fix: Replace full-image cache buffer with streaming band buffer to reduce memory usage (#2230)

This commit is contained in:
Justin Mitchell
2026-06-04 10:46:22 -04:00
committed by GitHub
parent a60f31cdd4
commit d9bcef7a58
5 changed files with 304 additions and 82 deletions
+45 -9
View File
@@ -1,5 +1,6 @@
#include "ImageBlock.h"
#include <FontCacheManager.h>
#include <GfxRenderer.h>
#include <Logging.h>
#include <Serialization.h>
@@ -55,10 +56,22 @@ bool renderFromCache(GfxRenderer& renderer, const std::string& cachePath, int x,
LOG_DBG("IMG", "Loading from cache: %s (%dx%d)", cachePath.c_str(), cachedWidth, cachedHeight);
// Read and render row by row to minimize memory usage
// Read several rows per SD access. A full-page image is re-rendered on every
// grayscale strip pass (~14x per page), and a one-row-per-read loop here means
// cachedHeight (~728) tiny reads through the storage mutex + SdFat each time —
// the dominant cost of displaying an image page. Batching rows into a ~4KB
// buffer cuts that to ~20 reads per pass without holding the whole image.
const int bytesPerRow = (cachedWidth + 3) / 4; // 2 bits per pixel, 4 pixels per byte
uint8_t* rowBuffer = (uint8_t*)malloc(bytesPerRow);
if (!rowBuffer) {
int rowsPerRead = 4096 / bytesPerRow;
if (rowsPerRead < 1) rowsPerRead = 1;
if (rowsPerRead > cachedHeight) rowsPerRead = cachedHeight;
uint8_t* readBuffer = (uint8_t*)malloc((size_t)rowsPerRead * bytesPerRow);
if (!readBuffer) {
// Fall back to a single-row buffer under memory pressure.
rowsPerRead = 1;
readBuffer = (uint8_t*)malloc(bytesPerRow);
}
if (!readBuffer) {
LOG_ERR("IMG", "Failed to allocate row buffer");
return false;
}
@@ -66,16 +79,31 @@ bool renderFromCache(GfxRenderer& renderer, const std::string& cachePath, int x,
DirectPixelWriter pw;
pw.init(renderer);
int rowsInBuffer = 0;
int bufferRow = 0;
for (int row = 0; row < cachedHeight; row++) {
if (cacheFile.read(rowBuffer, bytesPerRow) != bytesPerRow) {
LOG_ERR("IMG", "Cache read error at row %d", row);
free(rowBuffer);
return false;
if (bufferRow >= rowsInBuffer) {
const int toRead = (cachedHeight - row < rowsPerRead) ? (cachedHeight - row) : rowsPerRead;
const size_t bytes = (size_t)toRead * bytesPerRow;
if (cacheFile.read(readBuffer, bytes) != static_cast<int>(bytes)) {
LOG_ERR("IMG", "Cache read error at row %d", row);
free(readBuffer);
return false;
}
rowsInBuffer = toRead;
bufferRow = 0;
}
const uint8_t* rowBuffer = readBuffer + (size_t)bufferRow * bytesPerRow;
bufferRow++;
const int destY = y + row;
pw.beginRow(destY);
for (int col = 0; col < cachedWidth; col++) {
// On a grayscale strip pass only a narrow column window of the image is in
// the active band; skip the rest instead of unpacking+clipping every pixel.
int colStart, colEnd;
pw.bandColRange(x, cachedWidth, colStart, colEnd);
for (int col = colStart; col < colEnd; col++) {
const int byteIdx = col >> 2; // col / 4
const int bitShift = 6 - (col & 3) * 2; // MSB first within byte
uint8_t pixelValue = (rowBuffer[byteIdx] >> bitShift) & 0x03;
@@ -84,7 +112,7 @@ bool renderFromCache(GfxRenderer& renderer, const std::string& cachePath, int x,
}
}
free(rowBuffer);
free(readBuffer);
LOG_DBG("IMG", "Cache render complete");
return true;
}
@@ -92,6 +120,14 @@ bool renderFromCache(GfxRenderer& renderer, const std::string& cachePath, int x,
} // namespace
void ImageBlock::render(GfxRenderer& renderer, const int x, const int y) {
// The font-prewarm scan pass only accumulates glyphs; an image contributes
// none, and its DirectPixelWriter output bypasses the renderer's scan-mode
// suppression, so it would otherwise do a full (discarded) cache render every
// page view. Skip it here. The image still draws in the real BW/grayscale
// passes; on first view this just moves the one-time decode to the BW pass.
FontCacheManager* fcm = renderer.getFontCacheManager();
if (fcm && fcm->isScanning()) return;
LOG_DBG("IMG", "Rendering image at %d,%d: %s (%dx%d)", x, y, imagePath.c_str(), width, height);
const int screenWidth = renderer.getScreenWidth();