, and this device-model will be stopped by this
function.

Thanks
Wen Congyang

> +    if (ret)
> +        goto err;
> +
> +    dc->readwhat = GCSPRINTF("qemu save file %s", filename);
> +    dc->copywhat = "emulator record";
> +    dc->writewhat = "save/migration stream";
> +    dc->callback = emulator_body_done;
> +
> +    dc->readfd = open(filename, O_RDONLY);
> +    if (dc->readfd < 0) {
> +        LOGE(ERROR, "unable to open %s", dc->readwhat);
> +        goto err;
> +    }
> +
> +    if (fstat(dc->readfd, &st))
> +    {
> +        LOGE(ERROR, "unable to fstat %s", dc->readwhat);
> +        goto err;
> +    }
> +
> +    if (!S_ISREG(st.st_mode)) {
> +        LOG(ERROR, "%s is not a plain file!", dc->readwhat);
> +        goto err;
> +    }
> +
> +    qemu_state_len = st.st_size;
> +    rec.length = qemu_state_len + sizeof(ehdr);
> +
> +    ret = libxl__datacopier_start(dc);
> +    if (ret)
> +        goto err;
> +
> +    libxl__datacopier_prefixdata(egc, dc, &rec, sizeof(rec));
> +    libxl__datacopier_prefixdata(egc, dc, &ehdr, sizeof(ehdr));
> +
> +    stream->padding = ROUNDUP(qemu_state_len, REC_ALIGN_ORDER) - 
> qemu_state_len;
> +    return;
> +
> + err:
> +    assert(ret);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +static void emulator_body_done(libxl__egc *egc,
> +                               libxl__datacopier_state *dc,
> +                               int onwrite, int errnoval)
> +{
> +    libxl__stream_write_state *stream = CONTAINER_OF(dc, *stream, dc);
> +    STATE_AO_GC(stream->ao);
> +    int ret = 0;
> +
> +    if (onwrite || errnoval) {
> +        ret = ERROR_FAIL;
> +        goto err;
> +    }
> +
> +    dc->readwhat = "";
> +    dc->readfd = -1;
> +
> +    if (stream->padding) {
> +        assert(stream->padding < (1U << REC_ALIGN_ORDER));
> +
> +        dc->copywhat = "emulator padding";
> +        dc->writewhat = "save/migration stream";
> +        dc->callback = emulator_padding_done;
> +
> +        ret = libxl__datacopier_start(dc);
> +        if (ret)
> +            goto err;
> +
> +        libxl__datacopier_prefixdata(egc, dc, zero_padding, stream->padding);
> +        return;
> +    }
> +
> +    emulator_padding_done(egc, dc, 0, 0);
> +    return;
> +
> + err:
> +    assert(ret);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +static void emulator_padding_done(libxl__egc *egc,
> +                                  libxl__datacopier_state *dc,
> +                                  int onwrite, int errnoval)
> +{
> +    libxl__stream_write_state *stream = CONTAINER_OF(dc, *stream, dc);
> +    STATE_AO_GC(stream->ao);
> +    int ret = 0;
> +
> +    if (onwrite || errnoval) {
> +        ret = ERROR_FAIL;
> +        goto err;
> +    }
> +
> +    write_end_record(egc, stream);
> +    return;
> +
> + err:
> +    assert(ret);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +static void write_end_record(libxl__egc *egc,
> +                             libxl__stream_write_state *stream)
> +{
> +    libxl__datacopier_state *dc = &stream->dc;
> +    STATE_AO_GC(stream->ao);
> +    struct libxl_sr_rec_hdr rec = { REC_TYPE_END, 0 };
> +    int ret = 0;
> +
> +    dc->copywhat = "suspend footer";
> +    dc->writewhat = "save/migration stream";
> +    dc->callback = end_record_done;
> +
> +    ret = libxl__datacopier_start(dc);
> +    if (ret)
> +        goto err;
> +
> +    libxl__datacopier_prefixdata(egc, dc, &rec, sizeof(rec));
> +    return;
> +
> + err:
> +    assert(ret);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +static void end_record_done(libxl__egc *egc,
> +                            libxl__datacopier_state *dc,
> +                            int onwrite, int errnoval)
> +{
> +    libxl__stream_write_state *stream = CONTAINER_OF(dc, *stream, dc);
> +    STATE_AO_GC(stream->ao);
> +    int ret = 0;
> +
> +    if (onwrite || errnoval) {
> +        ret = ERROR_FAIL;
> +        goto err;
> +    }
> +
> +    stream_success(egc, stream);
> +    return;
> +
> + err:
> +    assert(ret);
> +    stream_failed(egc, stream, ret);
> +}
> +
> +/*
> + * Local variables:
> + * mode: C
> + * c-basic-offset: 4
> + * indent-tabs-mode: nil
> + * End:
> + */
> 


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.