search for: 32kbyte

...hdr); > > > + vb->bmap_hdr = kzalloc(hdr_len + vb->bmap_len, GFP_KERNEL); > > > > This ends up doing a 1MB kmalloc() right? That seems a _bit_ big. > > How big was the pfn buffer before? > > > Yes I would limit this to 1G memory in a go, will result in a 32KByte bitmap. > > -- > MST Limit to 1G is bad for the performance, I sent you the test result several weeks ago. Paste it bellow: ------------------------------------------------------------------------------------------------------------------------ About the size of page bitmap, I have test...

...hdr); > > > + vb->bmap_hdr = kzalloc(hdr_len + vb->bmap_len, GFP_KERNEL); > > > > This ends up doing a 1MB kmalloc() right? That seems a _bit_ big. > > How big was the pfn buffer before? > > > Yes I would limit this to 1G memory in a go, will result in a 32KByte bitmap. > > -- > MST Limit to 1G is bad for the performance, I sent you the test result several weeks ago. Paste it bellow: ------------------------------------------------------------------------------------------------------------------------ About the size of page bitmap, I have test...

...is 128kbit/sec, double what I was expecting. I then changed packet size to 86 which I expected should give a bitrate of 128kbit/sec, vnstat said I was using 24kbyte/sec which is 192kbit/sec I then changed packet size to 128, I expected to see a bitrate of 192kbit/sec, vnstat gave me a bitrate of 32kbyte/sec which is 256kbit/sec Therefore all measurements were 64kbit/sec greater than I anticipated, can somebody tell me why, or I have got something wrong here? thank you, Paul.

...I have only 32K (first section) + 8 (second section) = 40 Kbyte of RAM to do all, including the file system management (I get the FS from the EFSL project). Speex requires more or less 18600 byte for the heap (I don't like to have malloc function in my code ...) and the remaining space of the 32Kbyte of RAM is used for the speex variables and for the EFS library. I have only a few bytes to complete the first 32Kbyte section, Regarding the remaining 8kbyte section I use it for the stack. I don't have an additional RAM, and franking specking I don't want to put nose in the detail of the...

...performance improvement. Right? > > > > > > It's a tradeoff for sure. Measure it, see what the overhead is. > > > > > > > Hi MST, > > > > I have measured the performance when using a 32K page bitmap, > > Just to make sure. Do you mean a 32Kbyte bitmap? > Covering 1Gbyte of memory? Yes. > > > and inflate the balloon to 3GB > > of an idle guest with 4GB RAM. > > Should take 3 requests then, right? > No, we can't assign the PFN when allocating page in balloon driver, So the PFNs of pages allocated may be...

...performance improvement. Right? > > > > > > It's a tradeoff for sure. Measure it, see what the overhead is. > > > > > > > Hi MST, > > > > I have measured the performance when using a 32K page bitmap, > > Just to make sure. Do you mean a 32Kbyte bitmap? > Covering 1Gbyte of memory? Yes. > > > and inflate the balloon to 3GB > > of an idle guest with 4GB RAM. > > Should take 3 requests then, right? > No, we can't assign the PFN when allocating page in balloon driver, So the PFNs of pages allocated may be...

On 07/26/2016 06:23 PM, Liang Li wrote: > + vb->pfn_limit = VIRTIO_BALLOON_PFNS_LIMIT; > + vb->pfn_limit = min(vb->pfn_limit, get_max_pfn()); > + vb->bmap_len = ALIGN(vb->pfn_limit, BITS_PER_LONG) / > + BITS_PER_BYTE + 2 * sizeof(unsigned long); > + hdr_len = sizeof(struct balloon_bmap_hdr); > + vb->bmap_hdr = kzalloc(hdr_len + vb->bmap_len, GFP_KERNEL);

On 07/26/2016 06:23 PM, Liang Li wrote: > + vb->pfn_limit = VIRTIO_BALLOON_PFNS_LIMIT; > + vb->pfn_limit = min(vb->pfn_limit, get_max_pfn()); > + vb->bmap_len = ALIGN(vb->pfn_limit, BITS_PER_LONG) / > + BITS_PER_BYTE + 2 * sizeof(unsigned long); > + hdr_len = sizeof(struct balloon_bmap_hdr); > + vb->bmap_hdr = kzalloc(hdr_len + vb->bmap_len, GFP_KERNEL);

...a transmission: 1 the call count of madvise: 42 Maybe the result will be worse if the guest is not idle, or the guest has more RAM. Do you want more data? Is it worth to do that? Liang > > > > > 2. limit allocated bitmap size to something reasonable. > > > How about 32Kbytes? This is 256kilo bit in the map, which comes > > > out to 1Giga bytes of memory in the balloon. > > > > So, even the VM has 1TB of RAM, the page bitmap will take 32MB of > memory. > > Maybe it's better to use a big page bitmap the save the pages > > allo...

> > > > > > > > Hi MST, > > > > > > > > I have measured the performance when using a 32K page bitmap, > > > > > > Just to make sure. Do you mean a 32Kbyte bitmap? > > > Covering 1Gbyte of memory? > > Yes. > > > > > > > > > and inflate the balloon to 3GB > > > > of an idle guest with 4GB RAM. > > > > > > Should take 3 requests then, right? > > > > > > > No, w...

...a transmission: 1 the call count of madvise: 42 Maybe the result will be worse if the guest is not idle, or the guest has more RAM. Do you want more data? Is it worth to do that? Liang > > > > > 2. limit allocated bitmap size to something reasonable. > > > How about 32Kbytes? This is 256kilo bit in the map, which comes > > > out to 1Giga bytes of memory in the balloon. > > > > So, even the VM has 1TB of RAM, the page bitmap will take 32MB of > memory. > > Maybe it's better to use a big page bitmap the save the pages > > allo...

> > > > > > > > Hi MST, > > > > > > > > I have measured the performance when using a 32K page bitmap, > > > > > > Just to make sure. Do you mean a 32Kbyte bitmap? > > > Covering 1Gbyte of memory? > > Yes. > > > > > > > > > and inflate the balloon to 3GB > > > > of an idle guest with 4GB RAM. > > > > > > Should take 3 requests then, right? > > > > > > > No, w...

...ssion and it's bad for > > > performance improvement. Right? > > > > It's a tradeoff for sure. Measure it, see what the overhead is. > > > > Hi MST, > > I have measured the performance when using a 32K page bitmap, Just to make sure. Do you mean a 32Kbyte bitmap? Covering 1Gbyte of memory? > and inflate the balloon to 3GB > of an idle guest with 4GB RAM. Should take 3 requests then, right? > Now: > total inflating time: 338ms > the count of virtio data transmission: 373 Why was this so high? I would expect 3 transmissions. >...

...len = sizeof(struct balloon_bmap_hdr); > > + vb->bmap_hdr = kzalloc(hdr_len + vb->bmap_len, GFP_KERNEL); > > This ends up doing a 1MB kmalloc() right? That seems a _bit_ big. How > big was the pfn buffer before? Yes I would limit this to 1G memory in a go, will result in a 32KByte bitmap. -- MST

...bmap_hdr = kzalloc(hdr_len + vb->bmap_len, GFP_KERNEL); > > > > > > This ends up doing a 1MB kmalloc() right? That seems a _bit_ big. > > > How big was the pfn buffer before? > > > > > > Yes I would limit this to 1G memory in a go, will result in a 32KByte bitmap. > > > > -- > > MST > > Limit to 1G is bad for the performance, I sent you the test result several weeks ago. > > Paste it bellow: > ------------------------------------------------------------------------------------------------------------------------ &g...

...ed, May 25, 2016 at 10:10:47AM +0000, Li, Liang Z wrote: > > > > > > > > > > Hi MST, > > > > > > > > > > I have measured the performance when using a 32K page bitmap, > > > > > > > > Just to make sure. Do you mean a 32Kbyte bitmap? > > > > Covering 1Gbyte of memory? > > > Yes. > > > > > > > > > > > > and inflate the balloon to 3GB > > > > > of an idle guest with 4GB RAM. > > > > > > > > Should take 3 requests then, right? &...

...t; > > > > > It's a tradeoff for sure. Measure it, see what the overhead is. > > > > > > > > > > Hi MST, > > > > > > I have measured the performance when using a 32K page bitmap, > > > > Just to make sure. Do you mean a 32Kbyte bitmap? > > Covering 1Gbyte of memory? > Yes. > > > > > > and inflate the balloon to 3GB > > > of an idle guest with 4GB RAM. > > > > Should take 3 requests then, right? > > > > No, we can't assign the PFN when allocating page in...