search for: wce

...+), 1 deletion(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index adfba9f..1f8b111 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -478,7 +478,8 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev) struct virtio_blk_config, wce, &writeback); if (err) - writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE); + writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE) || + virtio_has_feature(vdev, VIRTIO_F_VERSION_1); return writeback; } -- MST

...+), 1 deletion(-) diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index adfba9f..1f8b111 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -478,7 +478,8 @@ static int virtblk_get_cache_mode(struct virtio_device *vdev) struct virtio_blk_config, wce, &writeback); if (err) - writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE); + writeback = virtio_has_feature(vdev, VIRTIO_BLK_F_WCE) || + virtio_has_feature(vdev, VIRTIO_F_VERSION_1); return writeback; } -- MST

...rs/block/virtio_blk.c index 553cc4c542b4..0e707b8cce9d 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -541,12 +541,9 @@ virtblk_cache_type_store(struct device *dev, struct device_attribute *attr, int i; BUG_ON(!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_CONFIG_WCE)); - for (i = ARRAY_SIZE(virtblk_cache_types); --i >= 0; ) - if (sysfs_streq(buf, virtblk_cache_types[i])) - break; - + i = sysfs_match_string(virtblk_cache_types, buf); if (i < 0) - return -EINVAL; + return i; virtio_cwrite8(vdev, offsetof(struct virtio_blk_config, wce), i); vir...

...rs/block/virtio_blk.c index 553cc4c542b4..0e707b8cce9d 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -541,12 +541,9 @@ virtblk_cache_type_store(struct device *dev, struct device_attribute *attr, int i; BUG_ON(!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_CONFIG_WCE)); - for (i = ARRAY_SIZE(virtblk_cache_types); --i >= 0; ) - if (sysfs_streq(buf, virtblk_cache_types[i])) - break; - + i = sysfs_match_string(virtblk_cache_types, buf); if (i < 0) - return -EINVAL; + return i; virtio_cwrite8(vdev, offsetof(struct virtio_blk_config, wce), i); vir...

Latest virtio spec says the feature bit name is VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_WCE is the legacy name. virtio blk header says exactly the reverse - fix that and update driver code to match. Cc: Paolo Bonzini <pbonzini at redhat.com> Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- Changs from v1: comments updated include/uapi/linux/virtio_blk.h | 6 +++...

Latest virtio spec says the feature bit name is VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_WCE is the legacy name. virtio blk header says exactly the reverse - fix that and update driver code to match. Cc: Paolo Bonzini <pbonzini at redhat.com> Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- Changs from v1: comments updated include/uapi/linux/virtio_blk.h | 6 +++...

Dear R helpers, I have a data set with 4 types (W, C, E & S). Now I have values for all types plus all possible combinations (the order is unimportant): W, C, WC, E, WE, CE, WCE, S, WS, CS, WCS, ES, WES, CES & WCES. Ideally I would like to represent everything in one graph and as concise as possible. Drawing 4 circles and depicting it as overlap just gives me 13 out of the 15 possibilities needed (as e.g. depicted here http://www.psy.ritsumei.ac.jp/~akitaoka/classic9e....

Latest virtio spec says the feature bit name is VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_WCE is the legacy name. virtio blk header says exactly the reverse - fix that and update driver code to match. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- I'm inclined to merge it for the current kernel - safe and avoids confusion. include/uapi/linux/virtio_blk.h | 6 +++---...

Latest virtio spec says the feature bit name is VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_WCE is the legacy name. virtio blk header says exactly the reverse - fix that and update driver code to match. Signed-off-by: Michael S. Tsirkin <mst at redhat.com> --- I'm inclined to merge it for the current kernel - safe and avoids confusion. include/uapi/linux/virtio_blk.h | 6 +++---...

Hello, I was doing performance testing, validating zvol performance in particularly, and found that zvol write performance to be slow ~35-44MB/s at 1MB blocksize writes. I then tested the underlying zfs file system with the same test and got 121MB/s. Is there any way to fix this? I really would like to have compatible performance between the zfs filesystem and the zfs zvols. # first test is a

On Tue, Jul 03, 2012 at 03:19:37PM +0200, Paolo Bonzini wrote: > This patch adds support for the new VIRTIO_BLK_F_CONFIG_WCE feature, > which exposes the cache mode in the configuration space and lets the > driver modify it. The cache mode is exposed via sysfs. > > Even if the host does not support the new feature, the cache mode is > visible (thanks to the existing VIRTIO_BLK_F_WCE), but not modifiable....

On Tue, Jul 03, 2012 at 03:19:37PM +0200, Paolo Bonzini wrote: > This patch adds support for the new VIRTIO_BLK_F_CONFIG_WCE feature, > which exposes the cache mode in the configuration space and lets the > driver modify it. The cache mode is exposed via sysfs. > > Even if the host does not support the new feature, the cache mode is > visible (thanks to the existing VIRTIO_BLK_F_WCE), but not modifiable....

VIRTIO_BLK_F_CONFIG_WCE is important in order to achieve good performance (up to 2x, though more realistically +30-40%) in latency-bound workloads. However, it was removed by mistake together with VIRTIO_BLK_F_FLUSH. It will be restored in the next revision of the virtio 1.0 standard, so do the same in Linux. Signed-off...

VIRTIO_BLK_F_CONFIG_WCE is important in order to achieve good performance (up to 2x, though more realistically +30-40%) in latency-bound workloads. However, it was removed by mistake together with VIRTIO_BLK_F_FLUSH. It will be restored in the next revision of the virtio 1.0 standard, so do the same in Linux. Signed-off...

...960 512-byte hdwr sectors (109204 MB) SCSI device sda: drive cache: write through sda: sda1 sda2 If I boot CentOS 3.6 in rescue mode I have write back cache enabled. I have tried to use the sdparm utility to enable write back cache but it says that this parameter is not changeable. sdparm --get=WCE /dev/sda -6 /dev/sda: IBM SERVERAID 1.00 WCE 0 [Changeable: n, def: 0, saved: 0] I have looked at the ips module parameters but none seem to affect the write cache. Any ideas how to enable write back cache? Thanks, Radu

virtio-net (non-vhost) and virtio-blk have everything in place to support virtio 1.0: let's enable the feature bit for them. Note that VIRTIO_F_VERSION_1 is technically a transport feature; once every device is ready for virtio 1.0, we can move this setting this feature bit out of the individual devices. Signed-off-by: Cornelia Huck <cornelia.huck at de.ibm.com> ---

On Wed, Nov 26, 2014 at 06:28:42PM +0100, Cornelia Huck wrote: > virtio-net (non-vhost) and virtio-blk have everything in place to support > virtio 1.0: let's enable the feature bit for them. Hmm I doubt that. At least not without more patches. For block, scsi, wce and config-wce must be off, and it must support ANY_LAYOUT (which might be a bit more code). For net, header size is different when mergeable bufs are off, and mac is read-only. > Note that VIRTIO_F_VERSION_1 is technically a transport feature; once > every device is ready for virtio 1.0,...

virtio-net (non-vhost) and virtio-blk have everything in place to support virtio 1.0: let's enable the feature bit for them. Note that VIRTIO_F_VERSION_1 is technically a transport feature; once every device is ready for virtio 1.0, we can move this setting this feature bit out of the individual devices. Signed-off-by: Cornelia Huck <cornelia.huck at de.ibm.com> ---

...ocks. */ __u8 alignment_offset; /* minimum I/O size without performance penalty in logical blocks. */ - __u16 min_io_size; + __virtio16 min_io_size; /* optimal sustained I/O size in logical blocks. */ - __u32 opt_io_size; + __virtio32 opt_io_size; /* writeback mode (if VIRTIO_BLK_F_CONFIG_WCE) */ __u8 wce; __u8 unused; /* number of vqs, only available when VIRTIO_BLK_F_MQ is set */ - __u16 num_queues; + __virtio16 num_queues; /* the next 3 entries are guarded by VIRTIO_BLK_F_DISCARD */ /* * The maximum discard sectors (in 512-byte sectors) for * one segment. */ -...

...to specify virtio 1.0 or 0.9 for mmio. > > Other transports are out of virtio 1.0 spec so > they just use legacy features. > > > The basic problem is that we decide via a feature bit that > > needs to be negotiated which feature bits we want to present. > > Consider wce as one example. This is not needed for modern guests, so > we can just mask it from modern feature mask. Consider virtio blk scsi > commands as another example. this feature is not supported in virtio > 1.0, so we must mask it from modern feature mask. > > Seems the same handling...