engines/xnvme: add support for fdp

Add FDP support to xnvme I/O engine. This support can be used only with
nvme-ns generic character device (/dev/ngXnY). The available backends are
--xnvme_async=io_uring_cmd and --xnvme_sync=nvme.
Add a xnvme-fdp config example file.

Update the minimum required xnvme version to 0.7.0

Signed-off-by: Ankit Kumar <ankit.kumar@samsung.com>
Signed-off-by: Vincent Fu <vincent.fu@samsung.com>

diff --git a/HOWTO.rst b/HOWTO.rst
index 24789f41686dcdeb0bb5549a7e77fdb79082432d..b047877ea3cefc791b7fc414d8aa843fb9c7ccda 100644 (file)
--- a/HOWTO.rst
+++ b/HOWTO.rst
@@ -2431,11 +2431,11 @@ with the caveat that when used on the command line, they must come after the
        For direct I/O, requests will only succeed if cache invalidation isn't required,
        file blocks are fully allocated and the disk request could be issued immediately.
 
-.. option:: fdp=bool : [io_uring_cmd]
+.. option:: fdp=bool : [io_uring_cmd] [xnvme]
 
        Enable Flexible Data Placement mode for write commands.
 
-.. option:: fdp_pli_select=str : [io_uring_cmd]
+.. option:: fdp_pli_select=str : [io_uring_cmd] [xnvme]
 
        Defines how fio decides which placement ID to use next. The following
        types are defined:
@@ -2450,7 +2450,7 @@ with the caveat that when used on the command line, they must come after the
        The available placement ID index/indices is defined by the option
        :option:`fdp_pli`.
 
-.. option:: fdp_pli=str : [io_uring_cmd]
+.. option:: fdp_pli=str : [io_uring_cmd] [xnvme]
 
        Select which Placement ID Index/Indicies this job is allowed to use for
        writes. By default, the job will cycle through all available Placement

diff --git a/configure b/configure
index 74416fd48bc73e35cd8fd5440b9733efd1d0adbb..6c9382517378894df2ee1d02733813f68eb51c8f 100755 (executable)
--- a/configure
+++ b/configure
@@ -2651,7 +2651,7 @@ fi
 ##########################################
 # Check if we have xnvme
 if test "$xnvme" != "no" ; then
-  if check_min_lib_version xnvme 0.2.0; then
+  if check_min_lib_version xnvme 0.7.0; then
     xnvme="yes"
     xnvme_cflags=$(pkg-config --cflags xnvme)
     xnvme_libs=$(pkg-config --libs xnvme)

diff --git a/engines/xnvme.c b/engines/xnvme.c
index bb92a121dc7f6fdaf248a8b35ac0a7251b859eb4..ce7b2bdd4bc6aee56cf6cb327b915668adee00c0 100644 (file)
--- a/engines/xnvme.c
+++ b/engines/xnvme.c
@@ -16,6 +16,7 @@
 #include <libxnvme_spec_fs.h>
 #include "fio.h"
 #include "zbd_types.h"
+#include "fdp.h"
 #include "optgroup.h"
 
 static pthread_mutex_t g_serialize = PTHREAD_MUTEX_INITIALIZER;
@@ -509,6 +510,7 @@ static enum fio_q_status xnvme_fioe_queue(struct thread_data *td, struct io_u *i
        uint16_t nlb;
        int err;
        bool vectored_io = ((struct xnvme_fioe_options *)td->eo)->xnvme_iovec;
+       uint32_t dir = io_u->dtype;
 
        fio_ro_check(td, io_u);
 
@@ -524,6 +526,10 @@ static enum fio_q_status xnvme_fioe_queue(struct thread_data *td, struct io_u *i
        ctx->cmd.common.nsid = nsid;
        ctx->cmd.nvm.slba = slba;
        ctx->cmd.nvm.nlb = nlb;
+       if (dir) {
+               ctx->cmd.nvm.dtype = io_u->dtype;
+               ctx->cmd.nvm.cdw13.dspec = io_u->dspec;
+       }
 
        switch (io_u->ddir) {
        case DDIR_READ:
@@ -947,6 +953,72 @@ exit:
        return err;
 }
 
+static int xnvme_fioe_fetch_ruhs(struct thread_data *td, struct fio_file *f,
+                                struct fio_ruhs_info *fruhs_info)
+{
+       struct xnvme_opts opts = xnvme_opts_from_fioe(td);
+       struct xnvme_dev *dev;
+       struct xnvme_spec_ruhs *ruhs;
+       struct xnvme_cmd_ctx ctx;
+       uint32_t ruhs_nbytes;
+       uint32_t nsid;
+       int err = 0, err_lock;
+
+       if (f->filetype != FIO_TYPE_CHAR) {
+               log_err("ioeng->fdp_ruhs(): ignoring filetype: %d\n", f->filetype);
+               return -EINVAL;
+       }
+
+       err = pthread_mutex_lock(&g_serialize);
+       if (err) {
+               log_err("ioeng->fdp_ruhs(): pthread_mutex_lock(), err(%d)\n", err);
+               return -err;
+       }
+
+       dev = xnvme_dev_open(f->file_name, &opts);
+       if (!dev) {
+               log_err("ioeng->fdp_ruhs(): xnvme_dev_open(%s) failed, errno: %d\n",
+                       f->file_name, errno);
+               err = -errno;
+               goto exit;
+       }
+
+       ruhs_nbytes = sizeof(*ruhs) + (FDP_MAX_RUHS * sizeof(struct xnvme_spec_ruhs_desc));
+       ruhs = xnvme_buf_alloc(dev, ruhs_nbytes);
+       if (!ruhs) {
+               err = -errno;
+               goto exit;
+       }
+       memset(ruhs, 0, ruhs_nbytes);
+
+       ctx = xnvme_cmd_ctx_from_dev(dev);
+       nsid = xnvme_dev_get_nsid(dev);
+
+       err = xnvme_nvm_mgmt_recv(&ctx, nsid, XNVME_SPEC_IO_MGMT_RECV_RUHS, 0, ruhs, ruhs_nbytes);
+
+       if (err || xnvme_cmd_ctx_cpl_status(&ctx)) {
+               err = err ? err : -EIO;
+               log_err("ioeng->fdp_ruhs(): err(%d), sc(%d)", err, ctx.cpl.status.sc);
+               goto free_buffer;
+       }
+
+       fruhs_info->nr_ruhs = ruhs->nruhsd;
+       for (uint32_t idx = 0; idx < fruhs_info->nr_ruhs; ++idx) {
+               fruhs_info->plis[idx] = le16_to_cpu(ruhs->desc[idx].pi);
+       }
+
+free_buffer:
+       xnvme_buf_free(dev, ruhs);
+exit:
+       xnvme_dev_close(dev);
+
+       err_lock = pthread_mutex_unlock(&g_serialize);
+       if (err_lock)
+               log_err("ioeng->fdp_ruhs(): pthread_mutex_unlock(), err(%d)\n", err_lock);
+
+       return err;
+}
+
 static int xnvme_fioe_get_file_size(struct thread_data *td, struct fio_file *f)
 {
        struct xnvme_opts opts = xnvme_opts_from_fioe(td);
@@ -971,7 +1043,9 @@ static int xnvme_fioe_get_file_size(struct thread_data *td, struct fio_file *f)
 
        f->real_file_size = xnvme_dev_get_geo(dev)->tbytes;
        fio_file_set_size_known(f);
-       f->filetype = FIO_TYPE_BLOCK;
+
+       if (td->o.zone_mode == ZONE_MODE_ZBD)
+               f->filetype = FIO_TYPE_BLOCK;
 
 exit:
        xnvme_dev_close(dev);
@@ -1011,6 +1085,8 @@ FIO_STATIC struct ioengine_ops ioengine = {
        .get_zoned_model = xnvme_fioe_get_zoned_model,
        .report_zones = xnvme_fioe_report_zones,
        .reset_wp = xnvme_fioe_reset_wp,
+
+       .fdp_fetch_ruhs = xnvme_fioe_fetch_ruhs,
 };
 
 static void fio_init fio_xnvme_register(void)

diff --git a/examples/xnvme-fdp.fio b/examples/xnvme-fdp.fio
new file mode 100644 (file)
index 0000000..86fbe0d
--- /dev/null
+++ b/examples/xnvme-fdp.fio
@@ -0,0 +1,36 @@
+; README
+;
+; This job-file is intended to be used either as:
+;
+; # Use the xNVMe io-engine engine io_uring_cmd async. impl.
+; fio examples/xnvme-fdp.fio \
+;   --section=default \
+;   --ioengine=xnvme \
+;   --xnvme_async=io_uring_cmd \
+;   --filename=/dev/ng0n1
+;
+; # Use the xNVMe io-engine engine with nvme sync. impl.
+; fio examples/xnvme-fdp.fio \
+;   --section=default \
+;   --ioengine=xnvme \
+;   --xnvme_sync=nvme \
+;   --filename=/dev/ng0n1
+;
+; FIO_BS="512" FIO_RW="read" FIO_IODEPTH=16 fio examples/xnvme-fdp.fio \
+;   --section=override --ioengine=xnvme --xnvme_sync=nvme --filename=/dev/ng0n1
+;
+[global]
+rw=randwrite
+size=2M
+iodepth=1
+bs=4K
+thread=1
+fdp=1
+fdp_pli=4,5
+
+[default]
+
+[override]
+rw=${FIO_RW}
+iodepth=${FIO_IODEPTH}
+bs=${FIO_BS}

diff --git a/fio.1 b/fio.1
index 0257513ba50f819f3b728e3163084c4afa817639..86cb2af683b466fdb12243a5c6aa17e5ee274b24 100644 (file)
--- a/fio.1
+++ b/fio.1
@@ -2192,10 +2192,10 @@ cached data. Currently the RWF_NOWAIT flag does not supported for cached write.
 For direct I/O, requests will only succeed if cache invalidation isn't required,
 file blocks are fully allocated and the disk request could be issued immediately.
 .TP
-.BI (io_uring_cmd)fdp \fR=\fPbool
+.BI (io_uring_cmd,xnvme)fdp \fR=\fPbool
 Enable Flexible Data Placement mode for write commands.
 .TP
-.BI (io_uring_cmd)fdp_pli_select \fR=\fPstr
+.BI (io_uring_cmd,xnvme)fdp_pli_select \fR=\fPstr
 Defines how fio decides which placement ID to use next. The following types
 are defined:
 .RS
@@ -2211,7 +2211,7 @@ Round robin over available placement IDs. This is the default.
 The available placement ID index/indices is defined by \fBfdp_pli\fR option.
 .RE
 .TP
-.BI (io_uring_cmd)fdp_pli \fR=\fPstr
+.BI (io_uring_cmd,xnvme)fdp_pli \fR=\fPstr
 Select which Placement ID Index/Indicies this job is allowed to use for writes.
 By default, the job will cycle through all available Placement IDs, so use this
 to isolate these identifiers to specific jobs. If you want fio to use placement