From: Vincent Fu <vincent.fu@samsung.com>
Date: Fri, 22 Nov 2024 16:29:05 +0000 (+0000)
Subject: engines/io_uring_cmd: disable iomem=malloc check for metadata
X-Git-Tag: fio-3.39~22
X-Git-Url: https://git.kernel.dk/?a=commitdiff_plain;h=d78f2f3f33f9f5f64bfa7a71db22aac911eda162;p=fio.git

engines/io_uring_cmd: disable iomem=malloc check for metadata

Before this patch, the io_uring_cmd ioengine would check that
iomem=malloc (the default) before allocating memory for metadata
buffers. If the user had selected a different option, fio would abort
the job with an error message.

This patch removes this check. We do not need to restrict users to
iomem=malloc for io_uring_cmd workloads involving protection
information. Users may wish to use huge pages for LBA data in order to
submit larger IOs. Since metadata buffers will be smaller they can still
use regular pages.

Reported-by: 전규범 <gyubeom.jeon@samsung.com>
Signed-off-by: Vincent Fu <vincent.fu@samsung.com>
---

diff --git a/engines/io_uring.c b/engines/io_uring.c
index 79eacbc4..facc967f 100644
--- a/engines/io_uring.c
+++ b/engines/io_uring.c
@@ -1353,14 +1353,8 @@ static int fio_ioring_init(struct thread_data *td)
 		md_size += page_mask + td->o.mem_align;
 		if (td->o.mem_align && td->o.mem_align > page_size)
 			md_size += td->o.mem_align - page_size;
-		if (td->o.mem_type == MEM_MALLOC) {
-			ld->md_buf = malloc(md_size);
-			if (!ld->md_buf) {
-				free(ld);
-				return 1;
-			}
-		} else {
-			log_err("fio: Only iomem=malloc or mem=malloc is supported\n");
+		ld->md_buf = malloc(md_size);
+		if (!ld->md_buf) {
 			free(ld);
 			return 1;
 		}