All of lore.kernel.org
 help / color / mirror / Atom feed
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
To: Zhanjun Dong <zhanjun.dong@intel.com>, <intel-xe@lists.freedesktop.org>
Subject: Re: [PATCH v2 3/3] drm/xe/guc: Reduce GuC log size from 8MB to 2MB
Date: Thu, 28 May 2026 21:18:28 +0200	[thread overview]
Message-ID: <cf526083-efe8-4e99-98a2-7c35206c9d74@intel.com> (raw)
In-Reply-To: <20260511194924.2016315-4-zhanjun.dong@intel.com>



On 5/11/2026 9:49 PM, Zhanjun Dong wrote:
> Reduce the default log buffer size to improve system responsiveness and

default log size is SZ_64K and is not changed by this patch

> readability. The previous 8MB threshold caused significant delays during

8MB size was used in CONFIG_DRM_XE_DEBUG

> log output and imposed a heavy load when printing to dmesg.

hmm, but that was on purpose, as any extra cost caused by such dump, which
should be sporadic anyway, we were willing to take just to be sure to do not
lost any information from the too small log

> 
> By reducing the size to 2MB, we maintain a sufficient history while
> ensuring faster flushing. With a typical 4:1 compression ratio, this 2MB
> buffer will result in approximately 512KB of compressed data, providing an
> efficient balance between log depth and system performance.

hmm, such dumps should be very sporadic, already after HW/FW being broken

so what do you mean by the 'system performance' here?

and maybe it would be sufficient just to introduce compression without
reducing the log size?

> 
> Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com>
> ---
>  drivers/gpu/drm/xe/xe_guc_log.h | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_guc_log.h b/drivers/gpu/drm/xe/xe_guc_log.h
> index d231def50692..44e81a54681f 100644
> --- a/drivers/gpu/drm/xe/xe_guc_log.h
> +++ b/drivers/gpu/drm/xe/xe_guc_log.h
> @@ -17,7 +17,7 @@ struct xe_device;
>  #define XE_GUC_LOG_CRASH_DUMP_BUFFER_SIZE	SZ_1M
>  #define XE_GUC_LOG_STATE_CAPTURE_BUFFER_SIZE	SZ_2M
>  #elif IS_ENABLED(CONFIG_DRM_XE_DEBUG)
> -#define XE_GUC_LOG_EVENT_DATA_BUFFER_SIZE	SZ_8M
> +#define XE_GUC_LOG_EVENT_DATA_BUFFER_SIZE	SZ_2M
>  #define XE_GUC_LOG_CRASH_DUMP_BUFFER_SIZE	SZ_1M
>  #define XE_GUC_LOG_STATE_CAPTURE_BUFFER_SIZE	SZ_1M
>  #else


  parent reply	other threads:[~2026-05-28 19:19 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-11 19:49 [PATCH v2 0/3] drm/xe: shrink and compress GuC snapshot dumps Zhanjun Dong
2026-05-11 19:49 ` [PATCH v2 1/3] drm/xe/guc: Compress GuC log and CTB dump with zstd Zhanjun Dong
2026-05-28 17:51   ` Julia Filipchuk
2026-05-28 18:10     ` Dong, Zhanjun
2026-05-11 19:49 ` [PATCH v2 2/3] drm/xe: Remove extra newlines from LRC snapshot dump Zhanjun Dong
2026-05-28 17:52   ` Julia Filipchuk
2026-05-11 19:49 ` [PATCH v2 3/3] drm/xe/guc: Reduce GuC log size from 8MB to 2MB Zhanjun Dong
2026-05-28 17:52   ` Julia Filipchuk
2026-05-28 19:18   ` Michal Wajdeczko [this message]
2026-06-01 23:20     ` Dong, Zhanjun
2026-06-02 13:45       ` Michal Wajdeczko
2026-06-02 18:37         ` Dong, Zhanjun
2026-05-12  7:41 ` ✗ CI.checkpatch: warning for drm/xe: shrink and compress GuC snapshot dumps (rev2) Patchwork
2026-05-12  7:42 ` ✓ CI.KUnit: success " Patchwork
2026-05-12  7:58 ` ✗ CI.checksparse: warning " Patchwork
2026-05-12  9:11 ` ✓ Xe.CI.BAT: success " Patchwork
2026-05-12 17:09 ` ✗ Xe.CI.FULL: failure " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=cf526083-efe8-4e99-98a2-7c35206c9d74@intel.com \
    --to=michal.wajdeczko@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=zhanjun.dong@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.