> -----Original Message-----
> From: Daniel P. Berrangé <berra...@redhat.com>
> Sent: Wednesday, March 20, 2024 6:42 PM
> To: Liu, Yuan1 <yuan1....@intel.com>
> Cc: pet...@redhat.com; faro...@suse.de; qemu-devel@nongnu.org;
> hao.xi...@bytedance.com; bryan.zh...@bytedance.com; Zou, Nanhai
> <nanhai....@intel.com>
> Subject: Re: [PATCH v5 5/7] migration/multifd: implement initialization of
> qpl compression
>
> On Wed, Mar 20, 2024 at 12:45:25AM +0800, Yuan Liu wrote:
> > the qpl initialization includes memory allocation for compressed
> > data and the qpl job initialization.
> >
> > the qpl initialization will check whether the In-Memory Analytics
> > Accelerator(IAA) hardware is available, if the platform does not
> > have IAA hardware or the IAA hardware is not available, the QPL
> > compression initialization will fail.
> >
> > Signed-off-by: Yuan Liu <yuan1....@intel.com>
> > Reviewed-by: Nanhai Zou <nanhai....@intel.com>
> > ---
> > migration/multifd-qpl.c | 243 +++++++++++++++++++++++++++++++++++++++-
> > 1 file changed, 242 insertions(+), 1 deletion(-)
> >
> > diff --git a/migration/multifd-qpl.c b/migration/multifd-qpl.c
> > index 056a68a060..6de65e9da7 100644
> > --- a/migration/multifd-qpl.c
> > +++ b/migration/multifd-qpl.c
> > @@ -9,12 +9,253 @@
> > * This work is licensed under the terms of the GNU GPL, version 2 or
> later.
> > * See the COPYING file in the top-level directory.
> > */
> > +
> > #include "qemu/osdep.h"
> > #include "qemu/module.h"
> > +#include "qapi/error.h"
> > +#include "migration.h"
> > +#include "multifd.h"
> > +#include "qpl/qpl.h"
> > +
> > +typedef struct {
> > + qpl_job **job_array;
> > + /* the number of allocated jobs */
> > + uint32_t job_num;
> > + /* the size of data processed by a qpl job */
> > + uint32_t data_size;
> > + /* compressed data buffer */
> > + uint8_t *zbuf;
> > + /* the length of compressed data */
> > + uint32_t *zbuf_hdr;
> > +} QplData;
> > +
> > +static void free_zbuf(QplData *qpl)
> > +{
> > + if (qpl->zbuf != NULL) {
> > + munmap(qpl->zbuf, qpl->job_num * qpl->data_size);
> > + qpl->zbuf = NULL;
> > + }
> > + if (qpl->zbuf_hdr != NULL) {
> > + g_free(qpl->zbuf_hdr);
> > + qpl->zbuf_hdr = NULL;
> > + }
> > +}
> > +
> > +static int alloc_zbuf(QplData *qpl, uint8_t chan_id, Error **errp)
> > +{
> > + int flags = MAP_PRIVATE | MAP_POPULATE | MAP_ANONYMOUS;
> > + uint32_t size = qpl->job_num * qpl->data_size;
> > + uint8_t *buf;
> > +
> > + buf = (uint8_t *) mmap(NULL, size, PROT_READ | PROT_WRITE, flags, -
> 1, 0);
> > + if (buf == MAP_FAILED) {
> > + error_setg(errp, "multifd: %u: alloc_zbuf failed, job num %u,
> size %u",
> > + chan_id, qpl->job_num, qpl->data_size);
> > + return -1;
> > + }
>
> What's the reason for using mmap here, rather than a normal
> malloc ?
I want to populate the memory accessed by the IAA device in the initialization
phase, and then avoid initiating I/O page faults through the IAA device during
migration, a large number of I/O page faults are not good for performance.
This problem also occurs at the destination, therefore, I recommend that
customers need to add -mem-prealloc for destination boot parameters.
> > + qpl->zbuf = buf;
> > + qpl->zbuf_hdr = g_new0(uint32_t, qpl->job_num);
> > + return 0;
> > +}
> > +
> > +static void free_jobs(QplData *qpl)
> > +{
> > + for (int i = 0; i < qpl->job_num; i++) {
> > + qpl_fini_job(qpl->job_array[i]);
> > + g_free(qpl->job_array[i]);
> > + qpl->job_array[i] = NULL;
> > + }
> > + g_free(qpl->job_array);
> > + qpl->job_array = NULL;
> > +}
> > +
> > +static int alloc_jobs(QplData *qpl, uint8_t chan_id, Error **errp)
> > +{
> > + qpl_status status;
> > + uint32_t job_size = 0;
> > + qpl_job *job = NULL;
> > + /* always use IAA hardware accelerator */
> > + qpl_path_t path = qpl_path_hardware;
> > +
> > + status = qpl_get_job_size(path, &job_size);
> > + if (status != QPL_STS_OK) {
> > + error_setg(errp, "multifd: %u: qpl_get_job_size failed with
> error %d",
> > + chan_id, status);
> > + return -1;
> > + }
> > + qpl->job_array = g_new0(qpl_job *, qpl->job_num);
> > + for (int i = 0; i < qpl->job_num; i++) {
> > + job = g_malloc0(job_size);
> > + status = qpl_init_job(path, job);
> > + if (status != QPL_STS_OK) {
> > + error_setg(errp, "multifd: %u: qpl_init_job failed with
> error %d",
> > + chan_id, status);
> > + free_jobs(qpl);
> > + return -1;
> > + }
> > + qpl->job_array[i] = job;
> > + }
> > + return 0;
> > +}
> > +
> > +static int init_qpl(QplData *qpl, uint32_t job_num, uint32_t data_size,
> > + uint8_t chan_id, Error **errp)
> > +{
>
> IMHO this method should be a normal constructor, it it should
> be responsible for allocating 'qpl' struct too, and returning
> it, not have the caller allocate it.
Thanks for your comments, I will refine this.
> > + qpl->job_num = job_num;
> > + qpl->data_size = data_size;
> > + if (alloc_zbuf(qpl, chan_id, errp) != 0) {
> > + return -1;
> > + }
> > + if (alloc_jobs(qpl, chan_id, errp) != 0) {
> > + free_zbuf(qpl);
> > + return -1;
> > + }
> > + return 0;
> > +}
> > +
> > +static void deinit_qpl(QplData *qpl)
> > +{
> > + if (qpl != NULL) {
> > + free_jobs(qpl);
> > + free_zbuf(qpl);
> > + qpl->job_num = 0;
> > + qpl->data_size = 0;
> > + }
> > +}
>
> This should also free 'qpl' instead of leaving it upto the
> caller.
Sure, I will refine this in the next version.
> > +/**
> > + * qpl_send_setup: setup send side
> > + *
> > + * Setup each channel with QPL compression.
> > + *
> > + * Returns 0 for success or -1 for error
> > + *
> > + * @p: Params for the channel that we are using
> > + * @errp: pointer to an error
> > + */
> > +static int qpl_send_setup(MultiFDSendParams *p, Error **errp)
> > +{
> > + QplData *qpl;
> > +
> > + qpl = g_new0(QplData, 1);
> > + if (init_qpl(qpl, p->page_count, p->page_size, p->id, errp) != 0) {
> > + g_free(qpl);
> > + return -1;
> > + }
> > + p->compress_data = qpl;
> > +
> > + assert(p->iov == NULL);
> > + /*
> > + * Each page will be compressed independently and sent using an
> IOV. The
> > + * additional two IOVs are used to store packet header and
> compressed data
> > + * length
> > + */
> > + p->iov = g_new0(struct iovec, p->page_count + 2);
> > + return 0;
> > +}
> > +
> > +/**
> > + * qpl_send_cleanup: cleanup send side
> > + *
> > + * Close the channel and return memory.
> > + *
> > + * @p: Params for the channel that we are using
> > + * @errp: pointer to an error
> > + */
> > +static void qpl_send_cleanup(MultiFDSendParams *p, Error **errp)
> > +{
> > + QplData *qpl = p->compress_data;
> > +
> > + deinit_qpl(qpl);
> > + g_free(p->compress_data);
> > + p->compress_data = NULL;
> > +}
> > +
> > +/**
> > + * qpl_send_prepare: prepare data to be able to send
> > + *
> > + * Create a compressed buffer with all the pages that we are going to
> > + * send.
> > + *
> > + * Returns 0 for success or -1 for error
> > + *
> > + * @p: Params for the channel that we are using
> > + * @errp: pointer to an error
> > + */
> > +static int qpl_send_prepare(MultiFDSendParams *p, Error **errp)
> > +{
> > + /* Implement in next patch */
> > + return -1;
> > +}
> > +
> > +/**
> > + * qpl_recv_setup: setup receive side
> > + *
> > + * Create the compressed channel and buffer.
> > + *
> > + * Returns 0 for success or -1 for error
> > + *
> > + * @p: Params for the channel that we are using
> > + * @errp: pointer to an error
> > + */
> > +static int qpl_recv_setup(MultiFDRecvParams *p, Error **errp)
> > +{
> > + QplData *qpl;
> > +
> > + qpl = g_new0(QplData, 1);
> > + if (init_qpl(qpl, p->page_count, p->page_size, p->id, errp) != 0) {
> > + g_free(qpl);
> > + return -1;
> > + }
> > + p->compress_data = qpl;
> > + return 0;
> > +}
> > +
> > +/**
> > + * qpl_recv_cleanup: setup receive side
> > + *
> > + * Close the channel and return memory.
> > + *
> > + * @p: Params for the channel that we are using
> > + */
> > +static void qpl_recv_cleanup(MultiFDRecvParams *p)
> > +{
> > + QplData *qpl = p->compress_data;
> > +
> > + deinit_qpl(qpl);
> > + g_free(p->compress_data);
> > + p->compress_data = NULL;
> > +}
> > +
> > +/**
> > + * qpl_recv: read the data from the channel into actual pages
> > + *
> > + * Read the compressed buffer, and uncompress it into the actual
> > + * pages.
> > + *
> > + * Returns 0 for success or -1 for error
> > + *
> > + * @p: Params for the channel that we are using
> > + * @errp: pointer to an error
> > + */
> > +static int qpl_recv(MultiFDRecvParams *p, Error **errp)
> > +{
> > + /* Implement in next patch */
> > + return -1;
> > +}
>
> The qpl library uses 'qpl_' as its name prefix, so using the
> same prefix in QEMU is fragile if future APIs are added to
> the library.
>
> Please consistently use 'multifd_qpl_' as the prefix for
> *every* method in this file.
Get it, thanks for the guidance, I will fix this.
> > +
> > +static MultiFDMethods multifd_qpl_ops = {
> > + .send_setup = qpl_send_setup,
> > + .send_cleanup = qpl_send_cleanup,
> > + .send_prepare = qpl_send_prepare,
> > + .recv_setup = qpl_recv_setup,
> > + .recv_cleanup = qpl_recv_cleanup,
> > + .recv = qpl_recv,
> > +};
> >
> > static void multifd_qpl_register(void)
> > {
> > - /* noop */
> > + multifd_register_ops(MULTIFD_COMPRESSION_QPL, &multifd_qpl_ops);
> > }
> >
> > migration_init(multifd_qpl_register);
> > --
> > 2.39.3
> >
> >
>
> With regards,
> Daniel
> --
> |: https://berrange.com -o-
> https://www.flickr.com/photos/dberrange :|
> |: https://libvirt.org -o-
> https://fstop138.berrange.com :|
> |: https://entangle-photo.org -o-
> https://www.instagram.com/dberrange :|
